WO2025217200A1

WO2025217200A1 - System and methods for determining and measuring cannabacea-based treatments

Info

Publication number: WO2025217200A1
Application number: PCT/US2025/023716
Authority: WO
Inventors: Itzhak Kurek; Jean-Christophe QUILLET; Michael M. SIANI-ROSE; Kenneth H. EPSTEIN; Robert COOPER MCKEE
Original assignee: Cannformatics Inc
Current assignee: Cannformatics Inc
Priority date: 2024-04-09
Filing date: 2025-04-08
Publication date: 2025-10-16
Anticipated expiration: 2026-10-09

Abstract

Provided herein are methods and systems for determining and measuring Cannabaceae- based treatments through analysis of biological samples. The methods comprise obtaining samples, quantifying metabolites, and generating a database of metabolic profiles and treatment responses. Statistical analysis calculates z-scores to assess physiological deviations, and machine learning algorithms predict optimal dosages of Cannabaceae-derived molecules to normalize metabolite levels. The system includes modules for sample collection, data management, statistical analysis, diagnostics, and personalized treatment recommendations, offering real-time adjustments to treatments based on individual metabolic responses.

Description

SYSTEM AND METHODS FOR DETERMINING AND MEASURING CANNABACEA- BASED TREATMENTS

CROSS REFERENCE

[0001] This application claims the benefit of U.S. Provisional Application No. 63/631,985 filed on April 9, 2024, which is incorporated by reference in its entirety.

BACKGROUND

Field of the Invention

[0002] The present invention relates to the use of medical cannabis (MC) in personalized treatment regimens and the application of machine learning (ML) algorithms for optimizing therapeutic outcomes. More specifically, the invention integrates pharmacometabolomic, cannabis-responsive biomarkers, and ML-based predictive models to analyze treatment response and adjust cannabinoid formulations accordingly.

[0003] Cannabis-based therapeutics have demonstrated efficacy in treating various conditions. Cannabaceae-derived molecules such as tetrahydrocannabinol (THC), cannabidiol (CBD), and cannabigerol (CBG) interact with the endocannabinoid system (ECS) to regulate neurotransmission, immune response, and metabolic homeostasis. Nowadays, Medical Cannabis (MC) has been used to manage conditions e.g., chronic pain, inflammatory disorders, epilepsy, and neuro- degenerative diseases. Despite these applications, response to cannabis treatment varies significantly between individuals, requiring objective, biomarker-based methods to determining dosing and formulations.

[0004] Current approaches to cannabis treatment optimization rely on: Subjective patient- reported outcomes rather than objective biochemical markers. Trial -and-error dosing without precision-guided adjustments. Lack of predictive models for individualized cannabinoid response profiling. Metab olomics has emerged as a promising tool for biochemical response analysis. Cannabaceae-responsive biomarkers have been identified in biological samples such as saliva, blood, and urine, but existing analytical methods lack predictive capabilities for treatment determination and eventual personalization.

[0005] Machine learning (ML) algorithms offer a data-driven approach to determining, predicting, and optimizing Cannabaceae-derived therapy. ML models can: Identify Cannabaceae- responsive metabolic biomarkers associated with treatment efficacy. Predict individual responses to Cannabaceae-derived formulations based on historical metabolic data. Adjust Cannabaceae- derived molecules dosages dynamically by incorporating real-time patient biomarker data. Supervised learning models, such as gradient boosting, deep neural networks (DNNs), and support vector machines (SVMs), have demonstrated success in metabolomics-based classification and prediction tasks.

[0006] There is a critical need for implementing new tools to integrate pharmacometabo- lomic and ML; utilize biomarker-based diagnostics to quantify treatment response; and employ predictive modeling to personalize Cannabaceae -derived molecules dosing. The present invention provides a comprehensive Al-based pharmacometabolomic system and method for determining, measuring, analyzing, predicting, optimizing, and/or personalizing medical cannabis therapies.

[0007] Provided herein are methods and systems for determining and measuring Canna- baceae-based treatments. Wherein the method may determine treatments to restore or maintain healthy physiological levels of one or more metabolites and/or biomarkers using Cannabaceae- derived molecules and the system may provide modules wherein the methods may be implemented.

[0008] Provided herein are methods for determining and measuring treatments to restore or maintain healthy physiological levels of one or more metabolites and/or biomarkers using Can- nabaceae-derived molecules comprising: (i) obtaining biological samples from at least one subject; (ii) analyzing the samples to quantify levels of one or more metabolites; and (iii) providing the treatment to the subject.

[0009] Provided herein are methods for determining and measuring Cannabaceae-based treatments comprising: (i) obtaining biological samples from at least one subject; (ii) analyzing the samples to quantify levels of one or more metabolites; (iii) generating a database wherein the data comprises relationships between the individual's information and metabolic data; and (iv) providing the treatment to the subject.

[0010] Provided herein are methods for determine and measure treatments to restore or maintain healthy physiological levels of one or more metabolites and/or biomarkers using Can- nabaceae-derived molecules comprising: (i) obtaining biological samples from at least one subject; (ii) analyzing the samples to quantify levels of one or more metabolites; (iii) generating a database wherein the data comprises relationship sb etween the individual's information and metabolic data; (iv) calculating z-scores in metabolite levels in individuals; and (v) providing the treatment to the subject.

[0011] Provided herein are methods for determine and measure treatments to restore or maintain healthy physiological levels of one or more metabolites and/or biomarkers using Can- nabaceae-derived molecules comprising: (i) obtaining biological samples from at least one subject; (ii) analyzing the samples to quantify levels of one or more metabolites; (iii) generating a database wherein the data comprises relationship sb etween the individual's information and metabolic data; (iv) calculating z-scores in metabolite levels in individuals; (v) estimating the treatment of Cannabaceae-derived molecules or mixture of Cannabaceae-derived molecules required to normalize the metabolite z-score toward approximately 0; and (vi) providing the treatment to the subject.

[0012] Provided herein are methods for determine and measure treatments to restore or maintain healthy physiological levels of one or more metabolites and/or biomarkers using Cannabaceae-derived molecules comprising: (i) obtaining biological samples from at least one individual, wherein the biological sample may comprise saliva; (ii) analyzing the samples to quantify levels of metabolites, including Cannabaceae-responsive biomarkers; (iii) generating a database, wherein the data comprises relationships between the individual's information and metabolic data; (iv) calculating z-scores in metabolite levels in individuals, defined as the number of standard deviations from the mean of at least one physiological range observed in a healthy population; (v) estimating the treatment of Cannabaceae-derived molecules or mixture of Cannabaceae-derived molecules required to normalize the metabolite z-score toward approximately 0; and (vi) providing the treatment to the subject.

[0013] Provided herein are methods for determine and measure treatments to restore or maintain healthy physiological levels of one or more metabolites and/or biomarkers using Cannabaceae-derived molecules comprising: (i) obtaining biological samples from at least one individual, wherein the biological sample may comprise saliva, blood, Urine, Cerebrospinal Fluid, tissue, hair, exhaled breath condensate, tears, feces or sweat; (ii) analyzing the samples to quantify levels of metabolites, including Cannabaceae-responsive biomarkers, wherein the analysis of samples to quantify levels of metabolites comprise Spectroscopy -Based Techniques, Chromatography-Based Techniques, Optical and Fluorescence-Based Techniques, Immunoassay and Biosensor-Based Techniques, Separation-Based Techniques, Isotope-Based Techniques, Electrochemical Techniques or any combination thereof, wherein the metabolites may comprise at least one of the groups consisting of mammalian metabolites, plant metabolites, microbial metabolites and any combination thereof; (iii) generating a database wherein the data comprises relationships between the individual's information and metabolic data, wherein each metabolite detected in a sample obtained from the individual is categorized into at least one category, wherein the at least one category may comprise at least one of the group consisting of endocannabinoid system -related metabolites; groups associated with medical conditions; metabolic responses, cohort profiles, individual profiles and any combinations thereof (iv) calculating z-scores of metabolite levels in individuals, defined as the number of standard deviations from the mean of at least one physiological range observed in a healthy population; (v) estimating the treatment of Canna- baceae-derived molecules or mixture of Cannabaceae -derived molecules required to normalize the metabolite z-score toward approximately 0, wherein the z-score calculation can include adjustments based on cohort-specific averages for subpopulations defined by demographic or medical characteristics; and (vi) providing the treatment to the subject. In some embodiments, the biological sample is saliva. In some embodiments, the analysis of samples to quantify levels of metabolites comprises mass spectrometry. In some embodiments, the quantified metabolites consist of mammalian metabolites. In some embodiments, the quantified metabolites consist of plant metabolites. In some embodiments, the category in which the metabolites are categorized comprises endocannabinoid system -related metabolites. In some embodiments, the category in which the metabolites are categorized can include medical conditions, metabolic responses, cohort profiles, individual profiles, or any combination thereof. In some embodiments the z-score calculations may include adjustments based on cohort-specific averages for subpopulations defined by demographic or medical characteristics. In some embodiments, the databases may further comprise a database of Cannabaceae contaminants detected in the biological sample of at least one individual who has consumed Cannabaceae -derived molecules. In some embodiments, the Cannabaceae contaminants can further comprise entries for specific chemicals or residues associated with Cannabaceae-derived products. In some embodiments, the databases can further include information relating to synthetic molecules or synthetic -derived metabolites, particularly those related to pharmaceuticals that interact with cannabinoid pathways. In some embodiments, such synthetic molecules can include, but are not limited to, cannabinoid analogs, synthetic cannabinoids, and pharmaceutical compounds that modulate or interfere the endocannabinoid system activity. In some embodiments, the presence of metabolites related to drugs can be documented to identify potential metabolic interactions or contraindications when administering Canna- baceae-based treatments. In some embodiments, the quantification of metabolites by mass spectrometry can further comprise chromatography technique to enhance metabolite detection accuracy. In some embodiments, the database of endocannabinoid system -related metabolites includes correlations between specific Cannabaceae-derived molecules and their impact on z-score changes. In some embodiments, the cannabis contaminants information is used to identify potential interactions between Cannabaceae-derived molecules, Cannabaceae contaminants and metabolic responses. In some embodiments, providing the treatment to the subject can comprise generating treatment outputs, wherein recommended treatments may comprise written treatment protocols specifying but not limited to cannabinoid type, dosage amount, administration frequency, and route of administration, based on the predicted metabolic response and individual condition. In some embodiments, the route of administration can comprise at least one of: Oral administration, including capsules, tablets, oils, tinctures, and edibles; Sublingual or buccal administration, including dissolvable strips, sprays, and oils applied under the tongue; Inhalation, including vaporized formulations or aerosolized delivery; Topical administration, including creams, patches, or gels applied to the skin; Transdermal delivery, comprising slow-release patches; or Rectal or vaginal administration, using suppositories. In some embodiments, written treatment protocols may be updated automatically or manually in response to newly collected metabolic data and ongoing evaluation of subject responses, allowing for iterative refinement of Cannabaceae-based therapy.

[0014] In some embodiments, the method may further comprise a step for generating personalized treatments plans for individuals. In some embodiments, the personalized treatment may be based on metabolite-level data and predicted Cannabaceae-derived molecule treatments. In some embodiments, the method can further comprise generating Cannabaceae-derived molecule combinations and dosages. In some embodiments, the method can be implemented on a software application. In some embodiments, the application can be implemented in mobile devices.

[0015] Provided herein are systems for determining Cannabaceae-based treatments comprising: (i) a biological sample; (ii) a sample processing module; (iii) a data management module; (iv) a statistical analysis module; (v) a machine learning module; (vi) a diagnostic module; and (vii) a personalization module for medical Cannabaceae-based treatments.

[0016] Provided herein are systems for determining Cannabaceae-based treatments comprising: (i) a biological sample test module; (ii) a sample processing module; (iii) a data management module; (iv) a statistical analysis module; (v) a machine learning module; (vi) a diagnostic module; (vii) a personalization module for medical Cannabaceae-based treatments; and (viii) a treatment provider module configured to provide the treatment for the subject.

[0017] Provided herein are systems for determining Cannabaceae-based treatments comprising: (i) a biological sample test module, wherein the module maybe configured to: (a) enable individuals to collect at least one biological sample; (b) store the at least one biological sample; and (c) maintain the at least one biological sample optimal condition while monitoring and preserving it during transportation; (ii) a sample processing module, wherein the module may be configured to: (a) extract metabolites from a biological sample; and (b) determine metabolite characteristics from the biological sample; (iii) a data management module, wherein the module may comprise (a) a database of individual metabolite levels and timestamps of Cannabaceae- based treatments; (b) a database of individual diagnostic information; (c) a database of individual condition or state evaluations, and timestamps, with and without Cannabaceae-based treatments; and (d) a database of individual medication and Cannabaceae -derived treatment compositions; (iv) a statistical analysis module, wherein said module may be configured to perform z -score evaluations; (v) a machine learning module, wherein said module may comprise at least (a) one machine learning model trained to predict any attribute or group of attributes within databases based on other database attributes, wherein the databases can comprise but not be limited to anyone of the (iii:c) databases; (b) one training system formachine learning models; (c) at least one machine learning model to identify complex, nonlinear relationships within data; (vi) a diagnostic module, wherein said module may comprise (a) a database of individual-specific medication, cannabinoid and Cannabaceae phytochemicals treatment profiles; (b) a statistical analysis component performing z-score evaluations of individual data; and (c) a machine learning module trained on metabolic pathways, mass spectrometry, and treatment outcome data; and, (vii) a personalization module for medical Cannabaceae-based treatments including: (a) identifying suitable Cannabaceae phytochemicals treatments; (b) mapping previously unknown correlations using machine learning; (c) updating a database with personalized treatment recommendations; (d) predicting potential effectiveness of medical Cannabaceae-based treatments; and, (e) provide iterative improvements to treatments based on monitored individual responses.

[0018] Provided herein are systems for determining Cannabaceae-based treatments comprising: (i) a biological sample test module, wherein the module maybe configured to: (a) enable individuals to collect at least one biological sample, wherein the biological sample can comprise saliva, blood, Urine, Cerebrospinal Fluid, tissue, hair, exhaledbreath condensate, tears, feces or sweat. In some embodiments, the biological sample comprises saliva; (b) store the at least one biological sample. In some embodiments, the storage of the at least one biological sample may comprise a drool collection kit; and (c) maintain the at least one biological sample in optimal condition while monitoring and preserving it during transportation. In some embodiments, the biological sample is stored at about -20 °C for up to about 24 hours; (ii) a sample processing module, wherein the module may be configured to: (a) extract metabolites from a biological sample. In some embodiments, the extraction of metabolites from a biological sample comprises extracting the metabolites using chromatography methods. In some embodiments the chromatography method is selected from the group consisting of liquid chromatography or gas chromatography. In some embodiments, the chromatography method comprises liquid chromatography; and (b) determining metabolite characteristics from the biological sample. In some embodiments, the metabolite characteristics of the biological sample comprises quantified levels of metabolites. In some embodiments, the quantification of levels of metabolites comprises Spectroscopy -Based Techniques. In some embodiments, the spectroscopy -based technique comprises mass spectrometry. In some embodiments, the metabolite characteristics maybe selected from at least one of the groups consisting of mammalian metabolites, plant metabolites, microbial metabolites, synthetic metabolites, or any combination thereof. In some embodiments, the metabolites quantified and determined comprise Cannabaceae -derived molecules. In some embodiments, the metabolites comprise endocannabinoid-system metabolic markers. In some embodiments, the quantified and determined metabolites comprise Cannabaceae -responsive biomarkers, groups associated with medical conditions, metabolic responses, cohort profiles, individual profiles, or any combinations thereof. In some embodiments, the quantified and determined metabolites comprise lipid metabolites. In some embodiments, the metabolites can comprise Cannabaceae contaminants. In some embodiments the Cannabaceae contaminants comprise unwanted Canna- baceae-derived molecules. In some embodiments, the metabolites comprise specific chemicals or residues associated with Cannabaceae-derived products; (iii) a data management module, wherein the module comprises: (a) a database of individual metabolite levels and timestamps of Cannabaceae-based treatments. In some embodiments, the database of individual metabolite levels and timestamps comprises metabolic profiles, including levels of cannabinoids and their metabolites, lipid metabolites, amino acids, and inflammatory markers; (b) a database of individual diagnostic information. In some embodiments, the individual diagnostic information comprises a database of metabolic profiles, historical treatment data, Cannabaceae-specific metabolic responses, contaminants detected in biological samples, and data representations of annotated molecule features and interactions obtained through multi-omics analysis; (c) a database of individual condition or state evaluations, and timestamps, with and without Cannabaceae-based treatments. In some embodiments, the individual diagnostic information comprises a database of treatment regimens and outcomes, storing data on cannabis formulations, dosages, and patient responses; and (d) a database of individual medication and Cannabaceae-derived treatment compositions. In some embodiments, the database of individual medication and Cannabaceae-derived treatment compositions includes cannabis-responsive biomarkers, individual condition or state evaluations, timestamps, metabolic profiles, including levels of cannabinoids and their metabolites, lipid metabolites, amino acids, and inflammatory markers linked to individual metabolic deviations, treatment efficacy or any combination thereof . In some embodiments, the data management module may further comprise a knowledge database containing curated metabolic data from public and proprietary sources, integrated through automated workflows for machine learning applications. In some embodiments, the database of individual conditions further comprises longitudinal data capturing variations in endocannabinoid system -metabolic levels over time with and without Cannabaceae-based treatments. In some embodiments, the data management module may further comprise a bioinformatics processing pipeline derived database, which stores pre-processed and normalized metabolomic data for cross -functional integration and machine learning model training. In some embodiments, the data management module may further comprise a distributed database system for real-time access, retrieval, and storage of patient-specific metabolic and treatment data across multiple computing platforms; (iv) a statistical analysis module, wherein the statistical analysis comprises (a) performing z -score evaluations. In some embodiments, the z-score evaluation comprises analyzing relationships between individual endocannabinoid system metabolic levels and database information from at least one of the (iii) databases, wherein the z-score is calculated by comparing individual metabolite levels to a reference population mean and standard deviation. In some embodiments, the z-score evaluations may include conditions, diagnostics, Cannabaceae -derived treatment effects, metabolite deviations, biomarker shifts over time, or any combinations thereof, to quantify metabolic responses to Cannabaceae-based treatments; (b) associating mass spectrometry -detected metabolite levels with individual data in a database. In some embodiments, the mass spectrometry data includes intensity values corresponding to various m/z ratios and elution times from Liquid Chromatography-Mass Spectrometry( LC-MS) and Gas Chromatography -Mass Spectrometry (GC- MS analyses), stored as arrays or matrices with axes representing m/z ratios and retention times, and linked to individual biological samples and metabolic profiles; and (c) correlating individual metabolic data with timestamps of Cannabaceae-based treatments. In some embodiments, metabolic profiles at multiple time points, including pre-treatment (PRE), peak effect (PEAK), and post-treatment intervals, are associated with the specific cannabinoid dosages administered, and analyzed using machine learning models to determine biomarker shifts over time. In some embodiments, the statistical analysis module can be further configured to identify correlations between specific endocannabinoid system -metabolic markers and treatment efficacy; (v) a machine learning module, wherein said module may comprise: a) at least one machine learning model trained to predict any attribute or any group of attributes within data based on other database attributes, wherein the databases may include, but are not limited to, any one of the databases described in (iii). In some embodiments, the attribute or group of attributes can comprise individual metabolic profiles, cannabis treatment outcomes, cannabinoid dosages, metabolic shifts overtime, specific metabolite responses linked to behavioral changes in individuals. In some embodiments, cannabinoid dosages may include THC (0-50 mg), CBD (0-200 mg), and CBG (0-50 mg). In some embodiments, at least one machine learning model can be trained on: b) chromatography data. In some embodiments, the chromatography data comprises liquid chromatography data;

1) Spectroscopy data. In some embodiments, the spectroscopy data comprises mass spectrometry data;

2) metabolic pathways. In some embodiments, the metabolic pathways can be obtained from in-house databases or external databases; and,

3) treatment outcome data. c) one training system for machine learning models. In some embodiments, the training system is configured to divide data into training and test datasets, normalize metabolic data, and train an unsupervised neural network to map high -dimensional input vectors (e.g., metabolic profiles) to a low -dimensional latent space for predictive modeling and anomaly detection. In some embodiments, the machine learning model includes analysis of biomarker deviations, contaminants, and treatment outcomes over time.

[0019] At least one machine learning model to identify complex, nonlinear relationships within databases. In some embodiments, the machine learning model comprises a Neural Network trained to map high-dimensional input data, such as metabolic profiles and cannabinoid treatment data, to a score value, enabling the measurement of Cannabaceae-based treatments.

[0020] In some embodiments, the machine learning module may be configured to generate probabilities as indicative of physiological conditions. In some embodiments, the machine learning model can be trained using datasets of metabolic profiles, cannabinoid treatment dosages, and patient response data. In some embodiments the machine learning model can be configured to apply gradient boosting algorithms to classify samples and predict treatment outcomes. In some embodiments, the machine learning model can be configured to rank the importance of metabolites. In some embodiments, the machine learning module may further comprise a neural network trained on datasets of metabolic levels, diagnostic data, and treatment outcomes to enhance prediction accuracy; (vi) a diagnostic module, wherein said module may comprise: (a) a database of individual-specific medication, cannabinoid, Cannabaceae phytochemicals treatment profiles or any combinations thereof. In some embodiments, the diagnostic module further comprises individual metabolic profiles, mass spectrometry data, cannabinoid dosage records, timestamps of Cannabaceae treatments, patient-specific biomarkers, and longitudinal metabolic data linked to specific treatment outcomes; (b) a statistical analysis component performing z-score evaluations of individual data. In some embodiments, the z-score evaluations include the analysis of metabolic deviations from baseline values, tracking changes in response to cannabinoid treatments, integration of time-stamped metabolite data, or any combinations thereof. In some embodiments, the diagnostic module can be configured to assess treatment efficacy and patient response over time. In some embodiments, z-score calculation can include adjustments based on cohort-specific averages for subpopulations. In some embodiments, subpopulation may be defined by demographic or medical characteristics; (c) a machine learning model trained on: (1) chromatography data. In some embodiments, the chromatography data comprises liquid chromatography data; (2) Spectroscopy data. In some embodiments, the spectroscopy -based data comprises mass spectrometry data; (3) metabolic pathways. In some embodiments, the metabolic pathways can be obtained from in-house databases or external databases; and (4) treatment outcome data. In some embodiments, the machine learning model may be configured to generate probabilities as indicative of physiological conditions. In some embodiments, the machine learning model is trained using datasets of metabolic profiles, cannabinoid treatment dosages, and patient response data. In some embodiments the machine learning model is configured to apply gradient boosting algorithms to classify samples and predict treatment outcomes. In some embodiments, the machine learning model can be configured to rank the importance of metabolites. In some embodiments, the diagnostic module may be configured to generate treatment recommendations tailored to individual metabolic and diagnostic profiles; and (vii) a personalization module for medical Cannabaceae-based treatments including: (a) identifying suitable Cannabaceae phytochemicals treatments based on individual diagnostics. In some embodiments, the module utilizes patientspecific metabolomic profiles, diagnostic data, treatment history or any combination to recommend Cannabaceae-based formulations; (b) mapping previously unknown correlations using machine learning algorithms to uncover insights into metabolic pathways. In some embodiments, machine learning algorithms analyze metabolic data, treatment outcomes, and biomarker deviations to reveal novel relationships between endocannabinoid system metabolites and Cannabaceae phytochemicals. In some embodiments the analysis comprises identifying metabolic shifts, clustering patient response patterns, and predicting optimal cannabinoid formulations. In some embodiments, machine learning algorithms, including Gradient Boosting, Random Forest, Support Vector Machines (SVMs), Artificial Neural Networks (ANNs), and Graph Neural Networks (GNNs), are used to classify metabolic profiles, wherein classification can be performed by predictingindividuals treatment response category (e.g., high responders, partial responders, and non-responders) based on biomarker shifts and clinical symptom assessments; by identifying significant biomarkers from high-dimensional data, wherein feature selection methods such as Shapley Additive Explanations (SHAP), LASSO regression, and Recursive Feature Elimination (REE) can be employed to rank metabolites based on their predictive value for treatment efficacy; and/or by mapping metabolic pathway interactions associated with Cannabaceae -based treatments, wherein metabolic pathway analysis is conducted using multi -omics integration techniques, including gene-metabolite network analysis, pathway enrichment analysis, and Bayesian inference models.; (c) updating a database with personalized treatment recommendations. In some embodiments, the system is configured to continuously update individual treatment profiles. In some embodiments, the system may integrate new metabolic data and patient responses fortailored Cannabaceae-based therapy recommendations; (d) predicting potential effectiveness of medical Cannabaceae-based treatments. In some embodiments, predictive models may assess the likelihood of therapeutic success. In some embodiments the likelihood of therapeutic success comprises comparing patient-specific metabolic data with historical treatment outcomes stored in a database; and (e) provide iterative improvements to treatments based on monitored individual responses.

[0021] In some embodiments, feedback loops within the system allow for real-time adjustment of treatment protocols by analyzing patient metabolic responses overtime. In some embodiments, feedback loops within the system can be configured to analyze longitudinal metabolic data to adjust cannabinoid dosages and formulations dynamically. In some embodiments, the treatments are refined in real-time as new patient data becomes available. In some embodiments, the personalization module may be configured to generate treatment recommendations tailored to individual metabolic and diagnostic profiles. In some embodiments, the personalization module can be further configured to provide probability -based assessments of treatment outcomes based on historical individual data. In some embodiments, the personalization module further comprises a predictive analytics engine to determine long-term individual outcomes for specific cannabinoid-based treatments. In some embodiments, the machine learning module integrates realtime metabolic data to dynamically update training models and improve prediction accuracy. In some embodiments, the treatment efficacy module further comprises a feedback loop configured to enable real-time updates to treatment recommendations based on individual metabolic and symptomatic data. In some embodiments, the system can further comprise a metabolite -level database that integrates longitudinal data for tracking individual metabolic responses to Canna- baceae-derived treatments overtime. In some embodiments, the system can comprise a user interface for individuals to view predictions, treatment plans, and track progress based on their metabolic profiles. In some embodiments, the system further comprises the step of visualizing changes in z-scores and predicted Cannabaceae-derived molecules dosages through a graphical user interface. In some embodiments, the system can be implemented as a mobile application for individuals to access personalized treatment plans and track their progress. INCORPORATION BY REFERENCE

[0022] All publications, patents, and patent applications mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent, or patent application was specifically and individually indicated to be incorporated by reference.

BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The novel features of the disclosure are set forth with particularity in the appended claims. Abetter understanding of the features and advantages of the present disclosure will be obtained by reference to the following detailed description that sets forth illustrative embodiments, in which the principles of the disclosure are utilized, and the accompanying drawings (also “figure” and “FIG.” herein), of which:

[0024] FIG. 1 : Shows an exemplary diagram of a modular system for implementing a method for determining and measuring Cannabaceae-based treatments. 101 : Shows an exemplary representation of a biological sample collected from a subject. 102: Shows an exemplary sample processing module configured to prepare and extract molecular or biochemical data from the biological sample.: Shows an exemplary data management module configured to store, organize, and retrieve metabolomics or clinical data for downstream analysis. 104: Shows an exemplary statistical analysis module configured to evaluate biomarker distributions, trends, and treatment -related changes. 105: Showsan exemplary machine learning module trained to identify patterns and classify cannabis-responsive biomarker profiles. 106 Shows an exemplary diagnostic module configured to assess physiological conditions and identify therapeutic needs based on biomarker output. 107: Shows an exemplary personalization module for generating individualized medical Cannabaceae-based treatment recommendations.

[0025] FIG. 2: Shows an exemplary image of numerical scales of major cannabinoids and behavioral rating surveys used for datasets of children with ASD.

[0026] FIG. 3 : Shows an exemplary image of identification of potential ASD cannabis-responsive biomarkers that distinguish categories of patients. 301 : Shows an exemplary Venn diagram illustrating the unique and overlapping differentially -expressed cannabis-responsive biomarkers found in the categories of patients with ASD PRE/ASD PEAK, ASD PRE and ASD PEAK and TD/ASD PRE/ASD PEAK. The biomarker roles (lipid metabolism, neuroactivity and steroid activity) are color coded (white, gray and light gray, respectively). 302: Shows exemplary graphs of levels of potential cannabis-responsive biomarkers found in children with ASD at PRE (gray) and PEAK (light gray), and TD group (dark gray) in the overlapping categories described in (A). Each box plot horizontally enclosed by the lower and upper quartiles and median (solid horizontal line within the box) is indicated. The overlapping categories are indicated in the upper right corner..

[0027] FIG. 4: Shows an exemplary graph of identification of plant non-cannabinoid secondary metabolites (dietary phytochemical) that distinguish categories of patients. 401 : Shows an exemplary Venn diagram illustrating the unique and overlapping dietary phytochemicals found in the categories of patients ASD PRE/ASD PEAK, ASD PRE and ASD PEAK and TD/ASD PRE/ASD PEAK. 402: Shows an exemplary Levels of dietary phytochemicals found in children with ASD at PRE (black) and PEAK (gray), and TD group (light gray) in the overlapping categories described in (401). Each box plot horizontally enclosed by the lower and upper quartiles and median (solid horizontal line within the box) is indicated. The overlapping categories are indicated in the upper right comer. 402 A: Shows an exemplary bar graph representing the distribution of Corosolic acid. 402B: Shows an exemplary bar graph representing the distribution of Flavanone. 402C: Shows an exemplary bar graph representing the distribution of Zeaxanthin. 402D: Shows an exemplary bar graph representing the distribution of Naringenin. 402E: Shows an exemplary bar graph representing the distribution of Vitexin. 402F: Shows an exemplary bar graph representing the distribution of Rutin. 402G: Shows an exemplary bar graph representing the distribution of Sitosterol. 403 : Shows an exemplary graph representing time dependent levels of vitexin (apigenin 8-glucoside) detected at time points PRE (10 min before MC treatment), PEAK, Post-1 and Post-2 (90, 180 and 270 min after MC treatment, respectively) in child ID Al 8 of FIG. 2. 404: Shows an exemplary graph representing time dependent levels of rutin (quercetin 3 - rutinoside) detected at time points described in (C) in child ID A16 of FIG. 2.

[0028] FIG. 5 : Shows an exemplary Venn diagram illustrating the unique and overlapping cannabis-responsive biomarkers that respond (PRE/PEAK) to THC, CBD and CBG treatment. The biomarker functions (lipid metabolism, neuroactivity and steroid activity) are color coded (white, gray and light gray, respectively). 50 IB: Shows an exemplary representing CBG-respon- sive biomarkers. 502: Shows an exemplary graph representing potential THC -responsive biomarkers. 503 : Shows an exemplary graph representing potential CBD -responsive biomarkers.

[0029] FIG. 6: Shows exemplary simplified metabolic pathways associated with the differential expression of potential ASD cannabis-responsive biomarkers after THC, CBD and CBG treatment. Potential ASD cannabis-responsive biomarkers directly respond to THC, CBD and CBG found in the metabolic pathways of lysoglycerophospholipids, sphingolipid, fatty acid oxidation, anandamide and ethanolamine-phosphate (EthN-P), and their impact on ASD and depression, are indicated. [0030] FIG. 7: Shows an exemplary graph of Computer implementation system. 701 : Shows an exemplary graph of a computer system configured for data acquisition, processing, and output generation. 702: Shows an exemplary graph of a central processing unit configured to execute instructions. 703 : Shows an exemplary graph of a system component configured to communicate with one or more remote computer systems through a network. 704: Shows an exemplary graph of a memory or memory location for storing data. 705: Shows an exemplary graph of an electronic storage unit configured to store raw data, processed outputs, and model parameters. 706: Shows an exemplary graph of one or more peripheral devices configured to support data input and output operations. 707 : Shows an exemplary graph of a communication interface for transmitting data between system components. 708: Shows an exemplary graph of a user interface enabling user interaction with the system. 709: Shows an exemplary graph of an electronic display.

DETAILED DESCRIPTION

[0031] Provided herein are methods and systems for determining and measuring Canna- baceae-based treatments, wherein the method may determine treatments to restore or maintain healthy physiological levels of one or more metabolites and/or biomarkers using Cannabaceae- derived molecules and the system may provide modules wherein the methods may be implemented.

[0032] Linking the complex biochemical interactions between Cannabaceae -derived molecules and individual metabolic profiles is a critical challenge in personalized medicine. There is a pressing need for comprehensive systems that integrate metabolomic data, machine learning algorithms, and cannabinoid-specific responses to optimize therapeutic outcomes. Variability in individual metabolic states, including the endocannabinoid system, underscores the necessity for methods capable of capturing, analyzing, and adapting to this complexity. Implementing Al - driven pharmacometabolomic across diverse clinical and biological domains enables the development of dynamic, individualized treatment protocols that respond to metabolic feedback in real time. This invention addresses the unmet need by providing systems and methods that leverage advanced machine learning to process multi-dimensional metabolic data, identify relevant biomarkers, and iteratively refine Cannabaceae-based treatments, ensuring precise and effective therapeutic interventions.

[0033] While various embodiments of the present application have been shown and described herein, it will be obvious to those skilled in the art that such embodiments are provided by way of example only. Numerous variations, changes, and substitutions may occur to those skilled in the art without departing from the invention. It should be understood that various alternatives to the embodiments of the invention described herein may be employed.

[0034] Throughout this application, various embodiments may be presented in a range format. It should be understood that the description in range format is merely for convenience and brevity and should not be construed as an inflexible limitation on the scope of the disclosure. Accordingly, the description of a range should be considered to have specifically disclosed all the possible subranges as well as individual numerical values within that range. For example, description of a range such as from 1 to 6 should be considered to have specifically disclosed subranges such as from 1 to 3, from 1 to 4, from 1 to 5, from 2 to 4, from 2 to 6, from 3 to 6 etc., as well as individual numbers within that range, for example, 1, 2, 3, 4, 5, and 6. This applies regardless of the breadth of the range.

[0035] As used in the specification and claims, the singular forms “a,” “an,” and “the” include plural references unless the context clearly dictates otherwise. For example, the term “a sample” includes a plurality of samples, including mixtures thereof.

[0036] Whenever the term “at least,” “greater than,” or “greater than or equal to” precedes the first numerical value in a series of two or more numerical values, the term “at least,” “greater than” or “greater than or equal to” applies to each of the numerical values in that series of numerical values. For example, greater than or equal to 1, 2, or 3 is equivalent to greater than or equal to 1, greater than or equal to 2, or greater than or equal to 3.

[0037] Whenever the term “no more than,” “less than,” or “less than or equal to” precedes the first numerical value in a series of two or more numerical values, the term “no more than,” “less than,” or “less than or equal to” applies to each of the numerical values in that series of numerical values. For example, less than or equal to 3, 2, or 1 is equivalent to less than or equal to 3, less than or equal to 2, or less than or equal to 1.

[0038] “ About” with reference to a number refers to that number plus or minus 15% of that number. The term “about” a range refers to that range minus 15% of its lowest value and plus 15% of its greatest value.

[0039] The term “healthy physiological levels” or “control physiological levels” or “healthy levels” as used interchangeably herein, generally refers to a range of metabolic, biochemical, or physiological markers observed in individuals without pathological conditions, including but not limited to metabolic biomarkers associated with homeostasis, normal neurotransmitter function, balanced oxidative stress levels, and typical inflammatory responses.

[0040] The term “Cannabaceae,” “Cannabaceae-based,” or “Cannabaceae-derived” as used interchangeably herein, generally refers to compounds, extracts, or derivatives originating from the Cannabaceae family of plants, including but not limited to cannabinoids (such as THC, CBD, CBG), terpenes, flavonoids, and other phytochemicals present in Cannabis sativa, Cannabis in- dica, and related species.

[0041] The term "cannabinoid", as used interchangeably herein, generally refers to bioactive compounds that interact with cannabinoid receptors within the endocannabinoidome (eCBome), including but not limited to phytocannabinoids derived from Cannabis species (such as THC, CBD, CBG), synthetic cannabinoids, and endocannabinoids naturally produced in the human body (such as anandamide and 2-AG). The eCBome comprises, but is not limited to, these endocannabinoids as well as eCB-like lipid mediators (e.g., N-palmitoylethanolamine (PEA), N- oleoylethanolamine (OEA), and 2 -oleoylglycerol (2-OG)), their metabolic enzymes (fatty acid amide hydrolase (FAAH), monoacylglycerol lipase (MAGL), N-acylethanolamine acid amidase (NAAA), and a/p-hydrolases ABHD6 and ABHD12), and their molecular targets beyond CB1 and CB2 receptors, such as peroxisome proliferator-activated receptors (PPARa, PPARy), transient receptor potential (TRP) channels, and orphan G-protein coupled receptors (GPR18, GPR55, GPR119).

[0042] The term “metabolite” as used herein, generally refers to any molecule produced or utilized during metabolic processes within a biological system, including but not limited to amino acids, lipids, carbohydrates, organic acids, neurotransmitters, hormones, and signaling molecules that can be quantitatively measured in biological samples such as saliva, blood, and urine.

[0043] The term “individual”, “patient”, “subject” or “user” as used interchangeably herein, generally refers to a human subject undergoing medical evaluation or treatment, including but not limited to individuals receiving Cannabaceae-based therapies for neurological, psychiatric, inflammatory, or metabolic conditions.

[0044] The term “treatment” as used herein, generally refers to the administration of therapeutic agents or interventions, including but not limited to Cannabaceae-based compounds, to manage, alleviate, or modify the symptoms, progression, or underlying causes of a medical condition in an individual.

[0045] The term “peak effect” or “PEAK” as used interchangeable herein generally refers to the time point at which the maximal physiological or symptomatic impact of a Cannabaceae- based treatment is observed, as determined through observational methods, including but not limited to changes in metabolite levels, behavioral assessments, or other relevant biomarkers indicative of treatment response. [0046] The term “determining,” “measuring,” and “evaluating,” as used herein, should be interpreted broadly to include qualitative and quantitative assessments, including but not limited to detecting, analyzing, calculating, estimating, comparing, and interpreting data related to metabolic profiles, biomarker levels, physiological conditions, treatment responses, and any other relevant biological or clinical parameters.

[0047] There are several utilities and advantages of the methods and systems disclosed herein, such as, for example, (i) providing flexibility to tailor Cannabaceae -based treatments for different individuals, groups, orpopulations with various medical conditions and metabolic profiles; (ii) providing adaptability to adjust cannabis formulations and dosages based on real-time metabolic data without altering the overall treatment methodology; (iii) providing for the selection of personalized Cannabaceae-derived treatments based on metabolic biomarkers, genetic predispositions, and physiological conditions of individuals or subpopulations; (iv) providing for comprehensive metabolic profiling and classification of individuals and groups based on cannabis response biomarkers, enabling precise and scalable therapeutic interventions; (v) providing for iterative adjustments to treatment regimens through machine learning algorithms that continuously update based on new metabolic data and monitored responses from individuals or populations; (vi) providing for the discovery of novel correlations between Cannabaceae-derived molecules and metabolic pathways using machine learning, thereby enhancing the understanding of cannabinoid metabolism and its therapeutic potential; (vii) providing for one-time, multiple-time, or ongoing monitoring of metabolic responses to Cannabaceae-based treatments at both individual and population levels; and (viii) providing for one-time, multiple-time, or ongoing optimization of cannabis-based treatment protocols to ensure sustained therapeutic efficacy and safety across diverse patient populations.

[0048] In some embodiments, the system and methods disclosed herein are applicable to a range of medical conditions, including but not limited to: Alzheimer’s disease, Anorexia Nervosa, Anxiety Disorders, Appetite Loss, Arthritis, Autism Spectrum Disorder, Autoimmune Disease, Body Aches, Brain Injury, Bulimia Nervosa, Cachexia/Wasting Syndrome, Cancer and related conditions, CaudaEquina, Cerebral Palsy, Chemotherapy -induced Anorexia, Chronic Debilitating Migraines, Chronic Motor Tic, Chronic Nervous System Disorders, Chronic or Debilitating Disease, Chronic Pain, Chronic Pancreatitis, Chronic Renal Failure, Chronic Traumatic Encephalopathy, CIDP, Colitis, Complex Regional Pain Syndrome, Corticobasal Degeneration, Crohn’s Disease, Cystic Fibrosis, Debilitating Psychiatric Disorders, Decompensated Cirrhosis, Dementia, Depression, Diabetes, Dravet Syndrome, Dyskinetic CP, Dysmenorrhea, Dystonia, Ehlers-Danlos Syndrome, Endometriosis, Epilepsy, Fibromyalgia, Fibrous Dysplasia, Friedreich’s Ataxia, Glaucoma, Hepatitis C, Huntington’s Disease, Hydrocephalus, Hydromye- lia, IBD, IBS, Inflammation, Interstitial Cystitis, Lennox -Gastaut Syndrome, Lewy Body Disease, Loss of Appetite, Lupus, MALS Syndrome, Migraine, Mitochondrial Disease, MS, Muscle Pain, Muscle Spasms, Muscular Dystrophy, Myasthenia Gravis, Myoclonus, Nausea or Severe Vomiting, Neuropathy, OCD, Parkinson’s Disease, Peripheral Neuropathy, PTSD, Rheumatoid Arthritis, Seizures, Sickle Cell Anemia, Sjogren’s Syndrome, Tourette’s Syndrome, Traumatic Brain Injury, and Ulcerative Colitis.

[0049] In some embodiments, the Cannabaceae-derived molecules analyzed and measured can include but are not limited to: 10-Ethoxy-9-hydroxy-delta-6a-tetrahydrocannabinol, 10-Oxo- delta-6a-tetrahydrocannabinol (OTHC), 8,9-Dihydroxy-delta-6a-tetrahydrocannabinol, Canna- bichromanon (CBCF), Cannabichromene (CBC), Cannabichromenic acid (CBCA), Canna- bichromevarin (CBCV), Cannabichromevarinic acid (CBCVA), Cannabicyclol (CBL), Cannabi- cyclolic acid (CBLA), Cannabicyclovarin (CBLV), Cannabidiol (CBD), Cannabidiol monometh- ylether (CBDM), Cannabidiolic acid (CBD A), Cannabidiorcol (CBD -Cl), Cannabidivarin (CBDV), Cannabidivarinic acid (CBDVA), Cannabielsoic acid B (CBEA-B), Cannabielsoin (CBE), Cannabielsoin acid A (CBEA-A), Cannabifuran (CBF), Cannabigerol (CBG), Can- nabigerol monomethylether (CBGM), Cannabigerolic acid (CBGA), Cannabigerolic acid monomethylether (CBGAM), Cannabigerovarin (CBGV), Cannabigerovarinic acid (CBGVA), Cannabinodiol (CBND), Cannabinodivarin (CBVD), Cannabinol (CBN), Cannabinol methylether (CBNM), Cannabinol-C2 (CBN-C2), Cannabinol-C4 (CBN-C4), Cannabinolic acid (CBNA), Cannabiorcool (CBN-C1), Cannabiripsol (CBR), Cannabitriol (CBT), Cannabitriol- varin (CBTV), Cannabivarin (CBV), Cannbicitran (CBT), Dehydrocannabifuran (DCBF), Delta -

8-tetrahydrocannabinol (A8-THC), Delta-8-tetrahydrocannabinolic acid (A8-THCA), Delta-9- cis-tetrahydrocannabinol (cis-THC), Delta-9-tetrahydrocannabinol (THC), Delta-9-tetrahydro- cannabinol-C4 (THC-C4), Delta-9-tetrahydrocannabinolic acid A (THCA-A), Delta-9 -tetrahy- drocannabinolic acidB (THCA-B), Delta-9-tetrahydrocannabinolic acid-C4 (THCA-C4), Delta-

9-tetrahydrocannabiorcol (THC-C1), Delta-9-tetrahydrocannabiorcolic acid (THCA-C1), Delta- 9-tetrahydrocannabivarin (THCV), Delta-9-tetrahydrocannabivarinic acid (THCVA), and Tryhy- droxy-delta-9-tetrahydrocannabinol (triOH-THC).

[0050] Provided herein are methods and systems for determining and measuring Canna- baceae-based treatments. Wherein the method may determine treatments to restore healthy physiological levels using Cannabaceae-derived molecules and the system may provide modules wherein the methods may be implemented. [0051] In some embodiments, the method approach applied to the systems may utilize a pipeline, as shown in FIG. 1.

[0052] The systems disclosed herein, including computer systems FIG. 7, may comprise one or more non -transitory computer readable storage media 705 encoded with computer program instructions that, when executed by one or more computers, cause the one or more computers to perform operations including training or operation of a machine learning model with input modalities of metabolomic data assigned to a plurality of individual or population-based biological samples. In some embodiments, the input modalities comprise multi-omics data, including metabolic profiles, cannabinoid treatment data, and diagnostic information. In some embodiments, the training comprises learning a low-dimensional representation of the plurality of biological samples. In some embodiments, the training or operation comprises identifying clusters within the plurality of biological samples in the low-dimensional representation, including clusters associated with Cannabaceae-based treatment responses, metabolic deviations, andbiomarker profiles.

Method

[0053] Provided herein are methods for determining and measuring treatments to restore or maintain healthy physiological levels of one or more metabolites and/or biomarkers using Can- nabaceae-derived molecules comprising: (i) obtaining biological samples from at least one subject; (ii) analyzing the samples to quantify levels of one or more metabolites; and (iii) providing the treatment to the subject.

[0054] Provided herein are methods for determining and measuring Cannabaceae-based treatments comprising: (i) obtaining biological samples from at least one subject; (ii) analyzing the samples to quantify levels of one or more metabolites; (iii) generating a database wherein the data comprises relationships between the individual's information and metabolic data; and (iv) providing the treatment to the subject.

[0055] Provided herein are methods for determining and measuring treatments to restore or maintain healthy physiological levels of one or more metabolites and/or biomarkers using Can- nabaceae-derived molecules comprising: (i) obtaining biological samples from at least one subject; (ii) analyzing the samples to quantify levels of one or more metabolites; (iii) generating a database wherein the data comprises relationship sb etween the individual's information and metabolic data; (iv) calculating z-scores in metabolite levels in individuals; and (v) providing the treatment to the subject.

[0056] Provided herein are methods for determining and measuring treatments to restore or maintain healthy physiological levels of one or more metabolites and/or biomarkers using Can- nabaceae-derived molecules comprising: (i) obtaining biological samples from at least one subject; (ii) analyzingthe samples to quantify levels of one or more metabolites; (iii) generating a database wherein the data comprises relationships between the individual's information and metabolic data; (iv) calculating z-scores in metabolite levels in individuals; (v) estimating the treatment of Cannabaceae-derived molecules or mixture of Cannabaceae-derived molecules required to normalize the metabolite z-score toward approximately 0; and (vi) providing the treatment to the subject.

[0057] Provided herein are methods for determining and measuring treatments to restore or maintain healthy physiological levels of one or more metabolites and/or biomarkers using Cannabaceae-derived molecules comprising: (i) obtaining biological samples from at least one individual, wherein the biological sample may comprise saliva; (ii) analyzingthe samples to quantify levels of metabolites, including Cannabaceae-responsive biomarkers; (iii) generating a database, wherein the data comprises relationships between the individual's information and metabolic data; (iv) calculating z-scores in metabolite levels in individuals, defined as the number of standard deviations from the mean of at least one physiological range observed in a healthy population; (v) estimating the treatment of Cannabaceae-derived molecules or mixture of Cannabaceae-derived molecules required to normalize the metabolite z-score toward approximately 0; and (vi) providing the treatment to the subject.

[0058] Provided herein are methods for determining and measuring Cannabaceae-based treatments to restore healthy physiological levels using Cannabaceae-derived molecules, comprising: (i) obtaining biological samples from at least one individual, wherein the biological sample may comprise saliva, blood, Urine, Cerebrospinal Fluid, tissue, hair, exhaled breath condensate, tears, feces or sweat; (ii) analyzingthe samples to quantify levels of metabolites, including Cannabaceae-responsive biomarkers, wherein the analysis of samples to quantify levels of metabolites comprise Spectroscopy-Based Techniques, Chromatography -Based Techniques, Optical and Fluorescence-Based Techniques, Immunoassay and Biosensor-Based Techniques, Separation-Based Techniques, Isotope-Based Techniques, Electrochemical Techniques or any combination thereof, wherein the metabolites may comprise at least one of the groups consisting of mammalian metabolites, plant metabolites, microbial metabolites and any combination thereof; (iii) generating a database wherein the data comprises relationships between the individual's information and metabolic data, wherein each metabolite detected in a sample obtained from the individual is categorized into at least one category, wherein the at least one category may comprise at least one of the group consisting of endocannabinoid system -related metabolites; groups associated with medical conditions; metabolic responses, cohort profiles, individual profiles and any combinations thereof; (iv) calculating z-scores of metabolite levels in individuals, defined as the number of standard deviations from the mean of at least one physiological range observed in a healthy population; (v) estimating the treatment of Cannabaceae-derived molecules or mixture of Cannabaceae-derived molecules required to normalize the metabolite z -score toward approximately 0, wherein the z-score calculation can include adjustments based on cohort-specific averages for subpopulations defined by demographic or medical characteristics. In some implementations of the method, the biological sample is saliva. In some embodiments, the analysis of samples to quantify levels of metabolites comprises mass spectrometry. In some embodiments, the quantified metabolites consist of mammalian metabolites. In some embodiments, the quantified metabolites consist of plant metabolites. In some embodiments, the category in which the metabolites are categorized comprises endocannabinoid system -related metabolites. In some embodiments, the category in which the metabolites are categorized can include medical conditions, metabolic responses, cohort profiles, individual profiles, or any combination thereof. In some embodiments the z-score calculations may include adjustments based on cohort-specific averages for subpopulations defined by demographic or medical characteristics.

[0059] In some embodiments, the databases may further comprise a database of Canna- baceae contaminants detected in the biological sample of at least one individual who has consumed Cannabaceae-derived molecules. In some embodiments, the Cannabaceae contaminants can further comprise entries for specific chemicals or residues associated with Cannabaceae-derived products. In some embodiments, the databases can further comprise a metabolite-level database that integrates longitudinal data for tracking individual metabolic responses to Cannabaceae-derived treatments overtime. In some embodiments, the databases may further comprise a database of predictions, wherein the database is generated by implementing machine learning algorithms to improve the accuracy of dosage recommendations of Cannabaceae-derived treatments.

[0060] In some embodiments, the quantification of metabolites by mass spectrometry can further comprise chromatography technique to enhance metabolite detection accuracy; and (vi) providing the treatment to the subject. In some embodiments, providing the treatment to the subject can comprise generating treatment outputs, wherein recommended treatments may comprise written treatment protocols specifying but not limited to cannabinoid type, dosage amount, administration frequency, and route of administration, based on the predicted metabolic response and individual conditions. In some embodiments, the route of administration can comprise at least one of: Oral administration, including capsules, tablets, oils, tinctures, and edibles; Sublingual or buccal administration, including dissolvable strips, sprays, and oils applied under the tongue; Inhalation, including vaporized formulations or aerosolized delivery; Topical administration, including creams, patches, or gels applied to the skin; Transdermal delivery, comprising slow-release patches; or Rectal or vaginal administration, using suppositories. In some embodiments, written treatment protocols may be updated automatically or manually in response to newly collected metabolic data and ongoing evaluation of subject responses, allowing for iterative refinement of Cannabaceae-based therapy.

[0061] In some embodiments, the database of endocannabinoid system -related metabolites includes correlations between specific Cannabaceae -derived molecules and their impact on z- score changes. In some embodiments, the cannabis contaminants information is used to identify potential interactions between Cannabaceae-derived molecules, Cannabaceae contaminants and metabolic responses. In some embodiments, the method may further comprise a step for generating personalized treatments plans for individuals. In some embodiments, the personalized treatment may be based on metabolite -lev el data and predicted Cannabaceae-derived molecule treatments. In some embodiments, the method can further comprise generating Cannabaceae-derived molecule combinations and dosages.

[0062] In some embodiments, the method can be implemented on a software and/or computer application. In some embodiments, the application can be implemented in mobile devices.

Systems

[0063] In some embodiments, the systems for determining Cannabaceae-based treatments FIG. 1 comprises: (i) a biological sample collection module 101; (ii) a sample processing module 102; (iii) a data management module 103; (iv) a statistical analysis module 104; (v) a machine learning module 105; (vi) a diagnostic module 106; (vii) a personalization module for medical Cannabaceae-based treatments 107; and (viii) a treatment provider module 107.

[0064] In some embodiments the systems for determining Cannabaceae-based treatments FIG. 1 comprises: (i) a biological sample test module 101, wherein the module may be configured to: (a) enable individuals to collect at least one biological sample; (b) store the at least one biological sample; and (c) maintain the at least one biological sample in optimal condition while monitoring and preserving it during transportation; (ii) a sample processing module 102, wherein the module may be configured to: (a) extract metabolites from a biological sample; and (b) determine metabolite characteristics from the biological sample; (iii) a data management module 103, wherein the module may comprise; (a) a database of individual metabolite levels and timestamps of Cannabaceae-based treatments; (b) a database of individual diagnostic information; (c) a database of individual condition or state evaluations, and timestamps, with and without Cannabaceae-based treatments; and (d) a database of individual medication and Cannabaceae-derived treatment compositions; (iv) a statistical analysis module 104, wherein said module may be configured to perform z-score evaluations; (v) a machine learning module 105, wherein said module may comprise at least: (a) one machine learning model trained to predict any attribute or group of attributes within databasesbased on other database attributes, wherein the databases can comprise but not be limited to anyone of the databases mentioned on iii-c; (b) one training system for machine learning models; (c) at least one machine learning model to identify complex, nonlinear relationships within data; (vi) a diagnostic module 106, wherein said module may comprise: (a) a database of individual-specific medication, cannabinoid and Cannabaceae phytochemicals treatmentprofiles; (b) a statistical analysis component performing z-score evaluations of individual data; and (c) a machine learning model trained on metabolic pathways, mass spectrometry, and treatment outcome data; and, (vii) a personalization module for medical Cannabaceae-based treatments 107 including: (a) identifying suitable Cannabaceae phytochemicals treatments; (b) mapping previously unknown correlations using machine learning; (c) updating a database with personalized treatment recommendations; (d) predicting potential effectiveness of medical Cannabaceae-based treatments; (e) provide iterative improvements to treatments based on monitored individual responses; and, (viii) a treatment provider module 107.

[0065] In some embodiments, the treatment provider module can be the personalization module. In some embodiments the presentation of the treatment can comprise generating treatment outputs, wherein recommended treatments may comprise written treatment protocols specifying but not limited to cannabinoid type, dosage amount, administration frequency, and route of administration, based on the predicted metabolic response and individual condition. In some embodiments, the route of administration can comprise at least one of : Oral administration, including capsules, tablets, oils, tinctures, and edibles; Sublingual or buccal administration, including dissolvable strips, sprays, and oils applied under the tongue; Inhalation, including vaporized formulations or aerosolized delivery; Topical administration, including creams, patches, or gels applied to the skin; Transdermal delivery, comprising slow-release patches; or Rectal or vaginal administration, using suppositories. In some embodiments, written treatment protocols may be updated automatically or manually in response to newly collected metabolic data and ongoing evaluation of a subject’s responses, allowingfor iterative refinement of Cannabaceae-based therapy.

[0066] In some embodiments, the systems for determining Cannabaceae-based treatments FIG. 1 comprises: (i) a biological sample test module 101, wherein the module is configured to: (a) enable individuals to collect at least one biological sample through a sample collection device. In some embodiments, the sample collection device can be configured to collect saliva, blood, Urine, Cerebrospinal Fluid, tissue, hair, exhaled breath condensate, tears, feces or sweat. In some embodiments, the biological sample comprises saliva, (b) store the at least one biological sample through a biological sample storage device, wherein the device to store the at least on biological sample can comprise a drool collection kit, a blood collection kit, a urine collection kit, a cerebrospinal fluid collection kit, a tissue collection kit, a hair collection kit, a condensate breath collection kit, a tears collection kit, a feces collection kit or a sweat collection kit. In some embodiments, the storage device comprises a drool collection kit; and (c) maintain the at least one biological sample optimal condition. In some embodiments, the biological sample storage device can be configured to preservethe biological sample under optimal conditions for subsequent analysis using liquid chromatography -mass spectrometry (LC-MS) and gas chromatography-mass spectrometry (GC-MS).

[0067] In some embodiments, the biological sample storage device can be configured to prevent enzymatic degradation and oxidative changes through the use of temperature-controlled storage, wherein the temperature canbe between about -196°C and about -80°C for cryopreservation, between about -80°C and about -20°C for long-term freezing, and between about -20°C and about 4°C for short-term refrigeration. In some embodiments, the biological sample can be maintained under these conditions for about 6 hours, 12 hours, 18 hours, 24 hours, 30 hours, 36 hours, 42 hours, and about 48 hours. In some embodiments, the biological sample storage device can further comprise chemical stabilizing agents configured to preserve metabolite integrity, wherein the chemical stabilizing agents can include but are not limited to butylated hydroxytoluene (BHT), ethylenediaminetetraacetic acid (EDTA), formic acid, boric acid, or sodium aside. In some embodiments, the biological sample storage device can be further configured to allow preprocessing of the sample through metabolite extraction using methanol, acetonitrile, isopropanol, or organic solvents such as hexane, chloroform, or methyl tert -butyl ether (MTBE). In some embodiments, the biological sample can undergo chemical derivatization, wherein the derivatization process is configured to protect cannabis-responsive biomarkers during sample preparation and separation, allowing for improved detection and quantification in GC-MS analysis.

[0068] In some embodiments, the chemical derivatization process can include but is not limited to sialylation, methylation, and acylation. In some embodiments, the biological sample storage device can be further configured to minimize freeze-thaw cycles by storing the biological sample in multiple aliquots, wherein each aliquot is maintained under controlled conditions until analysis. In some embodiments, the system can comprise a data tracking module configured to record storage conditions, including temperature, sample age, and chemical treatment history, to ensure optimal sample integrity for subsequent chromatographic analysis. [0069] In some embodiments, systems described herein comprise a sample processing module 102, wherein the module is configured to: (a) extract metabolites from a biological sample. In some embodiments, the extraction of metabolites from a biological sample comprises extracting the metabolites using chromatography methods. In some embodiments, the chromatography method is selected from the group consisting of liquid chromatography or gas chromatography. In some embodiments, the chromatography method comprises liquid chromatography, wherein the liquid chromatography is selected from the group consisting of high-performance liquid chromatography (HPLC), ultra-high-performance liquid chromatography (UHPLC), reversed - phase liquid chromatography (RPLC), normal -phase liquid chromatography (NPLC), hydrophilic interaction liquid chromatography (HILIC), or ion -exchange chromatography (IEC). In some embodiments, the chromatography method comprises gas chromatography (GC), wherein the gas chromatography is configured to analyze volatile or derivatized metabolites. In some embodiments, the gas chromatography method is selected from the group consisting of gas chromatography-mass spectrometry (GC-MS), two-dimensional gas chromatography (GC*GC), and gas chromatography-flame ionization detection (GC-FID). In some embodiments, the extraction of metabolites further comprises sample preparation steps configured to optimize chromatographic separation, wherein the sample preparation steps can include but are not limited to chemical deri- vatization, solid-phase extraction (SPE), liquid-liquid extraction (LLE), or protein precipitation. In some embodiments, the chemical derivatization process comprises sialylation, alkylation, acylation, or methylation to enhance the volatility and detectability of metabolites in gas chromatography analysis. In some embodiments, the extraction process is configured to preserve metabolite integrity by incorporating temperature-controlled processing, antioxidant stabilization, and enzymatic inhibition. In some embodiments, the temperature-controlled processing can include maintaining the biological sample at between about -80°C and about 4°C during metabolite extraction to prevent degradation. In some embodiments, the extracted metabolites are subjected to pre-concentration techniques to enhance sensitivity, wherein the pre -concentration techniques can include evaporation under nitrogen, lyophilization, or solid phase microextraction (SPME).

[0070] In some embodiments, systems described herein comprise a sample processing module 102, wherein the module is configured to: (b) determining metabolite characteristics from the biological sample. In some embodiments, the metabolite characteristics of the biological sample comprise quantifying levels of metabolites and analyzing their structural, functional, and biochemical properties. In some embodiments, the quantification of metabolite levels comprises Spectroscopy -Based Techniques, wherein the spectroscopy-based technique can be selected from the group consisting of mass spectrometry (MS), nuclear magnetic resonance (NMR) spectroscopy, ultraviolet-visible (UV-Vis) spectroscopy, fluorescence spectroscopy, and Raman spectroscopy. In some embodiments, the spectroscopy-based technique can comprise mass spectrometry (MS), wherein the mass spectrometry technique is selected from the group consisting of tandem mass spectrometry (MS/MS), time-of-flight mass spectrometry (TOF-MS), Fourier- transform ion cyclotron resonance mass spectrometry (FT-ICR-MS), and orbitrap mass spectrometry. In some embodiments, the mass spectrometry technique can be coupled with a chromatography method, wherein the chromatography method is selected from liquid chromatography - mass spectrometry (LC-MS), gas chromatography -mass spectrometry (GC-MS), or capillary electrophoresis-mass spectrometry (CE-MS) to enhance metabolite separation, detection, and quantification.

[0071] In some embodiments, the metabolite characteristics may be selected from at least one of the groups consisting of mammalian metabolites, plant metabolites, microbial metabolites, synthetic metabolites, pharmaceutical compounds, or any combination thereof. In some embodiments, the quantified and determined metabolites comprise Cannabaceae-derived molecules, wherein Cannabaceae-derived molecules include but may not be limited to phytocannabinoids (such as tetrahydrocannabinol (THC), cannabidiol (CBD), cannabigerol (CBG), and canna- bichromene (CBC)), terpenes, flavonoids, and other bioactive compounds. In some embodiments, the metabolites comprise endocannabinoid-system metabolic markers, wherein the endo- cannabinoid-system metabolic markers include but are not limited to anandamide (AEA), 2-ara- chidonoylglycerol (2 -AG), palmitoylethanolamide (PEA), and oleoylethanolamide (OEA). In some embodiments, the quantified and determined metabolites comprise Cannabaceae -responsive biomarkers, wherein the Cannabaceae-responsive biomarkers are selected from groups associated with medical conditions, metabolic responses, cohort profiles, individual profiles, or any combination thereof.

[0072] In some embodiments, the quantified and determined metabolites can comprise lipid metabolites, wherein the lipid metabolites may be selected from fatty acids, sphingolipids, phospholipids, ceramides, lysophosphatidylcholines (LPCs), acylcamitines or any combination thereof. In some embodiments, the metabolites can comprise Cannabaceae contaminants, wherein the Cannabaceae contaminants can include but are not limited to residual solvents, pesticides, heavy metals, mycotoxins, microbial contaminants, or any unwanted Cannabaceae-derived molecules. In some embodiments, the metabolites can comprise specific chemicals or residues associated with Cannabaceae-derived products, wherein the specific chemicals or residues may include metabolic byproducts of cannabinoid degradation, oxidation products, or exogenous contaminants absorbed during cultivation, processing, or storage. In some embodiments, the determination of metabolite characteristics further comprises assessing metabolite stability, degradation kinetics, and metabolic transformations occurring post-administration of Cannabaceae- based treatments.

[0073] In some embodiments, systems described herein comprise: a data management module 103, wherein the module comprises: (a) a database of individual metabolite levels and timestamps of Cannabaceae-based treatments. In some embodiments, the database of individual metabolite levels and timestamps comprises metabolic profiles, wherein the metabolic profiles include but are not limited to quantitative and qualitative data on cannabinoids, cannabinoid metabolites, lipid metabolites, amino acids, inflammatory markers, oxidative stress markers, neurotransmitters, and other relevant biochemical compounds. In some embodiments, the database stores cannabinoid levels and their metabolic byproducts, wherein the cannabinoids can include tetrahydrocannabinol (THC), cannabidiol (CBD), cannabigerol (CBG), cannabichromene (CBC), and cannabinol (CBN), and their corresponding metabolites include but are not limited to 11 -hy- droxy-THC, THC-COOH, CBD-glucuronides, and hydroxylated CBG derivatives. In some embodiments, the database of individual metabolite levels further comprises lipid metabolites, wherein the lipid metabolites include but are not limited to fatty acids, phospholipids, sphingolipids, ceramides, acylcarnitines, and lysophosphatidylcholines (LPCs).

[0074] In some embodiments, the lipid metabolites may be associated with metabolic and inflammatory pathways influenced by Cannabaceae-based treatments. In some embodiments, the database includes amino acid profiles, wherein the amino acid levels include glutamate, gamma- aminobutyric acid (GABA), tryptophan, tyrosine, and branched-chain amino acids (BCAAs), which may serve as biomarkers for neurotransmitter activity and metabolic function in response to Cannabaceae-based interventions. In some embodiments, the database further comprises inflammatory markers, wherein the inflammatory markers include but are not limited to C -reactive protein (CRP), interleukins (IL-6, IL-10), tumor necrosis factor-alpha (TNF-a), and prostaglandins, which provide insights into immune modulation associated with Cannabaceae -derived treatments.

[0075] In some embodiments, the database stores timestamps corresponding to Cannabaceae-based treatment administration, wherein the timestamps record pre-treatment (PRE), peak effect (PEAK), and post-treatment intervals, enabling longitudinal tracking of individual responses to specific cannabinoid formulations. In some embodiments, the database further integrates demographic and diagnostic information, wherein the demographic data comprises age, sex, genetic predispositions, medical history, and lifestyle factors, and the diagnostic information includes clinical assessments, symptom severity scores, and biomarker-based evaluations of treatment efficacy. In some embodiments, the database is configured for real-time data integration, wherein new metabolic data and treatment timestamps are continuously updated to enhance the accuracy of predictive modeling for personalized Cannabaceae-based therapies; (b) a database of individual diagnostic information. In some embodiments, the individual diagnostic information comprises a structured database configured to store, analyze, and retrieve patient-specific diagnostic data, including but not limited to metabolic profiles, historical treatment data, Canna- baceae-specific metabolic responses, contaminants detected in biological samples, and data representations of annotated molecule features and interactions obtained through multi -omics analysis.

[0076] In some embodiments, the database of individual diagnostic information comprises metabolic profiles, wherein the metabolic profiles include but are not limited to quantitative and qualitative measurements of endogenous metabolites, Cannabaceae -derived metabolites, lip- idomic and proteomic markers, neurotransmitters, amino acids, inflammatory cytokines, and oxidative stress indicators. In some embodiments, the metabolic profiles can be generated using liquid chromatography-mass spectrometry (LC-MS), gas chromatography-mass spectrometry (GC- MS), nuclear magnetic resonance (NMR) spectroscopy, capillary electrophoresis -mass spectrometry (CE-MS), or any combination thereof. In some embodiments, the database further comprises historical treatment data, wherein historical treatment data may include data from previous Cannabaceae-based therapies administered to an individual, corresponding cannabinoid formulations (e.g., THC, CBD, CBG ratios), dosing regimens, administration routes (e.g., oral, sublingual, inhalation), treatment durations, and recorded clinical outcomes. In some embodiments, historical treatment data can time-stamped and associated with pre-treatment, peak-effect, and post-treatment metabolic profiles to enable longitudinal tracking of therapeutic responses.

[0077] In some embodiments, the database further comprises Cannabaceae -specific metabolic responses, wherein Cannabaceae -specific metabolic responses include but are not limited to changes in endocannabinoid system markers, alterations in lipid metabolism, modulation of neurotransmitter levels, and immune -related biomarker shifts in response to Cannabaceae-based treatment. In some embodiments, the Cannabaceae-specific metabolic responses are correlated with individual genetic polymorphisms, pharmacokinetic parameters, and environmental influences affecting cannabinoid metabolism. In some embodiments, the database further comprises contaminants detected in biological samples, wherein the contaminants include but are not limited to residual pesticides, heavy metals, solvents, microbial toxins, synthetic adulterants, or unintended byproducts from Cannabaceae-based formulations. In some embodiments, the contaminants are identified through targeted and untargeted mass spectrometry -based screening techniques and cross-referenced with regulatory safety thresholds for medical cannabis products.

[0078] In some embodiments, the database further comprises data representations of annotated molecule features and interactions obtained through multi -omics analysis, wherein multi - omics analysis includes but is not limited to genomics, transcriptomics, proteomics, metabolom- ics, and lipidomic. In some embodiments, the annotated molecular features can be linked to biochemical pathways, metabolic networks, and predictive machine learning models for optimizing Cannabaceae-based treatments.

[0079] In some embodiments, the database of individual diagnostic information is configured for real-time data integration, cross-validation with population-scale biomarker repositories, and iterative refinement of predictive models for personalized cannabinoid therapy recommendations; a database of individual condition or state evaluations and timestamps, with and without Cannabaceae-based treatments. In some embodiments, the database comprises longitudinal records of patient condition assessments, wherein the condition or state evaluations include but are not limited to clinical symptom scores, biomarker deviations, cognitive function assessments, behavioral metrics, physiological measurements, and patient-reported outcomes. In some embodiments, the database further comprises timestamps corresponding to the administration of Cannabaceae-based treatments, wherein timestamps indicate pre-treatment (PRE), peak-effect (PEAK), and post-treatment intervals, allowing for precise tracking of metabolic and symptomatic changes over time.

[0080] In some embodiments, the individual condition or state evaluations database includes baseline assessments prior to the initiation of Cannabaceae-based treatments, wherein baseline assessments comprise pre-existing metabolic profiles, endocannabinoid system function, inflammatory status, and neurotransmitter activity. In some embodiments, the database further includes comparative evaluations, wherein condition or state assessments collected after treatment are compared to baseline values to determine therapeutic efficacy. In some embodiments, the database further comprises a structured repository of treatment regimens and outcomes, wherein the repository stores data on specific cannabis formulations, cannabinoid ratios, terpene compositions, administration methods, and individualized dosages. In some embodiments, the treatment regimens include but are not limited to full-spectrum Cannabaceae extracts, isolated cannabinoids (such as tetrahydrocannabinol (THC), cannabidiol (CBD), and cannabigerol (CBG)), synthetic cannabinoid analogs, and adjunctive therapies. In some embodiments, the database of treatment regimens and outcomes includes detailed records of patient responses, wherein patient responses comprise biochemical, physiological, and behavioral data collected at predefined intervals. In some embodiments, patient responses are classified using machine learning algorithms trained to analyze treatment efficacy, detect non-responders, and predict optimal cannabinoid formulations for future interventions. In some embodiments, the database of condition or state evaluations further comprises a predictive analytics module configured to identify patterns in treatment response, wherein predictive analytics models integrate historical patient data, realtime metabolic fluctuations, and external variables such as age, sex, genetic predisposition, and environmental exposures.

[0081] In some embodiments, the system is configured to dynamically update the database with new patient records, refine predictive treatment models, and provide personalized recommendations for Cannabaceae-based interventions based on collected condition or state evaluations; and a database of individual medication and Cannabaceae-derived treatment compositions. In some embodiments, the database of individual medication and Cannabaceae-derived treatment compositions comprises structured and unstructured data related to patient-specific pharmacological treatments, Cannabaceae-derived therapies, metabolic responses, and associated clinical outcomes. In some embodiments, the database stores detailed records of cannabinoid formulations, including but not limited to full-spectrum extracts, broad-spectrum formulations, isolated cannabinoids (such as tetrahydrocannabinol (THC), cannabidiol (CBD), cannabigerol (CBG), and can- nabichromene (CBC)), synthetic cannabinoid analogs, and adjunctive pharmaceutical compounds.

[0082] In some embodiments, the database of individual medication and Cannabaceae-derived treatment compositions includes cannabis-responsive biomarkers, wherein the cannabis- responsive biomarkers include but are not limited to neurotransmitter-associated metabolites, lip - idomic markers, oxidative stress indicators, and inflammatory cytokines. In some embodiments, the database further comprises individual condition or state evaluations, wherein the condition or state evaluations include longitudinal patient-reported outcomes, clinical symptom assessments, and metabolomic deviations pre- and post-treatment. In some embodiments, the database is configured to store timestamps corresponding to treatment administration, enabling real-time tracking of metabolic fluctuations and treatment efficacy. In some embodiments, the database of individual medication and Cannabaceae-derived treatment compositions includes comprehensive metabolic profiles, wherein the metabolic profiles comprise levels of cannabinoids and their metabolites, lipid metabolites, amino acids, inflammatory markers, and other relevant biochemical compounds linked to individual metabolic deviations, treatment efficacy, or any combination thereof. In some embodiments, the database is structured to cross-reference metabolic deviations with historical treatment efficacy data to improve precision in personalized medicine applications. In some embodiments, the data management module further can comprise a knowledge database containing curated metabolic data from public and proprietary sources, wherein the curated database may be configured to integrate datasets from clinical trials, epidemiological studies, regulatory health agencies, and academic research publications. In some embodiments, the knowledge database can be integrated through automated workflows, enabling real-time data ingestion, processing, and standardization for machine learning applications. In some embodiments, the database of individual conditions may further comprise longitudinal data capturing variations in endocannabinoid system -metabolic levels overtime, wherein the longitudinal dataset is configured to record baseline metabolic markers, time -dependent fluctuations in endocannabinoid activity, and responses to Cannabaceae-based treatments across multiple physiological states. In some embodiments, the data management module can further comprise bioin- formatic processing pipeline-derived databases, wherein the bioinformatics pipeline may be configured to perform metabolomic data preprocessing, normalization, feature extraction, and batch effect correction, enabling cross-functional integration with multi -omics datasets and machine learning model training. In some embodiments, the data management module may further comprise a distributed database system, wherein the distributed database system may be configured for real-time access, retrieval, and storage of patient-specific metabolic and treatment data across multiple computing platforms, cloud-based storage infrastructures, and secure data-sharing networks. In some embodiments, the distributed database system may be designed to facilitate interoperability with electronic health records (EHRs), clinical decision -support systems (CDSS), and telemedicine platforms for Cannabaceae-based treatment monitoring and optimization;

[0083] In some embodiments, systems described herein comprise a statistical analysis module 104, wherein the statistical analysis is configured to: (a) perform z -score evaluations. In some embodiments, the z-score evaluation comprises analyzing relationships between individual endocannabinoid system metabolic levels and database information from at least one of the databases mentioned on (iii), wherein the z-score is calculated by comparing individual metabolite levels to a reference population mean and standard deviation. In some embodiments, the reference population mean, and standard deviation are derived from historical metabolomic datasets, cohortspecific biomarker distributions, or population-based multi-omics analyses. In some embodiments, the z-score evaluation is configured to normalize metabolic deviations across individuals by adjusting for age, sex, genetic predisposition, treatment history, and environmental factors. In some embodiments, the z-score evaluation may be applied to baseline metabolic assessments, post-treatment metabolic shifts, and longitudinal biomarker fluctuations to quantify treatment efficacy. In some embodiments, the z-score evaluations may include conditions, diagnostics, Cannabaceae-derived treatment effects, metabolite deviations, biomarker shifts overtime, or any combinations thereof, wherein the conditions may include neurological, psychiatric, inflammatory, or metabolic disorders associated with dysregulation of the endocannabinoid system.

[0084] In some embodiments, the z-score evaluations may further comprise comparative analyses between treated and untreated cohorts, allowing for differentiation between Canna- baceae-responsive and non-responsive individuals. In some embodiments, the z-score evaluation may be utilized to classify individual metabolic responses into categories, including but not limited to normal, hyperactive, hypoactive, or dysregulated metabolic states. In some embodiments, the classification of metabolic responsesis used to predict optimal cannabinoid -based interventions, wherein individuals with similar z-score patterns are grouped to identify shared metabolic response signatures. In some embodiments, the z-score evaluation may further incorporate machine learning-based anomaly detection models, wherein deviations exceeding predefined thresholds may trigger alerts for unexpected metabolic shifts, potential adverse reactions, or the need for dosage adjustments.

[0085] In some embodiments, the system may continuously update z-score thresholds based on new patient data, treatment responses, and emerging population -level metabolic trends. In some embodiments, the z-score evaluation results may be integrated with a clinical decision-support module, wherein healthcare providers receive quantitative insights on patient-specific metabolic responses to Cannabaceae-based treatments, enabling data-driven optimization of cannabinoid formulations, dosages, and treatment schedules; (b) associate mass spectrometry -detected metabolite levels with individual data in a database.

[0086] In some embodiments, the mass spectrometry data includes intensity values corresponding to various mass-to-charge (m/z) ratios and elution times. In some embodiments, the mass spectrometry data canbe obtained from Liquid Chromatography -Mass Spectrometry (LC- MS) and Gas Chromatography -Mass Spectrometry (GC-MS) analyses. In some embodiments, the mass spectrometry data is stored as arrays, matrices, or multi-dimensional datasets, wherein the axes represent m/z ratios, retention times, ion intensities, and sample identifiers, enabling comprehensive data structuring and retrieval. In some embodiments, the mass spectrometry data is linked to individual biological samples and metabolic profiles, wherein the biological samples comprise but are not limited to plasma, serum, saliva, urine, cerebrospinal fluid (CSF), or tissue homogenates.

[0087] In some embodiments, the metabolic profiles include quantified concentrations of endogenous metabolites, xenobiotics, Cannabaceae-derived compounds, and metabolic byproducts associated with cannabinoid metabolism. In some embodiments, the database further comprises metadata annotations, wherein each mass spectrometry entry may be associated with sample collection parameters, preprocessing conditions, instrument settings, ionization mode (e.g., electrospray ionization (ESI), matrix-assisted laser desorption/ionization (MALDI)), and analytical batch identifiers. In some embodiments, the system incorporates quality control (QC) metrics, wherein the QC data includes internal standard corrections, signal -to-noise ratios, and replicate sample consistency scores to ensure analytical robustness.

[0088] In some embodiments, the mass spectrometry -detected metabolite levels are cross- referenced with external biochemical databases, including but not limited to the Human Metabo- lome Database (HMDB), METLIN, Kyoto Encyclopedia of Genes and Genomes (KEGG), and LipidMaps, allowing for structural annotation and pathway enrichment analysis. In some embodiments, the mass spectrometry data is integrated into a longitudinal patient database, wherein repeated metabolomic assessments are time-stamped to track dynamic changes in metabolic pathways before, during, and after Cannabaceae -based treatment administration. In some embodiments, the mass spectrometry data is processed using advanced data normalization and feature extraction algorithms, including but not limited to peak alignment, baseline correction, batch effectremoval, and intensity scaling techniques, to improve comparability across samples and analytical runs.

[0089] In some embodiments, the system further comprises machine learning-based feature selection algorithms, wherein significant metabolite -level changes are automatically detected and prioritized based on treatment response, biomarker significance, and/or statistical confidence scores. In some embodiments, the system may generate predictive models linking specific metabolic shifts to Cannabaceae-based therapeutic outcomes, enabling personalized treatment optimization and biomarker discovery, (c) correlate individual metabolic data with timestamps of Cannabaceae-based treatments. In some embodiments, metabolic profiles at multiple time points, including pre-treatment (PRE), peak effect (PEAK), and post-treatment intervals, are associated with specific cannabinoid dosages, administration routes, and treatment durations, enabling a temporal assessment of metabolomic changes in response to Cannabaceae-based interventions.

[0090] In some embodiments, the metabolic data comprises quantified levels of cannabinoids and their metabolites, including but not limited to tetrahydrocannabinol (THC), cannabidiol (CBD), cannabigerol (CBG), cannabichromene (CBC), and their metabolic byproducts (e.g., 11 - hydroxy-THC, THC-COOH, CBD-glucuronides). In some embodiments, the metabolic data further comprises lipid metabolites, neurotransmitters, inflammatory cytokines, oxidative stress markers, and amino acid profiles, which are measured at distinct time points to capture dynamic metabolic fluctuations in response to treatment. In some embodiments, the system further comprises a statistical analysis module configured to identify correlations between specific endocannabinoid system -metabolic markers and treatment efficacy, wherein treatment efficacy is defined based on changes in biomarker concentrations, symptom reduction scores, and patient -reported outcomes. In some embodiments, the statistical analysis module applies multivariate regression models, principal component analysis (PCA), and clustering techniques to identify distinct metabolic signatures linked to successful Cannabaceae-based treatment responses. In some embodiments, the system dynamically updates individual treatment recommendations based on the observed correlations, wherein newly acquired metabolic data can be integrated into predictive models to refine dosing strategies, cannabinoid ratios, and treatment duration recommendations. In some embodiments, the system can be configured to provide real-time alerts when unexpected metabolic deviations occur, enabling clinicians to adjust cannabinoid formulations or discontinue treatment in cases of adverse metabolic responses.

[0091] In some embodiments, systems described herein comprise a machine learning module 105, wherein said module comprises: (a) at least one machine learning model trained to predict any attribute or group of attributes within data based on other database attributes, wherein the databases may include, but are not limited to, any one of the databases described in (iii). In some embodiments, the attribute or group of attributes comprise individual metabolic profiles, cannabis treatment outcomes, cannabinoid dosages, metabolic shifts over time, specific metabolite responses linked to behavioral changes in individuals, and statistical correlations between metabolic deviations and therapeutic effects. In some embodiments, cannabinoid dosages may include tetrahydrocannabinol (THC) in a range of about 0 mg to about 50 mg, cannabidiol (CBD) in a range of about 0 mg to about 200 mg, and cannabigerol (CBG) in a range of about 0 mg to about 50 mg, wherein dosages are time-stamped and cross-referenced with metabolic response data to establish dose-dependent relationships.

[0092] In some embodiments, the machine learning model is trained on multiple data modalities, including but not limited to: (1) Chromatography data. In some embodiments, the chromatography data comprises liquid chromatography data, wherein liquid chromatography techniques include but are not limited to high-performance liquid chromatography (HPLC), ultra-high-performance liquid chromatography (UHPLC), reversed-phase liquid chromatography (RPLC), and hydrophilic interaction liquid chromatography (HILIC). In some embodiments, chromatography data is further processed using peak alignment, retention time normalization, and batch correction techniques to ensure consistency across multiple sample runs; (2) Spectroscopy data. In some embodiments, the spectroscopy -based data comprises mass spectrometry data, wherein mass spectrometry techniques include but are not limited to time-of-flight mass spectrometry (TOF-MS), quadrupole-time-of-flight (QTOF-MS), Fourier-transform ion cyclotron resonance mass spectrometry (FT-ICR-MS), and orbitrap mass spectrometry. In some embodiments, mass spectrometry data includes m/z ratios, ion intensities, isotopic patterns, and fragmentation spectra, allowing for precise metabolite identification and quantification; (3) Metabolic pathways. In some embodiments, the metabolic pathways can be obtained from in-house databases or external databases, including but not limited to the Kyoto Encyclopedia of Genes and Genomes (KEGG), the Human Metabolome Database (HMDB), Reactome, and the Small Molecule Pathway Database (SMPDB). In some embodiments, metabolic pathway data is used to identify cannabinoidresponsive biomarkers and their downstream effects on lipid metabolism, neurotransmitter activity, and inflammatory response pathways. (4) Treatment outcome data. In some embodiments, treatment outcome data includes pre-treatment, peak-effect, and post-treatment assessments, wherein assessments can comprise clinical symptom scores, metabolic biomarker deviations, and patient-reported therapeutic effects.

[0093] In some embodiments, the machine learning model may be configured to generate probability scores indicative of physiological conditions, wherein probability scores may be derived from regression models, classification models, anomaly detection algorithms, and Bayesian inference techniques. In some embodiments, the machine learning model is trained using datasets of metabolic profiles, cannabinoid treatment dosages, and patient response data, wherein training datasets are curated from longitudinal patient records, controlled clinical trials, and real- world evidence studies. In some embodiments, the machine learning model is configured to apply gradient boosting algorithms. In some embodiments, the gradient boosting algorithms are selected from XGBoost, LightGBM, or CatBoost. In some cases, the gradient boosting algorithms are used to classify samples and predict treatment outcomes, either alone or in combination with other algorithms.

[0094] In some embodiments, the machine learning model is further configured to apply deep learning architectures, including but not limited to deep neural networks (DNNs) for pattern recognition, recurrent neural networks (RNNs) (e.g., for time-series forecasting), Graph Neural Networks (GNNs) to model complex relationships between multi-modal data, and autoencoders for feature extraction from high -dimensional metabolomic datasets. In some embodiments, gradientboosting algorithms are used in place of and/or in conjunction with one or more neural networks to create ensemble models with improved prediction power. In some embodiments, the machine learning model can be configured to rank the importance of metabolites, wherein metabolite ranking is performed using Shapley Additive Explanations (SHAP), gradient boosting derived feature importance or permutation feature importance, and LASSO regression techniques to identify biomarkers most predictive of treatment response. In some embodiments, training of machine learning models described herein may be supervised, unsupervised, and/or may comprise reinforcement. In some embodiments, the dataset containing metabolic data is normalized, the training system is subsequently configured to divide the preprocessed data into training and test datasets.

[0095] In some embodiments training an unsupervised, semi-supervised or supervised machine learning model to process high-dimensional input vectors (e.g., metabolic profiles, biomarker concentrations, and treatment history) is employed (e.g., to map them to low-dimensional latent spaces for predictive modeling, classification, and anomaly detection).

[0096] In some embodiments, the training dataset is structured using metabolomic profiles obtained from individuals undergoing Cannabaceae-based treatments, with sample collection at multiple time points including pre-treatment (PRE), peak effect (PEAK), and post -treatment intervals, wherein the time points are correlated with individual response metrics, symptom evaluations, and treatment efficacy scores. In some embodiments, data normalization techniques are applied to correct for batch effects, inter-individual variability, and mass spectrometry signal fluctuations, wherein normalization methods may include but are not limited to Min -Max scaling, probabilistic quotient normalization (PQN), z-score normalization, log transformation, and Pareto scaling.

[0097] In some embodiments, machine learning algorithms used for training the models may include but are not limited to: Gradient Boosting Models (e.g., XGBoost, LightGBM, CatBoost) for feature selection, predictions on high dimensional data inputs, and/or classification of treatment response patterns. Neural Networks, Graph Neural Networks, including Autoencoders, Variational Autoencoders (VAEs), and Self -Organizing Maps (SOMs) to model high-dimensional metabolomics data and discover latent metabolic patterns. Time-Series Models, including Recurrent Neural Networks (RNNs) and Long Short-Term Memory (LSTM) networks, to analyze longitudinal metabolic changes associated with Cannabaceae-derived treatments. Clustering Algorithms, such as K-means, DBSCAN, and Hierarchical Clustering, to segment patients based on their metabolomic profiles and identify treatment response subpopulations. In some embodiments, the training system is further configured to: Implement cross-validation techniques, including k-f old cross-validation and leave-one-out cross-validation, to ensure robustness of the trained model. Optimize hyperparameters using grid search or Bayesian optimization methods. Perform feature importance analysis to determine the most predictive metabolic biomarkers for Cannabaceae-basedtreatment efficacy. In some embodiments, the trained models are validated using independent test datasets comprising metabolic profiles from patients not included in the training dataset, wherein validation performance is assessed using metrics such as area under the receiver operating characteristic curve (AUC -ROC), precision-recall curves, mean squared error (MSE), Fl -score and classification accuracy. Generate synthetic data augmentation using generative adversarial networks (GANs) or variational autoencoders (VAEs) to improve model generalization in cases of limited sample size. In some embodiments, the training system incorporates a reinforcement learning framework, wherein a reward function is assigned based on improved patient outcomes, guiding the model to iteratively refine dosage recommendations and optimize treatment regimens. In some embodiments, the system continuously updates the training dataset by integrating new patient data, metabolomic measurements, and treatment outcomes, allowing for dynamic model retraining and continuous refinement of predictive performance.

[0098] In some embodiments, the machine learning model is configured to refine predictive accuracy over time, wherein model performance is assessed using cross-validation techniques and performance metrics such as mean absolute error (MAE) and area under the receiver operating characteristic (ROC-AUC) curve; at least one machine learning model to identify complex, nonlinear relationships within databases. In some embodiments, the machine learning model comprises a supervised learning model, such as gradient boosting algorithm, deep neural networks (DNNs), and support vector machines (SVMs) trained to classify samples or predict treatment outcomes. In some embodiments, the machine learning model comprises a variational autoencoder (VAE) trained to map high-dimensional input data, such as metabolic profiles and cannabinoid treatment data, to a low-dimensional latent space, enabling the identification of nonlinear correlations between individual metabolic responses and specific cannabis-based treatments. In some embodiments, the machine learning model is configured to analyze biomarker deviations and treatment response patterns by applying unsupervised learning techniques, including but not limited to: Clustering algorithms, such as k-means, hierarchical clustering, and densitybased spatial clustering (DBSCAN), to group individuals based on metabolic response profiles. Anomaly detection models, such as isolation forests or one-class support vector machines (SVMs), to identify metabolic deviations linked to adverse responses.

[0099] In some embodiments, the machine learning model is configured to analyze Canna- baceae contaminants detected in biological samples, wherein contaminants may include pesticide residues, solvent traces, or mycotoxins derived from Cannabaceae -based products. In some embodiments, the machine learning module further comprises a deep learning framework, such as a neural network trained on datasets of metabolic levels, diagnostic data, and treatment outcomes, wherein the neural network structure includes at least one of: Feedforward neural networks (FNNs) for predicting individual treatment outcomes based on metabolic and clinical variables. Recurrent neural networks (RNNs) for modeling temporal trends in metabolomic responses. Transformer-based architectures to map context and relationships between elements in datasets of metabolic pathways, metabolic levels, diagnostic data, and treatment outcomes in much more sophisticated ways to enhance prediction capacity.. ;

[00100] In some embodiments, systems described here comprise a diagnostic module 106, wherein said module comprises: a database of individual-specific medication, cannabinoid, Can- nabaceae phytochemicals treatment profiles, or any combinations thereof. In some embodiments, the database of individual-specific medication and Cannabaceae-derived treatment compositions includes detailed records of patient treatment regimens, wherein records include but are not limited to cannabinoid formulations, administration methods, dosage adjustments, and response monitoring. In some embodiments, the database tracks metabolic changes in response to Cannabaceae-derived molecules, allowing for longitudinal assessment of individual treatment efficacy. In some embodiments, the diagnostic module further comprises individual metabolic profiles, including mass spectrometry data, cannabinoid dosage records, timestamps of Cannabaceae treatments, patient-specific biomarkers, and treatment outcome data. In some embodiments, the individual metabolic profiles include quantitative measurements of cannabis -responsive biomarkers, such as anandamide (AEA), lysophosphatidylethanolamine (LysoPE (18: 1)), homovanillic acid (HVA), cortisol, palmitoyl-carnitine, arachidic acid, and 2 -hydroxybutyric acid, which have been identified as responsive to Cannabaceae -based treatments.

[00101] In some embodiments, cannabinoid dosage records comprise individualized treatment formulations, wherein cannabinoid concentrations can be categorized as follows: THC dosage categories: (0) No THC, (1) 0.05-5.00 mg, (2) 5.05-15.00 mg, and (3) >15.05 mg. CBD dosage categories: (0) No CBD, (1) 1-30 mg, (2) 31-84 mg, (3) 85-100 mg, and (4) >100 mg. CBG dosage categories: (0) No CBG, (1) 1-49 mg, and (2) >50 mg. In some embodiments, timestamps of Cannabaceae treatments include pre-treatment (PRE), peak effect (PEAK), and post-treatment intervals, wherein treatment efficacy is evaluated based on biomarker concentration shifts and patient-reported therapeutic effects. In some embodiments, patient-specific biomarkers are classified into neuroactive compounds, lipid metabolites, and steroid derivatives, allowing for the identification of metabolic signatures predictive of treatment response. In som e embodiments, machine learning models analyze these metabolic signatures to optimize Canna- baceae-based interventions, adjusting dosages dynamically based on real -time data collection. In some embodiments, the database is configured to integrate multi -omics data, wherein integration includes metabolomics, lipidomic, proteomics, and transcriptomics datasets, allowing for comprehensive modeling of the effects of Cannabaceae-derived molecules on physiological pathways. In some embodiments, the diagnostic module may further comprise a data harmonization framework, wherein metabolomic and treatment-related data are normalized, standardized, and preprocessed for downstream statistical modeling, machine learning training, and predictive analytics.

[00102] In some embodiments, systems described here comprise a statistical analysis component performing z-score evaluations of individual data. In some embodiments, the statistical analysis component is configured to quantify metabolic deviations from baseline reference values (e.g., healthy levels), wherein the z-score is calculated as a standardized measure representing the number of standard deviations a given metabolite level deviates from the reference population mean. In some embodiments, the z-score evaluations include the analysis of metabolic deviations from baseline values, tracking changes in response to cannabinoid treatments, integration of time-stamped metabolite data, or any combinations thereof, wherein baseline values are obtained from pre-treatment assessments, historical patient records, or population-level metabolic datasets. In some embodiments, z-score evaluations are performed at multiple time points, including but not limited to pre-treatment (PRE), peak effect (PEAK), and post-treatment intervals, allowing for a dynamic assessment of metabolic shifts following Cannabaceae -based interventions. In some embodiments, the statistical analysis component is configured to detect significant biomarker fluctuations, wherein fluctuations exceeding predefined z-score thresholds may indicate treatment efficacy, metabolic adaptation, or potential adverse responses. In some embodiments, the diagnostic module is configured to assess treatment efficacy and patient response overtime, wherein treatment efficacy is determined based on the magnitude and direction of z- score deviations across successive metabolic assessments.

[00103] In some embodiments, the diagnostic module applies trend analysis and statistical hypothesis testing, including but not limited to t-tests, ANOVA, multivariate regression models, and Bayesian inference techniques, to validate significant treatment-induced metabolic changes. In some embodiments, the z-score calculation includes adjustments based on cohort-specific averages for subpopulations, wherein cohort-specific adjustments are performed to account for age, sex, genetic variations, underlying medical conditions, and other demographic factors that may influence baseline metabolic profiles. In some embodiments, the subpopulation may be defined by demographic or medical characteristics, wherein demographic characteristics include but are not limited to age, sex, ethnicity, BMI, and lifestyle factors, and medical characteristics include but are not limited to neurological disorders, metabolic syndromes, autoimmune conditions, and inflammatory diseases. [00104] In some embodiments, subpopulation stratification is applied to enhance precision in z-score-based treatment assessments, ensuring that individualized therapeutic recommendations are tailored to population-specific metabolic baselines. In some embodiments, the statistical analysis component is further configured to incorporate machine learning-based anomaly detection models, wherein deviations exceeding predefined thresholds are automatically flagged for further clinical review, treatment optimization, or real-time dosage adjustments. In some embodiments, the statistical analysis module continuously updates baseline reference distributions using newly acquired longitudinal patient data, refining the accuracy of z-score-based metabolic deviation assessments overtime; (1) Chromatography data. In some embodiments, the chromatography data comprises liquid chromatography data, wherein the liquid chromatography method includes but is not limited to high-performance liquid chromatography (HPLC), ultra-high-performance liquid chromatography (UHPLC), reversed-phase liquid chromatography (RPLC), normal-phase liquid chromatography (NPLC), hydrophilic interaction liquid chromatography (HILIC), ion -exchange chromatography (IEC), and size-exclusion chromatography (SEC). In some embodiments, the chromatography data is derived from biological samples, including but not limited to plasma, serum, saliva, urine, and cerebrospinal fluid, wherein the chromatography process enables separation, identification, and quantification of Cannabaceae-derived metabolites, endocannabinoid system metabolic markers, lipid metabolites, amino acids, and inflammatory markers.

[00105] In some embodiments, the chromatography data is linked to mass spectrometry data, wherein preprocessing techniques include peak alignment, retention time normalization, baseline correction, and batch effect removal to enhance reproducibility across datasets. In some embodiments, the machine learning model is trained to analyze chromatography patterns, classify retention characteristics, and correlate metabolite retention times with cannabinoid metabolic responses. (2) Spectroscopy data. In some embodiments, the spectroscopy -based data comprises mass spectrometry (MS) data, wherein the mass spectrometry technique is selected from time-of- flightmass spectrometry (TOF-MS), quadrupole-time-of-flight mass spectrometry (QTOF-MS), Fourier-transform ion cyclotron resonance mass spectrometry (FT-ICR-MS), and orbitrap mass spectrometry.

[00106] In some embodiments, the mass spectrometry data comprises m/z ratios, ion intensities, retention times, and fragmentation spectra, wherein the machine learning model is trained to identify metabolite spectral signatures, classify unknown compounds, and predict biochemical relationships between metabolites and Cannabaceae -based treatments. In some embodiments, the spectroscopy data is derived from integrated LC-MS and GC-MS workflows, wherein liquid and gas phase separation techniques complement mass spectrometry -based metabolite quantification and structural characterization. In some embodiments, tandem mass spectrometry (MS/MS) fragmentation data is analyzed using machine learning models trained to recognize diagnostic fragmentation patterns, metabolite classes, and correlations between spectral features and cannabinoid-based treatment responses.

[00107] Metabolic pathways: In some embodiments, the metabolic pathways are obtained from in-house databases or external databases, including but not limited to the Kyoto Encyclopedia of Genes and Genomes (KEGG), the Human Metabolome Database (HMDB), Reactome, MetaCyc, and the Small Molecule Pathway Database (SMPDB). In some embodiments, metabolic pathway data is integrated with multi-omics datasets, including but not limited to genomic, transcriptomic, proteomic, lipidomic, and metabolomic datasets, to identify molecular interactions relevant to Cannabaceae-derived treatment responses.

[00108] In some embodiments, the machine learning model is configured to detect novel metabolic relationships, wherein pathway modeling techniques analyze flux distributions, reaction kinetics, and enzymatic transformations associated with cannabinoid metabolism. In some embodiments, metabolic pathway predictions incorporate biochemical reaction networks and metabolic flux analysis (MFA), allowing for enhanced interpretation of individualized metabolic responses to Cannabaceae-based treatments. In some embodiments, the machine learning model employs Graph Neural Networks, Bayesian inference models, or pathway enrichment algorithms to establish causal relationships between endocannabinoid system metabolic markers and cannabinoid treatment efficacy. In some embodiments, the machine learning model is configured to integrate chromatography, spectroscopy, and metabolic pathway data into a unified predictive framework, wherein feature selection algorithms identify biomarkers indicative of treatment response, metabolic deviations, and individualized cannabinoid therapy optimization; and (4) treatment outcome data. In some embodiments, treatment outcome data comprises longitudinal patientrecords, wherein the records include but are not limited to baseline metabolic assessments, pre-treatment and post-treatment biomarker deviations, patient-reported symptom scores, and clinical evaluations of treatment efficacy.

[00109] In some embodiments, treatment outcome data is collected at multiple time points, including but not limited to pre-treatment (PRE), peak effect (PEAK), and post-treatment intervals, allowing for a time-dependent analysis of therapeutic impact. In some embodiments, the machine learning model may be configured to generate probabilities indicative of physiological conditions, wherein the probability values correspond to predicted likelihoods of specific metabolic or clinical responses following Cannabaceae-based treatments. In some embodiments, the machine learning model applies classification algorithms, regression models, or probabilistic inference techniques, including but not limited to Bayesian networks, logistic regression, support vector machines (SVMs), and neural network -based predictive modeling.

[00110] In some embodiments, the machine learning model is trained using datasets of metabolic profiles, cannabinoid treatment dosages, and patient response data, wherein the metabolic profiles comprise quantified concentrations of cannabinoids and their metabolites, lipid metabolites, amino acids, inflammatory cytokines, and neurotransmitter levels. In some embodiments, cannabinoid treatment dosages include specific ratios of tetrahydrocannabinol (THC), cannabidiol (CBD), and cannabigerol (CBG), as well as administration methods, frequency, and cumulative dose over time. In some embodiments, patient response data is recorded using standardized clinical assessment scales, self-reported outcomes, and laboratory -based biomarker quantification. In some embodiments, the machine learning model is configured to apply gradient boosting algorithms to classify samples and predict treatment outcomes, wherein the gradient boosting algorithms are selected from XGBoost, LightGBM, CatBoost, or other ensemble learning techniques designed to improve model accuracy through iterative error minimization. In some embodiments, the machine learning model is further configured to analyze non-linear relationships between metabolic variables, allowing for improved identification of patient subpopulations with distinct Cannabaceae treatment responses. In some embodiments, the machine learning model can be configured to rank the importance of metabolites, wherein metabolite importance ranking is performed using Shapley Additive Explanations (SHAP), permutation feature importance, recursive feature elimination (RFE), or least absolute shrinkage and selection operator (LASSO) regression techniques. In some embodiments, ranked metabolites are prioritized for biomarker discovery, treatment efficacy prediction, and the refinement of individualized cannabinoid therapy recommendations.

[00111] In some embodiments, the diagnostic module may be configured to generate treatment recommendations tailored to individual metabolic and diagnostic profiles, wherein treatment recommendations are based on an analysis of past therapeutic responses, predicted biomarker deviations, and probabilistic treatment outcome modeling. In some embodiments, the diagnostic module incorporates reinforcement learning frameworks, wherein treatment protocols are dynamically adjusted based on real-time patient metabolic feedback and evolving biomarker trends. In some embodiments, the treatment recommendations are refined using a continuous learning approach, wherein the system integrates newly collected metabolic data into predictive models, enabling ongoing optimization of cannabinoid formulations, dosing strategies, and administration regimens. In some embodiments, the system provides clinicians and patients with real-time recommendations through a graphical user interface (GUI), automated alerts, or personalized reports summarizing expected treatment efficacy and potential metabolic risks.; and

[00112] In some embodiments, systems described herein comprise a personalization module for medical Cannabaceae-based treatments FIG. 1 configured to: (a) identify suitable Canna- baceae phytochemical treatments based on individual diagnostics. In some embodiments, the module is configured to analyze patient-specific metabolomic profiles, diagnostic data, treatment history, or any combination thereof to recommend Cannabaceae-based formulations tailored to individual physiological and metabolic needs. In some embodiments, the module utilizes pretreatment metabolic assessments to establish a baseline metabolic state, wherein the baseline assessment includes but is not limited to quantified levels of cannabinoids and their metabolites, lipidomic markers, neurotransmitters, amino acids, inflammatory cytokines, oxidative stress markers, and other biochemical indicators relevant to endocannabinoid system function. In some embodiments, the module integrates historical treatment data, wherein the historical treatment data comprises previous cannabinoid formulations, dosages, administration methods, treatment durations, and recorded patient responses, enabling data-driven optimization of Cannabaceae- based interventions.

[00113] In some embodiments, the module further incorporates genomic and phar- macogenomic data, wherein genetic variations in cannabinoid metabolism -related enzymes (e.g., cytochrome P450 isoforms CYP2C9, CYP3A4, CYP2C19, FAAH, and COMT) are analyzed to predict individualized pharmacokinetic and pharmacodynamic responses to specific cannabinoids. In some embodiments, the module applies machine learning algorithms to classify patients into response categories, wherein response categories include but are not limited to high responders, partial responders, and non-responders, allowing for personalized treatment adjustments. In some embodiments, the machine learning algorithms are selected from gradient boosting models, random forest classifiers, support vector machines (SVMs), deep neural networks (DNNs), or Bayesian networks, wherein the models are trained on longitudinal patient response datasets to improve prediction accuracy. In some embodiments, the module dynamically updates treatment recommendations by incorporating real-time patient monitoring data, wherein realtime data may include metabolite concentration changes, symptom progression, and biomarker deviations at pre-treatment (PRE), peak effect (PEAK), and post-treatment intervals.

[00114] In some embodiments, the module is further configured to assess potential contraindications and drug interactions, wherein the assessment is based on co -administered pharmaceuticals, pre-existing metabolic conditions, and documented adverse event profiles, ensuring that the recommended Cannabaceae-based formulations are both effective and safe for individual patients; (b) mapping previously unknown correlations using machine learning algorithms to uncoverinsights into metabolic pathways. In some embodiments, machine learning algorithms analyze metabolic data, treatment outcomes, and biomarker deviations to reveal novel relationships between endocannabinoid system metabolites and Cannabaceae phytochemicals. In some embodiments the analysis comprises identifying metabolic shifts, clustering patient response patterns, and predicting optimal cannabinoid formulations.

[00115] In some embodiments, machine learning algorithms, including Gradient Boosting, Random Forest, Support Vector Machines (SVMs), Artificial Neural Networks (ANNs), and Graph Neural Networks (GNNs),are used to classify metabolic profiles, wherein classification can be performed by predicting individual treatment response category (e.g., high responders, partial responders, and non-responders) based on biomarker shifts and clinical symptom assessments; by identifying significant biomarkers from high -dimensional data, wherein feature selection methods such as Shapley Additive Explanations (SHAP), LASSO regression, and Recursive Feature Elimination (REE) can be employed to rank metabolites based on their predictive value for treatment efficacy; and/or by mapping metabolic pathway interactions associated with Can- nabaceae-based treatments, wherein metabolic pathway analysis is conducted using multi -omics integration techniques, including gene-metabolite network analysis, pathway enrichment analysis, and Bayesian inference models.

[00116] In some embodiments, the machine learning algorithms are trained on longitudinal metabolomic datasets, wherein datasets include time-stamped measurements of cannabinoid metabolite levels, lipid metabolites, neurotransmitters, amino acids, inflammatory cytokines, and oxidative stress markers. In some embodiments, machine learning models are optimized through hyperparameter tuning techniques, including Bayesian optimization, grid search, and evolutionary algorithms, to improve predictive accuracy in modeling metabolic pathway interactions.

[00117] In some embodiments, the machine learning system is configured to detect non-linear relationships between cannabinoid intake and metabolic responses, wherein deep learning architectures such as convolutional neural networks (CNNs) and long short-term memory (LSTM) networks are implemented to process temporal fluctuations in metabolite levels. In some embodiments, machine learning models generate probabilistic associations between specific Cannabaceae phytochemicals and metabolic pathway alterations, wherein probabilistic scoring methods such as Monte Carlo simulations, Gaussian mixture modeling, and probabilistic graphical models are applied to quantify treatment-related metabolic shifts and infer causality in biomarker response patterns. [00118] In some embodiments, the insights generated by machine learning models are integrated into a decision-support framework, wherein the framework provides clinicians with realtime recommendations for personalized cannabinoid-based therapies based on predicted metabolic responses and biomarker deviations; c) updating a database with personalized treatment recommendations. In some embodiments, the system is configured to continuously update individual treatment profiles, wherein updates are based on longitudinal metabolic assessments, patient-reported outcomes, and biomarker fluctuations overtime. In some embodiments, the system integrates new metabolic data, pharmacokinetic measurements, and patient responses into a structured database to refine and improve Cannabaceae-based therapy recommendations. In some embodiments, the database of treatment recommendations includes baseline metabolic assessments, wherein baseline data comprises pre-treatment endocannabinoid system biomarkers, inflammatory cytokines, neurotransmitter levels, and oxidative stress indicators. In some embodiments, treatment recommendations are dynamically updated based on changes in metabolomic and clinical profiles, allowing for iterative refinement of cannabinoid formulations and dosages.

[00119] In some embodiments, the system implements machine learning-based treatment optimization, wherein machine learning models analyze historical patient data, biomarker deviations, and symptom progression to predict optimal cannabinoid formulations, dosing regimens, and treatment durations. In some embodiments, gradient boosting models, deep neural networks, and reinforcement learning algorithms are employed to generate adaptive treatment pathways tailored to individual metabolic responses. In some embodiments, treatment recommendations consider multi-omics integration, wherein datasets from metabolomics, transcriptomics, proteomics, and microbiome analyses are utilized to derive comprehensive patient-specific therapeutic strategies. In some embodiments, the system incorporates statistical inference models to quantify treatment efficacy, wherein efficacy is assessed based on clinical improvement scores, metabolite normalization trends, and predictive biomarker correlations. In some embodiments, real-time data ingestion enables the system to rapidly adjust treatment protocols, wherein newly collected patient data is automatically processed, analyzed, and integrated into the existing database. In some embodiments, the system comprises a personalized feedback module, wherein treatment modifications are continuously refined based on patient responses and emerging clinical insights. In some embodiments, the system includes a population -level treatment optimization framework, wherein anonymized data from multiple individuals is analyzed to identify shared metabolic signatures, treatment response patterns, and cohort-specific cannabinoid sensitivity markers. In some embodiments, this framework enables the development of standardized treatment protocols for specific subpopulations, ensuring both individualized and population -based therapeutic strategies.

[00120] In some embodiments, the treatment recommendation system is configured for integration with electronic health records (EHRs), wherein EHR compatibility allows for seamless data sharing with healthcare providers, clinical decision-support tools, and regulatory databases; (d) predicting potential effectiveness of medical Cannabaceae-based treatments. In some embodiments, predictive models may assess the likelihood of therapeutic success, wherein the likelihood is determined by analyzing patient-specific metabolic data, historical treatment outcomes, and biomarker deviations over time. In some embodiments, predictive models are configured to identify response patterns, stratify patient populations, and optimize cannabinoid -based treatment regimens. In some embodiments, the likelihood of therapeutic success comprises comparing patient-specific metabolic data with historical treatment outcomes stored in a database, wherein the database comprises longitudinal records of pre-treatment, peak-effect, and post-treatment metabolic profiles, as well as corresponding clinical response evaluations.

[00121] In some embodiments, treatment outcomes are classified into categories such as full responder, partial responder, or non-responder, wherein classification is based on biomarker shifts, symptom severity reduction, and patient-reported improvements. In some embodiments, predictive models may incorporate machine learning algorithms, including but not limited to gradient boosting, random forest classifiers, support vector machines (SVMs), artificial neural networks (ANNs), and probabilistic Bayesian models, analyzing metabolic and clinical datasets and predicting individualized responses to Cannabaceae-based treatments. In some embodiments, predictive models utilize supervised learning techniques, wherein training datasets include patient demographics, genetic predisposition, baseline metabolic markers, and cannabinoid treatment details. In some embodiments, unsupervised clustering techniques, such as k-means clustering, hierarchical clustering, and principal component analysis (PCA), are applied to detect hidden subpopulations with distinct metabolic response patterns. In some embodiments, the system is further configured to compute probability scores indicative of treatment success, wherein probability scores are derived from statistical confidence intervals, likelihood estimation models, and deep learning-based classification metrics. In some embodiments, Shapley Additive Explanations (SHAP) and LIME (Local Interpretable Model-agnostic Explanations) are implemented to rank the influence of specific metabolites on treatment outcomes. In some embodiments, the predictive model is continuously refined through iterative learning, wherein newly collected patient data is incorporated into the training set, enabling adaptive recalibration of treatment efficacy predictions. [00122] In some embodiments, real-time data integration allows for dynamic updates to therapeutic recommendations, ensuring that Cannabaceae-based treatments are continuously optimized based on individual metabolic responses; and (e) provide iterative improvements to treatments based on monitored individual responses. In some embodiments, feedback loops within the system allow for real-time adjustment of treatment protocols by analyzing patient metabolic responses overtime, wherein real-time analysis comprises tracking biomarker fluctuations, evaluating symptom progression, and dynamically modifying cannabinoid formulations based on observed metabolic trends. In some embodiments, feedbackloops within the system can be configured to analyze longitudinal metabolic data, wherein longitudinal data includes but is not limited to pre-treatment baseline measurements, peak-effect biomarker variations, and post-treatment metabolic stabilization patterns. In some embodiments, feedback loops incorporate machine learning-driven adaptive modeling, wherein treatment optimization algorithms continuously refine cannabinoid dosages and formulations in response to real-time patient data.

[00123] In some embodiments, the system dynamically adjusts cannabinoid dosages and formulations by integrating newly collected metabolic and clinical response data into predictive models, wherein the adjustment mechanism is based on: Identifying deviations from expected treatment responses, wherein unexpected metabolic fluctuations, or lack of therapeutic improvement trigger modifications to cannabinoid ratios or dosage levels. Predicting individual sensitivity to specific cannabinoids, wherein models classify patients into metabolic response categories to optimize personalized formulations. Evaluating cumulative dose-response relationships, wherein iterative adjustments are made to prevent treatment saturation, tolerance buildup, or adverse reactions. Incorporating multi -omics data layers, including but not limited to genomic, pro- teomic, and lipidomic datasets, to refine treatment recommendations based on an individual’s unique biochemical profile.

[00124] In some embodiments, real-time metabolic monitoring is conducted using high-frequency sampling, wherein sample collection schedules are adjusted dynamically based on prior biomarker variability patterns. In some embodiments, treatment refinement algorithms use reinforcementlearningmodels, wherein the system learns optimal treatment pathways over time by simulating different cannabinoid dosage adjustments and evaluating patient outcomes. In some embodiments, iterative treatment refinements are validated using statistical thresholding techniques, wherein anomalies, extreme biomarker deviations, or outlier response profiles are flagged for clinician review. In some embodiments, the system alerts healthcare providers when treatment modifications are recommended, ensuring clinician oversight in the iterative optimization of cannabinoid-based therapies. In some embodiments, iterative treatment refinement data is stored within a distributed database system, wherein patient response patterns are continuously aggregated to improve population-wide cannabinoid therapy recommendations. In some embodiments, insights from individual treatment optimizations are used to refine predictive models for future patients, ensuring that personalized cannabinoid dosing strategies evolve over time based on real-world treatment data.

[00125] In some embodiments, the personalization module may be configured to generate treatment recommendations tailored to individual metabolic and diagnostic profiles. In some embodiments, the personalization module can be further configured to provide probability -based assessments of treatment outcomes based on historical individual data. In some embodiments, the personalization module further comprises a predictive analytics engine to determine longterm individual outcomes for specific cannabinoid -based treatments. In some embodiments, the machine learning module integrates real-time metabolic data to dynamically update training models and improve prediction accuracy.

[00126] In some embodiments, the machine learning module integrates a treatment provider module 107, configured to generate treatment outputs, wherein recommended treatments may comprise written treatment protocols specifying but not limited to cannabinoid type, dosage amount, administration frequency, and route of administration, based on the predicted metabolic response and individual condition. In some embodiments, the route of administration can comprise at least one of: Oral administration, including capsules, tablets, oils, tinctures, and edibles; Sublingual or buccal administration, including dissolvable strips, sprays, and oils applied under the tongue; Inhalation, including vaporized formulations or aerosolized delivery; Topical administration, including creams, patches, or gels applied to the skin; Transdermal delivery, comprising slow-release patches; or Rectal or vaginal administration, using suppositories. In some embodiments, written treatment protocols may be updated automatically or manually in response to newly collected metabolic data and ongoing evaluation of subject’s responses, allowing for iterative refinement of Cannabaceae-based therapy.

[00127] In some embodiments, the ranked metabolites are used to refine personalized cannabinoid formulations, wherein treatment plans are iteratively updated based on newly acquired metabolic data.

[00128] In some embodiments, the treatment efficacy module further comprises a feedback loop configure to enable real-time updates to treatment recommendations based on individual metabolic and symptomatic data. In some embodiments, the system can further comprise a metabolite-level database that integrates longitudinal data for tracking individual metabolic responses to Cannabaceae-derived treatments over time. [00129] In some embodiments, the system can comprise a user interface for individuals to view predictions, treatment plans, and track progress based on their metabolic profiles. In some embodiments, the system further comprises the step of visualizing changes in z-scores and predicted Cannabaceae-derived molecules dosages through a graphical user interface.

[00130] In some embodiments, the system can be implemented as a mobile application for individuals to access personalized treatment plans and track their progress.

Computer implementation

[00131] The present disclosure provides computer systems that are programmed to implement methods of the disclosure. FIG. 7 shows a computer system 701 that is programmed or otherwise configured to control all the internal processes of the systems as programmed, such as data acquisition through sensors (e.g., physical, chemical, and biological data), sensor data fusion and commanding control loops, and creating data sets associated with each process. The computer system 701 can regulate various aspects of the production process. The computer system 701 can be an electronic device of a user or a computer system that is remotely located with respect to the electronic device. The electronic device can be a mobile electronic device.

[00132] The computer system 701 includes a central processing unit (CPU, also “processor” and “computer processor” herein) 705, which can be a single core or multi core processor, or a plurality of processors for parallel processing. The computer system 701 also includes memory or memory location 704 (e.g., random-access memory, read-only memory, flash memory), electronic storage unit 705 (e.g., hard disk), communication interface 707 (e.g., network adapter) for communicating with one or more other systems, and peripheral devices 706, such as cache, other memory, data storage and/or electronic display adapters. The memory 704, storage unit 705, interface 707 and peripheral devices 706 are in communication with the CPU 705 through a communication bus (solid lines), such as a motherboard. The storage unit 705 can be a data storage unit (or data repository) for storing data. The computer system 701 can be operatively coupled to a computer network (“network”) 730 with the aid of the communication interface 707. The network 703 can be the Internet, an internet and/or extranet, or an intranet and/or extranet that is in communication with the Internet. The network 730 in some cases is a telecommunication and/or data network. The network 703 can include one or more computer servers, which can enable distributed computing, such as cloud computing. The network 703, in some cases with the aid of the computer system 701, can implement a peer-to-peer network, which may enable devices coupled to the computer system 701 to behave as a client or a server. [00133] The CPU 705 can execute a sequence of machine-readable instructions, which can be embodied in a program or software. The instructions may be stored in a memory location, such as the memory 704. The instructions can be directed to the CPU 705, which can subsequently program or otherwise configure the CPU 705 to implement methods of the present disclosure. Examples of operations performed by the CPU 705 can include fetch, decode, execute, and writeback.

[00134] The CPU 705 can be part of a circuit, such as an integrated circuit. One or more other components of the system 701 can be included in the circuit. In some cases, the circuit is an application specific integrated circuit (ASIC).

[00135] The storage unit 705 can store files, such as drivers, libraries and saved programs. The storage unit 705 can store user data, e.g., user preferences and user programs. The computer system 701 in some cases can include one or more additional data storage units that are external to the computer system 701, such as located on a remote server that is in communication with the computer system 701 through an intranet or the Internet.

[00136] The computer system 701 can communicate with one or more remote computer systems through the network 730. For instance, the computer system 701 can communicate with a remote computer system of a user (e.g., Virtual Private Networks, Computer hosted in services such as Amazon Web Services (AWS), Satellite communication). Examples of remote computer systems include personal computers (e.g., portable PC), slate or tablet PC’s (e.g., Apple® iPad, Samsung® Galaxy Tab), telephones, Smart phones (e.g., Apple® iPhone, Android-enabled device, Huawei®, Blackberry®), or personal digital assistants. The user can access the computer system 701 via the network 730.

[00137] Methods as described herein can be implemented by way of machine (e.g., computer processor) executable code stored on an electronic storage location of the computer system 701, such as, for example, on the memory 704 or electronic storage unit 705. The machine executable or machine-readable code can be provided in the form of software. During use, the code can be executed by the processor 705. In some cases, the code can be retrieved from the storage unit 705 and stored on the memory 704 for ready accessby the processor 705. In some situations, the electronic storage unit 705 can be precluded, and machine-executable instructions are stored on memory 704.

[00138] The code can be pre-compiled and configured for use with a machine having a processer adapted to execute the code or can be compiled during runtime. The code can be supplied in a programming language that can be selected to enable the code to execute in a precompiled or as-compiled fashion. [00139] Aspects of the systems and methods provided herein, such as the computer system 701, can be embodied in programming. Various aspects of the technology may be thought of as “products” or “articles of manufacture” in the form of machine (or processor) executable code and/or associated data that is executed or embodied in a type of machine -readable medium. Machine-executable code can be stored on an electronic storage unit, such as memory (e.g., readonly memory, random-access memory, flash memory) or a hard disk. “Storage” type media can include any or all of the tangible memory of the computers, processors or the like, or associated modules thereof, such as various semiconductor memories, tape drives, disk drives and the like, which may provide n on-transitory storage at any time for the software programming. All or portions of the software may at times be communicated through the Internet or various other telecommunication networks. Such communications, for example, may enable loading of the software from one computer or processor into another, for example, from a management server or host computer into the computer platform of an application server. Thus, another type of media that may bear the software elements includes optical, electric, and electromagnetic waves, such as used across physical interfaces between local devices, through wired and optical landline networks and over various air-links. The physical elements that carry such waves, such as wired or wireless links, optical links, or the like, also may be considered as media bearing the software. As used herein, unless restricted to non -transitory, tangible “storage” media, terms such as computer or machine “readable medium” refer to any medium that participates in providing instructions to a processor for execution.

[00140] Hence, a machine-readable medium, such as computer-executable code, may take many forms, including but not limited to, a tangible storage medium, a carrier wave medium or physical transmission medium. Non-volatile storage media include, for example, optical or magnetic disks, such as any of the storage devices in any computer(s) or the like, such as may be used to implement the databases, etc. shown in the drawings. Volatile storage media include dynamic memory, such as main memory of such a computer platform. Tangible transmission media include coaxial cables; copper wire and fiber optics, including the wires that comprise a bus within a computer system. Carrier-wave transmission media may take the form of electric or electromagnetic signals, or acoustic or light waves such as those generated during radio frequency (RF) and infrared (IR) data communications. Common forms of computer-readable media therefore include for example: a floppy disk, a flexible disk, hard disk, magnetic tape, any other magnetic medium, a CD-ROM, DVD or DVD-ROM, any other optical medium, punch cards paper tape, any other physical storage medium with patterns of holes, a RAM, a ROM, a PROM and EPROM, a FLASH -EPROM, any other memory chip or cartridge, a carrier wave transporting data or instructions, cables or links transporting such a carrier wave, or any other medium from which a computer may read programming code and/or data. Many of these forms of computer readable media may be involved in carrying one or more sequences of one or more instructions to a processor for execution.

[00141] The computer system 701 can include or be in communication with an electronic display 709 that comprises a user interface (UI) 708 for providing, for example, settings, bioprocess report listing measured variables in real time of every stage of the system, capabilities to export and import files (e.g., configuration files, updates), calibration, alarms (e.g., errors, maintenance, replacement of consumables). Examples of UI’s include, without limitation, a graphical user interface (GUI) and web-based user interface.

[00142] Methods and systems of the present disclosure can be implemented by way of one or more algorithms. An algorithm can be implemented by way of software upon execution by the central processing unit 705. The algorithm can, for example, adjust variables of the control systems using feedback loops, detect problems in the process by image recognition and pattern analysis, fuzzy logic and with hard and soft threshold enforcements, correlate specific and unspecific data through machine learning (e.g., Supervised, Semi-supervised, Unsupervised, and/or Reinforcement) to optimize process conditions within the system, the process outcomes, modelling behavior and simulation. Additionally, quantum computing systems can be utilized to enhance computational efficiency and problem -solving capabilities by leveraging quantum algorithms for complex optimizations, probabilistic modeling, and accelerated data correlation, thereby improving system performance and predictive accuracy.

EXAMPLES

[00143] The following examples are provided to further illustrate some embodiments of the present disclosure but are not intended to limit the scope of the disclosure; it will be understood by their exemplary nature that other procedures, methodologies, or techniques known to those skilled in the art may alternatively be used.

Example 1: Methods and Systems for Personalized Cannabaceae-Based Treatments Using Machine Learning and Metabolomics Data Analysis.

[00144] This example demonstrates that the methods and systems disclosed herein can be implemented for the personalization of Cannabaceae-based treatments using machine learning and metabolomics data analysis, as shown in FIG. 1. In one exemplary implementation, saliva samples from individuals diagnosed with Autism Spectrum Disorder (ASD) are collected at multiple time points 101, including pre-treatment (PRE), peak effect (PEAK), and post-treatment intervals, following administration of medical cannabis (MC), as illustrated in 301 and 302. These collection timepoints are also associated with participant-specific cannabinoid exposures and behavioral responses, as shown in FIG. 2, specifically 201 (Cannabinoid dosage) and 202 (Behavior), wherein Cannabinoid treatment levels were defined as follows: THC: (0) No; (1) 0.05-5.00 mg; (2) 5.05-15.00 mg; and (3) >15.05 mg; CBD: (0) No; (1) 1-30 mg; (2) 31-84 mg; (3) 85-100 mg; and (4) >100 mg; and, CBG: (0) No; (1) 1-49 mg; (2) >50 mg, and wherein behavior ranking values were: (1) improved; (2) partially improved; and (3) worsened.

[00145] These samples are processed (102) using liquid chromatography -mass spectrometry (LC-MS) to identify and quantify cannabis-responsive biomarkers, such as N-acetylaspartic acid (NAA), lysophosphatidylethanolamine, and long-chain acylcarnitines, which are known to correlate with neuroinflammation, oxidative stress, and mitochondrial dysfunction, as depicted in FIG. 3, FIG. 4, and FIG. 5. Additional biomarker/metabolic data classifications are shown in 401, with compound-specific Venn diagram outputs in 402 and breakdowns by the cannabinoid compound shown in 402A (e.g. Corosolic acid), 402B (e.g. Flavanone) and 402C (e.g. Zeaxan- thin).

[00146] The collected metabolomic data is pre-processed to normalize variations, remove batch effects, and reduce dimensionality, using the statistical module disclosed herein and shown in 104. This dataset is then stored in a structured database that associates metabolic profiles with individual diagnostic information, cannabinoid treatment details (including THC, CBD, and CBG dosages), and timestamps of sample collection using the data management module disclosed herein (103). By implementing the machine learning module 105 disclosed herein, the biomarker correlations and grouping strategies were calculated 402D (e.g. Naringenin), 402E (e.g., Vitexin), 402F (e.g., Rutin), and 402G(e.g., Sitosterol). Time dependent levels of vitexin (apig- enin 8-glucoside) detected attime points PRE (10 min before MC treatment), PEAK, Post-1 and Post-2 (90, 180 and 270 min after MC treatment, respectively) in child ID Al 8 are shown in 403; and a representation of time dependent levels of rutin (quercetin 3 -rutinoside) detected at time points described in (403) in child (ID Al 6 of FIG. 2) are shown in 404. Simplified metabolic pathways associated with the differential expression of potential ASD cannabis -responsive biomarkers after THC, CBD and CBG treatment are shown in FIG. 6.

[00147] In some embodiments, machine learning algorithms such as Gradient Boosting (from the Scikit-learn package) are trained on this dataset to classify individuals based on treatment outcomes (e.g., improved behavior, partially improved behavior, or worsening behavior) and to predict optimal cannabinoid formulations for new patients, as shown in 105. Examples of Identification of potential THC-, CBD- and CBG-responsive biomarkers that distinguish patients with ASD at PRE vs PEAK. Venn diagram illustrating the unique and overlapping cannabis-responsive biomarkers that respond (PRE/PEAK) to THC, CBD and CBG treatment. The biomarker functions (lipid metabolism, neuroactivity and steroid activity) are shown in 501, 502, and 503. The models also identify key biomarkers that contribute to treatment efficacy, providing insights into metabolic pathways influenced by Cannabaceae-based treatments, as depicted in FIG. 6.

[00148] An iterative feedback loop is employed, wherein new metabolic data from ongoing patient monitoring is continuously fed into the training of machine learning models, linking treatment and outcomes, and refining predictions and treatment recommendations over time, as illustrated in 105. This adaptive process allows the system to dynamically adjust cannabinoid dosages and formulations, ensuring that treatments remain effective as individual metabolic responses evolve. The methods further allow for the analysis of treatment efficacy across populations, enabling the identification of population-level biomarkers and the development of standardized treatment protocols for specific subpopulations with similar metabolic profiles, as shown in FIG. 6

[00149] While preferred embodiments of the present disclosure have been shown and described herein, such embodiments are provided by way of example only. Numerous variations, changes, and substitutions may occur without departing from the disclosure. Various alternatives to the embodiments of the present disclosure may be employed in practicing the present disclosure. It is intended that the following claims define the scope of the present disclosure and that methods and structures within the scope of these claims and their equivalents be covered thereby.

Claims

CLAIMS What is claimed is:

1 . A method for determining treatments to restore healthy physiological levels of one or more metabolites and/or biomarkers in a subject using Cannabaceae -derived molecules, the method comprising: a) obtaining a biological sample from the subject; b) analyzing the sample to quantify levels of the one or more metabolites and/or biomarkers; and, c) providing a treatment comprising a Cannabaceae-derived molecule or a mixture of a plurality of Cannabaceae-derived molecules to the subject.

2. The method of claim 1, further including a database wherein the data comprises relationships between the individual’s information and metabolic data, wherein each metabolite detected in a sample obtained from the individual is categorized into at least one category.

3. The method of claim 2, further including calculating z-scores in metabolite levels in the subject, defined as the number of standard deviations from the mean of at least one physiological range observed in a control population comprised in the database.

4. The method of claim 3, further including estimating the treatment of Cannabaceae-derived molecules or mixture of Cannabaceae-derived molecules required to normalize or maintain the metabolite z-score.

5. The method of claim 1, wherein the biological sample comprises at least one of saliva, blood, Urine, Cerebrospinal Fluid, tissue, hair, exhaled breath condensate, tears, feces or sweat.

6. The method of claim 1, wherein the analysis of the sample to quantify levels of metabolites comprises at least one of Spectroscopy -Based Techniques, Chromatography -Based Techniques, Optical and Fluorescence-Based Techniques, Immunoassay and Biosensor-Based Techniques, Separation-Based Techniques, Isotope-Based Techniques, Electrochemical Techniques, or any combination thereof.

7. The method of claim 6, wherein the analysis of the sample to quantify levels of metabolites comprises analysis by mass spectrometry.

8. The method of claim 7, wherein the metabolite comprises at least one of the groups consisting of mammalian metabolites, plant metabolites, microbial metabolites, or any combination thereof.

9. The method of claim 1, wherein the structured database classifies metabolites based on endocannabinoid system markers, medical condition associations, metabolic responses, cohort profiling, individual metabolite deviations and any combinations thereof.

10. The method of any of claim 3, wherein the z-score calculation further includes adjustments based on cohort-specific averages for subpopulations defined by demographic or medical characteristics.

11. The method of claim 2, wherein the database further comprises a database of Cannabaceae contaminants detected in the biological sample of at least one individual who has consumed Cannabaceae-derived molecules.

12. The method of claim 11, wherein the Cannabaceae contaminants further comprise entries for specific chemicals or residues associated with Cannabaceae-derived products.

13. The method of claim 1, further comprising a metabolite -level database that integrates longitudinal data for tracking individual metabolic responses to Cannabaceae-derived treatments over time.

14. The method of claim 1, further comprising a prediction database, wherein the database is generated by implementing machine learning algorithms to improve the accuracy of dosage recommendations.

15. The method of claim 7, wherein mass spectrometry is complemented by chromatography techniques to enhance metabolite detection accuracy.

16. The method of claim 2, wherein the database of endocannabinoid system -related metabolites includes correlations between specific Cannabaceae-derived molecules and their impact on z- score changes.

17. The method of claim 11, wherein the cannabis contaminants information is used to identify potential interactions between Cannabaceae-derived molecules, Cannabaceae contaminants and metabolic responses.

18. The method of claim 1, further comprising generating a personalized treatment plan for individuals based on metabolite-level data and predicted Cannabaceae-derived molecule treatments.

19. The method of claim 1, further comprising generating Cannabaceae-derived molecule combinations and dosages.

20. A system for determining Cannabaceae -based treatments, comprising: a) a biological sample test; b) a sample processing module; c) a data management module; d) a statistical analysis module; e) a machine learning module; f) a diagnostic module; and, g) a personalization module for medical Cannabaceae-based treatments.

21. The system of claim 20, wherein the biological sample test module is configured to enable individuals to collect at least one biological sample; store the at least one biological sample; and maintain the at least one biological sample optimal condition while monitoring and preserving it during transportation.

22. The system of claim 20, wherein the sample processing module is configured to extract metabolites using chromatography to determine metabolite characteristics.

23. The system of claim 20, wherein the data management module comprises a database of individual metabolite levels and timestamps of Cannabaceae-based treatments; a database of individual diagnostic information; a database of individual condition or state evaluations, and timestamps, with and without Cannabaceae-based treatments; and a database of individual medication and Cannabaceae-derived treatment compositions.

24. The system of claim 20, wherein the statistical analysis module is configured to perform z- score evaluations to analyze relationships between individual endocannabinoid system -metabolic levels and database information, including conditions, diagnostics, and Cannabaceae-derived treatment effects; associate mass spectrometry-detected metabolite levels with individual data in a database; and correlate individual metabolic data with timestamps of Cannabaceae-based treatments;

25. The system of claim 20, wherein the machine learning module comprises a training system formachine learning models comprising database information and metabolic pathway data; at least one machine learning model trained to predict any attribute or group of attributes within the database based on other database attributes; and at least one machine learning model to identify complex, nonlinear relationships withing at least one database from the data management module.

26. The system of claim 20, wherein the diagnostic module comprises a database of individualspecific medication, cannabinoid and Cannabaceae phytochemicals treatment profiles; a statistical analysis component performing z-score evaluations of individual data; and a machine learning module trained on metabolic pathways, mass spectrometry, and treatment outcome data, configured to generate probabilities indicative of physiological conditions.

27. The system of claim 20, wherein the personalization module for medical Cannabaceae-based treatments, includes identifying suitable Cannabaceae phytochemicals treatments based on individual diagnostics; mapping previously unknown correlations using machine learning to uncover insights into metabolic pathways; and updating a database with personalized treatment recommendations; predicting potential effectiveness of medical Cannabaceae-based treatments; and, provide iterative improvements to treatments based on monitored individual responses.

28. The system of claim 22, wherein the chromatography method is selected from the group consisting of liquid chromatography or gas chromatography.

29. The system of claim 25, wherein the at least one machine learning model of the machine learning module is trained on a dataset comprising: a) metabolic pathways; b) mass spectrometry data; c) timestamps of Cannabaceae-based treatments; and/or d) clinical outcomes of Cannabaceae-based treatments in individuals with varying physiological conditions.

30. The system of claim 24, wherein the statistical analysis module identifies correlations between specific endocannabinoid system-metabolic markers and treatment efficacy.

31. The system of claim 23, wherein the database of individual conditions further comprises longitudinal data capturing variations in endocannabinoid system -metabolic levels over time with and without Cannabaceae-based treatments.

32. The system of claim 25, wherein the machine learning module further comprises a neural network trained on datasets of metabolic levels, diagnostic data, and treatment outcomes to enhance prediction accuracy.

33. The system of claim 27, wherein the personalization module generates treatment recommendations tailored to individual metabolic and diagnostic profiles.

34. The system of claim 20, wherein the personalization module is further configured to provide probability -based assessments of treatment outcomes based on historical individual data.

35. The system of claim 20, further comprising a user interface for individuals to view predictions, treatment plans, and track progress based on their metabolic profiles.

36. The system of claim 25, wherein the machine learning module integrates real-time metabolic data to dynamically update training models and improve prediction accuracy.

37. The system of claim 27, wherein the personalization module further comprises a predictive analytics engine to determine long-term individual outcomes for specific cannabinoid -based treatments.

38. The system of claim 30, wherein the treatment efficacy module further comprises a feedback loop enabling real-time updates to treatment recommendations based on individual metabolic and symptomatic data.

39. The system of claim 24, further comprising the step of visualizing changes in z-scores and predicted Cannabaceae-derived molecules dosages through a graphical user interface.

40. The system of claim 20, further comprising a mobile application for individuals to access personalized treatment plans and track their progress.