WO2025168926A1 - Systems and methods for mechanistic and machine learning approaches for modelling and optimizing downstream processing phase of fermentation-based bioprocesses - Google Patents

Abstract

Methods, systems, and processes are disclosed that allow a user to optimize a fermentation process and/or optionally optimize processes that occur downstream of the fermentation process. The methods, systems and/or processes allow for a user to input data, such as experimental data as needed, and/or to fix parameters in the system that will allow the system to optimize other non-fixed variables. The methods, systems and/or processes may use machine learning models to generate an iterative process that allows for the optimal process to be attained.

Description

Systems And Methods for Mechanistic and Machine Learning Approaches for Modelling and Optimizing Downstream Processing Phase of Fermentation-Based Bioprocesses

Field

The present invention relates to a system or platform that is comprehensively designed for fermentation and downstream processing processes. In an embodiment, the present invention relates to the design, modeling and optimizing of a process for a user, the process designed to accommodate a user’s particular strain of a host organism that produces one or more specific bioproducts.

Background

Fermentation processes generally consist of several key elements, with some common terminology to describe them. The fermentation itself, where a cell culture is fermented to grow cells (and produce the product, if the product is not the cells themselves) is considered a single step, and then the processing of the resulting fermentation broth is commonly referred to as downstream processing. This consists of a series of processing steps, from 1 or 2 to more than a dozen in some cases, to extract the desired product, purify it and output it in the desired medium. Typical downstream processing steps include centrifugation, membrane filtration, drying, and more, and each of these types has many variants, each of which has different parameters, operating modes, and many more factors to consider. Each of these steps is often referred to as a unit operation.

Processes can also be run at different scales, typically referencing the volume of fermentation broth, with different scales requiring different types of equipment and introducing different overheads and constraints, and the economics of different scales can vary enormously. For example, a benchtop process might involve fermenting 500ml or less within a shake-flask, and manual transfer of material between steps, but a production-scale system might surpass 1,000,000 I, and involve a dedicated facility with a staff of dozens. Different products will also be produced at different volumes - an enzyme used in minute quantities in a niche process will likely only require a relatively small scale, even for full production, but a commodity protein or biomass product such as a process to make plant based foods might easily require millions of liters of capacity for full production.

Location of production will also influence many production factors. The location will likely affect labor costs, utility prices, as well as the price of key inputs in the processes. All of these will have significant impacts upon the final unit economics and thus must be considered when planning scale up of a bioprocess or bioprocesses.

Moreover, along with the scale of the bio-production process, the usage of the equipment in the process and the purity requirements of the final product, as well as its form must all be considered. For example, a pharmaceutical compound or composition will have incredibly strict purity requirements, whereas a food grade product may be more lenient on certain requirements. These requirements and regulations also tend to differ in different jurisdictions across the world.

W02014099707A2, WO2009154624A1, W02021110870A1, WO2017149065A1,

W02007038572A2, WO2022246284A2, and CN115410657A all relate to patent application publications that focus on fermentation. However, none of these patent application publications disclose the software as disclosed herein that is able to design fermentation processes and associated downstream processes, such as software that designs, models, and optimizes processes for a particular strain of a host organism that outputs a bioproduct to find the optimal process(es) that is/are best suited for the user’s requirements.

CN104573882A relates to an optimization system for a water-based cooling system, using mechanistic modelling, and then reverse-engineering the structure of the pipeline, then optimizing the system using tabu search.

CN115600493A relates to the optimization of cold source systems - essentially air conditioning. The overall output is a heuristic control algorithm based upon prior learning to optimize both comfort of those using the system as well as power use.

KR20170020511A relates to biocatalytic methods for a particular acid and specific enzymes, and genetic coding approaches to those/ways of preparing them. Similar to W02014099707A2 and WO2009154624A1 cited above, KR20170020511A is a very pro- cess/product specific patent application, and thus is vastly different from the instant application, which is focused upon process design and optimization. Also, it relates to producing products of interest using specific genetic approaches.

US11746362B2 relates to a strain development approach for production of chemicals from GMOs at scale, using adjustment of the active metabolic network. Similar to WO2009154624A1 and KR20170020511A, it focuses on strain engineering, though with a slightly broader remit than those two patent application publications.

US2020089826A1 relates to a system for design optimization and performance prediction of parts being created from an additive metal manufacturing process. It utilizes different types of modelling to achieve its results, focusing on modelling temperatures, grain structures, melting patterns and more.

To the inventors’ knowledge, although many of the above applications do disclose fermentation, they fail to disclose the advantages that are seen in the present invention in being able to test one or more parameters (potentially using an iterative approach) allowing one to identify the optimal parameters for (a) fermentation process(es) in order to identify the process that achieves the optimal results.

Summary

In an embodiment, the present invention relates to a system or platform that is comprehensively designed for fermentation and downstream processing processes. In one embodiment, the present invention relates to utilizing a particular host organism and output product to test a multitude of different processes and find the process (or processes) that is/are best suited for the user’s requirements.

In an embodiment, the present invention relates to process engineering (e.g., identifying the specific machines and industrial processes used in the production of particular bioproducts) rather than genetic engineering. Some elements of the invention (e.g. the details of how the fermentation is performed) might be part of a typical output of our platform, forming part of a process recommendation.

In an embodiment, the platform focuses on designing optimal processes and identifying optimal process parameters for a bioprocess running at industrial scale, as well as predicting and quantifying larger scale performance from small scale results. This includes predicting performance at pilot scale from lab scale, or industrial scale from demonstration scale, or any other combination of input and output scales.

In an embodiment, the platform allows users to predict key issues they are likely to encounter prior to scaling their bioprocess from small-scale experimental results to a large scale bioprocess, allowing them to address potential problems before performing costly large-scale tests.

In an embodiment, the platform can identify key issues in a large-scale bioprocess and extrapolate those to appropriate small-scale experiments to address those issues.

In an embodiment, the platform covers the entire bioprocess (not just fermentation), and the platform is designed so that it can recommend parameters without experimental input. Where experimental data is provided, the platform is agnostic to how those parameters are collected or what manner of device was used for determining those parameters on the experimental scale.

In an embodiment, the platform operates at a higher level, looking at the entire process, not just fermentation, and evaluating overall protein yields and quality metrics as well as many other considerations, rather than specifically covering a single factor such as feed strategy.

In an embodiment, the platform is a software platform, and is focused on process design and optimization, and is hardware agnostic.

In an embodiment, the present invention optimizes for unit cost, titer, product quality or other objectives, or combinations of these. In an embodiment, the platform of the present invention also optimizes more than just the fermentation, but optimizes the entire bioprocess all the way through to an end product, including downstream processing of the product.

In an embodiment, the modelling system is also a hybrid of ML and mechanistic approaches, but the system is not focused on a particular organism, output product or process, so the platform is a robust platform that has a much broader focus.

In an embodiment, the platform is able to learn from empirical data to adjust its modelling to capture dynamics present within the data, as well as those within the mechanistic models, and is able to improve its modelling capabilities as more and more data is uploaded.

In an embodiment, the platform can integrate with equipment to automatically collect data and information on experiments, production runs or other relevant usage, and collate that data within the platform to inform and improve modelling.

In an embodiment, users will be able to view experiments and production runs within the platform and perform analysis(es) and gain insights from their data.

In an embodiment, the system/platform is able to predict overall fermentation time, and the platform models and outputs a much wider array of parameters, and is able to actively optimize for those factors.

In an embodiment, the platform of the present invention relates to and is able to select and optimize bio-manufacturers’ processes for producing bioproducts using the fermentation of cell cultures.

In an embodiment, the platform is able to calculate key sustainability metrics including, but not limited to, emissions, waste, water and energy use of a process, and also allow users to optimize their process with respect to one or more of these factors.

In an embodiment, the platform is able to calculate the impact of different media sources on a bioprocess, including any processing required to convert the media source into a form suitable for a fermentation process. This could include, but is not limited to, converting waste streams or side streams from other industries such as brewers’ spent grain into suitable feedstocks for fermentation processes.

In an embodiment, the platform is able to calculate and optimize not only for a single product, but for multiple products, for example calculating and optimizing the output of a precision fermented protein along with another product made from the cell biomass.

In an embodiment, the platform is able to calculate and optimize not only a linear process, comprising one or more unit operations arranged in a linear fashion, but also branching processes, wherein unit operations can produce multiple output streams, each of which may result in their own sub-processes comprising one or more unit operations.

Brief Description of the Drawings

Fig. 1 depicts the fermentation process and downstream processing steps after fermentation has occurred.

Fig. 2 depicts a block diagram schematic showing the architecture that a user encounters when accessing the platform.

Fig. 3 depicts a block diagram demonstrating the modular aspects of the operation architecture.

Fig. 4 depicts the inputs and outputs into and from the DSP (downstream processing) engine of the system architecture.

Fig. 5 depicts the inputs and outputs from the DSP engine with an optimization module incorporated into the system.

Fig. 6 depicts the standard user interface displayed to a user whilst modelling or optimizing a bioprocess within the system, which is clear and easy to understand, whilst being reminiscent of the process flow diagrams commonly used in industry.

Detailed Description

Detailed Description

The present invention relates to methods, systems, and processes that allow a user to optimize a fermentation process and/or optionally optimize processes that occur downstream of the fermentation process. The methods, systems and/or processes allow for a user to input data, such as experimental data as needed, and/or to fix parameters in the system that will allow the digital signal processor associated with the system to optimize other non-fixed variables. Alternatively, the user can input only minimal information about the host organism and the system of the present invention is designed to sample all possible outcomes to let the user know the ideal parameters and/or conditions that will be used to generate the ideal fermentation and/or downstream processing conditions to give optimal results and/or to meet the users needs. The methods, systems and/or processes may use machine learning models as part of the process that allows for the optimal process to be attained.

System focus and scope

The software platform of the present invention is intended to supercharge the R&D and scaling journey for companies using fermentation to produce products. This encompasses a wide range of possibilities and products, including algae, fungal, microbial and other host organisms, and products ranging from dyes to proteins to fats and much more. In an embodiment, one focus of the platform is supporting customers producing proteins using precision fermentation, but the platform will be expanded to serve a wider range of potential markets and use-cases.

In an embodiment, the platform allows users to model an entire fermentation bioprocess computationally, from the fermentation process until the product(s)/composition(s)/formu- lation(s) resulting from the bioprocess has been completely processed. For example, if a powderized product is to be generated, the computational modeling will include all steps in the process through to drying. In an embodiment, the platform will not only promote un- derstanding of all the key process dynamics such as mass and energy balances, but it will also include information on the economics and sustainability of the process. However, beyond this process modelling, the platform also allows users to optimize existing processes, create new optimized processes from scratch, as well as facilitating key decision-making by allowing comparisons of different options. The platform will allow the user to at least be able to answer the following questions: At what scale should the user operate? What price and scale does the user need for an adequate break-even point? Will scaling affect other key metrics, such as product quality?

The models also support both large and small scales, allowing users to understand key scale-up dynamics, such as whether certain processes will scale effectively, or how scaling might affect metrics like unit cost.

These small scale models will also allow prediction of larger scale performance, by identifying key factors and patterns within small scale performance that are indicative of large- scale performance, allowing users to identify scaling issues prior to scaling up their real- world equipment and facilities. Similarly, if a user is facing issues at a large scale, the system can scale key dynamics down to a small scale to help the user identify which small scale tests or experiments are most suitable to perform to resolve their problems.

The system also integrates experimental data, allowing it to learn the particular dynamics of a user’s bioprocess directly from real-world results, integrating those with existing models to truly capture the nuances of process performance and ensure the most accurate results.

Background

Fermentation processes generally consist of several key elements, with some common terminology to describe them. The fermentation itself, where a cell culture is fermented to grow cells (and produce the product, if the product is not the cells themselves) is considered a single step, and then the processing of the resulting fermentation broth is commonly referred to as downstream processing. This consists of a series of processing steps, from 1 or 2 to dozens in some cases, to extract the desired product, purify it and output it in the desired medium. Typical downstream processing steps include centrifugation, membrane filtration, drying, and more, and each of these types has many variants, each of which has different parameters, operating modes, and many more factors to consider. Each of these steps is often referred to as a unit operation.

Processes can also be run at different scales, typically referencing the volume of fermentation broth, with different scales requiring different types of equipment and introducing different overheads and constraints, and the economics of different scales can vary enormously. For example, a benchtop process might involve fermenting 500ml or less within a shake-flask, and manual transfer of material between steps, but a production-scale system could surpass 1,000,000 I, and involve a dedicated facility with a staff of dozens. Different products will also be produced at different volumes - an enzyme used in minute quantities in a niche process will likely only require a relatively small scale, even for full production, but a commodity protein or biomass product might easily require millions of liters of capacity for full production.

Location of production will also influence many production factors - labor, utility prices, as well as the price of key inputs will have significant impacts upon the final unit economics and sustainability and thus is a key metric to consider when planning scale up of a bioprocess.

Alongside scale, the usage of the product also determines the purity requirements of the final product, alongside its form. A pharmaceutical product will have incredibly strict purity requirements, whereas a food grade product may be more lenient on certain requirements. These requirements and regulations also tend to differ in different jurisdictions across the world.

The economics and market situation of the end product will also massively influence the approach taken to production. A commodity product may have an annual demand of hundreds of thousands of tons, whilst retailing at a few dollars per kg. This in turn will limit the production to processes that can support such large volume, and require them to be ultra efficient, as any losses are key. Those same processes must also be incredibly cheap on a per unit basis, which often eliminates high-performance but high cost unit operations such as chromatography. The production may also need to be colocated or nearby to both inputs and the final end user, as transportation costs will increase with distance, making the product economically inviable, as well as less sustainable.

Conversely, a low volume, high value product may retail for thousands or millions of dollars per kg, or even per gram . This allows production techniques to be vastly more flexible, and process inefficiencies can be entirely acceptable if they produce a better product. Price and location of inputs becomes significantly less important.

Product dynamics such as shelf life will also influence production, as a product with a short shelf life must be produced either on demand or in sync with demand, and likely nearby, limiting flexibility and options. Inversely, if a product has a long shelf life, it can be produced in a more location-agnostic manner, and production can also be run in a batched manner to take advantages of economies of scale.

Design principles

In an embodiment, the present invention has been designed with an architecture based upon a cloud-based system, which offers a wide range of solutions for scalable applications, delegated authentication, encrypted-at-rest highly scalable NoSQL DBs and excellent machine learning support.

In an embodiment, the platform uses frameworks and languages for both the web front-end and back-end elements, enabling rapid development, excellent support and wide ranging library support. In an embodiment, the present invention uses a modular system design for unit operations, allowing new unit operations to be easily added in future without extensive modification.

Overall system structure

In an embodiment, the architecture has been split broadly between the visual web layer and the back-end code, allowing each to use languages, frameworks and tools that best support their respective functions. This approach also allows the more intensive processing and simulation to scale independently from the web code, and ensures the web frontend always remains responsive.

In an embodiment, the present invention may make use of readily available computer pro- grams/algorithms, databases and associated authentication protocols. By incorporating data libraries of common substances, proteins, equipment and other process ancillaries, the platform of the present invention employs a system that simplifies the user experience while still ensuring that all of the detailed characteristics of a bioprocess are captured.

In an embodiment, the invention uses those same data sources to reduce the data required of new users, allowing them to assimilate the system/software and to start using the platform rapidly.

Modular unit operation architecture

In an embodiment, each unit operation follows a common pattern, allowing them to be easily combined together, and also offering straight-forward extensibility as the number of operations is expanded and modelled to support more process options. It also allows the system to be easily upgraded and/or allows the improvement of a particular model without impacting the wider platform.

Process Calculation Process calculations draw on user-provided product and process information, calling on unit operation models as well as the library of substances and proteins held internally as needed to calculate the performance of a particular process. Parameters and settings for each operation can be specified by a user, or can be calculated automatically by the system. The system is designed to be extensible from the outset, incorporating further economic factors or nuances of process design with minimal extra development.

Techno-economic analysis (TEA) functionality is brought in for larger scale processes, enabling calculation of OpEx, CapEx and financial information, in addition to equipment sizing. Where experimental data is available for a given product and process, the DSP engine can be run utilizing a combination of the base mechanistic models augmented with machine learning models in certain key areas to augment modelling fidelity.

In an embodiment, the system incorporates economic analysis capabilities through its TEA module. The system may evaluate one or more economic aspects of each identified optimal process, including detailed calculations of operating expenditure (OpEx), capital expenditure (CapEx), and key financial metrics. The OpEx calculations may account for raw materials, utilities, labor, maintenance, and consumables, while CapEx calculations may include equipment costs, installation costs, and facility requirements. The system may be configured to generate detailed financial metrics including at least one of return on investment (ROI), net present value (NPV), and internal rate of return (IRR), allowing users to make informed decisions about process implementation based on both technical and economic considerations.

In one embodiment, the system can provide an interactive economic parameter input interface to enable users to customize key economic variables that affect process economics. Using the input interface, the Users may be able to input and modify parameters including at least one of: raw material costs, utility rates, labor rates, and equipment costs specific to their intended production location or region. The system may maintain default values for these parameters based on industry standards. Users may be able to override these with their own values to reflect their specific economic context. This customization ensures that the economic analysis accurately reflects the real-world conditions under which the process will operate, enabling more accurate financial projections and better-informed decision-making.

In an embodiment, the system incorporates a dedicated TEA page, including a summary of the economics of the process, as well as detailed breakdowns of operating expenditure (OpEx), capital expenditure (CapEx), and key financial metrics. For OpEx, the breakdown may include fixed and variable Cost of Goods Sold (COGS), annual production cost and fixed and variable operating expenditure, while the CapEx breakdown may include cost of equipment by type, instrumentation, land costs, design and engineering costs, and working capital. The TEA page may also include charts showcasing the factors comprising total OpEx and CapEx in a visual format, and may additionally include charts detailing the cashflow of the process over a project's lifetime.

In an embodiment, the platform’s process results view allows the user to view the process in a familiar layout evocative of a process flow diagram, with key summary information such as unit cost, process time and product yield and purity available at a glance. This view also shows the user to view product recovery at each stage of the process, as well as high level mass flow, allowing rapid understanding and easy identification of problematic areas or areas that need further review.

This process view also allows users to access the overall mass flow for the process, showing what has been inserted into the process and what has been removed at each step. Users are able to configure maximum permitted levels of particular substances in the final output, and there is also a Ul element to highlight these along with whether the current process meets those requirements.

If a user desires more detail on a particular unit operation, the user can open up a detailed view which shows key information on the parameters used for that step, along with more information on process time, energy use and more, as well as a dedicated mass balance for that operation.

In an embodiment, the system can perform sensitivity analysis on one or both of the economic and process parameters to determine how variations in different factors affect the overall process economics. The sensitivity analysis may evaluate the impact of changes in key variables, including at least one of raw material costs, utility prices, labor rates, product yield, and equipment efficiency on financial metrics including unit cost, ROI, and payback period. The system may generate sensitivity charts and tables that visualize these relationships, helping users identify which parameters have the greatest impact on process economics and where efforts to optimize or control costs would be most beneficial. This analysis also helps users understand the robustness of their process economics against potential market fluctuations or process variations.

In an embodiment, the system can employ scale-appropriate TEA modules that automatically adjust the economic analysis methodology based on the process scale being evaluated. For example, for laboratory-scale processes (typically <10L), the TEA module may focus on consumable costs and equipment utilization. For pilot-scale processes (typically 10-1000L), the module may incorporate additional factors such as labor requirements and utility consumption. For commercial-scale processes (>1000L), the TEA module may implement comprehensive analysis including at least one of detailed CapEx estimation, facility requirements, maintenance costs, and scale-dependent effects on unit operations. This scale-appropriate approach ensures that economic evaluations accurately reflect the cost structures and economic considerations relevant to each scale of operation, enabling more accurate financial projections as users plan scale-up activities.

In an embodiment, the system incorporates sustainability analysis capabilities through its LCA module. The system may evaluate one or more sustainability aspects of each identified optimal process, including detailed calculations of Life Cycle Analysis (LCA), as well as carbon accounting metrics, such as Scope 1 (direct) and Scope 2 (indirect) emissions. The calculations may account for raw material choices, transportation distances, energy use, product yield, and equipment efficiency. The system may be configured to generate detailed sustainability metrics including at least one of Global Warming Potential, water use and energy use, allowing users to make informed decisions about process implementation based on both technical and environmental considerations.

In one embodiment, the system can provide an interactive sustainability parameter input interface to enable users to customize key energy consumption variables that affect process sustainability. Using the input interface, the Users may be able to input and modify parameters including at least one of: total energy generated at facility, total purchased energy and type of fuel used and equipment dynamics specific to their intended production location or region. The system may maintain default values for these parameters based on industry standards. Users may be able to override these with their own values to reflect their specific environmental context. This customization ensures that the sustainability analysis accurately reflects the real-world conditions under which the process will operate, enabling more accurate sustainability projections and better-informed decision-making.

In an embodiment, the system incorporates a dedicated Sustainability page, including a summary of the sustainability of the process, as well as detailed breakdowns of energy, water and waste usage. This may include detailed breakdowns of Life Cycle Analysis (LCA), as well as carbon accounting metrics, such as Scope 1 (direct) and Scope 2 (indirect) emissions. The LCA may adhere to the IS014040 and ISO14044 standards, and include impact categories such as Global Warming Potential and water use, and the carbon accounting metrics may adhere to the GHG Protocol standard. The TEA page may also include charts showcasing the sustainability impacts in a visual format, including a Sankey diagram portraying the contribution of each process/raw material to the total sustainability impact of the system, and visualisations of different scenarios such as reduced transportation distance or increased renewable energy usage, highlighting their effect on the total sustainability impact.

In an embodiment, the sustainability module may provide suggestions and alternatives to reduce the greenhouse gas emissions and sustainability impact in the form of scenario analysis and written suggestions. It may also perform a comparative analysis where products developed and measured on the platform will be compared to similar product benchmarks gathered from industry.

In an embodiment, the system can perform sensitivity analysis on environmental and sustainability factors, in addition to process parameters, and optionally also economic parameters. This will highlight how variations in these factors affect both process economics as well as the sustainability of the process. The sensitivity analysis may evaluate the impact of changes in key variables, including at least one of raw material choices, transportation distances, energy use, product yield, and equipment efficiency on sustainability metrics including water use, Global Warming Potential, and greenhouse gas emissions. The system may generate charts and tables to visualise these relationships, helping users identify which parameters have the greatest impact on process sustainability and where efforts to optimize or control environmental impact would be most beneficial. This analysis also helps users understand the robustness of their process sustainability against potential market fluctuations or process variations.

In addition, the platform is able to calculate the impact of different media sources on a bioprocess, including any processing required to convert the media source into a form suitable for a fermentation process. This could include, but is not limited to, converting waste streams or side streams from other industries such as brewers’ spent grain into suitable feedstocks for fermentation processes. Alongside this additional input processing, the platform is able to calculate and optimize not only for a single product, but for multiple products, for example calculating and optimizing the output of a precision fermented protein along with another product made from the cell biomass.

Finally, the platform is able to calculate and optimize not only a linear process, comprising one or more unit operations arranged in a linear fashion, but also branching processes, wherein unit operations can produce multiple output streams, each of which may result in their own sub-processes comprising one or more unit operations. This is particularly crucial in commodity markets such as food, where volumes are high, unit costs are low, and efficiency of purification and downstream processing is key, and so users may wish to additionally process waste streams to maximize product retention.

Process Optimization

The platform of the present invention offers the ability to either optimize an existing process, by adjusting process parameters to achieve better results, or to create an optimal process from scratch. This optimization routine sits on top of the main DSP calculation engine, and uses a multi-objective optimization algorithm to try a plurality of possible processes to find an optimal one for the user’s particular product and/or for other process parameters.

Currently, the user selects which unit operations make up a downstream process, and then the system searches the multi-dimensional space covered by the possible ranges for each and every parameter within that process, running combinations to determine the process results, such as cost, time, yield, and product quality. It then identifies an optimal process and returns this to the user.

In an embodiment, the system will also be able to select the unit operations that make up the process, deciding how many to include and also deciding on the type to be used. Users can fix one or more parameters if the user so chooses, and by fixing those values, the user can optimize other parameters.

In an embodiment, the optimizer will explore parameter ranges for all other parameters as in the previous case, but will leave the fixed parameters unchanged. This also allows users to limit the scope of their experiments, thereby only optimizing a subset of a process. This also allows one to simulate a particular piece of equipment with known parameters, as well as perform many other functions.

In an embodiment, users can determine which criteria the optimization uses to assess an optimal process, as well as how the optimization ranks those criteria.

Initial results from pilot tests with a real-world user and process saw a significant improvement over a baseline process, with process time reduced by 37.4%, product recovery increased by 8.6x, and product concentration increased by 2. lx. These changes combined to significantly improve the economics of the process, resulting in a 55% cost reduction. This resulted in the process moving from being economically unviable to profitable.

In an embodiment, the optimization produces an optimal process wherein the process time is reduced by at least 30% due to selection of more appropriate parameter settings which rebalances unit operations to preserve process outcomes whilst reducing time. In an embodiment, the optimization produces an optimal process wherein the product recovery is increased by at least a factor of 5 due to reducing product loss at each step.

In an embodiment, the optimization produces an optimal process wherein the product concentration is increased by at least 2-fold due to adjustment of key control parameters to increase concentration whilst also maintaining or improving other process dynamics.

In an embodiment, the optimisation produces an optimal process wherein the total process cost is reduced by at least 45% due to reductions in time, labour, consumables and equipment costs.

Integration of experimental data

In an embodiment, the platform supports the integration of experimental data, providing more ongoing value to customers. Customers are able to upload their own raw experimental data, which is then used to augment the existing mechanistic models and capture key nuances of the customer’s experimental process and deliver more accurate results.

This combines with the existing mechanistic models in several ways. These include:

- Key constants and factors within the mechanistic models are overwritten or adapted using learnings derived from the experimental data to provide more accurate, personalized results.

- In certain areas, the experimental data is used to train ML (machine learning) models, which are used to supplement or replace modules within the mechanistic model. This allows modelling of functionality and nuances that are difficult or impossible to model mechanistically, while retaining the explainability of the wider mechanistic approach. In an embodiment, by employing an iterative approach, the platform is able to hone parameters over time to make the processes better suit the user’s needs, and give better processes.

The specific features that are augmented in this way vary from unit operation to unit operation, and depend on the specific data points that a customer has available, as well as the volume of data they have collected. This allows this approach to be tuned to the needs of the customer, as well as allowing the models to learn as a customer performs additional experimentation, while at the same time, still being able to provide value to those customers that have yet to collect meaningful data.

Experimental data may be added to the platform manually or be collected automatically via integration with equipment, allowing experiments to be logged and analyzed on the platform, as well as for the resulting data to be automatically used to enhance the platform’s models, improving their fidelity.

Experimental data may also be used to enhance prediction not only of process(es) at the scale at which the experiments were performed, but also at larger and/or smaller scales through the use of scale-up and/or scale-down models.

Initial results from pilot tests with a real-world user and process saw a significant improvement in the accuracy of process predictions once experimental data was uploaded to the platform, with process time predictions improved by 9.2x, and process recovery predictions improved by 1.2x.

In an embodiment, the platform is able to model and predict the performance of processes wherein the accuracy of predictions of process time are improved by at least a factor of 7 once experimental data has been uploaded to the platform and integrated with the models, due to improvements in the modelling of key process dynamics extracted from the data.

In an embodiment, the platform is able to model and predict the performance of processes wherein the accuracy of predictions of process recovery are improved by at least a factor of 7 once experimental data has been uploaded to the platform and integrated with the models, due to improvements in the modelling of key process dynamics extracted from the data.

User experience

In an embodiment, UX (user experience) is an important element of the system. This is a complex domain, and with many models, factors and competing dynamics it would be easy to overwhelm users, who particularly in early-stage startups are less familiar with bioprocess engineering. Thus, the present invention aims from the outset to abstract away as much detail as possible to simplify both the onboarding experience and ongoing user interactions, while at the same time ensuring that power users have the flexibility the users require. In an embodiment, the platform is sufficiently flexible so that users with more experience are able to see more parameters and perform their own manipulation of the platform to suit their needs.

When developing a process, the present invention provides process suggestions and key information with the minimum of information about a customer’s process. As the user performs experiments and analysis, the user is able to enter that new data and improve the certainty of the user’s results as well as unlock new insights. For later stage users who may have a more detailed understanding of their setup, the user is able to progress directly to the more detailed behavior and understanding. This approach not only allows the user to use the tool regardless of their prior knowledge, it also lowers the friction within the onboarding process.

In an embodiment, this will be supported by an intuitive interface with extensive self-serve help functionality, video guides and FAQs.

In an embodiment, this ensures that the system and support requirements are minimized without compromising customer satisfaction, allowing the system to be scaled rapidly and cost-effectively.

Fig. 1 depicts the fermentation process and downstream processing steps after fermentation has occurred. As can be seen from the figure, the fermentation process is shown on the left and shows the inputs and the outputs into/from the stirred tank fermenter, the inputs comprising inoculant, media, and gases, and the outputs which include waste gases from the fermentation process. The downstream processing steps are illustrated by moving the fermented material to a holding tank, which then may be subsequently centrifuged, moved to another holding tank and then further processed by processes such as purification procedures such as membrane filtration or other procedures known to those of skill in the art.

In more detail, Fig. 1 illustrates a schematic representation of a complete bioprocess, comprising both fermentation and downstream processing (DSP) stages. The diagram is divided into two main sections separated by a dotted line: the fermentation section on the left and the downstream processing section on the right.

In the fermentation section, three input streams are shown entering a stirred tank fermenter: inoculant, media, and gases. The stirred tank fermenter is depicted as a vessel with an internal stirring mechanism and a conical bottom. A waste stream exits the bottom of the fermenter, representing waste gases and other byproducts of the fermentation process.

The downstream processing section shows a series of unit operations connected in sequence. The fermentation output first enters a holding tank, followed by a disc stack centrifuge for liquid-solid separation. The centrifuge produces a solids waste stream at its bottom. The liquid phase continues to another holding tank before entering a membrane TFF (Tangential Flow Filtration) unit, which receives a buffer input stream. The membrane TFF unit performs further separation, producing a liquids output stream.

The flow direction is indicated by arrows connecting the various units, showing the sequential nature of the process. This arrangement demonstrates a typical bioprocess flow, starting from raw materials and proceeding through separation and purification steps to obtain the desired product.

The diagram effectively illustrates the integration between fermentation and downstream processing stages, highlighting the complexity and multiple steps involved in a complete bioprocess operation.

Fig. 2 depicts a block diagram schematic showing the architecture that a user encounters when accessing the platform. The architecture comprises user data, which may be related to products processes and experimental data. Any of a plurality of back-end platforms may be used such as various modules and various data-containing libraries. These include but are not limited to mechanistic modules, machine learning models, and TEA (techno- economic analysis) modules that can calculate various financial considerations and/or track the production and distribution of goods, substance libraries, protein or biomolecule libraries, or other similar modules and libraries. The platform also may contain a web interface and authentication software associated with the platform that may restrict or give access to a given user.

In more detail, Fig. 2 illustrates a block diagram schematic showing the system architecture deployed on a cloud platform. The diagram is organized into several key components that demonstrate the flow of information and user interaction within the system.

The leftmost section shows the Database component, represented by four storage units containing User Data, Products, Processes, and Experimental Data. These databases are connected bidirectionally to the Platform Back-end section.

The Platform Back-end section, positioned in the center-left, contains six distinct modules: Mechanistic models, ML Models (Machine Learning Models), TEA module (Techno- Economic Analysis), LCA (LifeCycle Assessment) module, Substance Library, and Protein Library. This section interfaces with both the Database and Web front-end components through bidirectional connections.

The Web front-end section is shown on the right side of the cloud platform, featuring the UI/UX (User Interface/User Experience) component. This connects to a User Authentication module, which serves as the gateway between the system and external users. The User Authentication module interfaces with the User, represented by a stick figure symbol on the far right of the diagram.

This architecture demonstrates the integrated nature of the platform, showing how user interactions flow through authentication, into the front-end interface, through to the pro- cessing modules and databases, enabling the platform's bioprocess optimization capabilities.

Fig. 3 depicts a block diagram demonstrating the modular aspects of the operation architecture. This figure shows the inputs and outputs for the mechanistic model for unit operation. The inputs include the input stream, the machine settings and model constants and factors. The outputs include consumables, power, labor, various outer outputs such as product streams and waste streams, and equipment sizing. The TEA module and machine learning models may also be accessed.

In more detail, Fig. 3 illustrates a block diagram demonstrating the modular aspects of the unit operation architecture, centered around the Mechanistic Model for Unit Operation. The diagram shows both inputs and outputs, as well as supporting analytical modules.

The left side of the diagram depicts three primary inputs flowing into the mechanistic model: Input Stream, Machine settings, and Model constants and factors. A Side Stream(s) input is shown entering from the top of the model.

The right side of the diagram shows multiple outputs branching from the mechanistic model: Consumables, Power, Labour, and Equipment sizing. The Output section is further detailed to include both Product streams and Waste streams.

The bottom of the diagram shows two supporting modules that feed into the main mechanistic model: a Techno-economic analysis Module (represented by a rectangular box) and ML Model(s) (represented by a cylindrical database symbol).

This diagram shows how various inputs are processed through the mechanistic model for each unit operation in a modular fashion, supported by economic and machine learning capabilities.

Fig. 4 depicts the inputs and outputs into and from the DSP engine of the system architecture. The inputs show the customer data, machine learning models, the TEA module, the protein library, the substance library and the unit operation library all of which undergo processing to give the outputs that are shown in figure 4. Note that the customer data can be input and the experimental data can generate an iterative process with the machine learning model that is able to optimize parameters using the DSP engine.

In more detail, Fig. 4 depicts the inputs and outputs into and from the DSP (Downstream Processing) engine of the system architecture. The diagram shows the complete flow of information and the interaction between various components of the system. The left side shows Customer Data, represented as a cylindrical database, which provides four key inputs to the DSP Engine: Product requirements, Process operations, Operation configuration, and Experimental Data. The Experimental Data additionally feeds into the ML Model(s), shown as a stacked cylindrical symbol below the DSP Engine.

The top of the diagram shows four library modules feeding into the DSP Engine:

- A TEA Module listing CapEx, OpEx, Equipment sizing, Cleaning (CIP, SIP), Labour, and Financials

- A Protein Library containing Physical properties, interactions, Sequences, Folding/bind- ing, and Key vulnerabilities

- A Substance Library showing Physical properties and interactions

- A Unit Operation Library containing multiple Unit Operation Models, depicted as stacked rectangles

The right side of the diagram shows three categories of outputs from the DSP Engine:

- Output parameters including Product yield, Product purity, and Waste streams

- Cost factors including CapEx and OpEx

- Process information showing Time taken and break-downs by operation

This diagram shows how the DSP Engine integrates various data sources and libraries to process inputs and generate detailed operational outputs for an entire end-to-end bioprocess.

Fig. 5 depicts the inputs and outputs from the DSP engine with an optimization module incorporated into the system. Figure 5 shows another embodiment of the invention showing how the optimization module uses the DSP engine to generate a plurality of potential processes, wherein these potential processes are fed back into the optimization module that may send data back to the DSP engine to produce new potential processes that are once again fed back into the optimization module, which eventually outputs a unique (or several unique) optimized process(es).

In more detail, Fig. 5 depicts the inputs and outputs from the DSP engine with an optimization module incorporated into the system. The diagram illustrates the iterative optimization process used to identify optimal bioprocess parameters.

The flow begins on the left with Customer Data, shown as a cylindrical database, which provides two key inputs to the Optimization Module: Product requirements and Process operations. The Optimization Module interfaces with the DSP Engine in a cyclic manner, shown by directional arrows.

The bottom portion of the diagram shows a distinctive feature where the DSP Engine generates multiple Potential Processes. These potential processes feed back into the Optimization Module and show how multiple optimization iterations are evaluated.

The right side of the diagram shows the final output as an Optimal Process. This represents the culmination of the iterative optimization process, where the most suitable process parameters have been identified based on the customer requirements and operational constraints.

This diagram effectively demonstrates the iterative nature of the optimization process, showing how the system evaluates multiple potential processes to arrive at an optimal solution for the bioprocess configuration.

Fig. 6 depicts a typical user interface through which a user can view a process. This includes the input mixture to the bioprocess, including the mass of each and every component molecule or substance within that mixture. The flow of mixture through the different unit operations is then denoted with arrows, and any waste material is clearly shown. Clear icons indicate at a glance what operations are where, and the final output mixture is visible, along with the masses of each molecule and substance. The interface also shows various key pieces of information, including but not limited to the product yield, product purity, unit cost and overall process time.

Computer Hardware and Software

The present invention includes a computer system, a method, and/or a computing device. In a basic configuration of a computing device, the computing device may include one or more processors and a system memory. In some embodiments, the computing device may include one or more processors and a system memory. A memory bus may be used for communicating between the one or more processors and the system memory.

Depending on the desired configuration, the processor may be of any type, including, but not limited to, a microprocessor (pP), a microcontroller (pC), and a digital signal processor (DSP), or any combination thereof. Further, the one or more processors may include one more levels of caching, such as a level cache memory, a processor core, and registers, among other examples. The processor core may include an arithmetic logic unit (ALU), a floating-point unit (FPU), and/or a digital signal processing core (DSP Core), or any combination thereof. A memory controller may be used with the processor, or, in some implementations, the memory controller may be an internal part of the memory controller.

Depending on the desired configuration, the system memory may be of any type, including, but not limited to, volatile memory (such as RAM), and/or non-volatile memory (such as ROM, flash memory, etc.), or any combination thereof. The system memory may include an operating system, one or more engines, and/or program data. In some embodiments, the engine may be an application, a software program, a service, or a software platform. The system memory may also include a storage engine that may store any information disclosed herein.

Moreover, the computing device may have additional features or functionality, and additional interfaces to facilitate communications between the basic configuration and any desired devices and interfaces. For example, a bus/interface controller may be used to facilitate communications between the basic configuration and data storage devices via a storage interface bus. Any data storage devices may be one or more removable storage devices, one or more non-removable storage devices, or a combination thereof. Examples of the one or more removable storage devices and the one or more non-removable storage devices include magnetic disk devices (such as flexible disk drives and hard-disk drives (HDD)), optical disk drives (such as compact disk (CD) drives or digital versatile disk (DVD) drives), solid state drives (SSD), and tape drives, among others.

In some embodiments, an interface bus may facilitate communication from or between various interface devices (e.g., one or more output devices, one or more peripheral interfaces, and one or more communication devices) to the basic configuration via the bus/interface controller. Some of the one or more output devices include a graphics processing unit and an audio processing unit, which may be configured to communicate to various external devices, such as displays or speakers, via one or more A/V ports.

The one or more peripheral interfaces may include a serial interface controller or a parallel interface controller, which may be configured to communicate with external devices, such as input devices (e.g., a keyboard, a mouse, a pen, a voice input device, or a touch input device, etc.) or other peripheral devices (e.g., a printer or a scanner, etc.) via one or more I/O ports.

Further, the one or more communication devices may include a network controller, which may be arranged to facilitate communication with one or more other computing devices over a network communication link via one or more communication ports. The one or more other computing devices may include servers, databases, mobile devices, and other comparable devices.

In an embodiment, a network communication link may occur via communication media. The communication media are typically embodied by the computer-readable instructions, data structures, program modules, or other data in a modulated data signal, such as a carrier wave or other transport mechanism, and include any information delivery media. A “modulated data signal” is a signal that has one or more of its characteristics set or changed in such a manner as to encode information in the signal. By way of example, and not limitation, the communication media may include wired media (such as a wired network or direct-wired connection) and wireless media (such as acoustic, radio frequency (RF), microwave, infrared (IR), and other wireless media). The term “computer-readable media,” as used herein, includes both storage media and communication media.

It should be appreciated that the system memory, the one or more removable storage devices, and the one or more non-removable storage devices are examples of computer- readable storage media. The computer-readable storage media in an embodiment, is a tangible device that can retain and store instructions (e.g., program code) for use by an instruction execution device (e.g., the computing device). As such, computer storage media is part of the computing device.

The computer readable storage media/medium can be a tangible device that can retain and store instructions for use by an instruction execution device. The computer readable storage media/medium may be, for example, but is not limited to, an electronic storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, and/or a semiconductor storage device, or any suitable combination thereof. A non-exhaustive list of more specific examples of the computer readable storage media/medium includes the following: a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), a static random access memory (SRAM), a portable compact disc read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, and/or a mechanically encoded device (such as punch-cards or raised structures in a groove having instructions recorded thereon), and any suitable combination of the foregoing. A computer readable storage medium, as used herein, is not to be construed as being transitory signals per se, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through a waveguide or other transmission media (e.g., light pulses passing through a fiber-optic cable), or electrical signals transmitted through a wire.

The computer may be used to control hardware that is not normally a part of the computing system. The computer using a computer program may control other devices such as counters, pickers, conveyors, robotic arms, and other industrial devices. The computers may also be used in one or more of data collection, as a control card for equipment, in industrial imaging and other applications requiring high-speed data, as a controller in machine vision applications to automate quality control systems, in automatic inspection, measurement, verification, and/or flaw detection, to operate direct equipment, for example, robots, in video surveillance and analytics requiring HD image capturing, in facial recognition, in real-time detection, and in post analytics in applications that require removable drive bays for swappable hard drives for easy data backup, and/or as embedded computers.

The computer may also employ artificial intelligence (Al) or heuristic technologies. In an embodiment, the use of high-speed computers allows large amounts of data to be processed and with intelligent algorithms, the software can “learn” from the data based upon patterns in causative and/or correlated data.

In an embodiment, the present invention relates to systems and methods/processes. In an embodiment, the present invention relates to a method of optimizing a fermentation process and/or a downstream process that is downstream of the fermentation process in a system, said method comprising: having a user select one or more unit operations that make up the fermentation process and/or the downstream process, wherein the system searches a multi-dimensional space covered by possible ranges for one or more parameters within the fermentation process and/or the downstream process, wherein the system calculates combinations for each and every parameter in the one or more parameters to determine the fermentation process and/or the downstream process results, wherein said system identifies an optimal process and outputs the optimal process to the user, wherein the system comprises a computer and requisite hardware and software to perform the method. In a variation, the method further comprises fixing at least one parameter, or at least two parameters, or at least three parameters. In a variation, more than one parameter is fixed. In a variation, the method further comprises simulating a piece of equipment using each and every parameter. In a variation, the method further comprises using machine learning software. In a variation, the machine learning software uses an iterative process wherein data is continually refined. In a variation, the user is able to manipulate the machine learning software. In a variation, the user may input data into the system that allows an iterative process to be used to generate the optimal outcome.

In an embodiment, the system further comprises output that comprises one or more members selected from the group consisting of a process flow diagram, a summary of unit cost, process time, product yield, product purity, product recovery at each stage of the process, and a high-level mass flow. In a variation, the system further comprises software to evaluate the output thereby providing a user with a rapid understanding and easy identification of problematic areas or areas that need further review. In a variation, the method optimizes both the fermentation process and the downstream process.

In an embodiment, the present invention relates to a system that comprises hardware, software, and at least one processor for manipulating and/or processing the software, the system configured to optimize a fermentation process and/or a downstream process that is downstream of the fermentation process, wherein the system searches a multidimensional space covered by possible ranges for one or more parameters within the fermentation process and/or the downstream process, wherein the system calculates combinations for each and every parameter in the one or more parameters to determine the fermentation process and/or the downstream process results, wherein said system identifies an optimal process and outputs the optimal process to a user. In a variation, the system allows the user to fix one or more parameters. In a variation, the system allows the user to fix more than one parameter. In a variation, the system utilizes machine learning software. In a variation, the system allows the user to input data. In a variation, the system allows the user to input data into the machine learning software. In a variation, the system further outputs data that comprises one or more members selected from the group consisting of a process flow diagram , a summary of unit cost, process time, product yield, product purity, product recovery at each stage of the process, and a high-level mass flow. In a variation, the system only optimizes the fermentation process. In a variation, the system only optimizes the downstream process. In a variation, the system optimizes both the fermentation process and the downstream process.

It should be understood and it is contemplated and within the scope of the present invention that any feature that is enumerated above can be combined with any other feature that is enumerated above as long as those features are not incompatible. Whenever ranges are mentioned, any real number that fits within the range of that range is contemplated as an endpoint to generate subranges. In any event, the invention is defined by the below claims.

The terminology used herein is for the purpose of describing particular aspects only and is not intended to be limiting of the disclosure. As used herein, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. As used herein, the term "and/or" includes any and all combina- tions of one or more of the associated listed items. It will be further understood that the terms "comprises," "comprising," "includes," and/or "including" when used herein specify the presence of stated features, integers, actions, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, actions, steps, operations, elements, components, and/or groups thereof.

It will be understood that, although the terms first, second, etc., may be used herein to describe various elements, these elements should not be limited by these terms. These terms are only used to distinguish one element from another. For example, a first element could be termed a second element, and, similarly, a second element could be termed a first element without departing from the scope of the present disclosure.

Relative terms such as "below" or "above" or "upper" or "lower" or "horizontal" or "vertical" may be used herein to describe a relationship of one element to another element as illustrated in the Figures. It will be understood that these terms and those discussed above are intended to encompass different orientations of the device in addition to the orientation depicted in the Figures. It will be understood that when an element is referred to as being "connected" or "coupled" to another element, it can be directly connected or coupled to the other element, or intervening elements may be present. In contrast, when an element is referred to as being "directly connected" or "directly coupled" to another element, there are no intervening elements present.

Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure belongs. It will be further understood that terms used herein should be interpreted as having a meaning consistent with their meaning in the context of this specification and the relevant art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.

It is to be understood that the present disclosure is not limited to the aspects described above and illustrated in the drawings; rather, the skilled person will recognize that many changes and modifications may be made within the scope of the present disclosure and appended claims. In the drawings and specification, there have been disclosed aspects for purposes of illustration only and not for purposes of limitation, the scope of the disclosure being set forth in the following claims.

Claims

Claims

1. A system that comprises hardware, software, and at least one processor for manipulating and/or processing the software, the system configured to optimize a fermentation process and/or a downstream process that is downstream of the fermentation process, wherein the system searches a multi-dimensional space covered by possible ranges for one or more parameters within the fermentation process and/or the downstream process, wherein the system calculates combinations for each and every parameter in the one or more parameters to determine the fermentation process and/or the downstream process results, wherein said system identifies an optimal process and outputs the optimal process to a user.

2. The system of claim 1, wherein the system allows the user to fix one or more parameters.

3. The system of claim 2, wherein the system allows the user to fix more than one parameter.

4. The system of any preceding claim, wherein the system utilizes machine learning software.

5. The system of any preceding claim, wherein the system allows the user to input data.

6. The system of claim 5, wherein the system allows the user to input data into the machine learning software.

7. The system of claim 6, wherein the system further outputs data that comprises one or more members selected from the group consisting of a process flow diagram, a summary of unit cost, process time, product yield, product purity, product recovery at each stage of the process, and a high-level mass flow.

8. The system of any preceding claim, wherein the system only optimizes the downstream process.

9. The system of any preceding claim, wherein the system optimizes both the fermentation process and the downstream process.

10. The system of any preceding claim, wherein said system identifies an optimal process and evaluates at least one economic aspect of the identified optimal process, including at least one of operating expenditure (OpEx), capital expenditure (CapEx), and financial metrics, and outputs the optimal process and the economic aspect of the identified optimal process to a user.

11. The system of claim 10, wherein the economic aspect includes a detailed breakdown of OpEx and CapEx factors.

12. The system of any of claims 10 to 11, wherein the economic aspect further includes a calculation of a payback period.

13. The system of any of claims 10 to 12, wherein the system further allows a user to input economic parameters, such as raw material costs and labor rates, which are used in the evaluation of the economic aspect.

14. The system of any of claims 10 to 13, wherein the system allows a user to view a quick overview of OpEx and CapEx figures from a process view.

15. The system of any of claims 10 to 14, wherein the system provides a dedicated Techno-Economic Analysis (TEA) page providing a more detailed breakdown of the economic aspect.

16. The system of any of claims 10 to 15, wherein the economic aspect output further includes a calculation of sensitivity analysis of the economic output to various economic and/or process parameters.

17. The system of any of claims 10 to 16, wherein the system uses a scale-appropriate TEA module depending on process scale for the calculation of the financial aspects.

18. The system of any of claims 10 to 17, wherein the economic aspect output also includes the cost per unit of product.

19. The system of any preceding claim , wherein said system identifies an optimal process and evaluates at least one sustainability aspect of the identified optimal process, including at least one of total energy use, total waste generated, Scope 1 (direct) emissions, and Scope 2 (indirect) emissions, and outputs the optimal process and the sustainability aspect of the identified optimal process to a user.

20. The system of claim 19, wherein the system allows the user to input energy consumption parameters, such as total energy generated at facility, total purchased energy and type of fuel used, which are used in the evaluation of the sustainability aspect.

21. The system of claims 19 to 20, wherein the system allows a user to view a quick overview of the total measured environmental impact categories and carbon accounting metrics from a process view.

22. The system of claims 19 to 21, wherein the system provides at least one of a dedicated Lifecycle Assessment (LCA) page and a carbon accounting results page, providing a more detailed breakdown of the sustainability aspect.

23. The system of claims 19 to 22, wherein the sustainability aspect output further includes a calculation of sensitivity analysis of the sustainability output to various sustainability, economic and/or process parameters.

24. The system of claims 19 to 23, wherein the sustainability aspect output further includes a contribution analysis portraying the contribution of each process/raw material to the total sustainability impact of the system.

25. The system of claims 19 to 24, wherein the sustainability aspect output further includes a scenario analysis where different scenarios such as more renewable energy, transport distance reduction and their effect on total sustainability impact are shown.

26. The system of claims 19 to 25, wherein the sustainability aspect performs a life cycle analysis adherent to the IS014040 and ISO14044 standards.

27. The system of claims 19 to 26, wherein the sustainability aspect output provides a comparative analysis where products developed and measured on the platform will be compared to similar product benchmarks gathered from industry.

28. A method of optimizing a fermentation process and/or a downstream process that is downstream of the fermentation process in a system, said method comprising: receiving a user selection for one or more unit operations that make up the fermentation process and/or the downstream process, searching a multi-dimensional space covered by possible ranges for one or more parameters within the fermentation process and/or the downstream process, calculating combinations for each and every parameter in the one or more parameters to determine the fermentation process and/or the downstream process results, and identifying an optimal process and outputting the optimal process to the user, wherein the system comprises a computer and requisite hardware and software to perform the method.

29. The method of claim 28, further comprising fixing at least one parameter.

30. The method of claim 29, wherein more than one parameter is fixed.

31. The method of any of claims 28 to 30, further comprising simulating a piece of equipment using each and every parameter.

32. The method of any of claims 28 to 31, further comprising using machine learning software.

33. The method of claim 32, wherein the machine learning software uses an iterative process wherein data is continually refined.

34. The method of any of claims 32 to 33, further comprising having the user manipulate the machine learning software.

35. The method of any of claims 28 to 34, wherein the user enters data into the system.

36. The method of any of claims 28 to 35, wherein the system further comprises output that comprises one or more members selected from the group consisting of a process flow diagram, a summary of unit cost, process time, product yield, product purity, product recovery at each stage of the process, and a high-level mass flow.

37. The method of claim 36, wherein the system further comprises software to evaluate the output thereby providing a user with a rapid understanding and easy identification of problematic areas or areas that need further review.

38. The method of any of claims 28 to 37, wherein the method optimizes both the fermentation process and the downstream process.

39. The method of any of claims 28 to 38, wherein the method utilizes a cloud-based system .

40. The method of any of claims 28 to 39, wherein, wherein the step of identifying an optimal process and outputting the optimal process to the user said further comprises identifying an optimal process and evaluating at least one economic aspect of the identified optimal process, including at least one of operating expenditure (OpEx), capital expenditure (CapEx), and financial metrics, and outputting the optimal process and the economic aspect of the identified optimal process to a user.

41. The method of claim 40, wherein the economic aspect includes a detailed breakdown of OpEx and CapEx factors.

42. The method of any of claims 40 to 41, wherein the economic aspect further includes a calculation of a payback period.

43. The method of any of claims 40 to 42, wherein the method further comprises allowing a user to input economic parameters, such as raw material costs and labor rates, which are used in the evaluation of the financial aspect.

44. The method of any of claims 40 to 43, wherein the method allows a user to view a quick overview of OpEx and CapEx figures from a process view.

45. The method of any of claims 40 to 44, wherein the method provides a dedicated Techno-Economic Analysis (TEA) page providing a more detailed breakdown of the economic aspect.

46. The method of any of claims 40 to 45, wherein the economic aspect output further includes a calculation of sensitivity analysis of the economic output to various economic and/or process parameters.

47. The method of any of claims 40 to 46, wherein the method uses a scale-appropriate TEA module depending on process scale for the calculation of the economic aspects.

48. The method of any of claims 40 to 47, wherein the economic aspect output also includes the cost per unit of product.

49. The method of any of claims 28 to 48, wherein the step of identifying an optimal process and outputting the optimal process to the user further comprises identifying an optimal process and evaluating at least one sustainability aspect of the identified optimal process, including at least one of total energy use, total waste generated, Scope 1 (direct) emissions, and Scope 2 (indirect) emissions, and outputting the optimal process and the sustainability aspect of the identified optimal process to a user.

50. The method of claim 49, wherein the method allows the user to input energy consumption parameters, such as total energy generated at facility, total purchased energy and type of fuel used, which are used in the evaluation of the sustainability aspect.

51. The method of claims 49 to 50, wherein the method allows a user to view a quick overview of the total measured environmental impact categories and carbon accounting metrics from a process view.

52. The method of claims 49 to 51, wherein the method provides at least one of a dedicated Lifecycle Assessment (LCA) page and a carbon accounting results page, providing a more detailed breakdown of the sustainability aspect.

53. The method of claims 49 to 52, wherein the sustainability aspect output further includes a calculation of sensitivity analysis of the sustainability output to various sustainability, economic and/or process parameters.

54. The method of claims 49 to 53, wherein the sustainability aspect output further includes a contribution analysis portraying the contribution of each process/raw material to the total sustainability impact of the system.

55. The method of claims 49 to 54, wherein the sustainability aspect output further includes a scenario analysis where different scenarios such as more renewable energy, transport distance reduction and their effect on total sustainability impact are shown.

56. The method of claims 49 to 55, wherein the sustainability aspect performs a life cycle analysis adherent to the IS014040 and ISO14044 standards.

57. The method of claims 49 to 56, wherein the sustainability aspect output provides a comparative analysis where products developed and measured on the platform will be compared to similar product benchmarks gathered from industry.