KR102698843B1 - Genotoxicity test automation system and method - Google Patents

Abstract

A system and method for automating genotoxicity testing are disclosed. The genotoxicity testing system according to one embodiment of the present invention includes: a design processing unit which provides a plurality of test layouts preset for each test upon receiving a test request for a specific test substance from a user terminal, and processes a test full-cycle design including test items and test procedures according to at least one test layout selected by a user through the user terminal; a test processing unit which receives and stores test data acquired during a test according to the test full-cycle design from the user terminal, and provides a report form in the form of an electronic document pre-matched with at least one test layout, receives test data transmitted according to input items in the report form, and generates a final report; and a verification unit which processes a verification procedure for a test result according to a preset test guideline.

Description

{GENOTOXICITY TEST AUTOMATION SYSTEM AND METHOD}

The disclosed embodiments relate to techniques for automating genotoxicity testing.

A variety of tests can be conducted to evaluate the properties or safety of a test substance that may affect human health.

Among the above-mentioned tests, genotoxicity tests can be applied in various fields such as medical, healthcare, cosmetics, and food. As the need for new vaccines for various diseases and infectious diseases increases, methods to perform these genotoxicity tests more efficiently and manage them systematically are being sought.

Republic of Korea Patent Publication No. 10-2260274 (May 28, 2021)

The disclosed embodiments are intended to provide a system and method for automating a genotoxicity test for computerizing process processing related to a genotoxicity test, and for automating management such as securing reliability of genotoxicity test data and processing related data according to a standardized format through the computerized system.

According to one embodiment, a system for automated genetic toxicity testing includes: a design processing unit which provides an automated authoring tool for test design upon receiving a test request for a specific test substance from a user terminal, and processes a test full-cycle design including test items and test procedures according to at least one test layout set by a user via the user terminal; a test processing unit which receives and stores test data acquired during a test according to the test full-cycle design from the user terminal, and provides a report form in the form of an electronic document pre-matched with each of the at least one test layout, receives the test data transmitted according to input items in the report form, and generates a final report; and a verification unit which processes a verification procedure for a test result according to a preset test guideline.

The above test processing unit can, when storing the test data, match each test data with log information in a preset format and store it.

The above log information may include at least one of test identification information, test details, and update information, and the update information may include at least one of update date and time, update user, and update details.

The above test processing unit extracts and provides the pre-matched report form as a specific test layout is selected, receives and registers the test data entered according to the report form, and can create and match and store a history of test data for a related test using the log information.

The above test processing unit can process the following procedures, including the next user report, based on the design prior to the test, when data entry for required input items in the above report form is completed.

The above test guidelines may include at least one of the following: a first test guideline based on OECD guidelines and local guidelines, and a second test guideline based on laws relating to electronic signatures and electronic records, including 21 CFR Part 11.

The above verification unit verifies the test results according to the test guidelines, generates a notification message for a test result in which an abnormality occurs in the verification result, and transmits the notification message to the user terminal, and the notification message may include a link for accessing the corresponding test data in which an abnormality occurred and related data.

According to another embodiment, a method for automating a genotoxicity test is provided, which is performed by an automated genotoxicity test system, comprising: a step of providing an automated authoring tool for designing a test upon receiving a test request for a specific test substance from a user terminal; a step of processing a test full-cycle design including test items and test procedures according to at least one test layout set by a user through the user terminal; a step of receiving and storing test data acquired during a test according to the test full-cycle design from the user terminal, and providing a report form in the form of an electronic document pre-matched with each of the at least one test layout, and receiving the test data transmitted according to input items in the report form to generate a final report; and a step of processing a verification procedure for a test result according to a preset test guideline.

The above-mentioned automated genetic toxicity test method can store the test data by matching each test data with log information in a preset format when storing the test data.

The above log information may include at least one of test identification information, test details, and update information, and the update information may include at least one of update date and time, update user, and update details.

In addition, a computer-readable recording medium recording a computer program for executing a method for implementing the disclosed embodiment may be further provided.

According to the disclosed embodiments, it is expected that by performing a full-cycle design in relation to a genotoxicity test for a specific test substance and entering test data acquired during the test according to the designed test full-cycle design, it is possible to automatically computerize and construct various data including test data.

Additionally, according to the disclosed embodiments, the reliability of genotoxicity test data can be secured by applying a standardized workflow.

Additionally, according to the disclosed embodiments, standards and processes for linking with related tasks can be established.

Additionally, according to the disclosed embodiments, data related to genotoxicity testing can be data processed in a standardized format.

In addition, according to the disclosed embodiments, the reliability of the test data can be secured through verification of the test data through various test guidelines.

FIG. 1 is a drawing for explaining the connection relationship between an automated genetic toxicity test system and a user terminal according to one embodiment.
Figure 2 is a drawing schematically illustrating an automated method for genetic toxicity testing according to one embodiment.
Figure 3 is a block diagram illustrating a detailed configuration of an automated genetic toxicity test system according to one embodiment.
Figures 4 to 10 are exemplary diagrams for explaining an automated method for genetic toxicity testing according to one embodiment.
Figure 11 is a flow chart for explaining a method for automating a genetic toxicity test according to one embodiment.
FIG. 12 is a block diagram illustrating a computing environment including a computing device according to one embodiment.

Hereinafter, specific embodiments of the present invention will be described with reference to the drawings. The following detailed description is provided to help a comprehensive understanding of the methods, devices, and/or systems described herein. However, this is only an example and the present invention is not limited thereto.

In describing embodiments of the present invention, if it is judged that a detailed description of a known technology related to the present invention may unnecessarily obscure the gist of the present invention, the detailed description will be omitted. In addition, the terms described below are terms defined in consideration of their functions in the present invention, and may vary depending on the intention or custom of the user or operator. Therefore, the definitions should be made based on the contents throughout this specification. The terms used in the detailed description are only for describing embodiments of the present invention, and should never be limited. Unless clearly used otherwise, the singular form includes the plural form. In this description, expressions such as "comprises" or "comprising" are intended to indicate certain features, numbers, steps, operations, elements, parts or combinations thereof, and should not be construed to exclude the presence or possibility of one or more other features, numbers, steps, operations, elements, parts or combinations thereof other than those described.

The genotoxicity test disclosed in this example may be a field of testing that observes the phenomenon in which a test substance directly damages DNA or chromosomes, causing morphological changes or functional abnormalities. For example, the genotoxicity test may be a test to find out the carcinogenicity and mutagenicity of pharmaceuticals, pesticides, and various chemical substances.

FIG. 1 is a diagram for explaining a connection relationship between an automated genetic toxicity test system and a user terminal according to one embodiment, FIG. 2 is a diagram for schematically explaining a method for automated genetic toxicity testing according to one embodiment, and FIG. 3 is a block diagram for explaining a detailed configuration of an automated genetic toxicity test system according to one embodiment.

Hereinafter, a description will be given with reference to FIGS. 4 to 10, which are exemplary diagrams for explaining an automated genetic toxicity test method according to one embodiment.

The automated genotoxicity test system (100) disclosed in this embodiment may mean a configuration for automating tasks such as project decision, reference information setting, test design, test result collection, and reporting related to genotoxicity testing.

Referring to Fig. 1, the automatic genetic toxicity test system (100) may be configured to automatically build and manage procedures and test data related to a test for a specific test substance. This automatic genetic toxicity test system (100) may be connected to a user terminal (200) to transmit and receive information.

The user terminal (200) may refer to a user terminal including an operator who performs overall management of the system, including the design of the entire test cycle described below, through the genetic toxicity test automation system (100), and a tester who inputs various test data generated during the test. In this case, the tester may include a plurality of people, including a tester who performs the actual test and a test manager.

Referring to FIG. 2, the user terminal (200) may receive an automation authoring tool through a web interface implemented in the genetic toxicity test automation system (100) via a network, set up test-related processes including test full cycle design, and perform various tasks related to the test including test data registration during test processing using the automation process generated through the automation authoring tool. In this case, the user terminal (200) may be any terminal having computing and communication functions, and may be connected to the web interface of the genetic toxicity test automation system (100) via a web UI, email, messenger, or chat-bot. The user terminal (200) may be any wired or wireless terminal such as a mobile phone, a desktop, or a tablet PC.

When the genetic toxicity test automation system (100) processes tasks related to the genetic toxicity test, including the design of the entire test cycle, through a web page or application on the user terminal (200), it can provide messages such as guidance on test procedures, guidance on inputting input items, and requests for data input for required input items, using a chatbot or messenger. At this time, the messages sent and received through the chatbot or messenger can be subject to parsing and natural language processing that extracts words from the messages and decomposes them into sentences.

As shown in Fig. 2, the genetic toxicity test automation system (100) is also linked to each application for providing a number of services, including the PMS system, which is a project management system, and can transmit and receive necessary data to each other.

The genotoxicity test automation system (100) according to the present embodiment can implement hyper automation that automates and optimizes work processes by comprehensively utilizing automation, robotic process automation (RPA), artificial intelligence (AI), machine learning (ML), analysis, and automation tools and technologies. For example, the genotoxicity test automation system (100) can implement process automation by applying various automation technologies such as optical character recognition (OCR), machine learning, RPA, and chatbot. The process automation may mean that work processes such as test design, test data input, reporting, and verification related to genotoxicity tests are computerized and automatically processed according to preset criteria. At this time, the present embodiment can minimize the manual work of a tester by applying a detection technology for an input document utilizing deep learning.

In addition, the genetic toxicity test automation system (100) can build an open ecosystem and link various third-party equipment using Open API. For example, the genetic toxicity test automation system (100) can provide support for linking with various test equipment and linking API as an open system.

In addition, the genotoxicity test automation system (100) can be expanded to a cloud service. Specifically, the genotoxicity test automation system (100) can be implemented in the form of a cloud server so that users (testers and operators) can access the system through a user terminal (200) from anywhere, regardless of location. In this environment, the genotoxicity test automation system (100) can provide an automated authoring tool for designing the entire test cycle using a web page or application to the user terminal (200). Thereafter, the user terminal (200) can access the genotoxicity test automation system (100) to process work processes such as registering test data or receiving verified test results. At this time, the genotoxicity test automation system (100) can provide a standardized plurality of test layouts for designing the entire test cycle, provide data input items for obtaining standardized data, and generate a final report according to a standardized form. Through this, the present embodiment can implement data construction based on standardization of measurement through large-scale data analysis.

A detailed description of the above-described automated genetic toxicity test system (100) will be provided later.

Referring to FIG. 3, the genotoxicity test automation system (100) includes a design processing unit (110), a test processing unit (130), and a verification unit (150). The components illustrated in FIG. 3 are not essential for implementing the genotoxicity test automation system (100) according to the present disclosure, and thus the genotoxicity test automation system (100) described in this specification may have more or fewer components than the components listed above. For example, the genotoxicity test automation system (100) may additionally include a communication unit, a memory, an input unit, and an output unit.

The components illustrated in FIG. 3 may be communicatively connected to one another via a communications network (not shown). In some embodiments, the communications network may include the Internet, one or more local area networks, wire area networks, a cellular network, a mobile network, other types of networks, or a combination of such networks.

The design processing unit (110) provides an automated authoring tool for test design upon receiving a test request for a specific test substance from a user terminal (200), and can process a test full cycle design including test items and test procedures according to at least one test layout set by a user through the user terminal (200).

The above test pre-cycle design may refer to all processes related to non-clinical testing for a specific test substance. Referring to Fig. 6, the design processing unit (110) may receive a test substance-related file transmitted from an external system (e.g., PMS system) (PMS input) and identify the test substance based on this.

In addition, the design processing unit (110) can recognize and analyze the contents of the test substance-related file transmitted from an external system, and automatically identify the items required for designing the entire test cycle. At this time, the design processing unit (110) can use OCR technology to analyze the contents of the test substance-related file. For example, if the test substance-related file includes the test substance name and test type, the design processing unit (110) can automatically apply the identified items to the test entire cycle design through the analysis of the test substance-related file without the need for separate data input by the tester.

The above-described tests may include at least one of a reverse mutation assay, a chromosome aberration assay, an in vivo micronucleus assay, an in vitro micronucleus assay, an in vivo Comet assay, and an in vivo Pig-a gene mutation assay.

The reversion mutation test may refer to a test method for measuring genotoxicity by confirming whether a microorganism in which specific amino acid synthesis is inhibited is converted into an amino acid synthesis strain by a test substance. This is a test method that is quick and simple among genotoxicity tests and shows a very close correlation with the results of a carcinogenicity test, and can be widely used in the early screening stage of new drug development and in safety tests for pharmaceuticals, food additives, pesticides, general chemicals, etc. The chromosome aberration test may refer to a test method for measuring a structural abnormality of a chromosome caused by a test substance. The in vivo micronucleus test may refer to a test method used to detect damage to a chromosome or damage to a mitotic apparatus induced in bone marrow or peripheral blood cells of rodents administered a test substance. The in vitro micronucleus test may refer to a test method for measuring a substance that causes a structural abnormality (Clastogenic) and a numerical abnormality (Aneugenic) of a chromosome using mammalian cells. The above in vivo Comet assay is a test to evaluate damage at the DNA level in individual cells. It can mean a test to evaluate damage to DNA by placing a single cell suspension in low melting agar gel, dissolving it, and performing electrophoresis under alkaline (pH>13) conditions. The above in vivo Pig-a gene mutation assay is an in vivo gene mutation assay and can mean a test method to detect mutations in the Pig-a gene on the X chromosome.

Referring to FIG. 4, the design processing unit (110) may include test items to be performed for each test. For example, a reversion mutation test may include test items including Bacteria Strain Selection, S9 Mix, Positive Control Selection, Control Condition, and Dose Condition. At this time, the test items may include items that a tester performs when performing a test or items that must be considered when performing a test.

Referring to FIG. 5, the design processing unit (110) may provide an automated authoring tool (e.g., study layout designer of FIG. 5) for designing the entire test cycle. The automated authoring tool may have multiple test layouts for each test for designing the entire test cycle created and matched in advance. This automated authoring tool may be executed through an application pre-installed on the user terminal (200) or displayed through a web page.

Referring to FIG. 6, the design processing unit (110) can set a test cycle design based on multiple test layouts that must be performed in the test cycle from start to end for a specific test substance selected and transmitted as the user operates the automated authoring tool on the user terminal (200).

At this time, the design processing unit (110) can perform test design by providing multiple test layouts pre-matched to a specific test substance or a specific test through an automated authoring tool and allowing the user to select them.

The design processing unit (110) can perform a verification procedure for multiple test layouts selected by the user during the test pre-cycle design, and generate and provide a notification message so that the user can recognize that the test layout does not match the test material or the test.

The design processing unit (110) can perform a verification procedure on a test full cycle design selected and completed by a user, and generate and provide a notification message so that a user can be aware of cases where a test material or a test layout that must be included in the test is missing or an unnecessary test layout is included.

Through verification of the test layout and test pre-cycle design described above, this embodiment can be expected to have the effect of standardizing the entire test process for a genotoxicity test. At this time, since the design processing unit (110) also performs a verification procedure for the test layout set by the user, the reliability of the standardization can be further improved.

The test processing unit (130) receives and stores test data acquired during test execution according to the test pre-cycle design from the user terminal (200), and provides a report form in the form of an electronic document pre-matched with at least one test layout, so that the test data transmitted according to the input items in the report form can be received to generate a final report.

For example, test data may include, but is not limited to, the number of color changes in a reagent obtained by a tester using test equipment, data produced through machine counting, etc. Test data may vary from test substance to test substance or test to test.

Additionally, test data may include both text data and image data (including still images and moving images).

The input items described above may be items created so that data can be entered based on principles such as names, definitions, formats, and rules that have been established in advance to standardize the data being entered.

The genetic toxicity test automation system (100) can provide data entry guidance through a chatbot or messenger so that data can be entered into standardized input items according to standardized rules. To this end, the genetic toxicity test automation system (100) can preset data entry guidance for each input item through a test processing unit (130) and provide this to a user terminal (200) through a chatbot or messenger.

The final report described above is a report based on a format for reporting the results of a genotoxicity test, and may be a report for enabling the test results to be printed according to a standardized manual (e.g., genotoxicity test result report format) shared in advance between multiple organizations including public institutions.

When storing test data, the test processing unit (130) can match and store log information in a preset format with each test data. The log information can be used to identify the subject, time, location, etc. who performed changes, updates, etc. of the test data. For example, the log information can be used when verifying the possibility of data manipulation of the test data.

The above log information may include at least one of test identification information, test details, and update information.

The above test identification information may include, but is not limited to, the test name, test request date, and version, and information for identifying the test being performed may be added and changed.

The above test details may refer to items including test processing details and test progress status, as well as various matters occurring during the test, and the operator may add and change the included information. The above test processing details refer to matters actually processed by the user (e.g., tester) during the test, for example, dissolving 500 mg of test substance into 1 ml of DMSO.

The above update information may include at least one of update date, update user, and update history, but is not limited thereto, and various information related to the update of test data may be added and changed. In this embodiment, test authority may be preset for each user (e.g., tester), and the level of test data that can be accessed according to the test authority may also be preset. To this end, each test data and input item for entering the corresponding test data may have a level preset, and access authority may be matched and set according to this level.

Referring to FIGS. 7 to 10, the test processing unit (130) may extract and provide a pre-matched report form as a specific test layout is selected. For example, in the case of a reversion mutation test, the report form may include an electronic document-type report form including input items that must be entered corresponding to each of a reversion mutation test record sheet, a medium preparation and inoculation use record sheet, an OD value measurement record sheet, a test substance and S9 preparation record sheet, a test substance treatment record sheet, and a reversion mutation colony count sheet.

The test processing unit (130) receives and registers test data entered according to the report form, and may create, match, and store a history of test data for a related test using log information. The history of the test data may mean that it is created to check matters occurring during the processing of a genotoxicity test in the form of a history for each test. For example, the history of the test data may be created to include at least one of a test substance name, a test name, a data reception date, a prescription date, a version, a test detail, an update user, and an update date and time (including the date and time). At this time, the history of the test data may be created to be listed in chronological order according to the occurrence date of the data, or to be listed in an order preset by an operator, so as to facilitate confirmation.

When data entry for required input items in the report form is completed, the test processing unit (130) can process the following procedures, including the next user report, based on the test pre-cycle design.

For example, when data entry for required input items in the report form is completed, the test processing unit (130) can process the next procedure, such as starting the next test procedure, generating a final report, or sending an email for reporting to a superior, according to the test pre-cycle design as shown in FIG. 6.

As shown in FIGS. 7 to 10, the report form may include multiple input items that must be recorded during a test. For example, the input items may include all items that must be recorded in relation to the ongoing test, including Experiment ID, Experiment Title, Experiment Category, Version, Activation, Update User, Update Date Time, Activate, Received Date, Storage Date, and Confirmation Date.

The test processing unit (130) can receive, store and manage the test results verified through the verification unit (130). Although not shown, the genotoxicity test automation system (100) can have an internal or external database that stores various data related to the system, including test data and test results.

The test processing unit (130) can provide various data according to the user's request. At this time, the test processing unit (130) can authenticate the user and provide the data according to the access rights preset for each data.

The verification unit (150) can process a verification procedure for a test result according to preset guidelines. The test result can include a plurality of test data collected during test processing.

The above test guidelines may include at least one of the following: a first test guideline based on OECD guidelines and local guidelines, and a second test guideline based on laws relating to electronic signatures and electronic records, including 21 CFR Part 11.

The above first test guideline may be a test guideline for proving that the test data was obtained by a suitable method. Specifically, the above first test guideline may include guidelines by the International Conference on Harmonization of Technical Requirements for Registration of Pharmaceutical for Human Use (ICH) and the Organization for Economic Cooperation and Development (OECD) for genotoxicity tests of pharmaceuticals, etc.

The above local guidelines are based on the Act on Registration and Evaluation of Chemical Substances, etc., and may include test guidelines for reliability of data, evaluation of test methods, evaluation of report result description, statistical analysis of results, and uncertainty assessment of non-test data.

The above second test guideline may be a test guideline for detecting the possibility of manipulation of experimental data. Specifically, 21 CFR Part 11 covers Electronic Records, Electronic Signatures, Validation, Glossary of Terms, Time Stamps, Maintenance of Electronic Records, Electronic Copies of Electronic Records, limiting system access to authorized individuals, use of operational system checks, use of authority checks, use of device checks, determination that persons who develop, maintain, or use electronic systems have the education, training, and experience to perform their assigned tasks, establishment of and adherence to written policies that hold individuals accountable for actions initiated under their electronic signatures, appropriate controls over systems documentation, and use of closed systems. It may include guidelines related to at least one of controls for open systems corresponding to controls for closed systems and requirements related to electronic signatures.

The verification unit (150) can verify the test results according to the test guidelines, and generate a notification message for the test results in which an abnormality occurs and transmit it to the user terminal (200). The notification message can include a link for accessing the corresponding test data in which an abnormality occurred and related data.

When performing verification on test results, the verification unit (150) can output verification results according to test guidelines by inputting data in the test results using a pre-learned artificial intelligence model.

The above artificial intelligence model may be a pre-trained model to output test verification results according to genotoxicity test results based on past genotoxicity test results, test guidelines, test results satisfying the test guidelines, and test results not satisfying the test guidelines.

According to the present disclosure, the automated genetic toxicity test system (100) can perform calculations for learning the artificial intelligence model described above. A processor (not shown) provided in the automated genetic toxicity test system (100) can perform calculations for learning a neural network, such as processing input data for learning in deep learning, extracting features from input data, calculating errors, and updating weights of a neural network using backpropagation.

The above neural network model may be a deep neural network. In the present disclosure, neural network, network function, and neural network may be used with the same meaning. A deep neural network (DNN) may mean a neural network including multiple hidden layers in addition to an input layer and an output layer. Using a deep neural network, latent structures of data can be identified. That is, latent structures of a photo, text, video, voice, or music (e.g., what object is in the photo, what the content and emotion of the text are, what the content and emotion of the voice are, etc.) can be identified. A deep neural network may include a convolutional neural network (CNN), a recurrent neural network (RNN), a restricted Boltzmann machine (RBM), a deep belief network (DBN), a Q network, a U network, a Siamese network, etc.

A convolutional neural network is a type of deep neural network that includes a neural network that includes convolutional layers. A convolutional neural network is a type of multilayer perceptron designed to use minimal preprocessing. A CNN can consist of one or more convolutional layers and artificial neural network layers combined with them. A CNN can additionally utilize weight and pooling layers. Thanks to this structure, a CNN can fully utilize two-dimensional structured input data. A convolutional neural network can be used to recognize objects in images. A convolutional neural network can process image data by representing it as a matrix with dimensions. For example, in the case of image data encoded in RGB (red-green-blue), each of the R, G, and B colors can be represented as a two-dimensional (for example, in the case of a two-dimensional image) matrix. That is, the color value of each pixel of the image data can be an element of a matrix, and the size of the matrix can be the same as the size of the image. Therefore, the image data can be represented as three two-dimensional matrices (three-dimensional data array).

In a convolutional neural network, a convolutional process (input and output of a convolutional layer) can be performed by moving a convolutional filter and multiplying the matrix components at each location of the convolutional filter and the image. The convolutional filter can be composed of a matrix in the form of an n*n matrix. The convolutional filter can generally be composed of a fixed-shape filter that is smaller than the total number of pixels of the image. That is, when an m*m image is input to a convolutional layer (for example, a convolutional layer whose convolutional filter has a size of n*n), a matrix representing n*n pixels including each pixel of the image can be component-multiplied (i.e., multiplied between each component of the matrix) with the convolutional filter. By multiplying with the convolutional filter, a component matching the convolutional filter can be extracted from the image. For example, a 3*3 convolutional filter for extracting upper and lower straight line components from an image can be configured as [[0,1,0], [0,1,0], [0,1,0]]. When a 3*3 convolutional filter for extracting upper and lower straight line components from an image is applied to an input image, upper and lower straight line components matching the convolutional filter from the image can be extracted and output. The convolutional layer can apply a convolutional filter to each matrix for each channel representing the image (i.e., R, G, B colors in the case of R, G, B coded images). The convolutional layer can extract features matching the convolutional filter from the input image by applying the convolutional filter to the input image. The filter value of the convolutional filter (i.e., the value of each element of the matrix) can be updated by backpropagation during the learning process of the convolutional neural network.

The output of the convolutional layer can be connected to a subsampling layer to simplify the output of the convolutional layer, thereby reducing memory usage and computational amount. For example, when the output of the convolutional layer is input to a pooling layer having a 2*2 max pooling filter, the image can be compressed by outputting the maximum value included in each patch for each 2*2 patch from each pixel of the image. The above-described pooling may be a method of outputting the minimum value from the patch or the average value of the patch, and any pooling method may be included in the present disclosure.

A convolutional neural network may include one or more convolutional layers and sub-sampling layers. A convolutional neural network can extract features from an image by repeatedly performing a convolutional process and a sub-sampling process (e.g., the aforementioned max pooling). Through repeated convolutional processes and sub-sampling processes, the neural network can extract global features of an image.

The output of a convolutional layer or a subsampling layer can be input to a fully connected layer. A fully connected layer is a layer in which all neurons in one layer are connected to all neurons in the neighboring layer. A fully connected layer can mean a structure in a neural network in which all nodes in each layer are connected to all nodes in other layers.

At least one of the CPU, GPGPU, and TPU of the processor can process learning of a network function. For example, the CPU and the GPGPU can process learning of a network function and classification of data using the network function together. In addition, in one embodiment of the present disclosure, processors of a plurality of computing devices can be used together to process learning of a network function and classification of data using the network function. In addition, a computer program executed in a computing device according to one embodiment of the present disclosure can be a CPU, GPGPU, or TPU executable program.

Fig. 11 is a flow chart for explaining an automated genotoxicity test method according to one embodiment. The method illustrated in Fig. 11 can be performed by, for example, the aforementioned automated genotoxicity test system (100). In the illustrated flow chart, the method is described by dividing it into a plurality of steps, but at least some of the steps may be performed in a changed order, combined with other steps and performed together, omitted, divided into sub-steps and performed, or one or more steps not illustrated may be added and performed.

At steps 1100 and 1200, the automated genetic toxicity test system (100) may provide an automated authoring tool for test design upon receiving a test request for a specific test substance from a user terminal (200).

At step 1300, the genetic toxicity test automation system (100) can process a test full cycle design including test items and test procedures according to at least one test layout set by a user through a user terminal (200).

At step 1400, the genotoxicity test automation system (100) receives and stores test data acquired during test execution according to the test full cycle design from the user terminal (200), and provides a report form in the form of an electronic document pre-matched with at least one test layout, so that the test data transmitted according to the input items in the report form can be received to generate a final report.

At this time, the final report is a report based on a format for reporting the results of a genotoxicity test, and may be a report for enabling the test results to be printed according to a standardized manual (e.g., genotoxicity test result report format) shared in advance between multiple organizations including public institutions.

When saving test data, the genetic toxicity test automation system (100) can match each test data with log information in a preset format and save it.

The above log information may include at least one of test identification information, test details, and update information. The update information may include at least one of update date and time, update user, and update details.

At step 1500, the genotoxicity test automation system (100) can process a verification procedure for the test results according to preset test guidelines.

FIG. 12 is a block diagram illustrating a computing environment including a computing device according to one embodiment. In the illustrated embodiment, each component may have different functions and capabilities other than those described below, and may include additional components other than those described below.

The illustrated computing environment (10) includes a computing device (12). The computing device (12) may be one or more components included in an automated genetic toxicity test system (100) according to one embodiment.

A computing device (12) includes at least one processor (14), a computer-readable storage medium (16), and a communication bus (18). The processor (14) may cause the computing device (12) to operate in accordance with the exemplary embodiments described above. For example, the processor (14) may execute one or more programs stored in the computer-readable storage medium (16). The one or more programs may include one or more computer-executable instructions, which when executed by the processor (14) may cause the computing device (12) to perform operations in accordance with the exemplary embodiments.

A computer-readable storage medium (16) is configured to store computer-executable instructions or program code, program data, and/or other suitable forms of information. A program (20) stored in the computer-readable storage medium (16) includes a set of instructions executable by the processor (14). In one embodiment, the computer-readable storage medium (16) may be a memory (volatile memory such as random access memory, non-volatile memory, or a suitable combination thereof), one or more magnetic disk storage devices, optical disk storage devices, flash memory devices, any other form of storage medium that can be accessed by the computing device (12) and capable of storing desired information, or a suitable combination thereof.

A communication bus (18) interconnects various other components of the computing device (12), including the processor (14) and computer-readable storage media (16).

The computing device (12) may also include one or more input/output interfaces (22) that provide interfaces for one or more input/output devices (24) and one or more network communication interfaces (26). The input/output interfaces (22) and the network communication interfaces (26) are coupled to the communication bus (18). The input/output devices (24) may be coupled to other components of the computing device (12) via the input/output interfaces (22). Exemplary input/output devices (24) may include input devices such as a pointing device (such as a mouse or trackpad), a keyboard, a touch input device (such as a touchpad or a touchscreen), a voice or sound input device, various types of sensor devices and/or photographing devices, and/or output devices such as a display device, a printer, speakers, and/or a network card. The exemplary input/output devices (24) may be included within the computing device (12) as a component that constitutes the computing device (12), or may be coupled to the computing device (12) as a separate device distinct from the computing device (12).

The disclosed embodiments may be implemented in the form of a recording medium storing instructions executable by a computer. The instructions may be stored in the form of program codes, and when executed by a processor, may generate program modules to perform the operations of the disclosed embodiments. The recording medium may be implemented as a computer-readable recording medium.

Although representative embodiments of the present invention have been described in detail above, those skilled in the art will understand that various modifications can be made to the above-described embodiments without departing from the scope of the present invention. Therefore, the scope of the rights of the present invention should not be limited to the described embodiments, but should be determined not only by the claims described below but also by equivalents of the claims.

10: Computing Environment
12: Computing Devices
14: Processor
16: Computer readable storage medium
18: Communication bus
20: Program
22: Input/output interface
24: Input/output devices
26: Network Communication Interface
100: Automated Genetic Toxicity Testing System
200: User Terminal
110: Design Processing Unit
130: Test Processing Department
150: Verification Department

Claims (10)

A design processing unit that provides an automated authoring tool for test design upon receiving a test request for a specific test substance from a user terminal, and processes a test full cycle design including test items and test procedures according to at least one test layout set by a user through the user terminal, and automatically applies the design to recognize and analyze the contents of a test substance-related file including a test substance name and test type transmitted from an external system when designing the test full cycle;
A test processing unit that receives and stores test data acquired during a test according to the above test pre-cycle design from the user terminal, provides a report form in the form of an electronic document pre-matched with each of the at least one test layout, receives the test data transmitted according to input items in the report form, and generates a final report; and
Includes a verification unit that handles verification procedures for test results according to preset test guidelines;
The above design processing unit,
When designing the above test cycle, a verification procedure is performed on multiple test layouts selected by the user, and if the test layout does not match the test substance or the test, a notification message is provided so that the user can recognize this, and
By performing a verification procedure on the above test cycle design selected and completed by the user, if the test material or test layout that must be included in the test is missing or an unnecessary test layout is included, a notification message is provided so that the user can be aware of this.
An automated genetic toxicity test system in which the test data and the input items for entering the test data are set to levels in advance, and access rights are set to match and set according to the set levels. In claim 1,
The above test processing unit,
An automated genetic toxicity test system that saves the above test data by matching each test data with log information in a preset format. In claim 2,
The above log information includes at least one of test identification information, test details, and update information.
The above update information includes at least one of update date and time, update user, and update history. In claim 3,
The above test processing unit,
An automated genetic toxicity test system that extracts and provides a pre-matched report form as a specific test layout is selected, receives and registers the test data entered according to the report form, and creates and matches and stores a history of test data for a related test using the log information. In claim 4,
The above test processing unit,
An automated genetic toxicity test system that processes the following procedures, including the next user report, based on the test pre-cycle design, upon completion of data entry for required fields in the above report form. In claim 1,
The above test guidelines are:
An automated genotoxicity testing system comprising at least one of the following: a first test guideline based on OECD guidelines and local guidelines, and a second test guideline based on laws relating to electronic signatures and electronic records, including 21 CFR Part 11. In claim 6,
The above verification department,
The above test results are verified according to the above test guidelines, and a notification message is generated for the test results in which an abnormality occurs in the verification results and transmitted to the user terminal.
The above notification message includes a link for accessing the relevant test data and related data in which an abnormality occurred, and an automated genotoxicity test system. A method performed by an automated genetic toxicity test system,
A step of providing an automated authoring tool for test design upon receiving a test request for a specific test substance from a user terminal;
A step of processing a test cycle design including test items and test procedures according to at least one test layout set by a user through the user terminal, and automatically applying the recognized and analyzed contents of a test substance-related file including a test substance name and test type transmitted from an external system when designing the test cycle;
A step of receiving and storing test data acquired during a test according to the above test pre-cycle design from the user terminal, providing a report form in the form of an electronic document pre-matched with each of the at least one test layout, and receiving the test data transmitted according to input items in the report form to generate a final report; and
Includes a step of processing the verification procedure for the test results according to the preset test guidelines;
In the step of processing the above test cycle design,
When designing the above test cycle, a verification procedure is performed on multiple test layouts selected by the user, and if the test layout does not match the test substance or the test, a notification message is provided so that the user can recognize this, and
By performing a verification procedure on the above test cycle design selected and completed by the user, if the test material or test layout that must be included in the test is missing or an unnecessary test layout is included, a notification message is provided so that the user can be aware of this.
A method for automating a genotoxicity test, wherein the test data and the input items for entering the test data are set to levels in advance, and access rights are set to match and set according to the set levels. In claim 8,
An automated method for genetic toxicity testing, wherein when saving the above test data, each test data is matched with log information in a preset format and saved. In claim 9,
The above log information includes at least one of test identification information, test details, and update information.
A method for automating a genetic toxicity test, wherein the above update information includes at least one of update date and time, update user, and update history.