Systems and methods for designing vaccines

Abstract

To provide systems and methods for designing vaccines.SOLUTION: One or more operations in a system for designing vaccines include: applying, to a first temporal sequence data set, a plurality of driver models configured to generate output data representing one or more molecular sequences; training, for each of the plurality of driver models, the corresponding driver model; selecting, based on one or more trained translational responses, a set of trained driver models of the plurality of driver models; applying, to a second temporal sequence data set, the selected set of trained driver models; and selecting, based on second translational response data, a subset of trained driver models of the set of trained driver models.SELECTED DRAWING: Figure 3

Description

[Technical field]

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS This application claims priority to U.S. Provisional Patent Application No. 62 / 924,096, filed October 21, 2019, the entire contents of which are incorporated herein by reference.

[0002] The present disclosure relates generally to systems and methods for producing vaccines. [Background technology]

[0003] The mammalian immune system employs two general mechanisms to defend the body against environmental pathogens: upon encountering a pathogen-derived molecule, an immune response is activated to ensure defense against that pathogen.

[0004] The first immune system mechanism is the non-specific (or innate) inflammatory response. The innate immune system appears to recognize certain molecules that are present on pathogens but not on the body itself.

[0005] The second immune system mechanism is the specific or acquired (or adaptive) immune response. Innate responses are essentially the same to each injury or infection. In contrast, acquired responses arise specifically in response to molecules in or derived from pathogens. The immune system recognizes and responds to structural differences between self proteins and non-self (e.g., pathogen or pathogen-derived) proteins. Proteins that the immune system recognizes as non-self are called antigens. Pathogens usually express many highly complex antigens. The acquired immune system utilizes two functions; first, to generate immunoglobulins (antibodies) in response to many different molecules, called antigens, present on pathogens. Second, to recruit receptors that bind to processed forms of antigens displayed on the cell surface for other cells to recognize as infected cells.

[0006] In summary, adaptive immunity is mediated by specialized immune cells called B and T lymphocytes (or simply, B and T cells). Adaptive immunity has a specific memory of antigenic structures. Repeated exposure to the same antigen can result in an increased response, which can increase the level of induced defense against that particular pathogen. B cells generate and mediate their function through the action of antibodies. B cell-dependent immune responses are called "humoral immunity" because antibodies are found in bodily fluids. T cell-dependent immune responses are called "cell-mediated immunity" because effector activity is directly mediated by the local action of effector T cells. The local action of effector T cells is amplified by synergistic interactions between T cells and secondary effector cells such as activated macrophages. As a result, pathogens are killed and prevented from causing disease.

[0007] Like pathogens, vaccines work by initiating an innate immune response at the site of vaccination and activating antigen-specific T and B cells that can give rise to long-term memory cells in secondary lymphoid tissues. The correct interaction of the vaccine with the cells at the site of vaccination, as well as with T and B cells, is critical for the ultimate success of the vaccine.

[0008] To determine whether a candidate antigen can be a functional and effective vaccine, the candidate antigen usually needs to undergo rigorous testing and evaluation protocols. Traditionally, candidate antigens are preclinical tested, a process in which the candidate antigen is evaluated by in vitro assays, ex vivo assays, and by using various animal models (e.g., mouse model, ferret model, etc.).

[0009] One exemplary type of assay that can be used to measure biological responses is the hemagglutination inhibition assay (HAI). HAI applies a process called hemagglutination, in which sialic acid receptors on the surface of red blood cells (RBCs) bind to the hemagglutinin glycoprotein found on the surface of influenza viruses (and some other viruses), creating a network, or lattice structure, of interconnected red blood cells and virus particles, called hemagglutination. This hemagglutination occurs in a concentration-dependent manner for virus particles. HAI is a physical measurement that acts as a proxy for the ability of a virus to bind to similar sialic acid receptors on pathogen target cells in the body. The introduction of anti-viral antibodies generated in a human or animal immune response to another virus (which may be genetically similar or different from the virus used to bind to the RBCs in the assay). These antibodies disrupt the interaction of the virus with the red blood cells, changing the concentration of the virus enough to change the concentration at which hemagglutination is observed in the assay. One goal of HAI may be to characterize the concentration of antibody in antiserum, or in other samples containing antibodies, relative to the ability of the antibody to induce hemagglutination in an assay. The highest dilution of antibody that prevents hemagglutination is called the HAI titer (i.e., the assessed response).

[0010] Another approach to measuring biological responses is to measure a larger set of possible antibodies elicited by the human or animal immune response, which are not necessarily capable of affecting hemagglutination in an HAI assay. A common approach for this measurement utilizes enzyme-linked immunosorbent assay (ELISA) techniques, in which a viral antigen (e.g., hemagglutinin) is immobilized on a solid surface and then antibodies from an antiserum are bound to the antigen. The readout measures the catalysis of an exogenous enzyme substrate, either conjugated to an antibody from the antiserum or to another antibody that itself binds to the antibody of the antiserum. The catalysis of the substrate produces a product that is easily detectable. There are many variations of this type of in vitro assay. One such variation is called antibody forensics (AF); it is a multiplexed bead array technique that allows a single serum sample to be compared to many antigens simultaneously. These measurements characterize the concentration and total antibody recognition compared to the HAI titer, which is understood to be specifically related to interference with sialic acid binding by the hemagglutinin molecule. Thus, antisera antibodies may, in some cases, be proportionally higher or lower in measurement relative to the hemagglutinin molecule of one virus than the corresponding HAI titer of the hemagglutinin molecule of another virus; in other words, these two measurements, AF and HAI, are generally not linearly related.

[0011] Currently, traditional candidate antigen testing is only performed with the proviso of eliciting a preconceived "protective" immune response. That is, if an animal or assay fails to demonstrate an adequate response to a candidate antigen, the candidate antigen is typically "down-selected" (i.e., discarded as a productive candidate). For example, influenza antigens are often tested using sequential selection protocols, where the antigen is first evaluated by an in vitro assay to ensure that the antigen is amenable to large-scale production. Provided that the antigen meets these requirements, the antigen is then evaluated, for example, by immunization of mice to measure the antigen's ability to elicit a protective immune response from the mice. This response is typically expected to be protective against the antigen itself and against various other virus strains and / or virus strain components against which it is desired to protect. Ferrets are then evaluated as well, subject to mice or other previous measurements having previously demonstrated what is understood to be indicative of a protective response. Penultimately in human evaluation, ex vivo platforms such as human immune system replicas or non-human primates are evaluated; again, subject to success in the previous step. Summary of the Invention [Means for solving the problem]

[0012] In one aspect, a system for designing a vaccine is provided. The system includes one or more processors. The system includes a computer storage device storing executable computer instructions that, when executed by the one or more processors, cause the one or more processors to perform one or more operations. The one or more operations include applying a plurality of driver models to a first time series data set configured to generate output data representative of one or more molecular sequences, the first time series data set being indicative of the one or more molecular sequences and, for each of the one or more molecular sequences, one or more circulating periods of a pathogen strain that includes the molecular sequence as a natural antigen. The one or more operations include, for each of the plurality of driver models, training the driver model by: i) receiving from the driver model output data representing one or more predicted molecular sequences based on the received first time series data set; ii) applying a translational model configured to predict a biological response to the molecular sequences for a plurality of translational axes to the output data representing the predicted one or more molecular sequences to generate first translational response data representing one or more first translational responses corresponding to a particular translational axis of the plurality of translational axes based on the one or more predicted molecular sequences in the output data; iii) adjusting one or more parameters of the driver model based on the first translational response data; and iv) repeating steps i-iii for a number of iterations to generate learned translational response data representing one or more learned translational responses corresponding to the particular translational axis. The one or more operations include selecting a set of learned driver models from the plurality of driver models based on the one or more learned translational responses.The one or more operations include, for each trained driver model in the set of trained driver models: applying the trained driver model to the second time series dataset to generate trained output data representing one or more predicted molecular sequences for a particular season; applying a translational model to the final output data to generate second translational response data representing one or more second translational responses for each translational axis of the multiple translational axes; and selecting a subset of trained driver models in the set of trained driver models based on the second translational response data.

[0013] At least one of the plurality of driver models may include a recurrent neural network. At least one of the plurality of driver models includes a long-short-term memory recurrent neural network.

[0014] The output data representing one or more predicted molecular sequences based on the received first time series dataset may include output data representing antigens for each of the multiple disease seasons. The output data representing antigens for each of the multiple disease seasons may include antigens determined by predicting molecular sequences that will generate a maximized aggregate biological response across all pathogen strains circulating in a particular season. The output data representing antigens for each of the multiple disease seasons may include antigens determined by predicting molecular sequences that will generate a response that effectively immunizes against a maximum number of viruses circulating in a particular season.

[0015] The multiple translational axes may include at least one of: a ferret antibody forensics (AF) axis, a ferret hemagglutination inhibition (HAI) axis, a mouse AF axis, a mouse HAI axis, a human replica AF axis, a human AF axis, or a human HAI axis. The number of iterations is based on a predetermined number of iterations. The number of iterations is based on a predetermined error value. The one or more first translational responses include: a predicted ferret HAI titer, a predicted ferret AF titer, a predicted mouse AF titer, a predicted mouse HAI titer, a predicted human replica AF titer. , predicted human AF titer, or predicted human HAI titer.

[0016] The act of selecting a set of learned driver models from the plurality of driver models may include an act of assigning each driver model of the plurality of driver models to a class of driver models, each class being associated with a particular translational axis of the plurality of translational axes used to train the driver model. The act of selecting a set of learned driver models from the plurality of driver models may include, for each driver model of the plurality of driver models, comparing one or more learned translational responses of the driver model to one or more learned translational responses of at least one other driver model assigned to the same class as the driver model.

[0017] The operations may further include, for each trained driver model of the subset of trained driver models: validating the trained driver model by comparing second translational response data corresponding to the trained driver model to the observed experimental response data; and in response to the operation of validating the trained driver model, generating a vaccine including one or more molecular sequences represented by the trained output data corresponding to the trained driver model.

[0018] In one aspect, a system is provided. The system includes a computer-readable memory including computer-executable instructions. The system includes at least one processor configured to execute executable logic including at least one machine learning model trained to predict one or more molecular sequences, and the at least one processor is configured to perform one or more operations when the at least one processor executes the computer-executable instructions. The one or more operations include receiving time series data indicating one or more molecular sequences and, for each of the one or more molecular sequences, one or more circulating periods of a pathogen strain that includes the molecular sequence as a natural antigen. The one or more operations include processing the time series data through one or more data structures that store one or more portions of executable logic included in the machine learning model to predict the one or more molecular sequences based on the time series data.

[0019] Predicting one or more molecular sequences based on the time series data may include predicting one or more immunological properties that the predicted one or more molecular sequences will impart for future use. Predicting one or more molecular sequences based on the time series data may include predicting one or more molecular sequences that will generate a maximized aggregate biological response across all pathogen strains in the time series data. Predicting one or more molecular sequences based on the time series data may include predicting one or more molecular sequences that will generate a biological response that effectively covers a maximum number of pathogen strains in the time series data. The predicted one or more molecular sequences are used to design a vaccine against pathogen strains circulating during a period following one or more circulation periods of the time series data.

[0020] The machine learning model may include a recurrent neural network.

[0021] These and other aspects, configurations, and implementations may be expressed as methods, apparatus, systems, components, program products, methods of doing business, means or steps for performing a function, or in other ways, and will become apparent from the following description, including the claims.

[0022] The disclosed embodiments may provide one or more of the following advantages: Compared to conventional techniques, the vaccine is designed to confer more protection for a future disease season in terms of the amount of biological response to at least one pathogen strain of that future disease season; Compared to conventional techniques, the vaccine is designed for a future disease season to confer more protection in terms of the breadth of effective coverage against multiple pathogen strains of that future disease season (i.e., induce an effective immunological response against several pathogen strains of the future disease season); Unlike conventional techniques, rarely observed strains that may confer "more protection" because they cross-react with more strains than frequently observed strains are evaluated and vaccination efficacy for those strains is predicted.

[0023] These and other aspects, configurations, and implementations may be expressed as methods, apparatus, systems, components, program products, means or steps for performing a function, or in other ways.

[0024] These and other aspects, configurations, and implementations will become apparent from the following description, including the claims. [Brief description of the drawings]

[0025] [Figure 1] FIG. 1 illustrates an example of a system for designing a vaccine. [Figure 2A] FIG. 1 is a flow diagram of a method for designing a vaccine design system. [Figure 2B] FIG. 1 is a flow diagram of a method for designing a vaccine design system. [Diagram 3] 1 is a flow chart of a method for designing a vaccine. [Figure 4] 1 is a flowchart of a method for training one or more driver models to design a vaccine. [Diagram 5] FIG. 1 is a diagram showing improvements per translational axis compared to conventional techniques for designing vaccines. [Figure 6] FIG. 1 illustrates an example of a system for predicting biological responses using machine learning techniques. [Figure 7] 1 is a flow chart illustrating an example of a method for predicting biological responses using machine learning techniques. [Figure 8] 1 is an example of data used to train a machine learning model to predict biological responses. [Figure 9] FIG. 1 is a flow diagram of an example of training a machine learning model for predicting a biological response. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0026] Traditional methods of selecting candidate vaccines (CVs) and / or their antigens expressed as recombinant proteins may generally rely on several assumptions. As an illustrative example, in the case of influenza, traditional methods of selecting CVs may assume: (1) that for a given outbreak season, there is a "dominant strain"; (2) that naive ferrets are an accurate model of influenza drift (i.e., ferret cross-reactivity demonstrates whether one CV as an antigen confers protection against other circulating influenza strains); and (3) that the acquisition of ferret cross-reactivity may be a reliable predictor of the acquisition of human vaccine efficacy. Based on these assumptions, traditional methods of selecting CVs may have the following solutions: (1) select CVs that protect against dominant strains; (2) establish correlates of protection, for example, using ferret HAI; and (3) evaluate cross-reactivity of clinical isolates in ferrets. Furthermore, traditional methods of selecting CVs usually include selecting CVs that were circulating in the year prior to the year of vaccine recommendation and evaluating the selected CV against other frequently observed pathogenic strains (usually using ferrets).

[0027] Although these assumptions may have facilitated effective CVV selection more than 50 years ago when 1–10 pathogenic isolates were observed per year, these assumptions cannot facilitate effective CVV selection in the current disease seasons where thousands of pathogenic isolates are observed and reported. This is because it can be difficult to scale up ferret evaluations to thousands of pathogen isolates. As a result, in some cases, for example, the current selection of seasonal influenza vaccines typically achieves less than 50% vaccine effectiveness (i.e., percent reduction in severe disease in case-finding individuals in vaccinated populations compared to unvaccinated populations).

[0028] The systems and methods described herein can be used to alleviate one or more of the aforementioned shortcomings of conventional CV selection techniques. According to the systems and methods described in the present disclosure, a subset of an initial plurality of machine learning models (also referred to herein as driver models) is used to select one or more molecular sequences (e.g., antigen sequences) that are predicted to be superior in at least one translational axis. The translational axis can represent, for example, an evaluation criterion of the biological response of a human or non-human model to an antigen (e.g., the resulting HAI titer of a mouse exposed to a particular antigen, or the resulting HAI titer of a collected human serum, etc.). The subset of driver models is selected for rational use by first assigning each driver model of the initial plurality of driver models to one class of translational axes, each class of translational axes corresponding to one translational axis of a plurality of translational axes (e.g., at least one of the following: ferret AF, ferret HAI, mouse AF, mouse HAI, human replica AF, human AF, or human HAI).

[0029] In some embodiments, each driver model is trained to predict a molecular sequence that will generate a maximal (e.g., maximized) biological response (e.g., maximized mouse HAI titers) among all circulating pathogen strains in a particular disease season, or generate a response that effectively covers the maximum number of circulating pathogen strains in a particular disease season, based on time series data representing a plurality of molecular sequences and, for each molecular sequence, the circulating duration of pathogen strains that contain that molecular sequence as a native antigen. In some embodiments, for each driver model, a translational model configured to predict biological responses to molecular sequences across multiple translational axes is used to provide feedback in the form of translational response data representing one or more translational responses corresponding to the translational axis classes assigned to the driver model.

[0030] This process is performed over a number of iterations, where in each iteration the driver model updates one or more parameters (often referred to as weights and biases) based on feedback from the translational model. After the number of iterations, a set of trained driver models is selected. The selected set of trained driver models may include, for each class of translational axis, a trained driver model that predicted the molecular sequence that results in the desired (often: highest) aggregate (e.g., averaged) biological response (e.g., immune response) predicted by the translational model for that class of translational axis. For each trained driver model in the set of trained driver models, the antigen predicted by that trained driver model is then applied to a translational model that predicts the response to that antigen for each translational axis.

[0031] Next, a subset of trained driver models from the set of trained driver models is selected. Selecting the subset of trained driver models is based on the trained driver models that, for each translational axis, have the highest aggregate biological response across all pathogen strains of a particular pathogenic season predicted by the translational models for that translational axis. The method may include selecting a trained driver model from the set of trained driver models that predicted the inducing antigen. Each trained driver model from the subset of trained driver models is validated using observational data from human or non-human experiments. If the trained driver model is validated, the trained driver model is used to design a vaccine based on the antigen predicted by the validated trained driver model.

[0032] In the drawings, a particular arrangement or order of schematic elements, such as those representing devices, modules, instruction blocks, and data elements, is shown for ease of explanation. However, those skilled in the art should understand that the particular order or arrangement of the schematic elements in the drawings does not imply that a particular order or sequence of operations, or separation of operations, is required. Moreover, the inclusion of a schematic element in a drawing does not imply that such element is required in all embodiments, or that the configuration represented by such element is not included in or combined with other elements in some embodiments.

[0033] Furthermore, when a connecting element, such as a solid or dashed line or an arrow, is used in the drawings to describe a connection, relationship, or association between two or more other schematic elements, the absence of any such connecting element does not imply that the connection, relationship, or association cannot exist. In other words, some connections, relationships, or associations between elements are not shown in the drawings so as not to obscure the disclosure. In addition, for ease of illustration, a single connecting element is used to represent multiple connections, relationships, or associations between elements. For example, when a connecting element represents communication of signals, data, or instructions, it should be understood by those skilled in the art that such element represents one or more signal paths (e.g., buses) to effect the required communication.

[0034] Reference will now be made in detail to the embodiments, examples of which are illustrated in the accompanying drawings. In the following detailed description, numerous specific details are set forth in order to provide a thorough understanding of the various embodiments described. However, it will be apparent to those skilled in the art that the various embodiments described may be practiced without these specific details. In other instances, well-known methods, procedures, components, circuits, and networks have not been described in detail so as not to unnecessarily obscure aspects of the embodiments.

[0035] Below, several configurations are described, each of which may be used independently of one another or with any combination of the other configurations. However, any individual configuration may not address any of the problems discussed above, or may only address one of the problems discussed above. Some of the problems discussed above may not be completely solved by any of the configurations described herein. Even if a heading is provided, data related to a particular heading may not be found in the section having that heading, but may be found elsewhere in this specification.

[0036] 1 shows an example of a system 100 for designing a vaccine. System 100 includes a computer processor 110. Computer processor 110 includes computer readable memory 111, and computer readable instructions 112. System 100 also includes a machine learning system 150. Machine learning system 150 includes a machine learning model 120. Machine learning system 150 may be separate from computer processor 110 or may be integrated with computer processor 110.

[0037] The computer readable memory 111 (or computer readable medium) may be any data storage technology type suitable for the local technology environment, including semiconductor based memory devices, magnetic memory devices, and the like. The computer readable memory 111 may include, but is not limited to, embedded memory devices and systems, optical memory devices and systems, fixed memory, removable memory, disk memory, flash memory, dynamic random access memory (DRAM), static random access memory (SRAM), electronically erasable programmable read only memory (EEPROM), etc. In one embodiment, the computer readable memory 111 includes code segments having executable instructions.

[0038] In some implementations, the computer processor 110 includes a general-purpose processor. In some implementations, the computer processor 110 includes a central processing unit (CPU). In some implementations, the computer processor 110 includes at least one application specific integrated circuit (ASIC). The computer processor 110 may also include a general-purpose programmable microprocessor, a special-purpose programmable microprocessor, a digital signal processor (DSP), a programmable logic array (PLA), a field programmable gate array (FPGA), a special-purpose electronic circuit, or the like, or a combination thereof. The computer processor 110 is configured to execute program code means, such as computer executable instructions 112. In some implementations, the computer processor 110 is configured to execute the machine learning model 120.

[0039] The computer processor 110 is configured to receive a time series dataset 161. The time series dataset 161 may include data representing one or more molecular sequences and, for each of the one or more molecular sequences, one or more circulating periods of pathogenic strains that include the molecular sequence as a natural antigen. As an illustrative example, the time series dataset 161 may indicate molecular sequences and circulating periods (e.g., specific months, specific seasons of onset, etc.) for A / SINGAPORE / INFIMH160019 / 2016, A / MISSOURI / 37 / 2017, A / KENYA / 105 / 2017, A / MIYAZAKI / 89 / 2017, A / ETHIOPIA / 1877 / 201, A / OSORNO / 60580 / 2017, A / BRISBANE / 1059 / 2017, and A / VICTORIA / 11 / 2017. Although only eight pathogen strains have been described, the time series dataset 161 may contain molecular sequence information and circulation periods corresponding to billions of pathogen strains. The time series dataset 161 is obtained via one or more means, such as wired or wireless communication with a database (including cloud-based environments), fiber optic communication, Universal Serial Bus (USB), read-only memory (CD-ROM), etc.

[0040] In the machine learning system 150, machine learning techniques are applied to train the machine learning model 120, which when applied to input data produces an indication of whether an input data item has a relevant property, such as the probability that the input data item has a particular Boolean property, an estimate of a scalar property, or an estimate of a vector (i.e., an ordered combination of multiple scalars).

[0041] As part of training the machine learning model 120, the machine learning system 150 can form a training set of input data by identifying a positive training set of input data items determined to have the property of interest, and in some embodiments, forms a negative training set of input data items that lack the property of interest.

[0042] The machine learning system 150 extracts configuration values ​​from the input data of the training set; these configurations are variables that are deemed potentially relevant to whether an input data item has a relevant property. An ordered list of configurations of the input data is referred to herein as a configuration vector of the input data. In some implementations, the machine learning system 150 applies dimensionality reduction (e.g., by linear discriminant analysis (LDA), principal component analysis (PCA), learned deep configurations from neural networks, etc.) to reduce the data of the configuration vector of the input data. Reduce the amount of data to a smaller, more representative set of data.

[0043] In some implementations, the machine learning system 150 uses supervised machine learning to train the machine learning model 120, with constituent vectors of a positive training set and a negative training set as input. Various machine learning techniques are used in some implementations, such as linear support vector machines (linear SVMs), boosting other algorithms (e.g., AdaBoost), neural networks, logistic regression, naive Bayes, memory-based learning, random forests, bagged trees, decision trees, boosted trees, or boosted stumps. When applied to the constituent vectors extracted from the input data items, the machine learning model 120 outputs an indication of whether the input data item has a property of interest, such as a Boolean yes / no estimate, a scalar value representing a probability, a vector of scalar values ​​representing multiple properties, or a nonparametric distribution of scalar values ​​representing a discrete and non-empirical fixed number of multiple properties, the indication being explicitly or implicitly represented in a Hilbert space or a similar infinite-dimensional space.

[0044] In some embodiments, the validation set is formed from additional input data other than the input data in the training set that has already been determined to have or lack the property of interest. The machine learning system 150 applies the trained machine learning model 120 to the validation set data to quantify the accuracy of the machine learning model 120. Common metrics applied to measure accuracy include: precision=TP / (TP+FP) and recall=TP / (TP+FN), where precision is how many correctly predicted (TP, i.e., true positives) by the machine learning model 120 out of the total number of predictions made by the machine learning model 120 (TP+FP, i.e., false positives), and recall is how many correctly predicted (TP) by the machine learning model 120 out of the total number of input data items that had the property of interest (TP+FN, i.e., false negatives). The F-score (F-score=2×PR / (P+R)) unifies precision and recall into a single evaluation metric. In some implementations, the machine learning system 150 iteratively retrains the machine learning model 120 until a stopping condition occurs, such as an accuracy measurement indication that the model 120 is sufficiently accurate or a number of training rounds have been performed.

[0045] In some implementations, the machine learning model 120 includes a neural network. In some implementations, the neural network includes a recurrent neural network, RNN. RNN generally describes a class of artificial neural networks in which connections between nodes form a directed graph over time, which can exhibit dynamic behavior over time. Unlike feedforward neural networks, RNNs can use their internal state (memory) to process input sequences. In some implementations, the RNN includes a long short-term memory (LSTM) architecture. LSTM refers to an RNN architecture that has feedback connections and can process entire sequences of data (such as audio or video) rather than just single data points (such as images). The machine learning model 120 may include other types of neural networks, such as convolutional neural networks, radial basis function neural networks, physical neural networks (e.g., optical neural networks), etc. Exemplary methods for designing and training the machine learning model 120 are discussed in more detail below with reference to FIGS. 2A-4.

[0046] The machine learning model 120 is configured to predict one or more molecular sequences and what immunological properties the predicted one or more molecular sequences will confer for future use based on the received time series dataset 161. As an illustrative example, the received time series dataset 161 may include data representing a plurality of pathogen strains, each of which has circulated at one or more time points between January 1, 2014 and December 31, 2018. Assume that a number of viruses circulating between January 1, 2019 and May 31, 2019 are known to be circulating. The machine learning model 120 can predict one or more molecular sequences (e.g., antigens) that generate a maximized aggregate biological response (e.g., maximized mean human HAI titer) among all viruses circulating between January 1, 2019 and May 31, 2019 based on pathogen strains known to be circulating at one or more time points between January 1, 2014 and December 31, 2018. Additionally or alternatively, the machine learning model 120 can predict one or more molecular sequences that generate a biological response that effectively covers (e.g., effectively vaccinates) a maximum number of viruses circulating between January 1, 2019 and May 31, 2019 based on pathogen strains known to be circulating at one or more time points between January 1, 2014 and December 31, 2018. The predicted molecular sequence or sequences can be used to design a vaccine against the virus circulating in the future (such as from January 1, 2019 to May 31, 2019 in the above example).

[0047] 2A-2B show a flow diagram of an architecture 200 for designing a system for designing a vaccine. The architecture 200 includes a plurality of driver models 210, a translational model 220, and a feedback selection module 230. First, the plurality of driver models 210 are launched. Each of the plurality of driver models 210 is configured to generate data representing one or more molecular sequences (e.g., antigens) and a prediction as to what immunological properties each of the molecular sequences will confer for use, as discussed with reference to the machine learning model 120 of FIG. 1. In the illustrated embodiment, the plurality of driver models 210 include a first driver model 210a, a second driver model 210b, a third driver model 210c, a fourth driver model 210d, a fifth driver model 210e, a sixth driver model 210f, a seventh driver model 210g, an eighth driver model 210h, a ninth driver model 210i, and a tenth driver model 210j. Although ten driver models are illustrated, the plurality of driver models 210 may include more or fewer driver models (e.g., five driver models, thirty driver models, one hundred driver models, etc.) One or more of the driver models may be, for example, an RNN as previously described with reference to FIG.

[0048] The translational model 220 is configured to predict biological responses to molecular sequences for multiple translational axes. In the illustrated embodiment, the translational model 220 includes a ferret HAI translational axis 220a, a ferret AF translational axis 220b, a mouse HAI axis 220c, a mouse AF translational axis 220d, and a human replica AF translational axis 220e. Although specific translational axes are illustrated, the embodiments are not limited to these specific translational axes. For example, the translational model may additionally or alternatively include a human HAI translational axis, a human AF translational axis, a human replica HAI axis, or combinations thereof, among others. Some embodiments of the translational model 220 are discussed in more detail below with reference to FIGS. 6-9.

[0049] 2A, each of the driver models of the plurality of driver models 210 is assigned to a particular translational axis of the translational model 220. In the illustrated embodiment, the first driver model 210a and the third driver model 210c are assigned to the ferret HAI translational axis 220a, the second driver model 210b and the sixth driver model 210f are assigned to the ferret AF translational axis 220b, and the fourth driver model 210d and the eighth driver model 210h are assigned to the mouse HAI translational axis 220c. The fifth driver model 210e and the ninth driver model 210i are assigned to the mouse AF translational axis 220d, and the seventh driver model 210g and the tenth driver model 210j are assigned to the human replica AF translational axis 220e.

[0050] Each driver model of the plurality of driver models 210 receives a first time series data set 201. The first time series data set 201 may include a plurality of molecular sequences and a circulating period of a pathogen strain that includes at least one of the plurality of molecular sequences as a natural antigen. As an illustrative example, the first time series data set 201 may include molecular sequences and circulating periods of all observed pathogen strains that were circulating during a period between January 1, 2014 and December 31, 2018 (also referred to as an "epidemic season"). Based on the received first time series data set 201, each driver model of the plurality of driver models 220 may generate output data representing one or more molecular sequences. For example, the output data may represent molecular sequences (e.g., antigens) for each epidemic season of the epidemic season. For each disease season, molecular sequences can be determined by predicting the molecular sequences that will generate a maximized aggregate biological response across all circulating viruses in that disease season and / or that will generate a response that effectively covers (e.g., effectively vaccinates) the maximum number of circulating viruses in that disease season based on phylogenetic data from one or more disease seasons prior to that disease season.

[0051] The translational model 220 can receive output data from each driver model of the plurality of driver models 210 and generate, for each driver model of the plurality of driver models 210, first translational response data representing one or more translational responses corresponding to a particular translational axis assigned to the driver model. In the illustrated example, the translational model 220 can receive output data representing the predicted one or more molecular sequences from the first driver model 210a and predict ferret HAI titers for each molecular sequence of the one or more molecular sequences across all pathogen strains circulating in each disease season according to the ferret HAI translational axis 220a (i.e., for each pathogen strain in a particular disease season, predict the immune response of ferrets exposed to the pathogen strain after being immunized with the predicted molecular sequence).

[0052] The first translational response data corresponding to each driver model of the plurality of driver models 210 is received by a feedback selection module 230, which compares the predicted response for each outbreak season to a threshold response. For example, the feedback selection module 230 can aggregate (e.g., average) the predicted biological responses across all viruses for each outbreak season for each driver model, compare the aggregate response to a threshold aggregate response, and generate an error value based on the comparison. Additionally or alternatively, the feedback selection module 230 can compare the number of effectively vaccinated viruses for each driver model to a threshold number for each outbreak season, and generate an error value based on the comparison. The feedback selection module 230 can then cause each driver model to adjust one or more parameters (such as the weights and biases of the driver model) based on the error value for each outbreak season. This process is repeated for a number of iterations. The number of iterations may be a set number of iterations or may be determined based on a threshold error value (i.e., the process continues until the threshold error value is exceeded). Thus, at one high level: (1) for a particular disease season, each driver model can predict one or more molecular sequences to be used to immunize against the pathogen strains of that particular disease season based on the pathogen strains of the preceding disease season; (2) the performance of each driver model is evaluated for each disease season; and (3) the parameters of each driver model are adjusted based on the performance of the model during each disease season.

[0053] After that number of iterations, the performance of each of the driver models (sometimes referred to herein as trained driver models) is compared to other driver models assigned to the same translational axis as the driver model, and the driver model exhibiting the best performance is selected to generate a selection set of trained driver models 240. For example, after that number of iterations, the aggregate predicted ferret HAI titers of the molecular sequences predicted by the first driver model 210a are compared to the aggregate predicted ferret HAI titers of the molecular sequences predicted by the third driver model, and the feedback selection module 230 can select the driver model that corresponds to the highest aggregate predicted ferret HAI titer (or the highest number of pathogen strains that have been effectively vaccinated against) over all or part of the disease season. In the illustrated embodiment, the selection set of driver models 240 includes the first driver model 210a, the second driver model 210b, the fifth driver model 210e, the seventh driver model 210g, and the tenth driver model 210j.

[0054] 2B, each of the selected set of driver models 240 receives the second time series data set 202 and generates trained output data representing one or more molecular sequences for a particular disease season based on the second time series data set 202. Similar to the first time series data set 201, the second time series data set 202 may include data representing molecular sequences and circulating periods of all observed pathogen strains that were circulating at a given disease season. The disease seasons of the second time series data set 202 may be the same as or different from the disease seasons of the first time series data set 201. Each of the driver models in the selected set of driver models 240 may predict one or more molecular sequences (e.g., antigens) for one or more disease seasons. In some implementations, the predicted one or more molecular sequences are for one of the disease seasons of the temporal period (e.g., the latest disease season). As an illustrative example, assume that the received second time series dataset 202 includes data representing a plurality of pathogen strains, each pathogen strain known to have circulated at one or more time points between January 1, 2014 and April 31, 2018. Each of the driver models in the selected set of driver models 240 can predict one or more molecular sequences (e.g., antigens) that generate a maximized aggregate biological response across all viruses circulating between October 1, 2017 and April 31, 2019 based on pathogen strains known to have circulated in the preceding disease season between January 1, 2014 and September 30, 2017. Additionally or alternatively, each of the driver models in the selected set of driver models 240 may predict one or more molecular sequences that generate a biological response that effectively covers (e.g., effectively vaccinates) the maximum number of viruses circulating between October 01, 2017 and April 31, 2018 based on the pathogen strains known to be circulating in the preceding disease season between January 01, 2014 and September 30, 2017.

[0055] The translational model 220 receives trained output data from each of the driver models in the selected set of driver models 240 and generates second translational response data for each driver model based on the trained output data. The second translational response data represents one or more translational responses across all translational axes of the translational model 220 for each driver model based on one or more predicted molecular sequences of the driver model. As an illustrative example, the translational model 220 can receive trained output data from a first driver model 210a representing one or more molecular sequences. The translational model 220 generates trained output data for ferret HAI titers, ferret AF titers, mouse HAI titers, mouse AF titers, and human replicase titers for one or more molecular sequences predicted by the first driver model 210a across all strains. The second translational response data for each driver model in the selected set of driver models 240 is received by the feedback selection module 230. The feedback selection module 230 can compare the performance of each driver model for each translational axis and select the driver model that performs best in each axis or combination of axes to generate a selected subset of driver models 250. Using the previous example for illustration, with respect to the ferret HAI axis 220a, the feedback selection module 230 can compare the aggregate HAI titers across all pathogen strains circulating between January 1, 2019 and May 31, 2019 for one or more molecular sequences predicted by each of the driver models in the selected set of driver models 240. The feedback selection module 230 can then select the driver model that is found to have the highest aggregate HAI titers across all pathogen strains. In the illustrated embodiment, the selected subset of driver models 250 includes the second driver model 210b and the tenth driver model 210j. One or more of the selected subset 250 of driver models are included in the machine learning models 120 discussed above with reference to FIG.

[0056] Each of the driver models in the selected subset of driver models 250 is then validated based on real-world experimental observations. For example, the second translational response data corresponding to the second driver model 210b is compared to biological responses observed in a human HAI experiment (or a ferret HAI experiment, a mouse HAI experiment, etc.) in which a human subject is vaccinated with one or more molecular sequences predicted by the second driver 210b and exposed to one or more of the pathogen strains circulating between October 1, 2017 and April 31, 2018. The predicted and observed responses are compared by the feedback selection module 230 to generate an error value, which can determine whether one or more of the translational axes corresponding to the second driver model 210b (e.g., the ferret HAI translational axis 220a, if the second driver model 210b was selected based on its performance in the ferret HAI translational axis 220a) are good or poor predictors of human response based on the error value. If the error value meets the error threshold, the one or more molecular sequences predicted by the second driver model 210b can be used to design a vaccine for at least the disease season between October 1, 2017 and April 31, 2018, or even disease seasons following that disease season. For example, if a real-world ferret HAI experiment was used to validate the second driver model 210b, the determined error value can be used to adjust parameters of the translational model 220 or the second driver model 210b, or both.

[0057] 3 shows a flowchart of a method 300 for designing a vaccine. For illustrative purposes, the method 300 is described as being performed by the architecture 200 previously described with reference to FIGS. 2A-2B. The method includes applying a plurality of driver models to a first time series dataset (block 310), training each driver model with the first time series dataset (block 320), selecting a set of trained driver models (block 330), applying a selected set of the trained driver models to a second time series dataset (block 340), and selecting a subset of the trained driver models (block 350).

[0058] At block 310, each driver model of the plurality of driver models 210 receives the first time series data set 201. Based on the received first time series data set 201, each driver model of the plurality of driver models 220 may generate output data representative of one or more molecular sequences.

[0059] At block 320, for each of the driver models 210, the driver model is trained using the translational axis of the translational model 220 assigned to the driver model. FIG. 4 shows a flowchart of a method 400 of training one or more driver models for designing a vaccine. With reference to FIG. 4, the method 400 includes receiving output data from each driver model of the plurality of driver models 210 (block 410), applying the translational model 220 to the output data to generate first translational response data for each driver model of the plurality of driver models 210 according to the translational axis assigned to the driver model (block 420), adjusting, for each driver model of the plurality of driver models 210, one or more parameters of the driver model based on the first translational response data corresponding to the driver model (block 430), and repeating blocks 410-430 for a number of iterations (block 440).

[0060] At block 330, a selected set of driver models 240 is generated for each translational axis of the translational model 220 based on the behavior of the driver models assigned to that translational axis. For example, after that number of iterations, the aggregate predicted ferret HAI titers of the molecular sequences predicted by the first driver model 210a are compared to the aggregate predicted ferret HAI titers of the molecular sequences predicted by the third driver model 210c, and the feedback selection module 230 can select the driver model corresponding to the highest aggregate predicted ferret HAI titer (or the greatest number of pathogenic strains effectively vaccinated against).

[0061] At block 340, each of the selected set of driver models 240 receives the second time series data set 202 and generates learned output data representing one or more molecular sequences for a particular season of onset based on the second time series data set 202.

[0062] At block 350, the translational model 220 receives the trained output data from each of the driver models in the selected set of driver models 240 and generates second translational response data for each driver model based on the trained output data. The second translational response data represents, for each driver model, one or more translational responses across all translational axes of the translational model 220 based on the predicted one or more molecular sequences of the driver model. As an illustrative example, the translational model 220 can receive trained output data from the first driver model 210a representing one or more molecular sequences. The translational model 220 can predict ferret HAI titer, ferret AF titer, mouse HAI titer, mouse AF titer, and human replica AF titer for the one or more molecular sequences predicted by the first driver model 210a. The second translational response data for each driver model in the selected set of driver models 240 is received at the feedback selection module 230. The feedback selection module 230 may compare the performance of each driver model for each translational axis and select the driver model with the best performance in each axis to generate a selected subset of driver models 250.

[0063] Figure 5 shows a diagram depicting the improvements per translational axis compared to traditional techniques for designing vaccines. In an exemplary experiment, five different vaccine candidates were developed that mimic specific instances of the process described above (strains A / MISSOURI / 37 / 2017, A / OSORNO / 60580 / 2017, A / MIYAZAKI / 89 / 2017, A / ETHIOPIA / 1877 / 2017, and A / KENYA / 105 / 2017, respectively, abbreviations MO / 17, OS / 17, MI / 17, ET / 17, and KE / 17). ) and then evaluated against five different translational axes (shown crossed on the x-axis) for the conventionally selected CV A / SINGAPORE / INFIMH160019 / 2016. Each of the five different CVs selected by the systems and methods described herein is shown as a labeled marker on each of the translational axes, slightly offset within each translational axis for ease of viewing. The y-axis shows, for each translational axis, the proportion of March 2018 clinical isolates (later referred to as "seasonal surrogate strains") reported as of April 15, 2018 in the Global Initiative on Sharing All Influenza Data (GISAID) global database, which were predicted to be better protected by a particular antigen than the conventionally selected CV (A / SINGAPORE / INFIMH160019 / 2016), which was the standard of care (SOC) as of March 2018 for H3N2. For example, the left-most column (ferret HAI) shows that the translational model predicted that A / MISSOURI / 37 / 2017 would raise antibodies in ferrets that had uniformly higher HAI titers than conventionally selected CVs against all of these seasonal surrogate strains. As another example, in the right-most column (human serum antibody forensics (AF)), A / ETHIOPIA / 1877 / 2017 and A / OSORNO / 60580 / 2017 were predicted to be non-inferior to conventionally selected CVs. These results, taken together, suggested that these five candidates should show diverse and distinct non-inferior patterns of induced immune responses when assessed by different translational axes.

[0064] Exemplary translational models: 6 illustrates an example of a system 600 for predicting biological responses using machine learning techniques, according to one or more embodiments of the present disclosure. The system 600 can be used as a translational model, as discussed above. The system 600 includes a computer processor 610. The computer processor 610 includes a computer readable memory 611, and computer readable instructions 612. The system 600 also includes a machine learning system 650. The machine learning system 650 includes a machine learning model 620. The machine learning system 650 can be separate from or integrated with the computer processor 610.

[0065] The computer readable memory 611 (or computer readable medium) may include any data storage technology type suitable for the local technology environment, including but not limited to semiconductor-based memory devices, magnetic memory devices and systems, optical memory devices and systems, fixed memory, removable memory, disk memory, flash memory, dynamic random access memory (DRAM), static random access memory (SRAM), electronically erasable programmable read-only memory (EEPROM), etc. In some implementations, the computer readable memory 611 includes code segments having executable instructions.

[0066] In some implementations, the computer processor 610 includes a general-purpose processor. In some implementations, the computer processor 610 includes a central processing unit (CPU). In some implementations, the computer processor 610 includes at least one application specific integrated circuit (ASIC). The computer processor 610 may also include a general-purpose programmable microprocessor, a special-purpose programmable microprocessor, a digital signal processor (DSP), a programmable logic array (PLA), a field programmable gate array (FPGA), a special-purpose electronic circuit, or the like, or a combination thereof. The computer processor 610 is configured to execute program code means, such as computer executable instructions 612. In some implementations, the computer processor 610 is configured to execute the machine learning model 620.

[0067] The computer processor 610 is configured to obtain first molecular sequence data 661 of the first molecular sequence and second molecular sequence data 662 of the second molecular sequence. The first molecular sequence data 661 may include amino acid sequence data of a candidate antigen (e.g., an inoculation strain). The candidate antigen may correspond to, for example, an H3N1 virus. The second molecular sequence data 662 may include amino acid sequence data of a known virus strain against which protection is sought. For example, the second molecular sequence may be a known virus strain that emerged in 2001. In some embodiments, as described in more detail below with reference to FIG. 9, the computer processor 610 is also configured to receive non-human biological response data associated with the first and second molecular sequences. The non-human biological response data may include, for example, a biological response readout (e.g., antibody titer) that is a measure of the biological response of a non-human model (e.g., a mouse, a ferret, a human immune system replica, etc.) to the second molecular sequence after being inoculated with the first molecular sequence. As discussed in further detail below with reference to Figure 9, in some embodiments, the computer processor 610 can code the first molecular sequence data 661 and the second molecular sequence data 662 as amino acid mismatches. Such data is obtained via one or more means, such as wired or wireless communication with a database (including cloud-based environments), fiber optic communication, Universal Serial Bus (USB), read-only memory (CD-ROM), etc.

[0068] In the machine learning system 650, machine learning techniques are applied to train the machine learning model 620, which when applied to input data produces an indication of whether an input data item has a relevant property, such as the probability that the input data item has a particular Boolean property, or an estimate of a scalar property.

[0069] As part of training the machine learning model 620, the machine learning system 650 can form a training set of input data by identifying a positive training set of input data items determined to have the property of interest, and in some embodiments, forms a negative training set of input data items that lack the property of interest.

[0070] The machine learning system 650 extracts configuration values ​​from the input data of the training set, where these configurations are variables that are considered potentially relevant to whether the input data item has the relevant property. The ordered list of configurations of the input data is referred to herein as a configuration vector of the input data. In some implementations, the machine learning system 650 applies dimensionality reduction (e.g., by linear discriminant analysis (LDA), principal component analysis (PCA), learned deep configurations from neural networks, etc.) to reduce the amount of data of the configuration vector of the input data to a smaller, more representative set of data.

[0071] In some implementations, the machine learning system 650 uses supervised machine learning to train the machine learning model 620, with the constituent vectors of the positive and negative training sets as input. Various machine learning techniques are used in some implementations, such as linear support vector machines (linear SVMs), boosting other algorithms (e.g., AdaBoost), neural networks, logistic regression, naive Bayes, memory-based learning, random forests, bagged trees, decision trees, boosted trees, or boosted stumps. When applied to the constituent vectors extracted from the input data items, the machine learning model 620 outputs an indication of whether the input data item has a property of interest, such as a Boolean yes / no estimate, a scalar value representing a probability, a vector of scalar values ​​representing multiple properties, or a nonparametric distribution of scalar values ​​representing a discrete and non-empirical fixed number of multiple properties, the indication being explicitly or implicitly represented in a Hilbert space or a similar infinite-dimensional space.

[0072] In some embodiments, the validation set is formed from additional input data other than the input data in the training set that has already been determined to have or lack the property of interest. The machine learning system 650 applies the trained machine learning model 620 to the validation set data to quantify the accuracy of the machine learning model 620. Common metrics applied to measure accuracy include: precision=TP / (TP+FP) and recall=TP / (TP+FN), where precision is how many correctly predicted (TP, i.e., true positives) by the machine learning model 620 out of the total number of predictions made by the machine learning model 620 (TP+FP, i.e., false positives), and recall is how many correctly predicted (TP) by the machine learning model 620 out of the total number of input data items that had the property of interest (TP+FN, i.e., false negatives). The F-score (F-score=2×PR / (P+R)) unifies precision and recall into a single evaluation metric. In some implementations, the machine learning system 650 iteratively retrains the machine learning model 620 until a stopping condition occurs, such as an accuracy measurement indication that the model 620 is sufficiently accurate or a number of training rounds have been performed.

[0073] In some implementations, the machine learning model 620 includes a neural network. In some implementations, the neural network includes a convolutional neural network. The machine learning model 620 may include other types of neural networks, such as a recurrent neural network, a radial basis function neural network, a physical neural network (e.g., an optical neural network), etc. Specific methods of training a machine learning model according to one or more implementations of the present disclosure are discussed in more detail below with reference to FIGS. 8-9.

[0074] The machine learning model 620 is configured to predict a biological response 663 to the second molecular sequence based on the received data. For example, assume that the first molecular sequence data 661 represents the amino acid sequence of a candidate antigen to be used as a vaccination, and the second molecular sequence data 662 represents the amino acid sequence of a viral strain known to have been circulating in 2012. The machine learning model 620 can predict the biological response (e.g., antibody titers) that the human immune system would generate after encountering the second molecular sequence (e.g., a known viral strain) if the human immune system had been vaccinated with the first molecular sequence (i.e., the candidate antigen).

[0075] 7 is a flow chart illustrating an example of a method 700 for predicting a biological response using machine learning techniques, according to one or more embodiments of the present disclosure. For illustrative purposes, the method 700 is described as being performed by the system 600 for predicting a biological response using machine learning techniques previously discussed with reference to FIG. 6. The method 700 includes receiving first sequence data for a first molecular sequence (block 710), receiving second sequence data for a second molecular sequence (block 720), and predicting a biological response to the second molecular sequence (block 730).

[0076] At block 710, the computer processor 710 receives the first molecular sequence data 161 of the first molecular sequence. As previously indicated, the first molecular sequence data 161 may include amino acid sequence data of a candidate antigen (e.g., an inoculum strain). For example, the candidate antigen may correspond to an H3N1 virus.

[0077] At block 720, the computer processor 720 receives second molecular sequence data 662 for a second molecular sequence. The second molecular sequence data 662 may include amino acid sequence data of a known virus strain against which protection is sought. For example, the second molecular sequence may be a known virus strain that emerged in 2001.

[0078] In some embodiments, the method 700 further comprises: The method further includes coding the two molecular sequence data 662 as amino acid mismatches, for example by comparing regions of similarity between the first and second molecular sequences and coding a value of "1" for each non-matching amino acid pair within the region and a value of "0" for each matching amino acid pair within the region. A dissimilarity between the first and second molecular sequences, as defined by non-matching amino acids at positions within the regions of similarity between the molecular sequences, is then provided to the machine learning model 620.

[0079] In some embodiments, method 700 further includes receiving non-human biological response data associated with the first and second molecular sequences. The non-human biological response data may include, for example, a biological response readout (e.g., antibody titers) that is a measure of the biological response of a non-human model (e.g., mouse, ferret, replica human immune system, etc.) to the second molecular sequence after being inoculated with the first molecular sequence.

[0080] At block 730, the machine learning model 620 predicts a biological response to the second molecular sequence based on the received data. For example, the machine learning model 620 can predict a biological response (e.g., antibody titer) that a human immune system would generate after encountering a second molecular sequence (i.e., a known virus strain) if the human immune system had been inoculated with the first molecular sequence (i.e., a candidate antigen). In some embodiments, the machine learning model 620 is configured to predict a non-human biological response to the second molecular sequence. For example, the machine learning model can predict an antibody titer that an animal's immune system (e.g., a mouse, a ferret, etc.) would generate after encountering the second molecular sequence if the animal's immune system had been inoculated with the first molecular sequence.

[0081] How to train a machine learning model to predict biological responses: A method for training a machine learning model 620 for predicting biological responses will now be described. FIG. 8 illustrates an example of data used to train a machine learning model for predicting biological responses according to one or more embodiments of the present disclosure. As illustrated, data from thousands (or millions, billions, etc.) of experiments is used to build a comprehensive repository of biological response readout data and viral sequence data, for example, from ferret, mouse, and in vitro human immune system replica (e.g., MIMIC®) models. In the illustrated embodiment, the data includes antigen sequence data, viral sequence data, and biological response readouts evaluated by hemagglutination inhibition assay (HAI) and antibody forensics (AF). The viral sequence data includes a panel of known viral strains (referred to as the "readout" panel). The experiments are divided into batches called "cycles" (e.g., cycle 1 and cycle 2). In each cycle, the model system is challenged with selected molecular sequences (e.g., H3 proteins, vaccine formulations, etc.) and evaluated for their ability to generate an immune response against the panel of "readout" viral strains (referred to as the "readout panel"). Viral readout panels are selected to represent a broad sampling of influenza strains that have circulated during a defined time period (e.g., 1950-2016).

[0082] To correlate model experiments with human results, human sera are compared to a "readout" panel. In the illustrated example, for every antigen-strain / readout-strain pair tested in the model system, there is not necessarily a corresponding pair in the human serum measurements. This is because human samples may be collected from vaccinated individuals during a period that does not cover the entire year used for each of the cycles. Thus, the machine learning model is restricted to only those antigens and readouts tested in human sera, and a vector of human readout titers is selected as the target vector for the machine learning model. The human AF readout can be from human sera taken 21 days after vaccination, a time that is usually sufficient for subjects to seroconvert after vaccination.

[0083] Using the data obtained from the above experiments, a model is trained to predict the biological response, hi some embodiments, a linear model is used.

[0084] FIG. 9 is a flow diagram of an example of training a machine learning model for predicting biological responses, according to one or more embodiments of the present disclosure. As shown, a data matrix 900 is first prepared, with each row corresponding to a pair of viral antigens, such as the H3 region of an antigen strain and a "readout" strain. The columns (or configuration) of the matrix include dedicated columns for ferret model AF readout titer 902 and mouse model AF readout titer 903. In some embodiments, the missing titer data is entered at the average value of the column. However, any number of standard methods may be used to enter the missing titer data. The sequence column 901 represents an amino acid sequence difference (SeqDiff) representation between the antigen strain and the "readout" strain within a selected region, which in the illustrated example includes the H3 region of the antigen strain and the "readout" strain. The SeqDiff is created by examining at each position of the H3 amino acid sequence alignment whether that amino acid is the same or different between the antigen strain and the "readout" strain. If the amino acid between the two strains is not the same, a "1" is coded. If the amino acids between the two strains are the same, a "0" is coded. Coding the two sequences as amino acid mismatches essentially creates a protein Hamming distance metric, which generally reflects the number of positions where the corresponding amino acids differ. In some embodiments, columns that are consistently "0" across the training set are discarded. Columns 901, 902, 903 of each row are correlated with the corresponding human titer 904 using linear regression.

[0085] The columns 902, 903 containing the readout titers are, for example, z-score transformed before fitting a linear regression model. The z-scores can represent linearly transformed data values ​​with a mean of zero and a standard deviation of one, and can indicate how many standard deviations the observation is above or below the mean. Because the coding of the SeqDiff representation can be sparse, in some cases, principal component analysis (PCA) is used to reduce the dimensionality of the SeqDiff vector to five components. PCA refers to a statistical procedure that uses an orthogonal transformation to convert a set of observed values ​​of potentially correlated variables into a set of values ​​of linearly uncorrelated variables called principal components. PCA is used to highlight variability, highlight strong patterns in a data set, and reduce a large set of variables to a smaller set without losing significantly more information in the larger set. Linear models are trained on various combinations of the data to better understand the relative ability of mouse titers, ferret titers, and sequence data to predict human responses.

[0086] As explained above, the machine learning model is constructed as a linear model to predict biological responses, however, non-linear relationships may exist between the data configuration and human biological responses. Accordingly, using data from the aforementioned experiments, a model using deep neural networks, or other non-linear models, is constructed that 1) leverages the non-linear relationships in the data to make relatively accurate predictions when compared to the aforementioned linear models, and 2) can make predictions for both animal and human titers simultaneously. Predicting all titers together can take advantage of the recognition that strong signals of immune response are directly encoded in the protein sequences of the antigen and "readout" strains. By training the model to predict both human and animal titers from sequence alone, the machine learning model is forced to explore sequence-function relationships that drive immunogenicity across species. In statistical terms, this is called "borrowing strength" and allows the model to better leverage the large amount of data available in certain models (e.g., the ferret model) to generate more robust predictions for human responses. This approach can accommodate many more viral antigens and the construction of a data matrix with over 13,000 example rows. Similar to the linear model, the SeqDiff table of the H3 region for each virus strain and read strain pair The current data is used as input data.

[0087] In some embodiments, the target vector is the human titer in a linear model, while the nonlinear neural network model can represent a multi-target regression problem for, for example, seven output columns (ferret HAI and AF titers, mouse HAI and AF titers, MIMIC AF, human HAI, human AF). The detection limit for HAI experiments can typically be 40 (or 1:40 in dilution), so any measurements below this value are set to 40. Similarly, if an AF measurement is below 10000, it is set to 10000. HAI is expressed as log2(titer / 10) and AF is expressed as log2(titer). There can be an additional level of complexity in the human data and human replica data, where measurements are taken at the time of inoculation (Day 0) and after seroconversion (Day 21). Thus, human and human replica titers are expressed as log2 fold change of Day 21 / Day 0. If a titer value is missing in the target vector, it is set to zero and the neural network loss function is masked at that position. This ensures that predictions for missing values ​​do not contribute to the fitness of the model during training.

[0088] In some implementations, a neural network with two 128-node dense layers with relu activation and a 7-node dense output layer is used. A portion of the data (e.g., 15 percent of the data) is randomly set aside as a test set, and the neural network is trained for a number of epochs (e.g., 400, 500, 1000, etc.). In some implementations, the following parameters are used: learning rate=0.001; weight decay=0.0001; batch size=128.

[0089] In some embodiments, an L2 loss function is used for the human replica, human AF, and human HAI target vectors. In general, the L2 loss function minimizes the squared difference between the estimated target value and the existing target value. In some embodiments, a Huber loss function is used for the ferret data and the mouse data. In general, the Huber loss function is used in robust regression and may be less sensitive to data outliers than the L2 loss function, at least in some cases. To further bias the model, an explicit weighting approach is used to apply an additional penalty to misclassified human samples. For example, each target loss at each epoch of training is multiplied by the following weights: ferret HAI=0.8; ferret AF=1; mouse HAI=1; mouse AF=1; human HAI=2; human AF=2; MIMIC=1.5.

[0090] In the above description, for illustrative purposes, the pathogenic strain is sometimes described in the context of influenza strains, but the term pathogen is broadly interpreted to include any infectious agent.For example, the pathogenic strain may refer to, among other things, a virus strain, a bacterial strain, a protozoan strain, a prion strain, a viroid strain, or a fungal strain.The pathogenic strain may correspond to respiratory syncytial virus and other paramyxoviruses.The pathogenic strain may correspond, among other things, to whooping cough, diphtheria, or tetanus, etc.

[0091] Although the above description sometimes describes a disease season in relation to influenza season, the term disease season is broadly interpreted to include any discrete time interval. For example, a disease season may refer to, among other things, a particular month, a particular week, a particular set of weeks, a particular set of months, or a particular set of days. Furthermore, successive disease seasons may be constant or may vary. For example, two successive disease seasons may both be one month in length, or one disease season may be one month in length and a second disease season may be four days in length.

[0092] Although the above description describes certain translational axes / biological responses, such as ferret HAI titers and mouse AF titers, embodiments are not so limited. For example, one biological response / translational axis can correspond to antibody characterization, such as affinity and / or avidity for a panel of specific antigens and / or antigen fragments (e.g., protein arrays, phage display libraries, etc.), functional profiling, such as to determine anti-drug antibodies, immune-complementary interactions (e.g., phagocytosis, inflammation, membrane attack), antibody-dependent cellular cytotoxicity (ADCC) or similar Fc-mediated effector functions, profiling of formed immune complexes (e.g., receptor binding profiles), immunoprecipitation assays, or combinations thereof. One biological response / translational axis can correspond to antibody competition, where one target is bound by another antibody, or antiserum. One biological response / translational axis can correspond to that of antibody characterization mentioned above as well as antiserum characterization, which can correspond to functional assays (such as microneutralization assay, hemagglutination inhibition, and neuraminidase inhibition), binding assays (such as hemagglutination assay), enzymatic reaction assays (such as enzyme-linked lectin assay (ELLA)), ligand binding assays (such as binding of sialic acid derivatives and their mimetics), and fluorescent readout assays (such as 20-(4-methylumbelliferyl)-aDN-acetylneuraminic acid (MUNANA) cleavage).

[0093] One biological response / translational axis can correspond to in vivo evaluation utilizing either monoclonal or polyclonal antibodies by passive transfer and / or exogenous expression or transfer achieved by one or more of the following: transfection or endogenous expression via retroviral infection, or host genome modification such as by CRISPR, bibody-to-body fluid transfer, or a combination thereof. One biological response / translational axis can correspond to in vivo evaluation of immunity raised by immunization to evaluate antigenicity. One biological response / translational axis can correspond to characterization such as binding / affinity measurement of linear peptide antigens on major histocompatibility complex (MHC) class I and class II, and also to evaluate productive T cell epitope display for recognition by T cells. One biological response / translational axis can correspond to characterization such as affinity to a panel of antigen fragments (e.g., protein arrays, phage display libraries, etc.) to identify epitopes that are recognized. One biological response / translational axis can correspond to ex vivo and / or in vitro functional profiling, such as to determine T cell responses and / or mediated responses. One biological response / translational axis can correspond to in vivo and / or in situ measurement of proliferation (e.g., abundance in a tissue compartment) in response to natural infection and / or challenge and / or immunization of T cells associated with adaptive responses (e.g., αβ or γδ T cells). One biological response / translational axis can correspond to in vitro and / or ex vivo measurement of specificity of recognition by T cells associated with adaptive responses (e.g., αβ or γδ T cells) in response to natural infection and / or challenge and / or immunization as measured by competition with other epitopes.

[0094] One biological response / translational axis can correspond to in situ, ex vivo and / or in vivo assessment of morphological or physiological changes in response to the pathogen to be protected against or to surrogates such as pseudotyped viruses or bacteria, tissue formation, tissue repair, or tissue invasion. One biological response / translational axis can correspond to differences in in situ, ex vivo protein, gene expression and / or non-coding RNA levels in response to other antigens and / or physiological conditions characterized by biomarkers such as age, sex, frailty, nominal serostatus, race, haplotype, geographic location, etc ... The present invention can accommodate in situ assessment of protection, infection, or other overall physiological responses to naturally occurring or transmitted infection in model organisms, including, but not limited to, rats, rabbits, ferrets, guinea pigs, pigs, cows, chickens, sheep, dolphins, bats, dogs, cats, zebrafish and other bony fish, and non-human primates such as monkeys and apes.

[0095] With respect to responses to intentional infection (i.e., challenge) with homotypic and / or heterotypic infectious agents, including human control challenge studies, one biological response / translational axis can correspond to in situ, ex vivo, and / or in vivo evaluation of proteins or metabolites present in blood or tissues, where the proteins can be cytokines, hormones, or signaling molecules, and the metabolites can be vitamins, cofactors, or other metabolic by-products. One biological response / translational axis can correspond to in situ, ex vivo, and / or in vivo evaluation of the microbiome that is affected by or can affect the immune response. One biological response / translational axis can correspond to functional profiling ex vivo, in vitro phenotype, and / or functional T cell response profiling (receptor expression, cytokine production, cytotoxicity) in response to challenge with antigen alone or in combination with innate immune cells (natural killer (NK) cells, dendritic cells (DCs), neutrophils, macrophages, monocytes, etc.). One biological response / translational axis can correspond to epigenetic analysis performed using samples collected or generated using the techniques or methods described above.

[0096] Although the above description describes several methods and data for training a machine learning model to predict biological responses, other methods and data may also be used. For example, the neural network model may include more or fewer layers than the models described above, and each layer may have more or fewer nodes.

[0097] In the above description, the embodiments have been described with respect to numerous specific details that may vary from embodiment to embodiment. Therefore, the specification and drawings should be regarded as illustrative, and not in a limiting sense. The sole and exclusive indicator of the scope of the present disclosure and what the applicants deem the scope of the present disclosure is the literal and equivalent scope of the set of claims originating from this application, in the specific form originating from such claims, including any subsequent amendments. Any definitions expressly set forth herein for terms contained in such claims shall govern the meaning of such terms used in the claims. In addition, when the term "further comprising" is used in the above description or in the appended claims, what follows this phrase may be additional steps or entities, or sub-steps / sub-entities of the previously cited steps or entities.

Claims

1. A method implemented by one or more computers, comprising: obtaining, for each of a plurality of molecular sequences, a time sequence data set that includes data defining (i) the molecular sequence and (ii) one or more circulating periods of pathogenic strains that include the molecular sequence as a native antigen; processing the time sequence dataset using a driver neural network to generate output data representing a set of candidate molecular sequences; processing the data defining the candidate molecular sequence with a translational neural network to generate, for each candidate molecular sequence generated by the driver neural network, a biological response defining a predicted biological response to the pathogen of an entity vaccinated with the candidate molecular sequence; Selecting a subset of the set of candidate molecular sequences based on the predicted biological responses generated by the translational neural network. The method comprising:

2. The method of claim 1 , wherein the driver neural network comprises a recurrent neural network.

3. The method of claim 1 , wherein the driver neural network comprises a long-short-term memory recurrent neural network.

4. The method of claim 1 , wherein the output data representing the set of candidate molecular sequences includes one or more candidate molecular sequences for each of a plurality of seasons of onset.

5. 5. The method of claim 4, wherein selecting the subset comprises selecting candidate molecular sequences corresponding to a particular outbreak season predicted to achieve a maximized aggregate biological response across all pathogen strains circulating in that season.

6. The selection of the subset is based on candidate subsets corresponding to a particular disease season that are predicted to generate a biological response that effectively immunizes against the maximum number of viruses circulating during that season. The method of claim 4, further comprising selecting a child array.

7. 10. The method of claim 1, wherein the entity is: a ferret, a mouse, a human replica, or a human.

8. 10. The method of claim 1, wherein for each candidate molecular sequence, the predicted biological response of an entity vaccinated with the candidate molecular sequence is characterized as a predicted biological response measured by a hemagglutination inhibition assay.

9. 10. The method of claim 1, wherein for each candidate molecular sequence, a predicted biological response of an entity vaccinated with the candidate molecular sequence is characterized as a predicted biological response measured by enzyme-linked immunosorbent assay.

10. The method of claim 1 , wherein each candidate molecule sequence defines a respective antigen.

11. 10. The method of claim 1, wherein the translational neural network generates, for each candidate molecular sequence, a respective biological response to each of multiple strains of the pathogen.

12. For each candidate molecular sequence: generating an aggregate biological response by aggregating the respective biological responses for each of the plurality of strains of the pathogen; wherein selecting the subset is based on a respective aggregate biological response for each candidate molecular sequence; The method of claim 11 further comprising:

13. Generating an aggregate biological response for each candidate molecular sequence comprises the steps of: determining an average biological response; The method of claim 12, comprising:

14. For each candidate molecule sequence: determining, based on the biological responses for the plurality of strains of the pathogen, the number of strains of the pathogen for which vaccinating the entity with the candidate molecular sequence achieves at least a threshold biological response in the entity; wherein selecting the subset is based on the number of strains of the pathogen for which at least a threshold biological response is achieved in the entity by vaccinating the entity with the candidate molecular sequence; The method of claim 11 further comprising:

15. 10. The method of claim 1, wherein the driver neural network is one of an ensemble of driver neural networks, The method further comprises From the ensemble of driver neural networks, we select the one with the highest performance measure. selecting an appropriate subset of the ensemble of driver neural networks to Selecting molecular sequences for a vaccine against a pathogen using a suitable subset of the ensemble of driver neural networks. The method of claim 1 , comprising:

16. 16. The method of claim 15, The performance measures of each driver neural network in the ensemble are Across each of the translational axes, each of the plurality of translational axes corresponds to (i) a respective species of the entity to be vaccinated, or (ii) a respective measure of the biological response of the entity to be vaccinated, or (iii) both; The method.

17. For each candidate molecular sequence, processing the data defining the candidate molecular sequence with a translational neural network includes: jointly processing data defining (i) candidate molecular sequences and (ii) molecular sequences of strains of pathogens using a translational neural network; The method of claim 1 , comprising:

18. 18. The method of claim 17, the candidate molecule sequence comprises a candidate molecule amino acid sequence; the molecular sequence of the pathogen strain comprises the amino acid sequence of the pathogen strain; and the data defining (i) the candidate molecular sequence and (ii) the molecular sequence of the pathogen strain includes data identifying amino acid mismatches between corresponding positions of the candidate molecular amino acid sequence and the pathogen strain amino acid sequence; The method.

19. The system includes: one or more computers; and one or more storage devices communicatively coupled to the one or more computers, the one or more storage devices storing instructions that, when executed by the one or more computers, cause the one or more computers to perform operations, such as: obtaining, for each of a plurality of molecular sequences, a time sequence data set that includes data defining (i) the molecular sequence and (ii) one or more circulating periods of pathogenic strains that include the molecular sequence as a native antigen; processing the time sequence dataset using a driver neural network to generate output data representing a set of candidate molecular sequences; processing the data defining the candidate molecular sequence with a translational neural network to generate, for each candidate molecular sequence generated by the driver neural network, a biological response defining a predicted biological response to the pathogen of an entity vaccinated with the candidate molecular sequence; Selecting a subset of a set of candidate molecular sequences based on predicted biological responses generated by a translational neural network The system comprising:

20. One or more non-transitory computer storage media having stored thereon instructions for causing one or more computers to perform one or more computer-executed operations, the operations including: obtaining, for each of a plurality of molecular sequences, a time sequence data set that includes data defining (i) the molecular sequence and (ii) one or more circulating periods of pathogenic strains that include the molecular sequence as a native antigen; processing the time sequence dataset using a driver neural network to generate output data representing a set of candidate molecular sequences; For each candidate molecular sequence generated by the driver neural network, the data defining the candidate molecular sequence is translated into a translational neural network to generate a biological response defining a predicted biological response to the pathogen of an entity vaccinated with the candidate molecular sequence. Processing via a network; Selecting a subset of a set of candidate molecular sequences based on predicted biological responses generated by a translational neural network The non-transitory computer storage medium.

Images