Optimizing vaccine production by simulation

Abstract

Methods and systems for selecting a set of peptides from a plurality of peptides for production of a pharmaceutical product are disclosed. A request can be received to produce a vaccine that meets certain requirements, including a desired immune response and inclusion of certain types of peptides. The system can rank the peptides using one or more metrics that take into account immunogenicity and / or manufacturability. Based on the ranking, the system can select a set of peptides to include in a manufacturing simulation process that returns a set of peptides that are predicted to be successfully manufactured. The system refines its selection to a subset of manufacturable peptides based on certain criteria. The iterative process continues until a predefined condition is met, such as convergence of simulation results. Based on these results, the system identifies an optimal or near-optimal set of peptides that can be used for effective pharmaceutical production.

Description

[0001] Cross-reference to related applications

[0002] This application claims the benefit of U.S. Application No. 18 / 612,632, filed March 21, 2024, the entire contents of which are incorporated herein by reference.

[0003] sequence list

[0004] This application contains a sequence list, which is submitted electronically in XML format and is hereby incorporated by full reference. The XML file was created on March 13, 2024, named 146401.093459_SL.xml, and has a size of 2,572 bytes. Background Technology

[0005] Vaccines play a vital role in public health. They are designed to provide protection against disease by exposing the immune system to antigens (usually proteins) produced by pathogens or tumors, with the aim of training an effective adaptive immune response. One method of producing these life-saving vaccines involves generating protein fragments called peptides. Some vaccines directly include synthetic peptides, while others include synthetic nucleic acids that produce peptides upon injection. These peptides are amino acid sequences that act as antigens to trigger an immune response without causing disease. One of the challenges in vaccine production is selecting suitable combinations of peptides that not only activate an immune response but can also be manufactured with a high success rate. Therefore, determining the optimal combination of peptides that is both manufacturable and effective is a major challenge in vaccine development. Consequently, a more efficient method is needed to determine the optimal combination of peptides or nucleic acids for vaccine manufacturing. Summary of the Invention

[0006] This invention discloses a method and system for intelligently selecting peptide groups from a large number of peptides to produce a pharmaceutical product. The method may include the steps of: receiving a request to select peptides (e.g., one or more peptides) from a plurality of peptides to produce a pharmaceutical product; receiving data containing manufacturability information associated with each of the plurality of peptides; receiving data containing immunogenicity information associated with each of the plurality of peptides; and generating peptide groups from the plurality of peptides for production of the pharmaceutical product using a statistical modeling process based on the manufacturability information and information about a second feature; wherein the statistical model optimizes at least one of the sum of immunogenicity or sum of manufacturability associated with the peptide group while satisfying one or more criteria. The method may also include the steps of: ranking the plurality of peptides based on manufacturability information and second feature information associated with each peptide, wherein the second feature is the immunogenicity associated with each peptide; and selecting a first peptide group from the plurality of peptides for inclusion in a simulated manufacturing process, the simulated manufacturing process being part of a statistical modeling process; wherein the one or more criteria include a desired number of long peptides, a desired number of short peptides, and one or more specific target mutations that the drug is intended to effectively combat. The method may include the following steps: generating a second peptide group based on a simulated manufacturing process; anticipating that the second peptide group can pass the simulated manufacturing process; selecting a peptide subgroup from the second peptide group based on an immunogenicity score associated with each peptide and based on one or more criteria; and calculating a polymerization immunogenicity score for the peptide subgroup. The method may also include the following steps: repeatedly performing a simulated manufacturing process on a first peptide group for a certain number of iterations, generating a certain number of simulation results; and determining an average polymerization immunogenicity score associated with the first peptide group based on the number of simulation results. These steps may include calculating the product of the immunogenicity score and the manufacturability score for each peptide; immunogenicity information including the immunogenicity score for each peptide, manufacturability information including the manufacturability score for each peptide; and sorting based on the product of the immunogenicity score and the manufacturability score. The steps may include: receiving a request to select one or more peptides from a plurality of peptides to produce a pharmaceutical product; receiving data associated with the plurality of peptides, the received data including manufacturability information and information on one or more features associated with each of the plurality of peptides; and using a statistical model to determine a peptide group from the plurality of peptides for use in producing a pharmaceutical product based on the manufacturability information and information on at least one of the one or more features.

[0007] Information on one or more features may include one or more of the following: immunogenicity information, expected quantity information of different types of peptides, and specific target mutations that the drug is intended to effectively combat associated with each peptide. Determining the peptide set also includes ranking multiple peptides based on manufacturability information and feature information associated with each peptide; and selecting a first peptide set from the multiple peptides for inclusion in a simulated manufacturing process based on the ranking and one or more criteria. The criteria may include one or more of the following: expected quantity of long peptides, expected quantity of short peptides, and one or more specific target mutations that the drug is intended to effectively combat. The method may include the steps of: generating a second peptide set based on a simulated manufacturing process; anticipating that the second peptide set will pass the simulated manufacturing process; selecting a peptide subset from the second peptide set based on feature scores associated with each peptide and based on one or more criteria; and calculating a polymerization feature score for the peptide set. The method may include the steps of: repeatedly performing a simulated manufacturing process on the first peptide set a certain number of iterations to generate a certain number of simulation results; and determining an average polymerization feature score associated with the first peptide set based on the number of simulation results. Ranking multiple peptides may further include calculating the product of a feature score and a manufacturability score for each peptide, wherein information on at least one feature includes the feature score for each peptide, and manufacturability information includes the manufacturability score for each peptide; and the ranking is based on the product of the feature score and the manufacturability score. The selection of the peptide set may be based on a greedy search algorithm that optimizes objectives associated with the peptide set while satisfying one or more criteria. Attached Figure Description

[0008] Various embodiments according to this disclosure will be described with reference to the accompanying drawings, in which:

[0009] Figure 1 Exemplary system environments based on various implementation schemes, including a vaccine manufacturing simulator, are demonstrated.

[0010] Figure 2 An exemplary process for selecting peptides for vaccine production, based on various implementation schemes, is demonstrated.

[0011] Figure 3 Exemplary processes for simulating the expected immunogenicity of a group of peptides are demonstrated according to various implementation schemes.

[0012] Figure 4 Exemplary processes for simulating peptide manufacturing are shown according to various implementation schemes.

[0013] Figure 5 This is an example diagram showing the distribution of total immunogenicity according to various implementation schemes.

[0014] Figure 6 Exemplary processes for selecting peptides by comparing multiple sorting algorithms are demonstrated according to various implementation schemes.

[0015] Figure 7 This is an example diagram illustrating the different distributions of immunogenicity based on different sorting algorithms under various implementation schemes.

[0016] Figure 8 An exemplary process for selecting peptides for vaccine production, based on various implementation schemes, is demonstrated.

[0017] Figure 9 Components of a computing device that can be utilized according to various embodiments are shown.

[0018] Figure 10 The environment for implementing various aspects according to different implementation schemes is shown.

[0019] Figure 11 The components of the environment in which various implementation schemes can be realized are shown. Detailed Implementation

[0020] In the following description, various embodiments will be described. Specific configurations and details will be set forth for illustrative purposes in order to provide a thorough understanding of the embodiments. However, it will also be apparent to those skilled in the art that the embodiments may be practiced without specific details. Furthermore, well-known features may be omitted or simplified so as not to obscure the described embodiments.

[0021] The methods described and suggested herein relate to the selection of peptides for vaccine production. This invention discloses methods and systems for intelligently selecting peptide groups (e.g., selecting a group of 20 peptides from 100,000 peptides) from a large pool of peptides to produce a pharmaceutical product. Requests may be received to produce vaccines that meet specific requirements while maximizing immunogenicity, said specific requirements including a desired immune response and the inclusion of certain types of peptides (e.g., short peptides, long peptides, combinations of short and long peptides, such as a combination of 14 long peptides and 6 short peptides). In one embodiment, the distinction between short and long peptides is defined by their amino acid counts, with short peptides containing fewer amino acids than long peptides. This difference in length allows short and long peptides to elicit different immune responses. For example, CD8 T cells are typically activated by shorter peptides, typically 8-10 amino acids in length. On the other hand, CD4 T cells are typically activated by longer peptides, for example, 13-25 amino acids. The system can sort peptides using one or more metrics that consider immunogenicity (i.e., the ability to stimulate an immune response) and / or manufacturability (i.e., the likelihood of successful production). Based on this peptide sequencing, the system can select a set of peptides for a manufacturing simulation process, which returns a set of peptides expected to be successfully manufactured. Following the simulation, the system can refine these selections into subsets of manufactureable peptides based on specific criteria, such as peptide type or peptides covering certain mutations, while focusing on maximizing immunogenicity. This iterative process can continue until one or more predefined conditions are met, such as simulation convergence. Based on these results, the system can identify the optimal or near-optimal set of peptides suitable for the production of effective drugs. In one embodiment, the disclosed methods and systems are applicable not only to peptides but also to other biomolecules, such as deoxyribonucleic acid (DNA) and ribonucleic acid (RNA), which exhibit non-random and predictable manufacturing failure rates. The methods described herein for effectively evaluating and optimizing manufacturing processes are also applicable to such biomolecules.

[0022] The disclosed systems and methods for simulating drug manufacturing processes offer several technological advantages. For example, the simulation system can improve the efficiency and accuracy of selecting peptides for vaccine production. By using simulation algorithms, the system can effectively filter a large number of peptides and evaluate them based on their manufacturability and immunogenicity. The system simplifies the peptide selection process and ensures that selected peptides have a higher probability of successful production and effectiveness in stimulating an immune response. This targeted approach reduces the time and resources spent on currently available trial-and-error methods, thereby accelerating vaccine development cycles.

[0023] Furthermore, this system significantly reduces the likelihood of errors. Manual calculations, especially when dealing with large volumes of peptides, are prone to error. Traditionally, such complex tasks rely on the expertise and judgment of skilled professionals. Despite human expertise, errors can still occur, particularly when faced with repetitive and complex calculations. By automating the peptide selection process, this system greatly reduces the chances of human error and produces more reliable and accurate results. In vaccine development, where precision is paramount, even small errors can have significant consequences, potentially affecting the lives of thousands. Automating this process improves reliability and overall efficiency in vaccine development, enabling the delivery of vaccines that meet safety and efficacy standards while minimizing the potential risk of errors.

[0024] Furthermore, the system can run and compare multiple algorithms (such as various ranking algorithms) to determine which produces the best results. The ability to fine-tune the selection process is invaluable, as even slight improvements to the selection algorithm can have a profound impact on patient outcomes. By identifying the most effective algorithms, the system can provide a selected set of peptides with the greatest potential efficacy. When this marginal benefit is scaled up on a global healthcare scale, it could lead to significant advances in public health.

[0025] Figure 1 An exemplary system 100 according to at least one embodiment described herein is illustrated, which can be used to provide functionality related to a manufacturing simulation process to users, applications, clients, or other such entities. The exemplary system 100 may include one or more client devices 102 and a resource provider environment 104, which includes an interface 106, an access manager 108, a resource manager 112, and a manufacturing simulator 116.

[0026] exist Figure 1In the illustrated implementation, the resource provider environment 104 may include multiple resources 114 available to various users. These resources may include any suitable computing or electronic resources useful in a networked computing environment, as they relate to physical or virtual servers or computing instances, data repositories, etc. Users may communicate with these resources using various client devices 102, for example, by sending requests received by an interface 106 of the resource provider environment 104, where the interface 106 may, where appropriate, direct the request information within the environment 104. In at least one implementation, the request information is passed to an access manager 108, which may compare the request-related information with information stored in a user data repository 110 or other such location to attempt to verify the origin of the request and determine that the origin is authorized to access various resources. Once authentication and authorization are verified, the request information can be directed to a resource manager 112 to attempt to identify and allocate one or more suitable resources 114 to process the request. Once allocated, the request may be directed to the allocated resource, rather than initially being directed to resource manager 112.

[0027] In some implementations, a user may wish to perform a task involving selecting peptide groups from a peptide population to produce a pharmaceutical product. For example, manufacturing simulator 116 may receive a request from client device 102 via interface 106 to select a combination of peptides for producing a pharmaceutical product based on specified criteria. Information associated with this request can be directed to manufacturing simulator 116 to perform the simulation task. For example, client device 102 may send a request to select a specific number of peptides targeting a specific mutation, with a clear preference for long and short peptides. Upon receiving this request, manufacturing simulator 116 can perform a simulation and selection process tailored to these specified requirements. Figure 2-8 Let's discuss the features related to the manufacturing simulator 116 in more detail.

[0028] Figure 2 An exemplary process for selecting a first set of peptides from a large number of candidate peptides is illustrated. Figure 2As shown, the initial steps involve input 210, which includes data associated with a peptide pool of N peptides. Input 210 may contain data associated with each peptide, such as a unique identifier 211, a long or short peptide classification 212, a manufacturability score 213 indicating the likelihood of a peptide being successfully manufactured, an immunogenicity score 214 indicating the likelihood of a peptide inducing an immune response, or a combination thereof. In one embodiment, each peptide may also be associated with a solubility score quantifying peptide solubility. In one embodiment, each peptide is associated with one or more variants or mutations covered by a peptide window. When a variant (such as a mutation) is identified, multiple peptide sequences (also referred to as peptide windows) may cover that mutation. For example, the sequences FGLATEKSRWSGSHQ (SEQ ID NO:1) and LATEKSRWSG SHQFE (SEQ ID NO:2) both cover the mutation chr7:140453136:A:T. In one embodiment, input 210 may also include one or more mutations that a pharmaceutical product is intended to cover. For example, in a specific embodiment of a tumor with 10 mutations, input 210 may include details such as information associated with the 10 mutations and which mutations each peptide targets. Information about mutations corresponding to each peptide window may also be included in input 210. In one embodiment, manufacturability score 213 and immunogenicity score 214 may be determined using neural networks or other machine learning algorithms / models. In one embodiment, the manufacturability score may consider properties such as the solubility of the peptide, for example, when multiple peptides are combined together. Although each peptide can be dissolved individually, their combination may alter the solubility characteristics (e.g., may result in insolubility). These machine learning models may be trained to predict these scores for each peptide by taking these peptide characteristics as input.

[0029] Input 210 is passed to peptide sorting module 220, which performs one or more sorting algorithms on a peptide pool of N peptides and selects a first set of P peptides (e.g., 48 peptides from 100,000 candidate peptides). This initial selection may be referred to as the P peptide set. In one embodiment, peptide sorting module 220 is designed to evaluate and sort peptides using multiple metrics. This evaluation can be performed in various ways. In one embodiment, a simple metric can be used to evaluate and sort the peptide pool. For example, one approach is to evaluate peptides based solely on their immunogenicity score 214. Alternatively, the evaluation can be based on a combination of metrics multiplied by the immunogenicity score and the manufacturability score of each peptide (i.e., immunogenicity × manufacturability). In this embodiment, peptide sorting module 220 can sort peptides based on immunogenicity 214, immunogenicity 214 × manufacturability 213, or even immunogenicity × solubility. After determining the metric to use, peptide sorting module 220 sorts the N peptides in input 210. Based on this sorting, a predetermined number of the highest-ranking peptides (i.e., referred to as P peptides) are selected. In one implementation, the peptide sequencing module 220 may incorporate additional constraints when selecting an initial set of P peptides. These constraints may include a specific type of peptide (e.g., a minimum number of long and / or short peptides required) and the desired mutations that the ultimately selected peptides should cover. For example, if a drug is designed to cover tumors with 10 mutations, the goal might be to ensure the successful manufacture of a peptide that covers each of the 10 mutations. That is, the manufacturing simulator can maximize the immunogenicity of the manufactured peptides while ensuring that all 10 mutations are covered by at least one peptide, or that all mutations meet a certain minimum immunogenicity threshold for the manufactured peptides that cover them. For example, the peptide sequencing module 220 may identify the two highest-ranking peptides based on a ranking index. However, if both peptides target the same mutation, potentially leaving other mutations uncovered, the peptide sequencing module 220 may consider not only ranking in subsequent selections but also covering all mutations with at least one peptide, or ensuring that each mutation meets an immunogenicity score threshold.

[0030] In another embodiment, the peptide sorting module 220 can utilize optimization algorithms, such as a greedy search over N peptides, to search for an optimal or near-optimal set of peptides P constrained by one or more objectives. The greedy search may focus on optimizing certain metrics related to immunogenicity and / or manufacturability scores. For example, a greedy search could maximize each peptide i in peptide P. 1- (1-Immunogenicity) i This metric represents maximizing the probability of retaining at least one immunogenic peptide in the P peptide. Greedy search can alternatively maximize each peptide i in the P peptide. Immunogenicity i This metric represents the maximum total immunogenicity of all peptides in the P-peptide set.

[0031] To further illustrate greedy search with an illustrative example, the process can begin by initializing a set of 48 peptides (i.e., P peptides). This initial set can be selected based on metrics such as the highest individual immunogenicity score or the highest (immunogenicity × manufacturability) score, depending on the chosen criteria. In one implementation, the initialization can be organized to cover the target mutations as needed. For example, for each mutation, one or more peptides are selected, and the peptides selected for each mutation are those that produce the highest product of immunogenicity and manufacturability scores. Once an initial set of 48 peptides is established, greedy search iteratively evaluates potential replacements to enhance the selected target. In each iteration, the algorithm explores the possibility of replacing one peptide in the current set with a different peptide from the remaining candidate pool. The selection of a replacement is based on the incremental improvement it provides to the target, 1- (1-Immunogenicity) i For example, a) increasing the probability of having at least one highly immunogenic peptide, calculated as, or b) increasing the sum of the immunogenicity scores of the peptides in the group. If a substitution improves the group relative to the target, then the substitution is performed. In one implementation, a non-greedy substitution algorithm can be used. This substitution algorithm may not select the peptide substitution that brings the most significant improvement. The algorithm can explore new options and may select peptide substitutions that reduce immunogenicity. This exploration can provide possibilities for future substitutions that can collectively improve overall immunogenicity. Using this non-greedy substitution algorithm can provide greater benefit to patients because it is likely to improve immunogenicity, especially when dealing with a large number of patients. This process continues, with the algorithm performing one substitution at a time until no substitution is found that improves the group according to these metrics. In some implementations, a maximum number of iterations or limited computational resources can also be used as a termination criterion. The result is a refined set of 48 peptides that best meet the specific target of maximizing immunogenicity or having the probability of having highly immunogenic peptides.

[0032] After the peptide sequencing module 220 determines the initial selection of the P peptide, the selected peptide can be passed to the expected immunogenicity simulator 230, which selects a subgroup from the P peptide. The immunogenicity simulator 230 purifies the P peptide by selecting which manufactured peptides should be included in the pharmaceutical product (e.g., selecting up to 20 peptides from up to 48 successfully manufactured peptides), which may be referred to as subgroup S for the purposes of discussion. The expected immunogenicity simulator 230 can simulate the manufacturing process and select the S peptide from the peptides that pass through the manufacturing process, while taking into account other constraints, such as the mixing of short / long peptides, and ensuring that each mutation is covered by at least one peptide. For example, the expected immunogenicity simulator 230 may also consider constraints, such as the required number of long / short peptides, when determining which peptides are included in subgroup S from all peptides that survived the manufacturing process. Additionally, this determination is also based on whether the selection effectively covers all mutations, with each mutation covered by at least a certain number of peptides (e.g., each mutation is covered by at least one peptide). In one embodiment, if it is not possible to cover all mutations, a set of short / long peptides can be selected to maximize the number of mutations that can be covered. The expected immunogenicity simulator 230 can further calculate the expected immunogenicity score of the purified S-peptide group. According to... Figure 3-5 The expected immunogenicity simulator 230 was discussed in more detail.

[0033] Figure 2 The process shown is also an iterative process, starting with an input of 210 N-peptides, progressing to the final purification of the S-peptide and the calculation of its expected immunogenicity score. That is, throughout the process, the sorting algorithm and simulation algorithm are applied repeatedly 240 times, and each iteration generates an optimized expected immunogenicity score for the peptide group. This iterative cycle continues until certain criteria are met, such as when the mean or median of the expected immunogenicity scores reaches a stable state. Once the expected immunogenicity scores stabilize, the process ends, and the final stable expected immunogenicity score is then considered the score for the given sorting algorithm. This expected immunogenicity score represents the optimized immunogenicity of the peptide after the iterative simulation process. Figure 6 The iterative process for selecting and refining peptide groups to achieve optimal immunogenicity is further discussed. According to Figure 3 A more detailed discussion of the immunogenicity simulator 230 is provided, including its optimization algorithm and the process for selecting purified S-peptide groups.

[0034] Figure 3 An exemplary simulation process performed by the expected immunogenicity simulator 230 is illustrated. The expected immunogenicity simulator 230 can select a subgroup of purified peptides (e.g., selecting an S peptide from P peptides) based on the results of a sorting algorithm. Figure 3In the example shown, input 310 could be a group of 48 peptides selected from N candidate peptides. Each peptide in this group is associated with specific data, such as peptide type, manufacturability, immunogenicity, and / or solubility. The first phase of the process involves manufacturing simulation of input 310 via manufacturing simulation module 320. This module is designed to simulate the manufacturing process and predict which peptides can be successfully produced. Figure 4 The diagram illustrates an exemplary manufacturing simulation process performed by manufacturing simulation module 320. Peptides that successfully pass the manufacturing simulation are then forwarded to other processing modules for further evaluation. Example immunogenicity calculation module 330 can select 13 long peptides and 7 short peptides as S from the successfully manufactured peptides, such that 5 mutations are covered by at least one peptide, and the overall immunogenicity of the 20 peptides is maximized.

[0035] Figure 4 An exemplary manufacturing simulation process is illustrated. The process begins with 48 peptides, each assigned a corresponding manufacturability score, representing the likelihood of the peptide being successfully produced through the manufacturing process. In one embodiment, a Bernoulli trial is used in this simulation process. A Bernoulli trial is a randomized experiment with two possible outcomes, such as "success" and "failure." In this case, the trial is used to determine whether each peptide passes or fails the manufacturing simulation. The process works by generating random numbers based on a Bernoulli distribution (e.g., generating random numbers between 0 and 1) for each peptide in each iteration of the simulation. If the generated number is greater than the peptide's manufacturability score, the peptide is considered to have failed the simulation. Conversely, if the generated number is less than the manufacturability score, the peptide is considered to have passed the simulation and is predicted to be manufactured in the next iteration.

[0036] To illustrate this process, Figure 4 Taking peptide number 1 in the group as an example, its manufacturability score is 0.35. In the first simulation, for example, if a number of 0.7 is generated, the peptide is considered to fail and cannot be manufactured because the generated number is higher than the manufacturability score. In the second simulation, a number of 0.5 might be generated, which would result in another failure. However, in the Xth iteration, a number of 0.2 might be generated, which is lower than the manufacturability score, so the peptide passes the simulation. This process is repeated for each peptide in the group, eventually producing a set of peptides that are expected to pass each round of manufacturing simulations. For illustrative purposes, Figure 4 The total immunogenicity presented is calculated only for the peptides shown. In practice, other peptides may also survive the simulation, and the total immunogenicity (or the probability of having at least one highly immunogenic peptide, calculated as 1-) will be calculated. (1-Immunogenicity) i This will include immunogenicity scores for all peptides manufactured using the simulation method. (e.g.) Figure 3As shown, it is anticipated that these simulated peptide groups can be further refined and processed.

[0037] Continue the discussion Figure 3 Peptides passing through each manufacturing simulation 320 are sent to an immunogenicity calculation module 330, which calculates an immunogenicity score for peptide selection. In one embodiment, the number of peptides successfully passing through the manufacturing simulation module 320 may exceed the number expected for drug production. To address this, the immunogenicity calculation module 330 can select a subset from these peptides by sorting and selecting those with the highest immunogenicity scores. In one embodiment, selecting a subset from these peptides may involve considering the required number of a certain type of peptide or the desired mutation to be covered. In this case, the peptides passing through the manufacturing simulation may first be categorized by type or target mutation. From each category, some of the best-performing peptides (e.g., peptides with higher immunogenicity scores or (immunogenicity × manufacturability) scores) may be selected to form a refined subset. In one embodiment, the selection of the S peptide is based on both an indicator score (e.g., an immunogenicity score or (immunogenicity × manufacturability) score) and a target mutation. For example, a peptide may be associated with a higher indicator score (e.g., an immunogenicity score). However, selecting such a peptide may result in a mutation not being covered. In contrast, another peptide with a lower immunogenicity score may be able to cover the mutation. Although the latter peptide has a lower immunogenicity score, it may be the preferred choice because it is necessary to ensure that all mutations are effectively targeted, even if this means selecting a peptide with a lower index score. This purified subset (which may be referred to herein as the S peptide subset) is then used to calculate the polymeric immunogenicity score. In some embodiments, the number of peptides produced by manufacturing the simulated peptides may not reach the required number (e.g., less than the S count). In this case, experts in the field can design and use heuristic methods to add additional peptides to reach the required number of S peptides. After the S peptide purified subset is determined, the immunogenicity calculation module 330 can calculate the total immunogenicity of the S peptide subset. Figure 3 As shown, this iterative process can be performed multiple times until the distribution of the polymerase chain score stabilizes. That is, the iteration will continue until the median or mean of the polymerase chain score converges. In some implementations, the termination criterion may be reaching a certain number of iterations. Based on the simulation results from multiple iterations, the expected immunogenicity of the input 310 P-peptide set can be calculated.

[0038] For example, consider the group of 48 peptides represented in input 310. These peptides can undergo a simulated manufacturing process performed by the manufacturing simulation module 320. After one simulation iteration, it is expected that 15 long peptides and 10 short peptides will be successfully manufactured. If the goal is to select 20 peptides for drug production, including a combination of 14 long peptides and 6 short peptides, the immunogenicity calculation module 330 can select the top 14 long peptides with the highest immunogenicity scores from the 15 available peptides, and similarly select the top 6 short peptides with the highest immunogenicity scores from the 10 available short peptides. This selection forms a group of refined S peptides, including 14 long peptides and 6 short peptides. The immunogenicity module 330 can then calculate a polymeric immunogenicity score by summing the immunogenicity scores of the selected S peptides. This loop starts again from input 310, and in each iteration, a new polymeric immunogenicity score is generated. After a series of such iterations, the expected immunogenicity score of the peptide group of 48 peptides is determined. Figure 5 An example distribution of the polymeric immunogenicity score generated by this simulation process is shown.

[0039] Figure 5 An exemplary histogram obtained by performing, for example, 1,000 iterations is shown. The histogram is structured such that the x-axis represents the sum of immunogenicity and the y-axis represents the iteration frequency. Each iteration contributes a data point to the histogram by calculating the polymerization immunogenicity score of the S-peptide. After 1,000 iterations, Figure 5 The histogram in the figure visually represents the distribution of the total immunogenicity. Based on this distribution, the expected total immunogenicity is marked with a vertical line (510) in the figure. In this example, the expected total might be approximately 3.2. This expected total immunogenicity is then considered as a P-peptide or... Figure 4 The expected total immunogenicity of 48 peptides in the sample.

[0040] Figure 6An exemplary process for selecting peptide groups from a larger peptide pool using a vaccine manufacturing simulator is illustrated. The process begins with a large number of candidate peptides as input 610, potentially exceeding 100,000, which may be referred to as the N-peptide pool. The peptides in this pool are then evaluated and sorted by a peptide sorting module 620. The sorting module can sort the N-peptides according to various criteria, such as immunogenicity or composite indicators, such as the product of immunogenicity and manufacturability. Following the sorting process, the peptide sorting module 620 can select a preliminary set of P-peptides for further refinement. The selection may also consider one or more other constraints, such as a minimum number of short / long peptides and one or more mutations to be covered. In one embodiment, the peptide sorting module 620 may employ an optimization algorithm, such as a greedy replacement search, to identify the optimal set of P-peptides. Each sorting method, whether based on a specific metric or through optimization, is considered a sorting algorithm, such as sorting algorithm A 630 and sorting algorithm B 631. For example, sorting algorithm A 630 can sort peptides based on the product of immunogenicity and manufacturability, as well as other constraints (e.g., short / long peptides and mutations to be covered), while sorting algorithm B 631 can use a greedy search method to select P peptides. This vaccine manufacturing simulator aims to utilize various algorithms so that results can be compared and the effectiveness of each algorithm can be evaluated. The goal is to determine the algorithm that provides optimal performance in the context of vaccine manufacturing (e.g., maximizing the immunogenicity of the S peptide selected for manufacturing the drug product), while ensuring that each mutation is covered by at least one peptide.

[0041] After sorting and initial selection of P peptides, each of these peptides undergoes a series of iterative processes, such as iterations 690 and 691. These processes aim to calculate the expected total immunogenicity of the entire P peptide group. Each iteration involves a manufacturing simulator, such as 640 and 641, to simulate the manufacturing process of the P peptides. For each round of simulation, a subset of P peptides survives the manufacturing simulation, and these surviving peptides are expected to be manufactured. If the number of surviving peptides exceeds the number required for drug production, they can be reduced according to one or more constraints, such as selecting the peptides with the highest immunogenicity ranking while ensuring a threshold number of short / long peptides that can cover each mutation and / or ensuring a threshold immunogenicity score for each mutation. The resulting purified peptide subgroup can be referred to as the S peptide subgroup. For this subgroup, a total immunogenicity score is calculated, which marks the completion of one iteration in iterations 690 and 691.

[0042] These iterations are repeated many times, possibly tens of thousands or more, until a convergence point is reached. Convergence may occur when the distribution is stable, for example, when the mean or median of the distribution converges. At the end of the iteration, the expected total immunogenicity of the selected P peptides can be determined. The result of each iteration contributes to the overall result of a particular sorting algorithm, and multiple iterations of the sorting algorithm can be performed. For example, in the case of a greedy search sorting algorithm, each iteration may identify a different set of optimal P peptides. The vaccine manufacturing simulator continuously executes sorting algorithms (e.g., 630 and 631) and simulation processes, generating the expected total immunogenicity for each subgroup of purified S peptides. Using the sorting algorithm determination module 670, the sorting algorithm exhibiting the best performance can be selected to select peptides for drug production. To illustrate the results of applying different sorting algorithms in the vaccine manufacturing simulation, Figure 7 It depicts the different results of different distributions generated based on different sorting algorithms.

[0043] Figure 7 An exemplary histogram showing simulation results generated based on various sorting algorithms is shown. Figure 7 The histogram shown is structured with the x-axis representing the sum of immunogenicity and the y-axis showing the frequency of a specific immunogenicity sum during the simulation. In this histogram, there are two distributions represented by different contours. One contour, filled with blanks, corresponds to the results of sorting algorithm Y, and the other, drawn with vertical lines, represents the results of sorting algorithm X. The histogram includes bars of varying heights within the range of immunogenicity sums, where the height associated with each bar reflects the frequency of a specific sum observed in the simulation. The results show a difference between the two sorting algorithms, with algorithm X tending to predict a set of peptides with a higher expected immunogenicity sum of approximately 5, as shown by vertical line 720. In contrast, the blank-filled pattern of algorithm Y represents a lower expected immunogenicity sum of approximately 3.4, as shown by vertical line 710. From the results, it can be inferred that sorting algorithm X is more likely to select a group of peptides with higher cumulative immunogenicity compared to sorting algorithm Y. This may indicate that, assuming a higher immunogenicity sum is desirable for vaccine efficacy, algorithm X is more effective for this specific objective.

[0044] In one implementation, a pooling algorithm is further applied to the purified subgroups of S-peptides to further improve vaccine efficacy. For example, the S-peptides can be divided into different pools, each designed to cover a specific mutation or variant. Within each pool, the selection of peptides depends not only on their high individual scores but also on the degree to which they combine and interact with each other, such as synergistic or antagonistic effects. For example, peptides that enhance each other's efficacy or stability when mixed are grouped together, while those that might hinder each other's performance are separated. For example, some peptides are soluble when alone but become insoluble when mixed. In this case, these peptides might be assigned to separate pools because they cannot be used in pharmaceutical products when combined. This simulation increases the probability that the peptides available for pooling support multiple pooling configurations, thus eliminating the need to exclude highly immunogenic peptides simply because there is no pool where a highly immunogenic peptide can be placed.

[0045] Figure 8 Exemplary methods 800 that can be used according to various embodiments described herein are shown. It should be understood that, with respect to any process described herein, unless expressly stated otherwise, additional, fewer, or alternative steps may be performed in a similar or alternative order or in parallel within the scope of various embodiments.

[0046] Process 800 may begin by receiving a request 802 to select one or more peptides from a peptide pool to create a pharmaceutical product. Following this, the vaccine manufacturing simulation system may receive 804 or retrieve peptide-related data. This data includes manufacturability and immunogenicity information associated with each peptide. The system may select an initial set of peptides 806 based on a ranking algorithm that ranks multiple peptides according to information about manufacturability and immunogenicity. To further refine the initial set of peptides, the system may select a refined peptide group 808 based at least in part on the manufacturing simulation process. The system may determine 810 a refined peptide group for producing the pharmaceutical product from the multiple peptides based on manufacturability and immunogenicity information.

[0047] Computing resources (such as servers) that may have software and / or firmware updated in this manner will generally include at least a set of standard components configured for general operation, although various proprietary components and configurations may also be used within the scope of various embodiments. Figure 9Components of an example computing device 900 that can be utilized according to various embodiments are shown. As is known for computing devices, a computer will have one or more processors 902, such as a central processing unit (CPU), a graphics processing unit (GPU), etc., which one or more processors are electronically and / or communicatively coupled to various components using various buses, traces, and other such mechanisms. Processor 902 may include memory registers 906 and cache memory 904 for storing instructions, data, etc. In this example, chipset 914 (which in some embodiments may include a northbridge and a southbridge) may work with various system buses to connect processor 902 to components such as system memory 916 in the form of physical RAM or ROM, which may include code for the operating system and various other instructions and data used to operate the computing device. The computing device may also include or communicate with one or more storage devices 920 (such as hard disk drives, flash drives, optical storage devices, etc.) for persistent storage of data and instructions similar to or other than those stored in the processor and memory. The processor 902 can also communicate with various other components via a chipset 914 and an interface bus (or graphics bus, etc.), which may include communication devices 924 (such as a cellular modem or network card), media components 926 (such as a graphics card and audio components), and peripheral interfaces 930 for connecting peripheral devices (such as printers, keyboards, etc.). It may also include at least one cooling fan 932 or other such temperature regulation or reduction components, which may be driven by the processor or triggered by various other sensors or components on or off the device. Various other or alternative components and configurations known in the art for computing devices may also be utilized.

[0048] In some embodiments, at least one processor 902 can obtain data from physical memory 916 (such as a dynamic random access memory (DRAM) module) via a coherence configuration. It should be understood that various architectures can be utilized for such a computing device across the range of embodiments, and these architectures may include different choices, numbers, and parameters of buses and bridges. Data in memory can be managed and accessed by a memory controller (such as a DDR controller) via a coherence configuration. In at least some embodiments, data may be temporarily stored in a processor cache 904. The computing device 900 can also support multiple I / O devices using a set of I / O controllers connected via an I / O bus. I / O controllers may be present to support corresponding types of I / O devices, such as Universal Serial Bus (USB) devices, data storage devices (e.g., flash or disk storage devices), network cards, high-speed peripheral component interconnect (PCIe) cards or interfaces 930, communication devices 924, graphics or audio cards 926, and direct memory access (DMA) cards, and other such options. In some embodiments, components such as processors, controllers, and caches may be configured on a single card, board, or chip (i.e., a system-on-a-chip implementation), while in other embodiments, at least some of the components may be located in different locations, etc.

[0049] The operating system (OS) running on the processor 902 helps manage the various devices that can be used to provide input to be processed. For example, this can include enabling interaction with various I / O devices using associated device drivers, which may be related to data storage devices, device communications, user interfaces, etc. The various I / O devices will typically be connected via various device ports and communicate with the processor and other device components through one or more buses. Specific types of buses may exist that provide communication according to specific protocols, such as Peripheral Component Interconnect (PCI) or Small Computer System Interface (SCSI) communication, and other such options. Communication can occur using registers associated with corresponding ports, including registers such as data input and data output registers. Memory-mapped I / O can also be used for communication, where a portion of the processor's address space is mapped to a specific device, and data is written directly to and from that portion of the address space.

[0050] For example, such a device can be used as a server in a server cluster or data warehouse. Server computers often need to perform tasks outside of the CPU and main memory (i.e., RAM) environment. For example, a server may need to communicate with external entities (e.g., other servers) or use an external processor (e.g., a general-purpose graphics processing unit (GPGPU)) to process data. In such cases, the CPU may interact with one or more I / O devices. In some cases, these I / O devices may be dedicated hardware designed to perform specific roles. For example, an Ethernet network interface controller (NIC) can be implemented as an application-specific integrated circuit (ASIC) that includes digital logic operable to send and receive data packets.

[0051] In illustrative embodiments, the host computing device is associated with various hardware components, software components, and corresponding configurations that facilitate the execution of I / O requests. One such component is an I / O adapter that inputs and outputs data along a communication channel. In one aspect, the I / O adapter device may communicate as a standard bridge component to facilitate access between various physical and simulated components and the communication channel. In another aspect, the I / O adapter device may include an embedded microprocessor to allow the I / O adapter device to execute computer-executable instructions relating to the implementation of management functions or one or more such management functions, or to execute other computer-executable instructions relating to the implementation of the I / O adapter device. In some embodiments, the I / O adapter device may be implemented using multiple discrete hardware elements, such as multiple cards or other devices. A management controller may be configured in such a way that it is electrically isolated from any other components in the host device besides the I / O adapter device. In some embodiments, the I / O adapter device is externally attached to the host device. In some embodiments, the I / O adapter device is internally integrated into the host device. The I / O adapter device may also communicate with an external communication port component to establish a communication channel between the host device and one or more network-based services or other network-attached or directly attached computing devices. Illustratively, the external communication port component may correspond to a network switch, sometimes referred to as a top-of-rack (TOR) switch. The I / O adapter device can utilize the external communication port component to maintain a communication channel between one or more services (such as health check services, financial services, etc.) and the host device.

[0052] The I / O adapter device can also communicate with a Basic Input / Output System (BIOS) component. The BIOS component may include non-transient executable code (often referred to as firmware), which can be executed by one or more processors and is used to initialize and identify system devices such as video display cards, keyboards and mice, hard disk drives, optical disk drives, and other hardware on the host device. The BIOS component may also include or locate bootloader software that will be used to boot the host device. For example, in one embodiment, the BIOS component may include executable code that, when executed by a processor, causes the host device to attempt to locate a Preboot Execution Environment (PXE) boot software. Additionally, the BIOS component may include or utilize hardware latches electrically controlled by the I / O adapter device. Hardware latches can restrict access to one or more aspects of the BIOS component, thereby controlling modifications or configuration of the executable code maintained within the BIOS component. The BIOS component may connect to (or communicate with) multiple additional computing device resources such as processors, memory, etc. In one embodiment, such computing device resources may be physical computing device resources that communicate with other components via communication channels. A communication channel may correspond to one or more communication buses, such as shared buses (e.g., processor bus, memory bus), point-to-point buses (e.g., PCI or PCI Express buses), etc., on which components of the bare-metal host device communicate. Other types of communication channels, communication media, communication buses, or communication protocols (e.g., Ethernet communication protocols) may also be utilized. Additionally, in other embodiments, one or more of the computing device resource components may be virtualized hardware components emulated by the host device. In such embodiments, an I / O adapter device may implement a management process in which the host device is configured with physical or emulated hardware components based on various standards. The computing device resource components may communicate with the I / O adapter device via a communication channel. Furthermore, the communication channel may connect a PCI Express device to the CPU via a northbridge or host bridge, and other such options.

[0053] One or more controller components may communicate with the I / O adapter device via a communication channel for managing hard disk drives or other forms of memory. An example of a controller component could be a SATA hard disk drive controller. Similar to a BIOS component, a controller component may include hardware latches electrically controlled by the I / O adapter device or utilize their benefits. Hardware latches may restrict access to one or more aspects of the controller component. Illustratively, hardware latches may be controlled together or independently. For example, the I / O adapter device may selectively disable hardware latches for one or more components based on a trust level associated with a particular user. In another example, the I / O adapter device may selectively disable hardware latches for one or more components based on a trust level associated with the author or distributor of executable code to be executed by the I / O adapter device. In a further example, the I / O adapter device may selectively disable hardware latches for one or more components based on a trust level associated with the component itself. The host device may also include additional components that communicate with one or more of the illustrative components associated with the host device. Such components may include devices, such as one or more controllers combined with one or more peripheral devices, such as hard disks or other storage devices. Additionally, other components of the host device may include another set of peripheral devices, such as a graphics processing unit (“GPU”). Peripheral devices may also be associated with hardware latches for restricting access to one or more aspects of the components. As mentioned above, in one embodiment, the hardware latches may be controlled together or independently.

[0054] As discussed, different methods can be implemented in various environments based on the described embodiments. For example, Figure 10Examples of environments 1000 for implementing various aspects according to various embodiments are shown. As will be understood, although a web-based environment is used for illustrative purposes, different environments may be used to implement various embodiments as appropriate. The system includes an electronic client device 1002, which may include any suitable device operable to send and receive requests, messages, or information on a suitable network 1004 and to transmit information back to a user of the device. Examples of such client devices include personal computers, mobile phones, handheld messaging devices, laptop computers, set-top boxes, personal data assistants, e-book readers, etc. The network may include any suitable network, including intranets, the Internet, cellular networks, local area networks, or any other such networks or combinations thereof. The components used in such systems may depend at least in part on the type of network and / or environment selected. Protocols and components used for communication via such networks are well known and will not be discussed in detail herein. Communication on the network may be implemented via wired or wireless connections and combinations thereof. In this example, the network includes the Internet because the environment includes a web server 1006 for receiving requests and providing content in response to those requests. However, for other networks, alternative devices for similar purposes may be used, as will be apparent to those skilled in the art.

[0055] The illustrative environment includes at least one application server 1008 and a data storage area 1010. It should be understood that there may be several application servers, layers, or other elements, processes, or components, which may be chained or otherwise configured and can interact to perform tasks such as retrieving data from appropriate data storage areas. As used herein, the term "data storage area" refers to any means or combination of means capable of storing, accessing, and retrieving data, which may include any combination and number of data servers, databases, data storage devices, and data storage media in any standard, distributed, or clustered environment. Application server 1008 may include any suitable hardware and software for integration with data storage area 1010 as needed to perform aspects of one or more applications for client devices, and for handling most data access and business logic for the applications. The application server provides access control services in cooperation with the data storage area and is capable of generating content, such as text, graphics, audio, and / or video, to be delivered to the user; in this example, this content may be provided to the user by web server 1006 in the form of HTML, XML, or another suitable structured language. The processing of all requests and responses, as well as the delivery of content between client device 1002 and application server 1008, can be handled by web server 1006. It should be understood that the web server and application server are not necessary and are merely example components, as the structured code discussed herein can be executed on any suitable device or host machine as discussed elsewhere herein.

[0056] Data storage area 1010 may include several separate data tables, databases, or other data storage mechanisms and media for storing data related to specific aspects. For example, the illustrated data storage area includes a mechanism for storing peptide 1012 or peptide representation and analysis data 1016, which can be used to provide content specific to the production side. The data storage area is also shown as including a mechanism for storing characteristic data for peptide 1014. It should be understood that many other aspects may exist that may need to be stored in the data storage area, such as manufacturing data or other training data, which may be stored, as appropriate, in any of the mechanisms listed above or in another mechanism within data storage area 1010. Data storage area 1010 can be operated by logic associated with it to receive instructions from application server 1008 and, in response to such instructions, obtain, update, or otherwise process data. In one example, a user may submit a request for peptide synthesis. In this case, the data storage area can be used to access peptide information, characteristic data, and analysis data to obtain information about whether the peptide is synthetic. The information can then be returned to the user, such as in the form of a list of results on a webpage, which the user can view via a browser on user device 1002.

[0057] Each server will typically include an operating system that provides executable program instructions for the general administration and operation of the server, and will typically include a computer-readable medium storing instructions that, when executed by the server's processor, allow the server to perform its intended functions. Suitable implementations of the server's operating system and general functions are known or commercially available, and these implementations are readily apparent to those skilled in the art, particularly in accordance with this disclosure.

[0058] In one embodiment, the environment is a distributed computing environment utilizing several computer systems and components interconnected via communication links using one or more computer networks or direct connections. However, those skilled in the art will understand that such a system can be used in environments with... Figure 10 The system shown in the image operates just as well with fewer or more components. Therefore, Figure 10 The description of system 1000 in this document should be considered illustrative in nature and is not limited to the scope of this disclosure.

[0059] Figure 11An example environment 1100 is shown in which various embodiments can be implemented. In this example, a user is able to submit a request to a multi-tenant resource provider environment 1106 across at least one network 1104 using a client device 1102. The client device may include any suitable electronic device operable to send and receive requests, messages, or other such information over a suitable network and to transmit information back to the user of the device. Examples of such client devices include personal computers, tablet computers, smartphones, laptop computers, etc. The at least one network 1104 may include any suitable network, including intranets, the Internet, cellular networks, local area networks (LANs), or any other such networks or combinations, and communication on the network may be enabled via wired and / or wireless connections. The resource provider environment 1106 may include any suitable components for receiving requests and returning information or performing actions in response to such requests. For example, the provider environment may include web servers and / or application servers for receiving and processing requests and then returning data, web pages, videos, audio, or other such content or information in response to the requests.

[0060] In various embodiments, the provider environment may include multiple types of resources that can be used by multiple users for various purposes. As used herein, computing and other electronic resources utilized in the network environment may be referred to as "network resources." For example, these may include servers, databases, load balancers, routers, etc., which can perform tasks such as receiving, transmitting, and / or processing data and / or executing instructions. In at least some embodiments, at least for a defined period of time, all or part of a given resource or set of resources may be allocated to a specific user or assigned to a specific task. Sharing these multi-tenant resources from the provider environment is commonly referred to as resource sharing, web services, or "cloud computing," and other such terms, depending on the specific environment and / or implementation. In this example, the provider environment includes multiple resources 1114 of one or more types. For example, these types may include: application servers operable to process instructions provided by users, or database servers operable to process data stored in one or more data storage areas 1116 in response to user requests. As known for such purposes, users may also reserve at least a portion of the data storage in a given data storage area. Methods for enabling users to reserve various resources and resource instances are well known in the art, so this document will not discuss the detailed description of the entire process or the explanation of all possible components.

[0061] In at least some embodiments, a user wishing to utilize a portion of resource 1114 can submit a request, which is received by interface layer 1108 of provider environment 1106. The interface layer may include an application programming interface (API) or other exposed interfaces that enable users to submit requests to the provider environment. Interface layer 1108 in this example may also include other components, such as at least one web server, routing components, load balancers, etc. When a request to configure resources is received by interface layer 1108, information for that request can be directed to resource manager 1110 or other systems, services, or components configured to manage user accounts and information, resource configuration and usage, and other such aspects. Resource manager 1110 receiving the request can perform tasks such as authenticating the identity of the user submitting the request and determining whether the user has an existing account with the resource provider, where account data may be stored in at least one data store 1112 within the provider environment. Users can provide any of a variety of types of credentials to authenticate their identity to the provider. These credentials may include, for example, username and password pairs, biometric data, digital signatures, or other such information. The provider can verify this information based on information stored for the user. If a user has an account with appropriate permissions, status, etc., the resource manager can determine if there are sufficient resources available to satisfy the user's request, and if so, can configure resources or otherwise grant access to corresponding portions of those resources for the user's use, based on the amount specified in the request. For example, this amount could include the capacity to process a single request or perform a single task, a specified time period, or a cyclical / updatable period, and other such values. If the user does not have a valid account with the provider, the user account cannot access the resource type specified in the request, or other such reasons prevent the user from obtaining access to such resources, a message can be sent to the user enabling them to create or modify an account, or change the resource specified in the request, and other such options.

[0062] Once a user is authenticated, an account is verified, and resources are allocated, the user can utilize the allocated resources for specified capabilities, data transfer volumes, time periods, or other such values. In at least some embodiments, the user can provide a session token or other such credentials in subsequent requests to enable those requests to be processed on the user's session. The user can receive a resource identifier, a specific address, or other such information that enables the client device 1102 to communicate with the allocated resources without having to communicate with the resource manager 1110, at least until changes occur in aspects such as changes to the user account, the user no longer being granted access to the resources, or other such changes.

[0063] In this example, Resource Manager 1110 (or other such system or service) can also act as a virtual layer for hardware and software components, handling control functions beyond administrative actions, such as configuration, expansion, and replication. Resource Manager can utilize dedicated APIs in Interface Layer 1108, where each API can be provided to receive requests for at least one specific action to be performed regarding the data environment, such as configuring, expanding, cloning, or hibernating an instance. Upon receiving a request for one of the APIs, the web service portion of the interface layer can parse or otherwise analyze the request to determine the steps or operations required to perform or process the call. For example, a web service call might be received that includes a request to create a data repository.

[0064] In at least one embodiment, the interface layer 1108 includes a set of scalable, user-facing servers that can provide various APIs and return appropriate responses based on API specifications. The interface layer may also include at least one API service layer, which in one embodiment consists of stateless, redundant servers that process external user-facing APIs. The interface layer may be responsible for web service front-end features such as credential-based user authentication, user authorization, restricting user requests to the API server, validating user input, and marshalling or unmarshalling requests and responses. The API layer may also be responsible for reading database configuration data from and writing database configuration data to the management data store in response to API calls. In many embodiments, the web service layer and / or the API service layer will be the only externally visible components, or the only components visible to and accessible to the user controlling the service. As is known in the art, the servers of the web service layer may be stateless and horizontally scalable. The API servers and persistent data stores may be distributed across multiple data centers in a region, for example, enabling these servers to withstand the failure of a single data center.

[0065] Various embodiments can be further implemented in a wide range of operating environments, in some cases of which may include one or more user computers or computing devices that can be used to operate any of a number of applications. User or client devices may include any of a number of general-purpose personal computers, such as desktop or laptop computers running standard operating systems, and cellular, wireless, and handheld devices running mobile software and capable of supporting multiple network connectivity and messaging protocols. Such systems may also include multiple workstations running a variety of commercially available operating systems and any of other known applications for purposes such as research and development and database management. These devices may also include other electronic devices, such as virtual terminals, thin clients, gaming systems, and other devices capable of communicating via a network.

[0066] Most embodiments utilize at least one network familiar to those skilled in the art to support communication using various commercially available protocols, such as TCP / IP, FTP, UPnP, NFS, and CIFS. The network can be, for example, a local area network (LAN), a wide area network (WAN), a virtual private network (VPN), the Internet, an intranet, an extranet, a public switched telephone network (PSTN), an infrared network, a wireless network, and any combination thereof. In embodiments utilizing a web server, the web server can run any of various server or middleware applications, including HTTP servers, FTP servers, CGI servers, data servers, Java servers, and business application servers. One or more servers are also capable of executing programs or scripts in response to requests from user devices, such as by executing one or more web applications that can be implemented in any programming language (such as Java®, C, C#, or C++) or any scripting language (such as Perl, Python, or TCL) and combinations thereof. The server may also include a database server, including but not limited to database servers commercially available from Oracle®, Microsoft®, Sybase®, and IBM®.

[0067] The environment may include a variety of data storage areas as discussed above, as well as other memories and storage media. These may reside in various locations, such as on local storage media in one or more computers (and / or residing in one or more of one or more computers), or remotely in any or all of the computers spread across a network. In a particular set of embodiments, information may reside in a storage area network (SAN) familiar to those skilled in the art. Similarly, any necessary files for performing functions belonging to a computer, server, or other network device may be stored locally and / or remotely, as appropriate. Where the system includes computerized devices, each such device may include hardware elements that can be electrically coupled via a bus, including, for example, at least one central processing unit (CPU), at least one input device (e.g., mouse, keyboard, controller, touch-sensitive display element, or keypad), and at least one output device (e.g., display device, printer, or speaker). Such a system may also include one or more storage devices, such as disk drives, optical storage devices, and solid-state storage devices such as random access memory (RAM) or read-only memory (ROM), as well as removable media devices, memory cards, flash memory cards, etc. Such devices may also include a computer-readable storage medium reader, a communication device (e.g., a modem, a network card (wireless or wired), an infrared communication device), and working memory, as described above. The computer-readable storage medium reader may be connected to or configured to receive a computer-readable storage medium, which represents a remote, local, fixed, and / or removable storage device, as well as a storage medium for temporarily and / or more permanently containing, storing, transmitting, and retrieving computer-readable information.

[0068] Systems and various devices will typically also include multiple software applications, modules, services, or other elements residing within at least one working memory device, including an operating system and applications such as client applications or web browsers. It should be understood that alternative embodiments may have numerous variations different from the embodiments described above. For example, custom hardware may also be used, and / or specific elements may be implemented in hardware, software (including portable software, such as applets), or both. Furthermore, connectivity to other computing devices, such as network input / output devices, may be employed. Storage media and other non-transitory computer-readable media containing code, or portions thereof, may include any suitable media known or used in the art, such as, but not limited to, volatile and non-volatile, removable and non-removable media implemented in any method or technique for storing information such as computer-readable instructions, data structures, program modules, or other data: RAM, ROM, EEPROM, flash memory or other storage technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage devices, magnetic cartridges, magnetic tape, disk storage devices or other magnetic storage devices, or any other media that can be used to store desired information and can be accessed by system devices. Based on this disclosure and the teachings provided herein, those skilled in the art will understand other ways and / or methods of implementing various implementation schemes.

[0069] The description and drawings should therefore be considered illustrative rather than restrictive. However, it will be apparent that various modifications and changes can be made to the invention without departing from the broader spirit and scope of the invention as set forth in the claims.

Claims

1. A computer-implemented method, comprising: Receive a request to select one or more peptides from a plurality of peptides to produce a pharmaceutical product; Receive data containing manufacturability information associated with each of the plurality of peptides; Receive data containing immunogenicity information associated with each of the plurality of peptides; as well as Based on the manufacturability information and the second characteristic information, a statistical modeling process is used to generate a peptide group from the plurality of peptides for use in the production of the pharmaceutical product, wherein the statistical model optimizes at least one of the total immunogenicity or total manufacturability associated with the peptide group while satisfying one or more criteria.

2. The computer-implemented method of claim 1, wherein generating the peptide group further comprises: The plurality of peptides are sorted based on the manufacturability information and the second feature information associated with each peptide, wherein the second feature is the immunogenicity associated with each peptide; as well as Based on the sorting and the one or more criteria, a first peptide group is selected from the plurality of peptides to be included in a simulated manufacturing process, which is part of the statistical modeling process, wherein the one or more criteria include a expected number of long peptides, a expected number of short peptides, and one or more specific target mutations that the drug is intended to effectively combat.

3. The computer implementation method as described in claim 2, further comprising: A second peptide group is generated based on the simulated manufacturing process, wherein the second peptide group is expected to pass the simulated manufacturing process; Based on the immunogenicity score associated with each peptide and based on one or more of the criteria, a group of peptide subgroups is selected from the second peptide group; and Calculate the polymerization immunogenicity score of the peptide group.

4. The computer implementation method as described in claim 3, further comprising: The simulated manufacturing process is repeated for a certain number of iterations on the first peptide group to generate a certain number of simulation results; as well as Based on the number of simulation results, the average polymerase immunogenicity score associated with the first peptide group is determined.

5. The computer-implemented method of claim 2, wherein sorting the plurality of peptides further comprises: Calculate the product of the immunogenicity score and the manufacturability score for each peptide, wherein the immunogenicity information includes the immunogenicity score for each peptide, and the manufacturability information includes the manufacturability score for each peptide; and The sorting is based on the product of the immunogenicity score and the manufacturability score.

6. A computer-implemented method, comprising: Receive a request to select one or more peptides from a plurality of peptides to produce a pharmaceutical product; Receive data related to the plurality of peptides, the received data including manufacturability information and information on one or more features associated with each of the plurality of peptides; as well as Based on the manufacturability information and information on at least one of the one or more features, a statistical model is used to determine a peptide group from the plurality of peptides for use in the production of the pharmaceutical product.

7. The computer implementation method of claim 6, wherein the information of one or more of the features includes one or more of the following: immunogenicity information, expected quantity information of different types of peptides, and specific target mutations that the drug is intended to effectively combat associated with each peptide.

8. The computer implementation method of claim 6, wherein determining the peptide group further comprises: The multiple peptides are sorted based on the manufacturability information and the feature information associated with each peptide; as well as Based on the sorting and one or more criteria, a first peptide group is selected from the plurality of peptides to be incorporated into the simulated manufacturing process.

9. The computer implementation method of claim 8, wherein the criteria include one or more of the following: a desired number of long peptides, a desired number of short peptides, and one or more specific target mutations that the drug is intended to effectively combat.

10. The computer-implemented method of claim 8, further comprising: A second peptide group is generated based on the simulated manufacturing process, wherein the second peptide group is expected to pass the simulated manufacturing process; Based on feature scores associated with each peptide and based on one or more of the criteria, select a group of peptide subgroups from the second peptide group; and Calculate the polymerization characteristic score of the peptide group.

11. The computer-implemented method of claim 10, further comprising: The simulated manufacturing process is repeated for a certain number of iterations on the first peptide group to generate a certain number of simulation results; as well as Based on the number of simulation results, an average polymerization characteristic score associated with the first peptide group is determined.

12. The computer-implemented method of claim 8, wherein sorting the plurality of peptides further comprises: Calculate the product of a feature score and a manufacturability score for each peptide, wherein information on the at least one feature includes the feature score for each peptide, and the manufacturability information includes the manufacturability score for each peptide; and The sorting is based on the product of the feature score and the manufacturability score.

13. The computer implementation method of claim 8, wherein the selection of the peptide group is based on a greedy search algorithm that optimizes targets associated with the peptide group while satisfying one or more criteria.

14. A computing system comprising: Computing device processor; and A memory device including instructions that, when executed by the processor of the computing device, enable the computing system to: Receive a request to select one or more peptides from a plurality of peptides to produce a pharmaceutical product; Receive data related to the plurality of peptides, the received data including manufacturability information and information on one or more characteristics associated with each of the plurality of peptides; and Based on the manufacturability information and information on at least one of the features, a statistical model is used to determine a peptide group from the plurality of peptides for use in the production of the pharmaceutical product.

15. The computing system of claim 14, wherein one or more of the features include one or more of the following: immunogenicity information, expected quantity information of different types of peptides, and specific target mutation information that the drug is intended to effectively combat.

16. The computing system of claim 14, wherein the instructions further enable the computing system to: The plurality of peptides are sorted based on the manufacturability information and another feature associated with each peptide; and Based on the sorting, a first peptide group is selected from the plurality of peptides to be incorporated into the simulated manufacturing process.

17. The computing system of claim 14, wherein the instructions further enable the computing system to: A second peptide group is generated based on the simulated manufacturing process, which is expected to pass the simulated manufacturing process. Based on the feature scores associated with each peptide, a peptide subgroup is selected from the second group; and Calculate the polymerization characteristic score of the peptide group.

18. The computing system of claim 14, wherein the instructions further enable the computing system to: The simulated manufacturing process is repeatedly executed on the first peptide group for a certain number of iterations, generating a certain number of simulation results; and Based on the number of simulation results, an average polymerization characteristic score associated with the first peptide group is generated.

19. The computing system of claim 15, wherein sorting the plurality of peptides further comprises instructions enabling the computing system to perform the following operations: Calculate the product of the characteristic score and the manufacturability score for each peptide, wherein the characteristic score and the manufacturability score are present in the received data for each peptide; and The sorting is based on the product of the feature score and the manufacturability score.

20. The computing system of claim 15, wherein generating the peptide set comprises selecting the peptides according to one or more criteria specified in a received request, wherein the one or more criteria are selected from the group consisting of: a desired number of long peptides, a desired number of short peptides, and one or more specific target mutations that the drug is intended to effectively combat.

Images