TCR Repertoire Functional Unit

Abstract

A novel framework that converts T cell receptor (TCR) repertoire samples into vectors of fixed length. Short peptide sequences with different lengths in each TCR can be encoded into a numerical vector with fixed dimensions. A large amount of existing TCRs from healthy individuals can be pooled and a distribution of encoding vectors can be generated in a high-dimensional Euclidean space. Unsupervised clustering can be performed on "points" in this space (each point is a TCR), which can be grouped into antigen-specific clusters. The centroid of each cluster can be defined as a repertoire functional unit ("RFU"). For a new TCR repertoire sample, each TCR can be assigned to its most similar RFU group, and the RFU count can be normalized by the number of sequences in the repertoire. The output data can be a fixed-length RFU vector, with each number representing the relative abundance of a given RFU in the repertoire.

Description

[Technical field]

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS This application claims the benefit of priority under 35 USC Section 119(e) of U.S. Provisional Application No. 63 / 267,369, filed January 31, 2022, the disclosure of which is hereby incorporated by reference in its entirety into the disclosure of this application.

[0002] The present disclosure relates generally to immune repertoire-based disease diagnostic techniques, and more particularly to novel systems and methods for efficiently grouping similar T cell receptor (TCR) sequences, diagnosing patients with disease, and determining a patient's disease status by peripheral blood TCR repertoire. [Background technology]

[0003] The adaptive immune repertoire is a key regulator of diverse human diseases, and over 10,000 TCR repertoire sequencing (TCR-seq) samples have been generated in recent years. However, interpretation of TCR data has been hindered by the scarcity of known antigen specificities. Recent studies have demonstrated that similarities in the hypervariable complementarity determining region 3 (CDR3) of TCRs are responsible for structural similarity for antigen recognition. Thus, clustering of similar CDR3s has become an important method to identify antigen-specific receptors. Summary of the Invention [Means for solving the problem]

[0004] A method, system, and device for converting T cell receptor (TCR) repertoire samples into vectors of fixed length. Short peptide sequences with different lengths in each TCR can be encoded into a numerical vector with fixed dimensions. A large amount of existing TCRs from healthy individuals can be pooled and a distribution of encoding vectors can be generated in a high-dimensional Euclidean space. Unsupervised clustering can be performed on "points" in this space (each point is a TCR), which can be grouped into antigen-specific clusters. The centroid of each cluster can be defined as a repertoire functional unit ("RFU"). For a new TCR repertoire sample, each TCR can be assigned to its most similar RFU group, and the RFU count can be normalized by the number of sequences in the repertoire. The output data can be a fixed-length RFU vector, with each number representing the relative abundance of a given RFU in the repertoire.

[0005] The drawings described below are for illustration purposes only and are not intended to limit the scope of the present disclosure. [Brief description of the drawings]

[0006] [Figure 1] 1 is a diagram of a system according to some embodiments of the present disclosure. [Diagram 2] 1 is a block diagram illustrating components for implementing the methods described herein, according to some embodiments of the present disclosure. [Diagram 3] 1 is a flowchart illustrating a workflow of a numeric encoding framework for use in a Repertoire Functional Unit (RFU) process, according to some embodiments of the present disclosure. [Figure 4] 1 is a flow chart illustrating the Geometric Isometry-Based Antigen-Specific TCR Alignment (GIANA) process, according to some embodiments of the present disclosure. [Figure 5A]1 is a diagram illustrating repertoire visualization using trimer numeric encoding of TCRs, according to some embodiments of the present disclosure. [Figure 5B] 1 is a diagram illustrating repertoire visualization using trimer numeric encoding of TCRs, according to some embodiments of the present disclosure. [Figure 6A] 1 is a chart illustrating how the RFU process distinguishes between CD4 and CD8 T cell repertoires, according to some embodiments of the present disclosure. [Figure 6B] 1 is a chart illustrating how the RFU process distinguishes between CD4 and CD8 T cell repertoires, according to some embodiments of the present disclosure. [Figure 6C] 1 is a chart illustrating how the RFU process distinguishes between CD4 and CD8 T cell repertoires, according to some embodiments of the present disclosure. [Figure 7A] 1 is a chart illustrating how the RFU process distinguishes cancer patients from healthy controls ("HCs") and COVID-19 patients, according to some embodiments of the present disclosure. [Figure 7B] 1 is a chart illustrating how the RFU process distinguishes cancer patients from healthy controls ("HCs") and COVID-19 patients, according to some embodiments of the present disclosure. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0007] Many previous studies have applied TCR clustering to examine antigen-specific T cell responses during disease progression or immunotherapy treatment. It is speculated that integrating a large number of TCR-seq samples from many studies will provide more insight into immune-disease interactions and create new opportunities for prognosis and diagnosis. Nevertheless, high clustering specificity requires pairwise Smith-Waterman alignment of both CDR3 sequences and TCR variable gene (TRBV) alleles, which has quadratic computational complexity that usually cannot be scaled up to the scale of TCR repertoire samples (100K sequences or more). Motif-based clustering can achieve high speed but has very low specificity. Thus, none of the current TCR clustering methods are suitable for analyzing large cohorts of TCR-seq samples.

[0008] Unsupervised TCR clustering is a fundamental analysis of immune repertoire data. In an ideal scenario, all TCRs specific for the same epitope should be included in the same cluster. However, this is not feasible for sequence similarity or motif-based clustering approaches due to the expected diversity in TCR sequences with shared specificity. Such diversity is caused by the unique docking strategies of T cell receptors. For example, TCRs specific for influenza GIL epitopes usually contain classical RSS / RSA motifs in the CDR3 region, but related studies have reported that LGGW motifs also induce strong binding to GIL from different orientations. Such structural variations cannot be captured by simple Smith-Waterman alignment or motif grouping. As a result, CDR3s with dissimilar motifs end up being fragmented into small clusters despite sharing their specificity, which is a general limitation for current methods.

[0009] To address this challenge, we developed a new framework to convert TCR repertoire samples into "gene expression-like" vectors of fixed length. First, each TCR sequence in the TCR repertoire may be numerically encoded. More specifically, short peptide sequences with different lengths may be encoded into numerical vectors with fixed dimensions. Then, a large amount of existing TCRs from healthy individuals are pooled to generate a distribution of encoding vectors in a high-dimensional Euclidean space. Unsupervised clustering is performed on "points" in this space (each point is a TCR), which may be grouped into antigen-specific clusters. The centroid of each cluster may be defined as a repertoire functional unit ("RFU"). For a new TCR repertoire sample, each TCR may be assigned to its most similar RFU group, and the RFU count may be normalized by the number of sequences in the repertoire. The output data may be a fixed-length RFU vector, with each number representing the relative abundance of a given RFU in the repertoire.

[0010] The present disclosure will now be described in more detail hereinafter with reference to the attached drawings, which form a part hereof and which show, by way of non-limiting illustration, certain examples. However, it is intended that the subject matter may be described in a variety of different forms, and thus the subject matter encompassed or claimed should not be construed as being limited to any of the examples described herein. Among other things, the subject matter may be described as a method, device, component, or system. Thus, the examples may take the form of hardware, software, firmware, or any combination thereof (other than software per se). Thus, the following detailed description is not intended to be taken in a limiting sense.

[0011] Generally, terms may be understood, at least in part, from the usage in the context. For example, terms used herein, such as "and", "or", or "and / or", may include various meanings, depending at least in part on the context in which they are used. Typically, "or", when used in conjunction with a list such as A, B, or C, is intended to mean A, B, and C used in an inclusive sense, and A, B, or C used in an exclusive sense. Furthermore, the term "one or more", used at least in part depending on the context, may be used to describe any feature, structure, or characteristic in the singular sense, or to describe a combination of features, structures, or characteristics in the plural sense. Similarly, terms such as "a" or "the" may be understood to convey the singular or plural sense, depending at least in part on the context. Furthermore, it is understood that the term "based on" is not necessarily intended to convey an exclusive set of elements, and instead, the presence of additional elements not necessarily explicitly described may be acknowledged, also at least in part depending on the context.

[0012] The present disclosure is described below with reference to block diagrams and operational instructions of methods and devices. It is understood that each block of the block diagrams or operational instructions, and combinations of blocks in the block diagrams or operational instructions, can be implemented by analog or digital hardware and computer program instructions. These computer program instructions are provided to a processor of a general purpose computer, a special purpose computer, an ASIC, or other programmable data processing device to change its functions as detailed herein, so that the instructions executed via the processor of the computer or other programmable data processing device can perform the functions / operations specified in the block diagrams or operational blocks. In some alternative implementations, the functions / operations noted in the blocks may occur in a different order than that noted in the operational instructions. For example, two blocks shown in succession may be executed substantially simultaneously, or sometimes the blocks may be executed in the reverse order, depending on the functions / operations involved.

[0013] For purposes of this disclosure, a non-transitory computer-readable medium (or computer-readable storage medium) stores computer data, which may include computer program code (or computer-executable instructions) in machine-readable form that can be executed by a computer. By way of example, and not by way of limitation, a computer-readable medium may include a computer-readable storage medium for tangible or fixed storage of data, or a communication medium for the transitory interpretation of a signal containing the code. As used herein, computer-readable storage medium means physical or tangible storage (as opposed to a signal), and includes, without limitation, volatile and non-volatile, removable and non-removable media implemented in any method or technology for the tangible storage of information, such as computer-readable instructions, data structures, program modules, or other data. A computer readable storage medium includes, but is not limited to, RAM, ROM, EPROM, EEPROM, flash memory or other solid-state memory technology, CD-ROM, DVD or other optical storage, cloud storage, magnetic cassettes, magnetic tapes, magnetic disk storage or other magnetic storage devices, or any other physical or material medium that can be used to tangibly store desired information or data or instructions and that can be accessed by a computer or processor.

[0014] For purposes of this disclosure, the term "server" should be understood to mean a service point that provides processing, database, and communication facilities. By way of example, and not by way of limitation, the term "server" may mean a single physical processor with associated communication and data storage and database facilities, or it may mean a networked or clustered complex of processors and associated networks and storage devices, as well as operating software and one or more database systems and application software that facilitate the services provided by the server. A cloud server is an example.

[0015] For purposes of this disclosure, a "network" should be understood to mean a network that couples devices such that communications may be exchanged, such as between a server and a client device or other type of device, including between wireless devices coupled via a wireless network. A network may also include mass storage devices, such as network attached storage (NAS), storage area networks (SAN), content delivery networks (CDN), or other forms of computer or machine readable media. A network may include the Internet, one or more local area networks (LANs), one or more wide area networks (WANs), wireline type connections, wireless type connections, cellular, or any combination thereof. Similarly, sub-networks employing different architectures or conforming to or compatible with different protocols may interoperate within a larger network.

[0016] For purposes of this disclosure, a "wireless network" should be understood to couple client devices to a network. The wireless network may employ a standalone ad-hoc network, a mesh network, a wireless LAN (WLAN) network, a cellular network, and the like. The wireless network may further employ multiple network access technologies including Wi-Fi, Long Term Evolution (LTE), WLAN, Wireless Router (WR) mesh, or second, third, fourth, or fifth generation (2G, 3G, 4G, or 5G) cellular technologies, Bluetooth, 802.11b / g / n, and the like. The network access technologies may enable wide-area coverage for devices, such as client devices, with varying degrees of mobility.

[0017] Briefly, a wireless network may include substantially any type of wireless communication mechanism by which signals are communicated between devices, such as client devices or computing devices, between or within a network, etc.

[0018] A computing device may be capable of transmitting or receiving signals, e.g., over a wired or wireless network, or may process or store signals, e.g., in a memory as a physical memory state, and thus may operate as a server, i.e., devices capable of operating as a server may include, e.g., dedicated rack-mounted servers, desktop computers, laptop computers, set-top boxes, integrated devices combining various features, such as features of two or more of the above devices, and the like.

[0019] Referring now to Figure 1, a system 100 is shown. Figure 1 illustrates components of a general environment in which the systems and methods discussed herein may be implemented. Not all components are required to practice the present disclosure, and variations in the arrangement and type of components may be made without departing from the spirit and scope of the present disclosure.

[0020] The system 100 of FIG. 1 includes a network 104, which, as discussed above, may include, but is not limited to, a wireless network, a local area network (LAN), a wide area network (WAN), the Internet, or a combination thereof.

[0021] Network 104 may couple with, for example, one or more client devices 102, application servers 106, content servers 108, and databases 107 and components thereof, along with other networks or devices. Network 104 may be configured as various wireless sub-networks, etc., further layered on a standalone ad-hoc network to provide infrastructure oriented coupling for one or more client devices 102, application servers 106, content servers 108, and databases 107. Network 104 may be configured to employ any form of computer-readable medium or network to communicate information from one electronic device to another.

[0022] The one or more client devices 102 may include, for example, a desktop computer or a portable device, such as a mobile phone, a smartphone, a display pager, a radio frequency (RF) device, an infrared (IR) device, a near field communication (NFC) device, a personal digital assistant (PDA), a handheld computer, a tablet computer, a phablet, a laptop computer, a set-top box, a wearable computer, a smart watch, an integrated or distributed device that combines various features, such as those of the above devices, and the like.

[0023] The one or more client devices 102 may include at least one client application configured to receive content from another computing device. The one or more client devices 102 may communicate with other devices or servers over the network 104, where such communication may include sending and / or receiving messages, generating and providing TCR data, searching, rendering, and / or sharing TCR data, or any of a variety of other forms of communication. The one or more client devices 102 may process or store signals in memory, for example as physical memory states, and thus may act as a server.

[0024] The application server 106 and the content server 108 may include one or more devices configured to provide and / or generate any type or form of content to another device over a network. Devices that may operate as the application server 106 and / or the content server 108 may include personal computers, desktop computers, multiprocessor systems, microprocessor-based or programmable consumer electronics, network PCs, servers, and the like. The application server 106 and the content server 108 may store various types of data related to the content and services provided by the respective devices in a database 107.

[0025] Users (e.g., patients, doctors, technicians, etc.) can access services provided by application servers 106 and content servers 108, which may include, for example, application servers, authentication servers, search servers, and exchange servers over network 104 using one or more client devices 102. That is, for example, application servers 106 can store various types of applications as well as information related to the applications, including application data and user profile information.

[0026] 1 illustrates application server 106 and content server 108 as each being a single computing device, the disclosure is not so limited. For example, one or more functions of application server 106 and content server 108 may be distributed across one or more distinct computing devices. In another example, application server 106 and content server 108 may be integrated into a single computing device without departing from the scope of the disclosure.

[0027] Referring now to Figure 2, a block diagram illustrating components for implementing the methods described herein is shown. Figure 2 includes a TCR engine 200, a network 104, and a database 107. The TCR engine 200 may be a special purpose machine or processor and may be included in one or more of an application server 106, a content server 108, a web server, a third party server, a user's computing device, etc.

[0028] In one example, the TCR engine 200 may be a conventional personal computer, and the method described below may be implemented using a single thread on the CPU. In another example, when clustering reference data of 10 million sequences, the TCR engine 200 may be a high performance computing (HPC) supercluster (e.g., memory allocation of 128G, CPU node 8).

[0029] The TCR engine 200 may be a standalone application running on a device (e.g., a user device or a server / device connected to a system / web). In another example, the TCR engine 200 may function as an application installed on a device and / or a web-based application accessed by a device over a network. The TCR engine 200 may be installed as an augmented script, program, or application (e.g., a plug-in or extension) to another application, such as a health management application that aggregates and shares data related to a patient.

[0030] Database 107 may be any type of database or memory and may be associated with a server on a network (e.g., application server 106 and content server 108) or with a user's device (e.g., one or more client devices 102). Database 107 may contain data and metadata datasets associated with local and / or network information related to users, services, applications, content, and the like. Such information may be stored and indexed in database 107 independently and / or as linked or associated datasets. As discussed herein, it should be understood that the data (and metadata) in database 107 may be any type of information and type, known or hereafter known, without departing from the scope of this disclosure.

[0031] The database 107 can store data for users (e.g., user data), which can include, for example, information associated with the reference TCR-seq data, the patient's cancer diagnosis, the patient's chromosomal information, the patient's DNA information, the patient's blood information, the patient's demographic information, the patient's historical information, and the like, or some combination thereof.

[0032] The data (and metadata) in database 107 may be any type of information related to TCR-seq data, patients, physicians, content, devices, applications, service providers, and content providers, whether known or to become known, without departing from the scope of this disclosure.

[0033] Data stored in database 107 may be encrypted, for example using 256-bit encryption, so that the data is private and managed in accordance with the Health Insurance Portability and Accountability Act of 1996 (HIPPA).

[0034] The database 107 may store and index information as linked sets of data and metadata, and the relationships between data and metadata may be stored as n-dimensional vectors. Such storage may be accomplished through known or known vector or array storage, including but not limited to hash trees, queues, stacks, VLists, or any other type of known or known dynamic memory allocation method or technique. It should be understood that any known or known computational analysis method or algorithm, including but not limited to cluster analysis, data mining, Bayesian network analysis, hidden Markov models, artificial neural network analysis, logic models, and / or tree analysis, and others, may be applied to determine, derive, or otherwise identify vector information about the patient and / or healthcare provider.

[0035] As discussed above with reference to Figure 1, the network 104 may be any type of network, such as, but not limited to, a wireless network, a local area network (LAN), a wide area network (WAN), the Internet, or a combination thereof. The network 104 may facilitate a connection between the TCR engine 200 and a database 107 of stored resources. Indeed, as shown in Figure 2, the TCR engine 200 and the database 107 may be directly coupled by any method known or to become known that couples and / or enables communication between such devices and resources.

[0036] A combination of a major processor, server, or device including hardware programmed according to the special purpose functions herein may be conveniently referred to as a TCR engine 200. The TCR engine 200 may include a sample module 202, an AI module 204, an encoding module 206, a filtering module 208, an identification (ID) module 210, and a conversion module 212. The engines and modules discussed herein are non-exhaustive, as additional or fewer engines and / or modules (or sub-modules) may be applicable to the example systems and methods discussed. The operation, configuration, and functionality of each module, as well as their role in the example of the present disclosure, are discussed below.

[0037] The principles described herein can be embodied in many different forms. Antigen-reactive T cells are central mediators of immunity to various diseases and important targets of immunotherapy, but experimental detection of disease-associated T cells remains challenging because most disease antigens are unknown. Recent developments in deep immune repertoire sequencing (TCR-seq) technology have further emphasized the identification of such T cells, as this may open new opportunities for non-invasive clinical diagnosis, prognosis and long-term immune monitoring of patients. However, the human immune repertoire includes public T cells, naive T cells and memory / effector T cells specific for diverse antigens, and this complexity adds challenges (e.g., identifying cancer-associated T cells in TCR-seq data) that cannot be solved by conventional systems.

[0038] Previous studies on TCR repertoires in cancer patients have reported that simple statistics such as diversity and clonality are associated with clinical outcomes under certain conditions, demonstrating the utility of repertoire data as potential prognostic factors. However, with the rapid advances in immunotherapy and the rapid accumulation of TCR-seq data, more computational tools are needed to bridge the gap between basic immunogenomic research and clinical applications to benefit patients.

[0039] The disclosed systems and methods provide these necessary tools through a novel framework that implements ensemble machine learning software (termed TCRBoost) that uses TCR-seq data to provide de novo predictions of disease-associated immune repertoires. Groupings of similar TCR sequences are associated with shared antigen specificity and can be used to discover novel therapeutic targets. Conventional methods suffer from being computationally expensive and unable to scale up to the size of immune repertoire datasets.

[0040] Now referring to FIG. 3, a flow chart is shown illustrating the workflow of the numerical encoding framework used in the RFU process 300. The RFU process 300 can begin by performing a first clustering process 302 on a sample TCR repertoire sequencing dataset 301. Any amount and type of sample TCR repertoire sequencing dataset that fills the trimer substitution matrix, described in detail below, can be used. For example, the number of TCRs in the sample TCR repertoire sequencing dataset 301 can range from about 10 million to more than 100 million. In general, the more TCRs used in the sample TCR repertoire sequencing dataset 301, the more accurate the numerical encoding that can be obtained. It is contemplated that the sample TCR repertoire sequencing dataset 301 can include hundreds of millions to billions of TCRs.

[0041] In one example, each sample may be processed to ensure data quality. First, TCR clones that do not contain a defined variable gene (TRBV) may be removed. Second, CDR3 amino acid sequences that contain non-productive symbols, such as "*" or "_", may be eliminated. Third, clones may be ranked from high to low according to their estimated frequency, and the top amount (e.g., 10,000) or the largest number of remaining clones may be selected. Fourth, the format of the TRBV gene name may be modified to match the IMGT (imgt.org) convention. Samples may be derived from peripheral blood.

[0042] In one example, the sample TCR repertoire sequencing dataset 301 may include TCRs from over 2,000 samples covering cancer, infectious diseases, autoimmune disorders, and healthy controls merged into one file containing over 20 million TCRs. Ultra-large scale TCR clustering may be performed using the Geometric Isometric Based Antigen-Specific TCR Alignment (GIANA) process described in related Patent Cooperation Treaty (PCT) Publication WO2022 / 271566, filed June 17, 2022, entitled "TCR-Repertoire Framework for Multiple Disease Diagnosis." The complete disclosure of this application is incorporated herein by reference.

[0043] Referring now to Figure 4, a flow chart of the GIANA process is shown. Note that the steps shown in Figure 4 may be performed by the TCR engine 200 described above with reference to Figure 2.

[0044] In step 402, the sample module 202 can identify CDR3 sequences from the TCR dataset. The sample module 202 can receive the TCR dataset from, for example, the database 107. In step 404, the encoding module 206 can encode each of the CDR3 sequences from the TCR dataset into a numeric vector. The numeric vector can correspond to the sequence of amino acids in each of the CDR3 sequences.

[0045] In step 406, the transformation module 212 can transform the numeric vectors into coordinates in a high-dimensional Euclidean space. In step 408, the AI ​​module 204 can generate a predictive model using a neural network. The neural network can learn to generate a tree data structure of the numeric vectors based on the relative distance of the coordinates, and then group the coordinates into pre-clusters based on the relative distance. In step 410, the filtering module 208 can filter the CDR3 sequences in the pre-clusters. In step 412, the ID module 210 can identify antigen-specific CDR3 clusters from the filtered pre-clusters.

[0046] GIANA full mode (e.g., including precise and variable genes) may be performed to identify highly similar TCR clusters. The returned clusters may be processed in one or more ways. For example, clusters with more than 5 TCRs may be removed, since small clusters tend to have high antigen specificity. Additionally, clusters with identical sequences may be removed.

[0047] The GIANA process can be used to close the gap between speed and predictive accuracy, at approximately 600 times the speed of conventional methods (e.g., TCRdist) and with better precision and sensitivity than conventional methods. GIANA also enables ultra-fast queries of large reference cohorts and can process over 100 billion sequence comparisons in less than 3 minutes. In one example, GIANA can perform 10 7 10 for the reference sequence 4The TCRs of different TCRs can be compared. By applying GIANA to cluster large-scale TCR datasets, novel insights of disease-specific receptors can be revealed and new solutions for repertoire classification tasks can be provided. High accuracy is achieved by querying unknown TCR-seq samples against existing references with GIANA and can be used to identify cancer, infectious diseases, and autoimmune disorders. GIANA can be used as a non-invasive multiplex disease diagnostic platform based on TCRs.

[0048] Referring again to FIG. 3, in step 304, the resulting clusters 303 can be used to extract and define interchangeable trimers. In one example, an 8,000×8,000 trimer replacement matrix (M) with zeros 305 can be initialized. This matrix can be used to record the number of interchangeable trimer pairs calculated from the TCR clustering data. For each TCR cluster with s sequences, the mismatched amino acid position is marked as x. One position adjacent to x, i.e., x−1, x, x+1, can be the trimer of interest. Given a high default alignment score cutoff in GIANA (3.7), the majority of small clusters (size≦5) may contain as few as one mismatch. If a cluster contains more than one mismatch, the above procedure may be repeated for each mismatch. This results in each cluster being t 1 , t 2 , t s In particular, these trimers may overlap, and only unique trimers may be kept. Each pair of trimers may add 1 to the corresponding entry in the trimer permutation matrix. For example, after a cluster is processed (t 1 , t 2 ) may be increased by 1, where the trimmer in parentheses may indicate the position of the entry in matrix M. After processing all clusters, matrix M may be terminated.

[0049] The trimer isometric embedding is done by defining the trimer permutation matrix as

[0050]

number

[0051] This can be done because the replacement of trimer pairs is unordered. s M, expressed as s The Pearson correlation matrix of can be calculated. s The (i,j) entry of may be the Pearson correlation of trimers i and j (trimmers are sorted alphabetically). The Euclidean distance matrix (EDM) may be defined using the following formula:

[0052]

number

[0053] In step 306, multidimensional scaling (MDS) may be applied to the EDM. In one example, the dimension may be set to 500. In another example, the dimension may be increased to 1,000, 1,500, and 2,000. In step 307, the outcome of this analysis may be a numeric vector (β) of length 500 for each of the 8,000 amino acid trimers.

[0054] In step 308, average pooling may be performed. In step 309, a process of numerical encoding of the CDR3 sequences may be performed. The numerical encoding process 309 may incorporate TCRs with different lengths. From each CDR3 sequence, the first two and the last three amino acids (i.e., conserved motifs) may be removed. The remaining sequences are divided into tiling trimers. For example, the sequence ASDTAGK may result in ASD, SDT, DTA, TAG, and AGK. One or more n corresponding trimers may be selected, and the average of the numerical vectors of one or more n corresponding trimers may be used to obtain a numerical encoding vector with fixed dimensions for the TCR of interest.

[0055]

number

[0056] An important desired feature in the numerical encoding of TCRs is antigen specificity (i.e., TCRs specific for the same antigen are expected to have coordinates that lie close together in a high-dimensional Euclidean space with well-defined distances). To evaluate the performance of this new approach, we used a dataset of T cells with experimentally elucidated antigen specificity. First, we selected antigens with fewer than 100 associated TCRs in the dataset. The reason for applying this filter is that the TCRs reported from some high-throughput tetramer sorting experiments contained a high proportion of false positives. Next, we selected 3,487 TCRs that undoubtedly contained matched antigens. The distance for each pair of TCRs was then calculated and used as a predictor. The response vector was binary, with a value of 1 if the TCRs in the pair were specific for the same antigen and 0 otherwise.

[0057] To visualize the prediction accuracy, a receiver operating characteristic (ROC) curve was constructed and an AUC of 0.59 was observed. Despite the low overall AUC, this approach achieved a sensitivity of 19.5% at 95% specificity, which is at the same level as the previously described TCR clustering method. This is due to the fact that adjacent TCRs share similar amino acid sequences and similar TCRs may share antigen specificity. Thus, the new encoding method provides an absolute set of Euclidean coordinates to measure the similarity of TCRs. Importantly, this embedding covers all TCR lengths. The coordinate system is continuous, and infinitely close TCRs are almost certainly specific for the same antigen. This is simply because these TCRs will be "almost" identical. However, it has been repeatedly reported that TCRs with different motifs can recognize the same epitope, so it is possible that distant TCRs are specific for the same antigen. Thus, a low sensitivity but high specificity is expected.

[0058] After the numerical encoding process 309, a second clustering process 310 is performed using "points" in this space (each point is a TCR) which may be grouped into antigen-specific clusters. The second clustering process 310 may be performed using a dataset consisting of TCRs from healthy donors. In one example, the second clustering process 310 may be different from the first clustering process 302 described above. The second clustering process 310 may cluster sequences with different lengths. The second clustering process 310 may use a novel encoding approach which may be derived from a large TCR dataset and may carry information about antigen specificity.

[0059] In one example, a healthy donor-derived TCR dataset may include about 500,000 TCRs, although larger numbers are contemplated. For example, the number of TCRs in a healthy donor-derived dataset may range from about 500,000 to more than a million. In general, the more TCRs used in a healthy donor-derived dataset, the more accurate the resulting clustering may be. It is contemplated that a healthy donor-derived dataset may include hundreds of millions to billions of TCRs. Unsupervised k-means may be performed in a 500-dimensional space with, for example, 5,000 predefined centers (although any number may be selected). The TCRs may be divided into 5,000 clusters, since the top 10,000 clones with the highest abundance in each repertoire may cover the majority of the expanded TCRs. The number of clusters should not be too large to ensure sufficient hits in each cluster for downstream analysis. In one example, the average silhouette width reached 0.28, suggesting that TCRs within each cluster are closer to the cluster centroid than other clusters (i.e., the clustering is tighter). This result suggests that although TCRs in the human immune repertoire show high diversity, they also show conserved distribution patterns in the high-dimensional encoding space, possibly associated with common antigenic stimuli from the environment across different individuals.

[0060] In step 312, the RFU may be defined. In one example, the distribution of this distance was measured and it was observed that 99% of the distances between a TCR and its cluster centroid were less than 0.25. This is the 95% specificity cutoff for the ROC curve. It can therefore be concluded that TCRs in the same cluster are primarily specific for the same antigen. This result suggests that the centroid of each TCR cluster can be considered as a "functional unit" (i.e., RFU) of the immune repertoire, with each unit covering a variety of antigens. The immune repertoire can be considered as a patch of units covering all pathogens that may be encountered in a lifetime. Given the enormous amount of internal and external immune stimuli that the human body receives, the number of antigens to which each unit responds would be extremely large.

[0061] In step 314, the TCR repertoire samples may be converted into RFU vectors. For a given TCR repertoire sample, a 500-dimensional encoding vector may be calculated for each TCR. The vector may then be compared to each of the 5,000 RFU centroids using Spearman correlation. The vector is assigned to the RFU with the largest correlation. To reduce the effect of outlying coordinates and accelerate the speed of calculation, rank correlation may be used instead of Euclidean distance to assign RFUs. In one example, more than 70% of the TCRs in a sample have a Spearman correlation greater than 0.6, suggesting that most TCRs can be assigned to RFUs with similar centroids. Processing all K TCRs in a sample results in a vector of length 5,000, and in each entry, the count of the TCR may be assigned to the associated RFU. The final vector may be a vector normalized by K and multiplied by 10,000. The numerical encoding derived from the trimer permutation matrix allows for an alternative way of visualizing and comparing repertoire samples.

[0062] Referring now to Figures 5A-5B, diagrams illustrating repertoire visualization using trimer numeric encoding of TCRs are shown. Figure 5A shows a two-dimensional density plot of t-distributed stochastic neighborhood embedding (t-SNE) coordinates calculated from the original 500-dimensional numeric encoding matrix for both controls and Hodgkin's lymphoma patients. Figure 5B shows the difference in density for lymphoma patients subtracted from control density. Selected regions of the density plot have been highlighted to show enriched TCR motifs.

[0063] To illustrate the contrast visualization of immune repertoire samples, two samples from a recent study on B-cell Hodgkin's lymphoma were selected, one from a healthy control and the other from a lymphoma patient. Both samples were derived from peripheral blood. After numerical transformation, each sample was converted into a 10,000 × 500 matrix, with each row corresponding to a TCR and each column to the dimensions of the encoding space. The distribution of TCRs in this space was then visualized using tSNE as a dimensionality reduction technique. Other methods such as UMAP or PCA could serve the same purpose. Each TCR is represented by a point on the 2D tSNE plot shown in Figure 5A, from which the different patterns of TCR distribution between HCs and lymphoma patients can be easily visualized. The difference density plot shown in Figure 5B can be generated by subtracting the density of lymphoma patients from the controls and observing the regions (mapped against the TCR motifs) showing selective enrichment in lymphomas (YNSPL) or HCs (GNTEA). This analysis illustrates one example of how a numerical encoding approach can yield differentially regulated TCR patterns in cancer patients. As mentioned above, the RFU process can diagnose cancer from the general population even in the presence of other factors (e.g., herd immunity due to COVID-19).

[0064] Referring now to Figures 6A-6C, a chart is shown illustrating how the RFU process identifies CD4 and CD8 T cell repertoires. CD8+ and CD4+ T cells recognize different antigens bound to MHC class I and class II, respectively. Due to differences in class I and class II epitopes, it is expected that their specific T cell receptors may have distinguishable characteristics. In support of this view, a recent study has reported statistically significant coexistence of certain TCR variable genes and MHC alleles. Another study has also reported distinct signatures between CD8 and CD4 T cells, but this characteristic was defined at the repertoire level. Since RFU is expected to be antigen specific, we hypothesized that at least a subset of RFU would be consistently CD4+ or CD8+.

[0065] Two data sets containing both CD4+ and CD8+ T cell repertoires were processed. Figure 6A shows a sample containing 27 CD8+ and 46 CD4+ TCR repertoire samples, all from lymphoma patients. Figure 6B shows a sample containing 25 CD8+ and 25 CD4+ samples, all from healthy donors. RFU conversion was performed on both data sets, followed by PCA analysis. Both PC1 and PC2 were driven by differences between CD4+ and CD8+ T cells. Using the first PC as a predictor, the RFU can almost completely separate CD4 from CD8 repertoires. The results showed that a large fraction of RFUs conserved CD4+ or CD8+ identity across different individuals, regardless of antigen diversity. To prove this hypothesis, differential RFU analysis was performed by performing a two-sample Wilcoxon rank test between CD4 and CD8 groups for each RFU, and the average fold change was estimated. As expected, most RFUs showed consistent fold changes from the two sample cohorts (p≦2.2e-16, Spearman's correlation test), supporting the above conclusion. Figure 6C shows a scatter plot showing the high correlation between the fold changes of the two cohorts. The fold change for each RFU was calculated as the mean value of the CD4 samples relative to the mean value of the CD8 samples.

[0066] With reference to Figures 7A-7B, a chart is shown illustrating how the RFU process distinguishes cancer patients from healthy controls ("HCs") and COVID-19 patients. In one example, samples were analyzed that included 19 HCs and 56 lymphoma patients treated within the same cohort. Each sample was converted to an RFU vector as described above. Each dataset was represented as a matrix with 5,000 rows, each representing one RFU, and N columns, where N is the sample size. Principal component analysis (PCA) was performed on both datasets. The first two PCs are shown in Figure 7A. This simple unsupervised approach was easily sufficient to distinguish cancer from non-cancer subjects. Using PC1+PC2 as predictors, an AUC of 93.2% was reached. This result suggested that cancer is a major immune disease driving variation in the structure of the TCR repertoire that can be captured by our RFU approach.

[0067] With COVID-19 infection now widespread among over 16% of Americans, a significant proportion of the “healthy” population is expected to be COVID-19 patients. To test whether this new situation impacts cancer prediction, we constructed a new dataset consisting of 121 non-small cell lung cancer (“NSCLC”) patients and 160 individuals who were recently infected with COVID-19. Both datasets were profiled with the latest version of the reagents from AdaptiveBiotech’s immunoSEQ platform. As shown in Figure 7B, using PCA on the RFU matrix, a clear separation was observed between the lung cancer group and COVID-19 patients, while the difference between cancer and non-cancer only drove PC2, reaching an AUC of 96.3%. This result indicates that the immune response elicited by malignant lung tumors is distinct from acute viral infections in the upper respiratory tract, which can be captured using RFU analysis. Notably, the RFU method provides a uniform feature set that can be used by future supervised machine learning methods, such as boosting, SVM, random forests, deep neural network models, and others. These methods are expected to reach higher prediction accuracy and consistency with sufficient training samples for the cancer / non-cancer classification task.

[0068] For purposes of this disclosure, a module is a software, hardware, or firmware (or combination thereof) system, process, or functionality, or component thereof, that performs or facilitates the processes, features, and / or functions described herein (with or without human interaction or augmentation). A module may include sub-modules. The software components of a module may be stored in a computer-readable medium for execution by a processor. A module may be integral to one or more servers or may be hosted and executed by one or more servers. One or more modules may be grouped into an engine or application.

[0069] Those skilled in the art will recognize that the disclosed method and system may be implemented in many ways and are therefore not limited to the above examples. In other words, functional elements and individual functions implemented by single or multiple components in various combinations of hardware and software or firmware may be distributed in software applications at the client level or server level or both. In this regard, any number of features of the various embodiments described herein may be combined in a single or multiple embodiments, and alternative embodiments having less than or more than all of the features described herein are possible.

[0070] The functionality may be distributed, in whole or in part, among multiple components in ways now known or that will become known in the future; that is, multiple software / hardware / firmware combinations are possible in achieving the functions, features, interfaces, and preferences described herein. Moreover, the scope of the disclosure includes conventionally known ways of implementing the described features and functions and interfaces, as well as variations and modifications made to the hardware or software or firmware components described herein, now and in the future, as will be understood by those skilled in the art.

[0071] Furthermore, the method embodiments shown and described as flow charts in this disclosure are provided as examples to provide a more complete understanding of the present technology. The disclosed methods are not limited to the operations and logical flows presented herein. Alternative embodiments are contemplated in which the order of various operations is changed and in which sub-operations described as part of larger operations are performed independently.

[0072] Although various embodiments have been described for purposes of this disclosure, these embodiments should not be construed as limiting the teachings of this disclosure to these embodiments. Various changes and modifications may be made to the elements and operations described above in order to obtain results that remain within the scope of the systems and processes described in this disclosure.

Claims

1. encoding short peptide sequences of T cell receptors (TCRs) within a larger sequence of TCR samples into numerical vectors of fixed dimensions, the short peptide sequences having different lengths; converting each TCR in a pool of existing TCRs from healthy individuals into said numerical vector to generate a distribution of said numerical vectors in a high-dimensional Euclidean space; clustering the converted TCRs from the pool of existing TCRs into antigen-specific clusters, the centroid of each cluster being a repertoire functional unit ("RFU"); converting each TCR in one or more TCR repertoire samples to said numerical vector; assigning one or more of the converted TCRs from each of the one or more TCR repertoire samples to an RFU based on one or more correlations; and normalizing the number of RFUs with assigned converted TCRs from said each of said one or more TCR repertoire samples by the total number of TCRs in the corresponding TCR repertoire sample to generate a fixed length RFU vector for each of said one or more TCR repertoire samples. The method includes:

2. encoding short peptide sequences of T cell receptors (TCRs) within a larger sequence of TCR samples into numerical vectors of fixed dimensions, the short peptide sequences having different lengths; performing ultra-large-scale TCR clustering of the TCRs in said large array; using the clustered TCRs to define interchangeable trimers; inducing isometric embedding of the interchangeable trimmers; defining a Euclidean Distance Matrix (EDM) representing the interchangeable trimers; applying multidimensional scaling (MDS) to the EDM to derive a numerical vector for each of the interchangeable trimmers; removing one or more amino acids from each complementarity determining region 3 (CDR3) of each clustered TCR to form a respective sequence; splitting each individual sequence into tiling trimers; selecting one or more corresponding interchangeable trimers for each clustered TCR; and averaging the numerical vectors of the one or more corresponding interchangeable trimmers to obtain the numerical vector having a fixed dimension; an encoding step, converting each TCR in a pool of existing TCRs from healthy individuals into said numerical vector to generate a distribution of said numerical vectors in a high-dimensional Euclidean space; clustering the converted TCRs from the pool of existing TCRs into antigen-specific clusters, the centroid of each cluster being a repertoire functional unit ("RFU"); converting each TCR in one or more TCR repertoire samples to said numerical vector; assigning one or more of said converted TCRs from each of said one or more TCR repertoire samples to an RFU based on one or more correlations; normalizing the number of RFUs with assigned converted TCRs from each of said one or more TCR repertoire samples by the total number of TCRs in the corresponding TCR repertoire sample to generate a fixed length RFU vector for each of said one or more TCR repertoire samples; performing a first principal component (PC1) analysis on said fixed length RFU vectors of said one or more TCR repertoire samples; performing a second principal component (PC2) analysis on the fixed length RFU vectors of the one or more TCR repertoire samples; and Comparing the results of the PC1 analysis with the results of the PC2 analysis to distinguish between a set of healthy samples and a set of unhealthy samples. The method includes:

3. 3. The method of claim 2, wherein the step of discriminating between the set of healthy and non-healthy samples achieves an area under the curve (AUC) of at least 93%.

4. The method of claim 1, wherein the fixed length RFU vector represents the relative abundance of a given RFU in each TCR repertoire sample.

5. The method of claim 1, wherein the large array comprises a data set of TCRs ranging in number from about 10 million to 100 million.

6. The method of claim 1, wherein the large sequence comprises TCRs covering one or more of healthy donors, cancer, infectious diseases, and autoimmune disorders.

7. encoding the short peptide sequence, performing ultra-large-scale TCR clustering of the TCRs in said large array; using the clustered TCRs to define interchangeable trimers; inducing isometric embedding of the interchangeable trimmers; defining a Euclidean Distance Matrix (EDM) representing the interchangeable trimers; applying multidimensional scaling (MDS) to the EDM to derive a numerical vector for each of the interchangeable trimmers; removing one or more amino acids from each complementarity determining region 3 (CDR3) of each clustered TCR to form a respective sequence; splitting each individual sequence into tiling trimers; selecting one or more corresponding interchangeable trimers for each clustered TCR; and averaging the numerical vectors of the one or more corresponding interchangeable trimers to obtain the numerical vector having a fixed dimension for each clustered TCR. The method of claim 1 , comprising:

8. 2. The method of claim 1, wherein the pool of extant TCRs from healthy individuals comprises a data set of TCRs ranging in number from about 500,000 to about one million.

9. The method of claim 1 , wherein the one or more correlations comprises a rank correlation.

10. The method of claim 1 , wherein the one or more TCR repertoire samples comprise a first set of samples and a second set of samples.

11. performing a first principal component (PC1) analysis on said fixed length RFU vectors of said one or more TCR repertoire samples; performing a second principal component (PC2) analysis on the fixed length RFU vectors of the one or more TCR repertoire samples; and comparing the results of the PC1 analysis with the results of the PC2 analysis to distinguish between the first set of samples and the second set of samples. The method of claim 10 further comprising:

12. 12. The method of claim 11, wherein the first set of samples comprises healthy controls and the second set of samples comprises one or more of cancer, an infectious disease, and an autoimmune disorder.

13. 13. The method of claim 11 or 12, wherein discriminating between the first set of samples and the second set of samples achieves an area under the curve (AUC) of at least 90%.

14. 14. The method of any one of claims 11 to 13, wherein discriminating between the first set of samples and the second set of samples achieves an area under the curve (AUC) of at least 93%.

15. 15. The method of any one of claims 11 to 14, wherein discriminating between the first set of samples and the second set of samples achieves an area under the curve (AUC) of at least 94%.

16. 16. The method of any one of claims 11 to 15, wherein discriminating between the first set of samples and the second set of samples achieves an area under the curve (AUC) of at least 96%.

17. When executed by a processor, encoding short peptide sequences of T cell receptors (TCRs) within a larger sequence of TCR samples into numerical vectors of fixed dimensions, the short peptide sequences having different lengths; converting each TCR in a pool of existing TCRs from healthy individuals into said numerical vector to generate a distribution of said numerical vectors in a high-dimensional Euclidean space; clustering the converted TCRs from the pool of existing TCRs into antigen-specific clusters, the centroid of each cluster being a repertoire functional unit ("RFU"); converting each TCR in one or more TCR repertoire samples to said numerical vector; assigning one or more of the converted TCRs from each of the one or more TCR repertoire samples to an RFU based on one or more correlations; and normalizing the number of RFUs with assigned converted TCRs from each of said one or more TCR repertoire samples by the total number of TCRs in the corresponding TCR repertoire sample to generate a fixed length RFU vector for each of said one or more TCR repertoire samples. a processor operatively coupled to a memory storing non-transitory computer readable instructions that cause the processor to execute 3. A computing device comprising:

18. 18. The computing device of claim 17, wherein the fixed length RFU vector represents the relative abundance of a given RFU in each TCR repertoire sample.

19. 18. The computing device of claim 17, wherein the large array comprises a dataset of TCRs ranging in number from about 10 million to 100 million.

20. 20. The computing device of claim 17, wherein the large array comprises TCRs covering one or more of healthy donors, cancer, infectious diseases, and autoimmune disorders.

21. encoding the short peptide sequence, performing ultra-large-scale TCR clustering of the TCRs in said large array; using the clustered TCRs to define interchangeable trimers; inducing isometric embedding of the interchangeable trimmers; defining a Euclidean Distance Matrix (EDM) representing the interchangeable trimers; applying multidimensional scaling (MDS) to the EDM to derive a numerical vector for each of the interchangeable trimmers; removing one or more amino acids from each complementarity determining region 3 (CDR3) of each clustered TCR to form a respective sequence; splitting each individual sequence into tiling trimers; selecting one or more corresponding interchangeable trimers for each clustered TCR; and averaging the numerical vectors of the one or more corresponding interchangeable trimers to obtain the numerical vector having a fixed dimension for each clustered TCR.

20. The computing device of claim 17, comprising:

22. 18. The computing device of claim 17, wherein the pool of extant TCRs from healthy individuals comprises a data set of TCRs ranging in number from about 500,000 to about one million.

23. The computing device of claim 17 , wherein the one or more correlations include a rank correlation.

24. 20. The computing device of claim 17, wherein the one or more TCR repertoire samples comprise a first set of samples and a second set of samples.

25. The non-transitory computer readable instructions, when executed by a processor, performing a first principal component (PC1) analysis on said fixed length RFU vectors of said one or more TCR repertoire samples; performing a second principal component (PC2) analysis on the fixed length RFU vectors of the one or more TCR repertoire samples; and comparing the results of the PC1 analysis with the results of the PC2 analysis to distinguish between the first set of samples and the second set of samples.

25. The computing device of claim 24, further comprising a processor configured to execute:

26. 26. The computing device of claim 25, wherein the first set of samples comprises healthy controls and the second set of samples comprises one or more of a cancer, an infectious disease, and an autoimmune disorder.

27. 27. The computing device of claim 25 or 26, wherein the non-transitory computer readable instructions causing the processor to discriminate between the first set of samples and the second set of samples achieves an area under the curve (AUC) of at least 90%.

28. 28. The computing device of any one of claims 25 to 27, wherein discriminating between the first set of samples and the second set of samples achieves an area under the curve (AUC) of at least 93%.

29. 29. The computing device of any one of claims 25 to 28, wherein discriminating between the first set of samples and the second set of samples achieves an area under the curve (AUC) of at least 94%.

30. 30. The computing device of any one of claims 25 to 29, wherein discriminating between the first set of samples and the second set of samples achieves an area under the curve (AUC) of at least 96%.

31. When executed by a processor associated with a computing device, encoding short peptide sequences of T cell receptors (TCRs) within a larger sequence of TCR samples into numerical vectors of fixed dimensions, the short peptide sequences having different lengths; converting each TCR in a pool of existing TCRs from healthy individuals into said numerical vector to generate a distribution of said numerical vectors in a high-dimensional Euclidean space; clustering the converted TCRs from the pool of existing TCRs into antigen-specific clusters, the centroid of each cluster being a repertoire functional unit ("RFU"); converting each TCR in one or more TCR repertoire samples to said numerical vector; assigning one or more of the converted TCRs from each of the one or more TCR repertoire samples to an RFU based on one or more correlations; and normalizing the number of RFUs with assigned converted TCRs from each of said one or more TCR repertoire samples by the total number of TCRs in the corresponding TCR repertoire sample to generate a fixed length RFU vector for each of said one or more TCR repertoire samples. A non-transitory computer-readable storage medium tangibly encoded with computer-executable instructions for causing a processor to execute the program.

32. 32. The non-transitory computer-readable storage medium of claim 31 , wherein the fixed length RFU vector represents the relative abundance of a given RFU in each TCR repertoire sample.

33. 32. The non-transitory computer readable storage medium of claim 31 , wherein the large array comprises a dataset of TCRs ranging in number from about 10 million to 100 million.

34. 32. The non-transitory computer readable storage medium of claim 31 , wherein the large array comprises TCRs covering one or more of healthy donors, cancer, infectious diseases, and autoimmune disorders.

35. encoding the short peptide sequence, performing ultra-large-scale TCR clustering of the TCRs in said large array; using the clustered TCRs to define interchangeable trimers; inducing isometric embedding of the interchangeable trimmers; defining a Euclidean Distance Matrix (EDM) representing the interchangeable trimers; applying multidimensional scaling (MDS) to the EDM to derive a numerical vector for each of the interchangeable trimmers; removing one or more amino acids from each complementarity determining region 3 (CDR3) of each clustered TCR to form a respective sequence; splitting each individual sequence into tiling trimers; selecting one or more corresponding interchangeable trimers for each clustered TCR; and averaging the numerical vectors of the one or more corresponding interchangeable trimers to obtain the numerical vector having a fixed dimension for each clustered TCR; 32. The non-transitory computer readable storage medium of claim 31, comprising:

36. 32. The non-transitory computer readable storage medium of claim 31, wherein the pool of extant TCRs from healthy individuals comprises a dataset of TCRs ranging in number from about 500,000 to about one million.

37. 32. The non-transitory computer-readable storage medium of claim 31 , wherein the one or more correlations include a rank correlation.

38. 32. The non-transitory computer readable storage medium of claim 31 , wherein the one or more TCR repertoire samples comprise a first set of samples and a second set of samples.

39. The non-transitory computer readable instructions, when executed by a processor, performing a first principal component (PC1) analysis on said fixed length RFU vectors of said one or more TCR repertoire samples; performing a second principal component (PC2) analysis on the fixed length RFU vectors of the one or more TCR repertoire samples; and comparing the results of the PC1 analysis with the results of the PC2 analysis to distinguish between the first set of samples and the second set of samples.

40. The non-transitory computer-readable storage medium of claim 38, further causing a processor to execute:

40. 40. The non-transitory computer readable storage medium of claim 39, wherein the first set of samples comprises healthy controls and the second set of samples comprises one or more of cancer, an infectious disease, and an autoimmune disorder.

41. 41. The non-transitory computer readable medium of claim 39 or 40, wherein the computer executable instructions that cause the processor to discriminate between the first set of samples and the second set of samples achieves an area under the curve (AUC) of at least 90%.

42. 42. The non-transitory computer readable medium of any one of claims 39 to 41, wherein discriminating between the first set of samples and the second set of samples achieves an area under the curve (AUC) of at least 93%.

43. 43. The non-transitory computer readable medium of any one of claims 39 to 42, wherein discriminating between the first set of samples and the second set of samples achieves an area under the curve (AUC) of at least 94%.

44. 43. The non-transitory computer readable medium of any one of claims 39 to 42, wherein discriminating between the first set of samples and the second set of samples achieves an area under the curve (AUC) of at least 96%.

Images