[go: up one dir, main page]

WO2025085824A1 - Analyse multi-échelle de données de séquence d'acide ribonucléique pour prédire des réponses à des thérapies anticancéreuses - Google Patents

Analyse multi-échelle de données de séquence d'acide ribonucléique pour prédire des réponses à des thérapies anticancéreuses Download PDF

Info

Publication number
WO2025085824A1
WO2025085824A1 PCT/US2024/052082 US2024052082W WO2025085824A1 WO 2025085824 A1 WO2025085824 A1 WO 2025085824A1 US 2024052082 W US2024052082 W US 2024052082W WO 2025085824 A1 WO2025085824 A1 WO 2025085824A1
Authority
WO
WIPO (PCT)
Prior art keywords
cancers
network
iteration
metric
node
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
PCT/US2024/052082
Other languages
English (en)
Inventor
Joseph O. Deasy
Rena ELKIN
Larry Norton
Jung Hun Oh
Allen TANNENBAUM
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Memorial Sloan Kettering Cancer Center
Research Foundation of the State University of New York
Original Assignee
Memorial Sloan Kettering Cancer Center
Research Foundation of the State University of New York
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Memorial Sloan Kettering Cancer Center, Research Foundation of the State University of New York filed Critical Memorial Sloan Kettering Cancer Center
Publication of WO2025085824A1 publication Critical patent/WO2025085824A1/fr
Pending legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61P—SPECIFIC THERAPEUTIC ACTIVITY OF CHEMICAL COMPOUNDS OR MEDICINAL PREPARATIONS
    • A61P35/00—Antineoplastic agents
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
    • G01N33/48—Biological material, e.g. blood, urine; Haemocytometers
    • G01N33/50—Chemical analysis of biological material, e.g. blood, urine; Testing involving biospecific ligand binding methods; Immunological testing
    • G01N33/53—Immunoassay; Biospecific binding assay; Materials therefor
    • G01N33/574—Immunoassay; Biospecific binding assay; Materials therefor for cancer
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16B—BIOINFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR GENETIC OR PROTEIN-RELATED DATA PROCESSING IN COMPUTATIONAL MOLECULAR BIOLOGY
    • G16B25/00—ICT specially adapted for hybridisation; ICT specially adapted for gene or protein expression
    • G16B25/10—Gene or protein expression profiling; Expression-ratio estimation or normalisation
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16B—BIOINFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR GENETIC OR PROTEIN-RELATED DATA PROCESSING IN COMPUTATIONAL MOLECULAR BIOLOGY
    • G16B40/00—ICT specially adapted for biostatistics; ICT specially adapted for bioinformatics-related machine learning or data mining, e.g. knowledge discovery or pattern finding
    • G16B40/10—Signal processing, e.g. from mass spectrometry [MS] or from PCR
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
    • G16H10/40—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for data related to laboratory analysis, e.g. patient specimen analysis
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H20/00—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
    • G16H20/10—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to drugs or medications, e.g. for ensuring correct administration to patients
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/50—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for simulation or modelling of medical disorders
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N2800/00—Detection or diagnosis of diseases
    • G01N2800/52—Predicting or monitoring the response to treatment, e.g. for selection of therapy based on assay results in personalised medicine; Prognosis

Definitions

  • a sequencing system may generate sequence data using biological material.
  • a computing system may process the sequence data from the sequencing system to output information about the material.
  • One or more processors may construct, based on ribonucleic acid (RNA) sequence data obtained from a tumor of the subject, a network comprising a plurality of nodes and a plurality of edges.
  • RNA ribonucleic acid
  • Each node of the plurality of nodes may be associated with a respective RNA expression of a cancer associated gene.
  • Each edge of the plurality of edges may define a connection between a first respective node and a second respective node of the plurality of nodes to identify a respective weight metric between a first RNA expression corresponding to the first node and a second RNA expression of the second node.
  • the one or more processors may perform, for a plurality of iterations (sometimes herein referred to as scales), a respective diffusion operation throughout the network, for each edge of the plurality of edges, to assign a first value to each edge of the plurality of edges based on a second value of at least one adjacent edge of the plurality of edges.
  • the plurality of iterations may include a first iteration and at least one additional iteration.
  • the one or more processors may determine, for each iteration of the plurality of iterations, a respective -1- 4894-5448-8045.1 Atty. Dkt. No.: 115872-3100 curvature metric of the network using the weight metric defined by each edge of the plurality of edges of the network.
  • the one or more processors may select, from the plurality of iterations, a critical iteration based on a difference between the respective curvature metric of the network determined at the first iteration and the respective curvature metric of the network determined for an iteration from the at least one additional iteration.
  • the one or more processors may generate a plurality of features to include (i) the respective weight metric in each edge of the plurality of edges of the network at each iteration of the plurality of iterations, (ii) the respective curvature metric for the network for each iteration of the plurality of iterations, and (iii) the difference between the respective curvature metric for the network determined at the first iteration and the respective curvature metric for the network determined for the iteration from the at least one additional iteration.
  • the one or more processors may apply the plurality of features to a model to generate a score indicating the likelihood of responsiveness of the subject to the anti-cancer therapy.
  • the one or more processors may select the subject for administration of the anti-cancer therapy, responsive to the score satisfying a threshold. In some embodiments, the one or more processors may exclude the subject from administration of the anti-cancer therapy, responsive to the score not satisfying a threshold. In some embodiments, the one or more processors may perform the respective diffusion operation for each iteration by computing a graph profile of the network used to assign to a respective value to each weight metric of a plurality of weight metrics for at least one of the plurality of edges or the plurality of nodes in the network.
  • the one or more processors may perform, for the plurality of iterations, the respective diffusion operation throughout the network, for each node of the plurality of nodes, to assign a third value to each node of the plurality of nodes based on a fourth value of at least one adjacent node of the plurality of nodes.
  • the one or more processors may determine, for each iteration of the plurality of iterations, the respective curvature metric of the network in accordance with a Ollivier-Ricci curvature (ORC).
  • ORC Ollivier-Ricci curvature
  • the one or more processors may determine the respective curvature metric of the network using a weight metric defined by each edge of the plurality of edge of the network.
  • the one or more processors may select the critical iteration in accordance with a policy.
  • the policy may define at least one of: (i) selection based on maximum dispersion or variance at that iteration, (ii) selection based on a maximum value for the difference, (iii) selection based on an inflection of the curvature metric, or (iv) selection based on the respective curvature metric among one or more subsets of the plurality of edges of the network at the iteration.
  • the one or more processors may generate the plurality of features to include a respective value in each node of the plurality of nodes of the network at each iteration of the plurality of iterations.
  • the model may include at least one of a machine learning (ML) model or a statistical model.
  • the anti-cancer therapy is selected from among immune checkpoint blockade therapy, an anti-cancer vaccine, a monoclonal antibody-based immunotherapy, adoptive cell therapy, chemotherapy, hormonal therapy, and molecularly- targeted therapies (e.g., CDK4/6, MTOR, and PIK3CA inhibitors).
  • cancer examples include, but are not limited to, carcinomas, sarcomas, hematopoietic cancers. adrenal cancers, bladder cancers, blood cancers, bone cancers, brain cancers, breast cancers, carcinoma, cervical cancers, colon cancers, colorectal cancers, corpus uterine cancers, ear, nose and throat (ENT) cancers, endometrial cancers, esophageal cancers, gastrointestinal cancers, head and neck cancers, Hodgkin's disease, intestinal cancers, kidney cancers, larynx cancers, leukemias, liver cancers, lymph node cancers, lymphomas, lung cancers, melanomas, mesothelioma, myelomas, nasopharynx cancers, neuroblastomas, non- Hodgkin's lymphoma, oral cancers, ovarian cancers, pancreatic cancers, penile cancers, pharynx cancers, prostate cancers, rectal cancers, sar
  • FIG.1 depicts a block diagram of a schematic for network diffusion with multi-scale weighted network profiles.
  • FIG.2A shows a graph of diffused profiles of the network across multiple scales. -3- 4894-5448-8045.1 Atty. Dkt. No.: 115872-3100
  • FIG.2B shows a graph of edge curvatures of the network across multiple scales.
  • FIGs.3A–C shows standardized profiles for a number of edges across scales.
  • FIGs.4A–H show bar graphs of enrichment by process networks between responders and non-responders.
  • FIG.5A show a graph of a prediction on a test set with an 80/20 split for training and testing split of the dataset.
  • FIG.5B shows a graph of collective prediction on a test fold using three-fold cross validations.
  • FIG.6 depicts a block diagram of a system for determining likelihoods of responsiveness of subjects suffering from cancer to anti-cancer therapies, in accordance with an illustrative embodiment.
  • FIG.7 depicts a block diagram of a process to generate networks using subject data in the system for determining likelihoods of responsiveness of subjects, in accordance with an illustrative embodiment.
  • FIG.8 depicts a block diagram of a process to performing iterations to calculate curvature metrics using networks in the system for determining likelihoods of responsiveness of subjects, in accordance with an illustrative embodiment.
  • FIG.9 depicts a block diagram of a process to generate outputs for subjects in the system for determining likelihoods of responsiveness of subjects, in accordance with an illustrative embodiment.
  • FIG.10 depicts a flow diagram of a method of determining likelihoods of responsiveness of subjects suffering from cancer to anti-cancer therapies, in accordance with an illustrative embodiment.
  • FIG.11 depicts a block diagram of a server system and a client computer system, in accordance with one or more implementations. -4- 4894-5448-8045.1 Atty. Dkt.
  • the term “about” in reference to a number is generally taken to include numbers that fall within a range of 1%, 5%, or 10% in either direction (greater than -5- 4894-5448-8045.1 Atty. Dkt. No.: 115872-3100 or less than) of the number unless otherwise stated or otherwise evident from the context (except where such number would be less than 0% or exceed 100% of a possible value).
  • the “administration” of an agent or drug to a subject includes any route of introducing or delivering to a subject a compound to perform its intended function.
  • Administration can be carried out by any suitable route, including but not limited to, orally, intranasally, parenterally (intravenously, intramuscularly, intraperitoneally, or subcutaneously), rectally, intrathecally, intratumorally or topically. Administration includes self-administration and the administration by another.
  • biological sample means sample material derived from living cells. Biological samples may include tissues, cells, protein or membrane extracts of cells, and biological fluids (e.g., ascites fluid or cerebrospinal fluid (CSF)) isolated from a subject, as well as tissues, cells and fluids present within a subject.
  • biological fluids e.g., ascites fluid or cerebrospinal fluid (CSF)
  • Biological samples of the present technology include, but are not limited to, samples taken from breast tissue, renal tissue, the uterine cervix, the endometrium, the head or neck, the gallbladder, parotid tissue, the prostate, the brain, the pituitary gland, kidney tissue, muscle, the esophagus, the stomach, the small intestine, the colon, the liver, the spleen, the pancreas, thyroid tissue, heart tissue, lung tissue, the bladder, adipose tissue, lymph node tissue, the uterus, ovarian tissue, adrenal tissue, testis tissue, the tonsils, thymus, blood, hair, buccal, skin, serum, plasma, CSF, semen, prostate fluid, seminal fluid, urine, feces, sweat, saliva, sputum, mucus, bone marrow, lymph, and tears.
  • Bio samples can also be obtained from biopsies of internal organs or from cancers. Biological samples can be obtained from subjects for diagnosis or research or can be obtained from non-diseased individuals, as controls or for basic research. Samples may be obtained by standard methods including, e.g., venous puncture and surgical biopsy. In certain embodiments, the biological sample is a tissue sample obtained by needle biopsy.
  • cancer or “tumor” are used interchangeably and refer to the presence of cells possessing characteristics typical of cancer-causing cells, such as uncontrolled proliferation, immortality, metastatic potential, rapid growth and proliferation rate, and certain characteristic morphological features.
  • Cancer cells are often in the form of a tumor, but such cells can exist alone within an animal, or can be a non-tumorigenic cancer -6- 4894-5448-8045.1 Atty. Dkt. No.: 115872-3100 cell.
  • cancer includes premalignant, as well as malignant cancers.
  • the cancer is ovarian cancer.
  • “Curvature” is a local measure of how a geometric object (e.g., curve, surface, space) deviates from being flat in the Euclidean sense.
  • a change in curvature refers to a difference in curvature between networks.
  • curvature of the edges of a network refers to a parameter that measures the changes in the architecture or connectivity of a network of gene pathways for each individual tumor, where each network node represents a respective RNA expression level of a cancer associated gene, and each edge defines a connection between a first respective node and a second respective node of the network to identify a respective weight metric between a first RNA expression corresponding to the first node and a second RNA expression of the second node. Curvature measures the connectivity in the sense of feedback loops, and the weight metrics measure the projected impact upon the changes in the network architecture.
  • a “control” is an alternative sample used in an experiment for comparison purpose.
  • a control can be “positive” or “negative.”
  • a positive control a compound or composition known to exhibit the desired therapeutic effect
  • a negative control a subject or a sample that does not receive the therapy or receives a placebo
  • an “edge” of a network refers to one of the connections between two nodes (or vertices) of the network. In some embodiments, the edges are unidirectional or bidirectional.
  • the term “effective amount” refers to a quantity sufficient to achieve a desired therapeutic and/or prophylactic effect, e.g., an amount which results in the prevention of, or a decrease in a disease or condition described herein or one or more signs or symptoms associated with a disease or condition described herein.
  • the amount of a composition administered to the -7- 4894-5448-8045.1 Atty. Dkt. No.: 115872-3100 subject will vary depending on the composition, the degree, type, and severity of the disease and on the characteristics of the individual, such as general health, age, sex, body weight and tolerance to drugs. The skilled artisan will be able to determine appropriate dosages depending on these and other factors.
  • compositions can also be administered in combination with one or more additional therapeutic compounds.
  • the therapeutic compositions may be administered to a subject having one or more signs or symptoms of a disease or condition described herein.
  • a “therapeutically effective amount” of a composition refers to composition levels in which the physiological effects of a disease or condition are ameliorated or eliminated.
  • a therapeutically effective amount can be given in one or more administrations.
  • expression refers to the process by which polynucleotides are transcribed into mRNA and/or the process by which the transcribed mRNA is subsequently being translated into peptides, polypeptides, or proteins.
  • expression can include splicing of the mRNA in a eukaryotic cell.
  • the expression level of a gene can be determined by measuring the amount of mRNA or protein in a cell or tissue sample.
  • the expression level of a gene from one sample can be directly compared to the expression level of that gene from a control or reference sample.
  • the expression level of a gene from one sample can be directly compared to the expression level of that gene from the same sample following administration of the compositions disclosed herein.
  • RNA template from a DNA sequence (e.g., by transcription) within a cell
  • processing of an RNA transcript e.g., by splicing, editing, 5’ cap formation, and/or 3’ end formation
  • translation of an RNA sequence into a polypeptide or protein within a cell e.g., by splicing, editing, 5’ cap formation, and/or 3’ end formation
  • translation of an RNA sequence into a polypeptide or protein within a cell e.g., by splicing, editing, 5’ cap formation, and/or 3’ end formation
  • translation e.g., by splicing, editing, 5’ cap formation, and/or 3’ end formation
  • post-translational modification of a polypeptide or protein within a cell e.g., by post-translational modification of a polypeptide or protein within a cell
  • presentation of a polypeptide or protein on the cell surface e.
  • a “network” refers to a plurality of nodes that are connected by edges. Networks can represent many different types of data.
  • a “biological network” is a representation of systems as complex sets of binary interactions or relations between various biological entities. In general, networks or graphs are used to capture relationships between entities or objects.
  • the nodes of the network represent different entities (e.g.
  • edges convey information about the connections between the nodes.
  • a “node” represents an intersection point or vertex of a network.
  • polynucleotide “nucleic acid” and “oligonucleotide” are used interchangeably and refer to a polymeric form of nucleotides of any length, either deoxyribonucleotides or ribonucleotides or analogs thereof. Polynucleotides can have any three dimensional structure and may perform any function, known or unknown.
  • polynucleotides a gene or gene fragment (for example, a probe, primer, EST or SAGE tag), exons, introns, messenger RNA (mRNA), transfer RNA, ribosomal RNA, ribozymes, cDNA, recombinant polynucleotides, branched polynucleotides, plasmids, vectors, isolated DNA of any sequence, isolated RNA of any sequence, nucleic acid probes and primers.
  • a polynucleotide can comprise modified nucleotides, such as methylated nucleotides and nucleotide analogs.
  • modifications to the nucleotide structure can be imparted before or after assembly of the polynucleotide.
  • the sequence of nucleotides can be interrupted by non nucleotide components.
  • a polynucleotide can be further modified after polymerization, such as by conjugation with a labeling component.
  • the term also refers to both double and single stranded molecules. Unless otherwise specified or required, any embodiment of this disclosure that is a polynucleotide encompasses both the double stranded form and each of two complementary single stranded forms known or predicted to make up the double stranded form.
  • a polynucleotide is composed of a specific sequence of four nucleotide bases: adenine (A); cytosine (C); guanine (G); thymine (T); and uracil (U) for thymine when the polynucleotide is RNA.
  • polynucleotide sequence is the alphabetical representation of a polynucleotide molecule. This alphabetical representation -9- 4894-5448-8045.1 Atty. Dkt. No.: 115872-3100 can be input into databases in a computer having a central processing unit and used for bioinformatics applications such as functional genomics and homology searching.
  • polypeptide “peptide,” and “protein” are used interchangeably herein to refer to a polymer of amino acid residues.
  • the terms apply to naturally occurring amino acid polymers as well as amino acid polymers in which one or more amino acid residues are a non-naturally occurring amino acid, e.g., an amino acid analog.
  • the terms encompass amino acid chains of any length, including full length proteins, wherein the amino acid residues are linked by covalent peptide bonds.
  • prevention or “preventing” of a disorder or condition refers to a compound that, in a statistical sample, reduces the occurrence of the disorder or condition in the treated sample relative to an untreated control sample, or delays the onset of one or more symptoms of the disorder or condition relative to the untreated control sample.
  • sample refers to clinical samples obtained from a subject.
  • a sample is obtained from a biological source (i.e., a "biological sample"), such as tissue, bodily fluid, or microorganisms collected from a subject.
  • Sample sources include, but are not limited to, mucus, sputum, bronchial alveolar lavage (BAL), bronchial wash (BW), whole blood, bodily fluids, cerebrospinal fluid (CSF), urine, plasma, serum, or tissue.
  • BAL bronchial alveolar lavage
  • BW bronchial wash
  • whole blood bodily fluids
  • cerebrospinal fluid CSF
  • urine plasma
  • plasma serum
  • tissue tissue.
  • therapeutic agent is intended to mean a compound that, when present in an effective amount, produces a desired therapeutic effect on a subject in need thereof.
  • Treating” or “treatment” as used herein covers the treatment of a disease or disorder described herein, in a subject, such as a human, and includes: (i) inhibiting a disease or disorder, i.e., arresting its development; (ii) relieving a disease or disorder, i.e., causing regression of the disorder; (iii) slowing progression of the disorder; and/or (iv) inhibiting, relieving, or slowing progression of one or more symptoms of the disease or disorder.
  • treatment means that the symptoms associated with the disease are, e.g., alleviated, reduced, cured, or placed in a state of remission. -10- 4894-5448-8045.1 Atty. Dkt.
  • the various modes of treatment or prevention of disorders as described herein are intended to mean “substantial,” which includes total but also less than total treatment, and wherein some biologically or medically relevant result is achieved.
  • the treatment may be a continuous prolonged treatment for a chronic disease or a single, or few time administrations for the treatment of an acute condition.
  • FIG.1 depicted is a block diagram of a schematic for network diffusion with multi-scale weighted network profiles.
  • a weighted network is constructed from an input network of interacting objects, represented as nodes, and a network profile, used to assign the weights.
  • Network profiles are then computed as a function of scale by diffusing an initial profile, where diffusion is defined as the spread or mixing of information among nodes or edges in the network through their connections.
  • the weighted network is updated with the corresponding diffused network profile associated with that scale. Accordingly, network curvature, which quantifies the geometry of the network’s shape, is computed. -11- 4894-5448-8045.1 Atty. Dkt.
  • curvature may be computed on edges, nodes, subgraphs, or as a global network feature. Curvature considers the relationships between node- neighborhoods, as opposed to the nodes themselves in isolation. In this way, curvature provides a measure of the cooperation among objects in the network, which is influenced by the weights, and differences in curvature provide information on the network robustness as a system. For any two scales a and b (b>a), the difference in curvature, computed as the curvature at scale b minus the curvature at scale a, provides a relative measure of the change in the network’s robustness (or conversely, fragility) between the scales.
  • differences in curvature may be computed between aggregate-scales composited over a window of consecutive scales to boost the signal.
  • a critical scale is determined as the scale that optimally characterizes the system-level cooperation among communal subsets of the nodes.
  • One criterion for determining the critical scale is to maximize curvature variance (or dispersion).
  • Another criterion may be the inflection point where curvature changes sign, indicative of bridge-like edges transforming to hub-like edges (and vice-versa). While there are multiple criteria that can be used, the common factor is that whichever criterion is selected should identify the optimal resolution to capture system-level behavior associated with phenotypic outcomes.
  • the critical curvature defined as the curvature at the critical scale
  • the critical difference in curvature defined as the difference in curvature between the critical and initial scale.
  • the geometry may change gradually across scales, making the selection of a critical window preferable to a single scale.
  • the critical curvature and critical difference in curvature is defined the same as above in the case of a single scale, where the curvature in this case refers to an aggregate curvature over the critical window.
  • the multi-scale network profiles, geometric curvature profiles, and (critical) differences in curvature profiles are used as features to train a machine learning model for identifying biomarkers and predicting response. These features are suitable for a wide -12- 4894-5448-8045.1 Atty. Dkt. No.: 115872-3100 range of supervised and unsupervised machine learning approaches, including but not limited to logistic regression, random forest and gradient boosting machines.
  • the aforementioned multi-scale geometric network features are computed and fed to the model. The model then outputs a number between 0 and 1 predicting response, where the closer the output is to 1, the more likely the patient would benefit from receiving the therapy.
  • Dkt. No.: 115872-3100 assign diffused profile ⁇ ⁇ ⁇ ⁇ as node weights and compute ORC on edges, as usual (with recomputed nodal distributions ⁇
  • the Laplacian, computed from initial profile, is fixed across all iterations.
  • the graph distance, computed from the initial profile, used as the ground distance in computing ORC is fixed across all iterations. Referring to FIGs.2A and 2B, shown are graphs of diffused profiles and edge curvatures of the network across multiple scales.
  • FIG.3A shows standardized delta profiles for 32 significant edges with MWU-p ⁇ 0.0001.
  • FIG.3B shows standardized delta edge curvatures for 130 significant edges with MWU-p ⁇ 0.0001.
  • FIG.3C shows standardized delta node curvatures for 33 significant edges with MWU-p ⁇ 0.0001.
  • four genes are shown to be in common: TPST2, TPST1, CCL13, BAAT, with BAAT connected to only one other gene (SLC7A11) in the graph.
  • FIGs.4A–H depicted are bar graphs of enrichment by process networks between responders and non-responders.
  • FIGs.5A and 5B depicted are graphs of logistic regression predictions of drug responses.
  • FIG.5A shows a graph of a prediction on a test set with an 80/20 split for training and testing split of the dataset.
  • FIG.5B shows a graph of collective -15- 4894-5448-8045.1 Atty. Dkt. No.: 115872-3100 prediction on a test fold using three-fold cross validations. Diffused profile at critical time may be more predictive than initial profile.
  • the system 100 may include at least one data processing system 105, at least one sequencing device 110, at least one computing device 115, and at least one database 120, communicatively coupled with one another via at least one communication network 125.
  • the data processing system 105 may include at least one dataset retriever 130, at least one network constructor 135, at least one diffusion iterator 140, at least one curvature analyzer 145, at least one feature generator 150, at least one output evaluator 155, and at least one model 160.
  • the diffusion iterator 140 may perform diffusion operations through the network for a number of iterations.
  • the curvature analyzer 145 may calculate curvature metrics of the network.
  • the feature generator 150 may generate a set of features using the network.
  • the output evaluator 155 may determine a score to indicate a predicted responsiveness of the subject to anti-cancer therapy based on applying the set of features to the model 160.
  • the model 160 may be used to determine a score to indicate the predicted responsiveness of the subject to anti-cancer therapy.
  • the model 160 may include at least one input and at least output, among others.
  • the input may be related to the output via a set of parameters.
  • the input may include the set of features.
  • the output may include the score to indicate the predicted responsiveness of the subject to anti-cancer therapy.
  • the statistical model may include, for example, a regression model (e.g., a linear or logistic regression model) or a probability distribution (e.g., a normal distribution, binomial distribution, Poisson distribution, a Gamma distribution, a Chi-Square distribution, a Cauchy distribution), among others.
  • the sequencing device 110 may perform RNA sequencing on an RNA sample to generate RNA sequencing datasets.
  • the RNA sequencing performed may -18- 4894-5448-8045.1 Atty. Dkt.
  • No.: 115872-3100 include, for example, Poly(A) Selection RNA-seq, Total RNA-seq, strand-specific RNA- seq, single-cell RNA-seq, Long-read RNA-seq, small RNA-seq, or RNA capture sequencing, among others.
  • the genetic sequencing may be targeted to extract RNA expression data from the sample of the subject.
  • the genome sequencing dataset may include long reads (e.g., greater than 1000 base pairs) or short reads (e.g., between 50 to 300 base pairs).
  • the RNA sequencing dataset may include long reads (e.g., greater than 1000 base pairs) or short reads (e.g., between 50 to 300 base pairs).
  • the gene sequencing and RNA sequence may be maintained using one or more files according to a format (e.g., FASTQ, BCL, or VCF formats).
  • the computing device 115 may (sometimes herein referred to as an end user computing device) may be any computing device comprising one or more processors coupled with memory and software and capable of performing the various processes and tasks described herein.
  • the computing device 115 may be in communication with the data processing system 105, the sequencing device 110, and the database 120 via the communication network 125.
  • the computing device 115 may have at least one display.
  • the computing device 115 may be associated with an entity (e.g., a clinician) examining the subject or RNA data from the subject for cancer therapy administration.
  • the display may present information about the subject provided by the data processing system 105.
  • the database 120 may store and maintain various resources and data associated with the data processing system 105, the sequencing device 110, and the computing device 115, among others.
  • the database 120 may include a database management system (DBMS) to arrange and organize the data maintained thereon.
  • the database 120 may be in communication with the data processing system 105, the sequencing device 110, and the computing device 115, via the communication network 125. While running various operations, the data processing system 105, the sequencing device 110, and the computing device 115 may access the database 120 to retrieve identified data therefrom.
  • the data processing system -19- 4894-5448-8045.1 Atty. Dkt. No.: 115872-3100 105, the sequencing device 110, and the computing device 115 may also write data onto the database 120 from running such operations.
  • FIG.7 depicted is a block diagram of a process 200 to generate networks using subject data in the system 100 for determining likelihoods of responsiveness of subjects.
  • the sequencing device 110 may execute, carry out, or otherwise perform ribonucleic acid (RNA) sequencing for at least one subject 205.
  • the subject 205 may be at risk of or diagnosed with cancer.
  • the subject 205 may be under evaluation for responsiveness to anti-cancer therapy.
  • Tumor 210 to be used as the sample for RNA sequencing may be obtained from any tissue or organ of the subject 205, such as lung, head, neck, colon, rectum, uterus, endometrium, stomach, ovary, cervix, bladder, or breast, among others.
  • the cancer may include, for example, lung cancer, brain cancer, head and neck cancer, colon cancer, rectal cancer, uterine cancer, endometrial cancer, stomach cancer, ovarian cancer, cervical cancer, bladder cancer, or breast cancer, among others.
  • the cancer associated with the tumor 210 of the subject 205 may include, for example, at least one of carcinomas, sarcomas, hematopoietic cancers.
  • adrenal cancers bladder cancers, blood cancers, bone cancers, brain cancers, breast cancers, carcinoma, cervical cancers, colon cancers, colorectal cancers, corpus uterine cancers, ear, nose and throat (ENT) cancers, endometrial cancers, esophageal cancers, gastrointestinal cancers, head and neck cancers, Hodgkin's disease, intestinal cancers, kidney cancers, larynx cancers, leukemias, liver cancers, lymph node cancers, lymphomas, lung cancers, melanomas, mesothelioma, myelomas, nasopharynx cancers, neuroblastomas, non- Hodgkin's lymphoma, oral cancers, ovarian cancers, pancreatic cancers, penile cancers, pharynx cancers, prostate cancers, rectal cancers, sarcoma, seminomas, skin cancers, stomach cancers, teratomas, testicular cancers, thyroid cancers
  • the sequencing device 110 may perform RNA sequencing on the tumor 210 of the subject 205 to output, produce, or otherwise generate at least one RNA sequence dataset 215.
  • the RNA sequence dataset 215 may include a set of RNA sequences from the tumor 210 of the subject 205.
  • the RNA sequence dataset 215 may include one or more -20- 4894-5448-8045.1 Atty. Dkt. No.: 115872-3100 RNA expression levels of cancer-associated genes in the tumor 210 of the subject 205.
  • the RNA sequence dataset 215 may include an RNA expression profile of the tumor 210 of the subject 205.
  • the RNA expression profile may identify or include a set of RNA identifiers (e.g., TP53, BRCA1, etc.), an expression level for each RNA identifier, and metadata, among others.
  • the RNA sequence dataset 215 may include or identify metadata associated with the set of RNA sequences, such as an identifier (e.g., an anonymized identifier) for the subject 205.
  • the sequencing device 110 may provide, send, or otherwise transmit the RNA sequence dataset 215 to the data processing system 105.
  • RNA expression levels in the RNA sequence dataset 215 may include, for example, RNA associated with one or more of: ABL1, ACTB, ACTG1, ACTN1, ACVR1, ADAM15, AKT1, AKT2, APP, AR, ARRB2, ATM, ATXN1, AXIN1, BCAR1, BCL2, BCL2L1, BRCA1, BTK, C14orf1, CASP8, CCND1, CCND3, CCNE1, CD247, CDC42, CDK4, CDK5, CDKN1A, CDKN1B, CHD3, COIL, COPS5, COPS6, CREBBP, CRK, CRMP1, CSNK2A2, CTNNB1, DAXX, DLG4, DNM2, DVL2, EGFR, EIF2AK2, EP300, ESR1, EWSR1, EZR, FASLG, FEZ1, FGFR1, FN1, FOS, FXR2, GFI1B, GNAI1, GRB2, GSK3B, HCK, HDAC3, HGS
  • the RNA expression levels in the RNA sequence dataset 215 may include, for example, RNA associated with one or more of: ACTB, -21- 4894-5448-8045.1 Atty. Dkt. No.: 115872-3100 ACVR1, ADAM15, AKT1, APP, AR, ARRB2, ATXN1, AXIN1, BCL2, BRCA1, BTK, CASP8, CD247, CDC42, CDK5, CDKN1A, CHD3, COIL, COPS6, CREBBP, CRK, CRMP1, CSNK2A2, CTNNB1, DLG4, DVL2, EGFR, EIF2AK2, EP300, ESR1, EWSR1, FASLG, FGFR1, FN1, FXR2, GNAI1, GRB2, GSK3B, HDAC3, HGS, HIPK2, HRAS, HSF1, HSP90AA1, HTT, JAK1, JUN, LYN, MAGEA11, MAPK1, MAPK14, MDM2, MUC1,
  • the dataset retriever 130 may parse or process the RNA sequence dataset 215 to extract or identify the RNA expression levels of cancer-associated genes in the tumor 210 of the subject 205. In some embodiments, the dataset retriever 130 may process the RNA sequence dataset 215 to identify the RNA expression profile. In some embodiments, the dataset retriever 130 may perform filter (e.g., for quality control) on the data identified from the RNA sequence dataset 215. The filtering may include, for example, removal of RNA with low or no expressions, reduction of noise for RNA counts, and exclusion of RNA that are irrelevant to the cancer, among others. The dataset retriever 130 may store and maintain the RNA sequence dataset 215 on the database 120.
  • filter e.g., for quality control
  • the network constructor 135 may create, generate, or otherwise construct at least one network 220 based on the RNA sequence dataset 215 obtained from the tumor 210 of the subject 205.
  • the network 220 may be a graph, tree, or otherwise structural representation (e.g., a Markov chain) of the relationships among the RNA expression levels in the cancer-associated genes in the tumor 210 of the subject 205.
  • the network 220 may include a set of nodes 225A–N (hereinafter generally referred to nodes 225) and a set of edges 230A–N, among others. Each node 220 may be associated with a respective RNA expression of the cancer-associated gene in the tumor 210 of the subject 205.
  • Each edge 230 may define a connection between a pair of nodes 225 (e.g., a first node 225 and a -22- 4894-5448-8045.1 Atty. Dkt. No.: 115872-3100 second node 225).
  • the set of edges 230 may have or be associated with a corresponding set of weight metrics 235A–N (hereinafter generally referred to as weight metrics 235).
  • weight metrics 235 hereinafter generally referred to as weight metrics 235.
  • Each edge 230 may define, specify, or otherwise identify a respective weight metric 235 between a first RNA expression corresponding to the first node 225 and a second RNA expression corresponding to the second node 225 in the pair of nodes.
  • the network constructor 135 may select or identify the set of RNA expression levels from the RNA sequence dataset 215. For each RNA expression, the network constructor 135 may create, produce, or otherwise generate a corresponding node 225 to include in the network 220. Using the RNA sequence dataset 215, the network constructor 135 may identify or determine one or more correlations between a pair of nodes with respect to RNA expression levels. For each identified interaction between a pair of RNA expression levels, the network constructor 135 may create, produce, or otherwise generate a corresponding edge 230 between the pair of nodes 225 corresponding to the pair of RNA expression levels to include in the network 220.
  • the network constructor 135 may calculate, generate, or otherwise determine a corresponding weight metric 235 based on the interaction between the corresponding pair of RNA expression levels.
  • the weight metric 235 may indicate a degree of interactions between the pair of RNA expression levels.
  • the construction of the network 220 may be based on one or more evidenced-based interactions and/or inputs provided by a protein-protein interactome database (e.g., the Human Reference Protein Database (HPRD), the Human Reference INteractome (HuRI), Search Tool for the Retrieval of Interacting Genes/ Proteins (STRING) etc.).
  • the network 220 may have a topology (e.g., a connectivity structure) and a geometry (including a curvature) that gives a measure of their functional robustness.
  • the network constructor 135 may store and maintain the network 220 using one or more data structures, such as an array, a linked list, a stack, a queue, a hash table, a tree, a heap, a graph, a matrix, or a class, among others, on the database 120.
  • FIG.8 depicted is a block diagram of a process 300 to performing iterations to calculate curvature metrics using networks in the system 100 for determining likelihoods of responsiveness of subjects. Under the process 300, the diffusion -23- 4894-5448-8045.1 Atty.
  • iterator 140 may carry out, execute, or otherwise perform a diffusion operation throughout the network 220 for a set of iterations 305A–N (hereinafter generally referred to as iterations 305).
  • iterations 305 (sometimes herein referred to as scale) of the diffusion operation, the diffusion iterator 140 may set, update, or otherwise modify the values of the set of nodes 225 and the set of edges 230 based on the values of adjacent nodes 225’ and edges 230’ respectively.
  • the diffusion iterator 140 may set or assign an edge value 310 to the edge 230 in the network 220 based on a value of at least one adjacent edge 230’.
  • the edge value 310 may correspond to the weight metric 235 of the adjacent edge 230’.
  • the diffusion iterator 140 may calculate, generate, or otherwise determine the edge value 310 based on the values identified by the one or more adjacent edges 230’.
  • the number of adjacent edges 230’ may depend on the current iteration 305 performed on the network 220.
  • the diffusion iterator 140 may use the weight metrics 235 of the immediately adjacent edges 230’ (e.g., as shown) in the network 220 to update a given edge 230 at the first iteration 305.
  • the diffusion iterator 140 may use the weight metrics 235 of further edges 230’ (e.g., two or more edges out) in the network 220 to update the given edges 230.
  • the diffusion iterator 140 may set or assign a node value 315 to the node 225 in the network 220 based on a value of at least one adjacent node 225’.
  • the node value 315 may correspond to a combination (e.g., a sum or average) of the weight metrics 235 identified by the edges 230 linked with the adjacent node 225’.
  • the diffusion iterator 140 may calculate, generate, or otherwise determine the node value 315 based on the values (e.g., combination of the weight metrics 235) associated with one or more adjacent nodes 225.
  • the number of adjacent nodes 225’ may depend on the current iteration 305 performed on the network 220.
  • the diffusion iterator 140 may use the weight metrics 235 associated with the immediately adjacent nodes 225’ (e.g., as shown) in the network 220 to update a given node 225 at the first iteration 305.
  • the diffusion iterator 140 may use the weight metrics 235 associated with farther nodes 230’ (e.g., two or more edges out) in the network 220 to update the given node 225.
  • the diffusion iterator 140 may repeat through the set of nodes 225 and edges 230 to complete the iteration 305 of the diffusion operation. -24- 4894-5448-8045.1 Atty. Dkt. No.: 115872-3100
  • the set of edges 230 of the network 220 may have the set of updated weight metrics 235’.
  • the diffusion iterator 140 may determine, generate, or otherwise compute at least one graph profile of the network 220 at each iteration 305.
  • the graph profile (sometimes herein referred to as a diffusion profile or a diffused graph profile) may be a representation defining the relationship among the set of nodes 225 and the set of edges 230 in the network 220.
  • the representation of the graph profile may include, for example, a vector or matrix (e.g., an adjacency matrix, a degree matrix, a transition probability matrix, a Laplacian matrix, or stochastic matrix) defining the set of weight metrics 235 corresponding to the set of edges 230.
  • the representation may also identify the set of nodes 225 include in the network 220.
  • the diffusion iterator 140 may set or assign the node value 315 to the weight metric 235 (or the combination of the weight metrics 235) of each node 225.
  • the node value 315 may be determined from the relationships defined by the graph profile, such as the combination of the weight metrics 235 of the edges 230 connected to the node 225 or adjacent nodes 225’.
  • the diffusion iterator 140 may set or assign the edge value 310 to the weight metric 235 of each edge 230.
  • the edge value 310 may be determined from the relationships defined by the graph profile, such as the weight metrics 235 of the adjacent edges 230’.
  • the curvature analyzer 145 may calculate, generate, or otherwise determine at least one curvature metric 320A–N (hereinafter generally referred to as a curvature metric 320) of the network 220, using at least the set of weight metrics 235’ defined by the corresponding set of edges 230.
  • the curvature metric 320 may be for at least a portion of the set of weight metrics 235’ defined by a corresponding portion of the set of edges 230.
  • the determination of the curvature metric 320 may be performed subsequent to updating of the set of nodes 225 and the set of edges 230.
  • the curvature metric 320 may identify or indicate a degree of curvature of the network 220, relative to a straight line or surface in a Euclidean or pseudo-Euclidean geometry.
  • the curvature analyzer 145 may determine the curvature metric 320 of the network 220 for a given iteration 305 in accordance with any number of curvature measure functions, such as Ollivier-Ricci curvature (ORC), Forman-Ricci -25- 4894-5448-8045.1 Atty. Dkt. No.: 115872-3100 curvature, scalar curvature, or sectional curvature, among others.
  • ORC Ollivier-Ricci curvature
  • the curvature analyzer 145 may calculate, generate, or otherwise determine the curvature metric 320 based on the weight metric 235’ defined by each edge 230 (or node 225) of the network 220. For instance, the curvature analyzer 145 may determine the curvature metric 320 for the network 220, as a function (e.g., a curvature measure function) of the set of weight metrics 235’ defined by the corresponding set of edges 230 of the network 220. Over multiple iterations 305 of the diffusion operation through the network 220, the curvature analyzer 145 may determine a set of curvature metrics 320 corresponding to the set of iterations 305.
  • a function e.g., a curvature measure function
  • the diffusion iterator 140 may identify or determine whether to perform another iteration 305 of the diffusion operation.
  • the diffusion iterator 140 may perform the diffusion operations for a fixed maximum number of iterations (e.g., ranging from 10 to 1000).
  • the diffusion iterator 140 may maintain a counter to keep track of a number of iterations, and may repeat the diffusion operations (e.g., as detailed herein) until reaching the maximum number of iterations.
  • the diffusion iterator 140 may determine whether to perform another, subsequent iteration 305 based on the set of curvature metrics 320.
  • the diffusion iterator 140 may calculate or determine a difference between the curvature metric 320 of the current iteration 305 versus the curvature metric 320 of the previous iteration 305.
  • the diffusion iterator 140 may compare the difference with a convergence threshold. If the difference between the curvature metrics 320 is less than or equal to the convergence threshold, the diffusion iterator 140 may halt iterations 305. On the other hand, if the difference between the curvature metrics 320 is greater than the convergence threshold, the diffusion iterator 140 may determine to continue with another iteration 305 of the diffusion operation.
  • the curvature analyzer 145 may identify or select at least one critical iteration 305’ based on a difference between the curvature metric 320 of one iteration 305 and the curvature metric 320 of an additional iteration 305.
  • the selection of the critical iteration 305’ may be performed after completion of the set of iterations 305 of the diffusion operations.
  • the additional iteration 305 may correspond to the immediately subsequent iteration 305.
  • No.: 115872-3100 145 may calculate, generate, or determine the difference between each pair of curvature metrics 320 corresponding to one iteration 305 and the additional iteration 305, across the set of iterations 305. From the differences between each pair of iterations 305, the curvature analyzer 145 may select the iteration 305 as the critical iteration 305’ corresponding to the maximum difference. The critical iteration 305’ may correspond to the additional iteration 305. In some embodiments, the curvature analyzer 145 may select the critical iteration 305’ in accordance with a policy.
  • the policy may define, specify, or identify selection of the critical iteration 305’ based on, for example: a maximum dispersion or variance of the curvature metric 320 at the corresponding iteration 305; a maximum value of the difference between the curvature metric 320 of one iteration 305 and the curvature metric 320 of the subsequent iteration 305; an inflection of the curvature metric 320 among the set of iterations 305 (e.g., an increase then decrease in the value of the curvature metric 320); or a difference in the curvature metrics 320 among subsets of edges 230 in the network 220 at a particular iteration 305, among others.
  • the curvature analyzer 145 may check the set of curvature metrics 320 across the set of iterations 305 against the policy. When a given iteration 305 satisfies the specifications of the policy, the curvature analyzer 145 may select the iteration 305 as the critical iteration 305’.
  • FIG.9 depicted is a block diagram of a process 400 to generate outputs for subjects in the system 100 for determining likelihoods of responsiveness of subjects.
  • the feature generator 150 may create, package, or otherwise generate a set of features 405A–N (hereinafter generally referred to as features 405).
  • Thet set of features 405 may be generated using the network 220 to be used to determine likelihood of responsiveness of the subject 205 to anti-cancer therapy.
  • the set of features 405 may identify or include one or more of: the weight metrics 235’ of each edge 230 of the network 220 at each iteration 305; a value associated with each node 225 in the network 220 (e.g., combination of weight metrics 235’ of edges 230 connected to the given node 225); the curvature metric 320 for the network 220 for each iteration 305; the difference between the curvature metric 320 for the network 220 determined at the one iteration 305 and the curvature metric 320 determined for an additional iteration 305; the -27- 4894-5448-8045.1 Atty.
  • the output evaluator 155 may use the model 160 to determine likelihoods of responsiveness of subjects to anti-cancer therapy.
  • the anti-cancer therapy may be selected from among immune checkpoint blockade therapy, an anti-cancer vaccine, a monoclonal antibody-based immunotherapy, adoptive cell therapy, chemotherapy, hormonal therapy, and molecularly-targeted therapies, among others.
  • the output evaluator 155 may use a set of models 160, with each model 160 particular to at least one type of anti-cancer therapy. For instance, the output evaluator 155 may maintain one model 160 to determine predicted responsiveness to immune checkpoint blockade therapy, another model 160 to determine predicted responsiveness to hormonal therapy, and so forth.
  • the model 160 may be a machine learning (ML) model.
  • the model 160 may have been initialized, trained, or established using training data. The training data may identify or include a set of examples corresponding to sample subjects.
  • Each example may include a sample set of features (e.g., similar to the set of features 405) for the given sample subject and a label indicating one of responsiveness or non-responsiveness of the sample subject to the anti-cancer therapy.
  • the model 160 may be trained (e.g., by the data processing system 105) iteratively in accordance with supervised learning.
  • the sample set of features may be fed into the model 160 to generate an output indicating one of responsiveness or non-responsiveness.
  • the output from the model 160 may be compared with the label to determine an error metric (e.g., mean squared error, mean absolute error, Huber loss, or cross-entropy loss, among others).
  • the error metric may be used to update the parameters of the model 160, and this process may be repeated until convergence.
  • the model 160 may be a statistical model.
  • the model 160 may be fitted (e.g., by the data processing system 105) onto sample data including a set of examples corresponding to sample subjects. Each example may include a sample set of features (e.g., similar to the set of features 405) for the given sample subject and a label indicating one of responsiveness or non-responsiveness of the sample subject to the anti- -28- 4894-5448-8045.1 Atty. Dkt. No.: 115872-3100 cancer therapy.
  • the parameters of the model 160 may be fitted to the sample data using an objective function (e.g., mean squared error, cross- entropy loss, or maximum likelihood estimation).
  • the parameters of the model 160 may be optimized or updated to minimize the loss function.
  • the updating of the model 160 may be repeated until the fitting is determined to be satisfactory (e.g., loss below a threshold).
  • the output evaluator 155 may provide, feed, or otherwise apply the set of features 405 to the model 160 to generate at least one score 410. In applying, the output evaluator 155 may evaluate or process the set of features 405 in accordance with the parameters of the model 160. From processing the set of features 405 using the model 160, the output evaluator 155 may calculate, determine, or otherwise generate the score 410.
  • the score 410 may identify or indicate a likelihood of the responsiveness of the subject 205 to the anti-cancer therapy.
  • the output evaluator 155 may apply the set of features 405 to each of the set of models 160 corresponding to the different types of anti- cancer therapy to generate a set of scores 410.
  • Each score 410 may identify or indicate a likelihood of the responsiveness of the subject 205 to the types of anti-cancer therapy associated with the model 160.
  • the score 410 generated using the model 160 associated with adoptive cell therapy may indicate the likelihood of the responsiveness of the subject 205 to the adoptive cell therapy.
  • the output evaluator 155 may identify or determine whether to select the subject 205 for the administration of the anti-cancer therapy. To determine, the output evaluator 155 may compare the score 410 with a threshold.
  • the threshold may demarcate, define, or identify a value for the score 410 at which to select or exclude the associated subject 205 from administration of the anti-cancer therapy. If the score 410 satisfies (e.g., greater than or equal to) the threshold, the output evaluator 155 may include or select the subject 205 for the administration of the anti-cancer therapy. In some embodiments, the output evaluator 155 may classify the subject 205 as likely to be responsive to the anti-cancer therapy. Otherwise, if the score 410 does not satisfy (e.g., is less than) the threshold, the output evaluator 155 may exclude the subject 205 from the administration of the anti-cancer therapy.
  • the output evaluator 155 may classify the subject 205 as unlikely to be responsive to the anti-cancer -29- 4894-5448-8045.1 Atty. Dkt. No.: 115872-3100 therapy.
  • the output evaluator 155 may perform the determination for each type of anti- cancer therapy.
  • the output evaluator 155 may store and maintain an association between the subject 205 and one or more of: the score 410; an indication of selection or exclusion of the subject 205 for the administration of the anti-cancer therapy; a classification of the subject 205 as likely to be responsive or unlikely to be responsive; or an identification of the anti-cancer therapy, among others.
  • the association may be maintained using one or more data structures, such as an array, linked list, a matrix, a table, a heap, a stack, a queue, a tree, or a class object, among others.
  • the output evaluator 155 may produce, create, or otherwise generate at least one instruction 415 to send to the computing device 115.
  • the instruction 415 may include information about the evaluation of the subject 205 for the evaluation of anti-cancer therapy to be presented via the computing device 115.
  • the information may identify or include, for example, one or more of: an identification of the subject 205 (e.g., using an anonymized identifier); the score 410; an indication of selection or exclusion of the subject 205 for the administration of the anti-cancer therapy; a classification of the subject 205 as likely to be responsive or unlikely to be responsive; or an identification of the anti-cancer therapy, among others.
  • the instruction 415 may also include a script defining the layout of the presentation of the information.
  • the output evaluator 155 may send, transmit, or otherwise provide at least one instruction 415 to the computing device 115.
  • the computing device 115 may display, render, or otherwise present the information included in the instruction 415.
  • the computing device 115 may present the information via a graphical user interface of an application running on the computing device 115.
  • the presented information may include the identification of the subject 205 (e.g., using an anonymized identifier); the score 410; the indication of selection or exclusion of the subject 205 for the administration of the anti-cancer therapy; the classification of the subject 205 as likely to be responsive or unlikely to be responsive; or the identification of the anti-cancer therapy, among others.
  • the clinician examining the subject 205 may decide on which type of anti-cancer therapy to select and whether to deliver or administer the anti-cancer -30- 4894-5448-8045.1 Atty. Dkt.
  • the subject 205 may be provided or administered with the anti-cancer therapy identified in the instruction 415, when the subject 205 is classified as likely to be responsive to the given anti-cancer therapy.
  • the anti-cancer therapy may be administered to the tumor 210 (or anatomical sites associated with the tumor 210) associated with the cancer in the subject 205.
  • the data processing system 105 may identify particular subjects 205 as potentially responsive or non-responsive to types of anti-cancer therapy.
  • the iterative performances of the diffusion operations on the network 220 by the data processing system 105 may also detect and pinpoint RNA expression levels of genes that are correlated with the differences between responders and non-responders.
  • the set of features 405 that are derived from the network 220 may be applied to the model 160 to generate the scores 410 indicating likelihood of responsiveness to the anti-cancer therapy in the subject 205.
  • the scores 410 may be used to determine to select or exclude the subject 205 from administration of the anti-cancer therapy.
  • the RNA expression levels of genes correlated with responders can be readily deduced, thereby improving diagnosis. This can improve clinical such subjects 205 determined to be responders may be administered with the anti-cancer therapy, thus improving clinical outcomes for subjects 205 at risk or diagnosed with cancer.
  • the ability to use RNA data may significantly reduce the storage consumption and computational complexity on the data processing system 105, relative to approaches that rely on DNA data to diagnose individuals with cancer.
  • a computing system may construct a network using an RNA dataset (505).
  • the computing system may perform a diffusion operation on the network (510).
  • the computing system may determine a curvature metric (515).
  • the computing system may determine whether to perform additional diffusion operations (520). If the -31- 4894-5448-8045.1 Atty. Dkt.
  • the computing system iterate through method 500 from step (510). On the other hand, if the determination is not to perform additional diffusion operations, the computing system may select a critical iteration (525). The computing system may generate a set of features (530). The computing system may apply the set of features to a model (535). The computing system may generate a responsive score based on applying the set of features to the model (540). The computing system may determine whether the score satisfies a threshold (545). When the score satisfies the threshold, the computing system may select the subject for therapy (550). Else, when the score does not satisfy the threshold, the computing system may exclude the subject for therapy (555). The computing system may generate an output (560). C.
  • FIG.11 shows a simplified block diagram of a representative server system 600, client computing system 614, and network 626 usable to implement certain embodiments of the present disclosure.
  • server system 600 or similar systems can implement services or servers described herein or portions thereof.
  • Client computing system 614 or similar systems can implement clients described herein.
  • the system 100 described herein can be similar to the server system 600.
  • Server system 600 can have a modular design that incorporates a number of modules 602 (e.g., blades in a blade server embodiment); while two modules 602 are shown, any number can be provided.
  • Each module 602 can include processing unit(s) 604 and local storage 606.
  • Processing unit(s) 604 can include a single processor, which can have one or more cores, or multiple processors.
  • processing unit(s) 604 can include a general-purpose primary processor as well as one or more special-purpose co- processors such as graphics processors, digital signal processors, or the like.
  • some or all processing units 604 can be implemented using customized circuits, such as application specific integrated circuits (ASICs) or field programmable gate arrays (FPGAs).
  • ASICs application specific integrated circuits
  • FPGAs field programmable gate arrays
  • such integrated circuits execute instructions that -32- 4894-5448-8045.1 Atty. Dkt. No.: 115872-3100 are stored on the circuit itself.
  • processing unit(s) 604 can execute instructions stored in local storage 606.
  • Local storage 606 can include volatile storage media (e.g., DRAM, SRAM, SDRAM, or the like) and/or non-volatile storage media (e.g., magnetic or optical disk, flash memory, or the like). Storage media incorporated in local storage 606 can be fixed, removable or upgradeable as desired. Local storage 606 can be physically or logically divided into various subunits such as a system memory, a read-only memory (ROM), and a permanent storage device.
  • the system memory can be a read-and-write memory device or a volatile read-and-write memory, such as dynamic random-access memory.
  • the system memory can store some or all of the instructions and data that processing unit(s) 604 need at runtime.
  • the ROM can store static data and instructions that are needed by processing unit(s) 604.
  • the permanent storage device can be a non-volatile read-and-write memory device that can store instructions and data even when module 602 is powered down.
  • storage medium includes any medium in which data can be stored indefinitely (subject to overwriting, electrical disturbance, power loss, or the like) and does not include carrier waves and transitory electronic signals propagating wirelessly or over wired connections.
  • local storage 606 can store one or more software programs to be executed by processing unit(s) 604, such as an operating system and/or programs implementing various server functions such as functions of the system 100 of FIG.1 or any other system described herein, or any other server(s) associated with system 100 or any other system described herein.
  • “Software” refers generally to sequences of instructions that, when executed by processing unit(s) 604 cause server system 600 (or portions thereof) to perform various operations, thus defining one or more specific machine embodiments that execute and perform the operations of the software programs.
  • the instructions can be stored as firmware residing in read-only memory and/or program code stored in non-volatile storage media that can be read into volatile working memory for execution by processing unit(s) 604.
  • Software can be implemented as a single program or a collection of separate programs -33- 4894-5448-8045.1 Atty. Dkt. No.: 115872-3100 or program modules that interact as desired.
  • processing unit(s) 604 can retrieve program instructions to execute and data to process in order to execute various operations described above.
  • multiple modules 602 can be interconnected via a bus or other interconnect 608, forming a local area network that supports communication between modules 602 and other components of server system 600.
  • Interconnect 608 can be implemented using various technologies including server racks, hubs, routers, etc.
  • a wide area network (WAN) interface 610 can provide data communication capability between the local area network (interconnect 608) and the network 626, such as the Internet. Technologies can be used, including wired (e.g., Ethernet, IEEE 802.3 standards) and/or wireless technologies (e.g., Wi-Fi, IEEE 802.11 standards).
  • local storage 606 is intended to provide working memory for processing unit(s) 604, providing fast access to programs and/or data to be processed while reducing traffic on interconnect 608. Storage for larger quantities of data can be provided on the local area network by one or more mass storage subsystems 612 that can be connected to interconnect 608. Mass storage subsystem 612 can be based on magnetic, optical, semiconductor, or other data storage media.
  • Direct attached storage storage area networks, network-attached storage, and the like can be used. Any data stores or other collections of data described herein as being produced, consumed, or maintained by a service or server can be stored in mass storage subsystem 612. In some embodiments, additional data storage resources may be accessible via WAN interface 610 (potentially with increased latency).
  • Server system 600 can operate in response to requests received via WAN interface 610. For example, one of modules 602 can implement a supervisory function and assign discrete tasks to other modules 602 in response to received requests. Work allocation techniques can be used. As requests are processed, results can be returned to the requester via WAN interface 610. Such operation can generally be automated.
  • WAN interface 610 can connect multiple server systems 600 to each other, providing scalable systems capable of managing high volumes of activity.
  • Other techniques -34- 4894-5448-8045.1 Atty. Dkt. No.: 115872-3100 for managing server systems and server farms (collections of server systems that cooperate) can be used, including dynamic resource allocation and reallocation.
  • Server system 600 can interact with various user-owned or user-operated devices via a wide-area network such as the Internet. An example of a user-operated device is shown in FIG.6 as client computing system 614.
  • Client computing system 614 can be implemented, for example, as a consumer device such as a smartphone, other mobile phone, tablet computer, wearable computing device (e.g., smart watch, eyeglasses), desktop computer, laptop computer, and so on.
  • client computing system 614 can communicate via WAN interface 610.
  • Client computing system 614 can include computer components such as processing unit(s) 616, storage device 618, network interface 620, user input device 622, and user output device 624.
  • Client computing system 614 can be a computing device implemented in a variety of form factors, such as a desktop computer, laptop computer, tablet computer, smartphone, other mobile computing device, wearable computing device, or the like.
  • Processing unit(s) 616 and storage device 618 can be similar to processing unit(s) 604 and local storage 606 described above. Suitable devices can be selected based on the demands to be placed on client computing system 614; for example, client computing system 614 can be implemented as a “thin” client with limited processing capability or as a high-powered computing device. Client computing system 614 can be provisioned with program code executable by processing unit(s) 616 to enable various interactions with server system 600.
  • Network interface 620 can provide a connection to the network 626, such as a wide area network (e.g., the Internet) to which WAN interface 610 of server system 600 is also connected.
  • network interface 620 can include a wired interface (e.g., Ethernet) and/or a wireless interface implementing various RF data communication standards such as Wi-Fi, Bluetooth, or cellular data network standards (e.g., 3G, 4G, LTE, etc.). -35- 4894-5448-8045.1 Atty. Dkt. No.: 115872-3100
  • User input device 622 can include any device (or devices) via which a user can provide signals to client computing system 614; client computing system 614 can interpret the signals as indicative of particular user requests or information.
  • user input device 622 can include any or all of a keyboard, touch pad, touch screen, mouse or other pointing device, scroll wheel, click wheel, dial, button, switch, keypad, microphone, and so on.
  • User output device 624 can include any device via which client computing system 614 can provide information to a user.
  • user output device 624 can include a display to display images generated by or delivered to client computing system 614.
  • the display can incorporate various image generation technologies, e.g., a liquid crystal display (LCD), light-emitting diode (LED) including organic light-emitting diodes (OLED), projection system, cathode ray tube (CRT), or the like, together with supporting electronics (e.g., digital-to-analog or analog-to-digital converters, signal processors, or the like).
  • LCD liquid crystal display
  • LED light-emitting diode
  • OLED organic light-emitting diodes
  • CRT cathode ray tube
  • Some embodiments can include a device such as a touchscreen that function as both input and output device.
  • other user output devices 624 can be provided in addition to or instead of a display. Examples include indicator lights, speakers, tactile “display” devices, printers, and so on.
  • Some embodiments include electronic components, such as microprocessors, storage and memory that store computer program instructions in a computer-readable storage medium. Many of the features described in this specification can be implemented as processes that are specified as a set of program instructions encoded on a computer-readable storage medium. When these program instructions are executed by one or more processing units, they cause the processing unit(s) to perform various operation indicated in the program instructions. Examples of program instructions or computer code include machine code, such as is produced by a compiler, and files including higher-level code that are executed by a computer, an electronic component, or a microprocessor using an interpreter.
  • processing unit(s) 604 and 616 can provide various functionality for server system 600 and client computing system 614, including any of the functionality described herein as being performed by a server or client, or other functionality.
  • server system 600 and client computing system 614 are illustrative and that variations and modifications are possible.
  • Computer systems used in connection with embodiments of the present disclosure can have other capabilities not specifically described here.
  • server system 600 and client computing system 614 are described with reference to particular blocks, it is to be understood that these blocks are defined for convenience of description and are not intended to imply a particular physical arrangement of component parts.
  • blocks can be but need not be located in the same facility, in the same server rack, or on the same motherboard. Further, the blocks need not correspond to physically distinct components. Blocks can be configured to perform various operations, e.g., by programming a processor or providing appropriate control circuitry, and various blocks might or might not be reconfigurable depending on how the initial configuration is obtained. Embodiments of the present disclosure can be realized in a variety of apparatus including electronic devices implemented using any combination of circuitry and software. While the disclosure has been described with respect to specific embodiments, one skilled in the art will recognize that numerous modifications are possible. Embodiments of the disclosure can be realized using a variety of computer systems and communication technologies including but not limited to the specific examples described herein.
  • Embodiments of the present disclosure can be realized using any combination of dedicated components and/or programmable processors and/or other programmable devices.
  • the various processes described herein can be implemented on the same processor or different processors in any combination.
  • components are described as being configured to perform certain operations, such configuration can be accomplished, e.g., by designing electronic circuits to perform the operation, by programming programmable electronic circuits (such as microprocessors) to perform the operation, or any combination thereof.
  • programmable electronic circuits such as microprocessors
  • Computer programs incorporating various features of the present disclosure may be encoded and stored on various computer-readable storage media; suitable media include magnetic disk or tape, optical storage media such as compact disk (CD) or DVD (digital versatile disk), flash memory, and other non-transitory media.
  • Computer-readable media encoded with the program code may be packaged with a compatible electronic device, or the program code may be provided separately from electronic devices (e.g., via Internet download or as a separately packaged computer-readable storage medium).

Landscapes

  • Health & Medical Sciences (AREA)
  • Engineering & Computer Science (AREA)
  • Medical Informatics (AREA)
  • Public Health (AREA)
  • General Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Physics & Mathematics (AREA)
  • Biomedical Technology (AREA)
  • Data Mining & Analysis (AREA)
  • Epidemiology (AREA)
  • Primary Health Care (AREA)
  • Theoretical Computer Science (AREA)
  • Molecular Biology (AREA)
  • Databases & Information Systems (AREA)
  • Pathology (AREA)
  • Software Systems (AREA)
  • Chemical & Material Sciences (AREA)
  • Biophysics (AREA)
  • Evolutionary Computation (AREA)
  • Medicinal Chemistry (AREA)
  • General Physics & Mathematics (AREA)
  • Immunology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Spectroscopy & Molecular Physics (AREA)
  • Artificial Intelligence (AREA)
  • Biotechnology (AREA)
  • Urology & Nephrology (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Mathematical Physics (AREA)
  • General Engineering & Computer Science (AREA)
  • Computing Systems (AREA)
  • Genetics & Genomics (AREA)
  • Evolutionary Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Hematology (AREA)
  • Microbiology (AREA)
  • Computational Linguistics (AREA)
  • Food Science & Technology (AREA)
  • Oncology (AREA)
  • Analytical Chemistry (AREA)

Abstract

L'invention concerne des systèmes et des procédés pour déterminer une probabilité de réactivité d'un sujet souffrant d'un cancer à une thérapie anticancéreuse. Un système informatique peut construire, sur la base de données de séquence d'acide ribonucléique (ARN), un réseau. Dans le réseau, chaque nœud peut être associé à une expression d'ARN et chaque bord peut identifier une mesure de poids entre des niveaux d'expression d'ARN pour une paire de nœuds. Le système informatique peut effectuer, pour une pluralité d'itérations, une opération de diffusion dans tout le réseau. Le système informatique peut déterminer une métrique de courbure pour chaque itération à l'aide de la métrique de poids définie par chaque bord ou nœud du réseau. Le système informatique peut sélectionner une itération critique sur la base d'une différence de métriques de courbure. Le système informatique peut appliquer une pluralité de caractéristiques du réseau à un modèle pour générer un score indiquant la probabilité de réactivité du sujet à la thérapie anticancéreuse.
PCT/US2024/052082 2023-10-20 2024-10-18 Analyse multi-échelle de données de séquence d'acide ribonucléique pour prédire des réponses à des thérapies anticancéreuses Pending WO2025085824A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
US202363592027P 2023-10-20 2023-10-20
US63/592,027 2023-10-20

Publications (1)

Publication Number Publication Date
WO2025085824A1 true WO2025085824A1 (fr) 2025-04-24

Family

ID=95449207

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/US2024/052082 Pending WO2025085824A1 (fr) 2023-10-20 2024-10-18 Analyse multi-échelle de données de séquence d'acide ribonucléique pour prédire des réponses à des thérapies anticancéreuses

Country Status (1)

Country Link
WO (1) WO2025085824A1 (fr)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20190095575A1 (en) * 2013-05-30 2019-03-28 Genomic Health, Inc. Gene Expression Profile Algorithm for Calculating a Recurrence Score for a Patient with Kidney Cancer
WO2019121564A2 (fr) * 2017-12-24 2019-06-27 Ventana Medical Systems, Inc. Approche de pathologie computationnelle pour une analyse rétrospective d'études d'essais cliniques reposant sur le diagnostic d'accompagnement basés sur des tissus
US20200370124A1 (en) * 2017-11-17 2020-11-26 Gmdx Co Pty Ltd. Systems and methods for predicting the efficacy of cancer therapy
WO2021211057A1 (fr) * 2020-04-14 2021-10-21 National University Of Singapore Procédé de prédiction de la réactivité à une thérapie du cancer
WO2023133597A1 (fr) * 2022-01-10 2023-07-13 The United States Of America, As Represented By The Secretary, Department Of Health And Human Services Procédés de prédiction de réponse et de résistance au traitement d'un patient par l'intermédiaire de transcriptomiques monocellulaires de leurs tumeurs

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20190095575A1 (en) * 2013-05-30 2019-03-28 Genomic Health, Inc. Gene Expression Profile Algorithm for Calculating a Recurrence Score for a Patient with Kidney Cancer
US20200370124A1 (en) * 2017-11-17 2020-11-26 Gmdx Co Pty Ltd. Systems and methods for predicting the efficacy of cancer therapy
WO2019121564A2 (fr) * 2017-12-24 2019-06-27 Ventana Medical Systems, Inc. Approche de pathologie computationnelle pour une analyse rétrospective d'études d'essais cliniques reposant sur le diagnostic d'accompagnement basés sur des tissus
WO2021211057A1 (fr) * 2020-04-14 2021-10-21 National University Of Singapore Procédé de prédiction de la réactivité à une thérapie du cancer
WO2023133597A1 (fr) * 2022-01-10 2023-07-13 The United States Of America, As Represented By The Secretary, Department Of Health And Human Services Procédés de prédiction de réponse et de résistance au traitement d'un patient par l'intermédiaire de transcriptomiques monocellulaires de leurs tumeurs

Similar Documents

Publication Publication Date Title
JP7681145B2 (ja) 生体試料の多検体アッセイのための機械学習実装
Jamshidi et al. Evaluation of cell-free DNA approaches for multi-cancer early detection
Bhinder et al. Artificial intelligence in cancer research and precision medicine
Kristensen et al. Principles and methods of integrative genomic analyses in cancer
McDermott et al. Challenges in biomarker discovery: combining expert insights with statistical analysis of complex omics data
TWI814753B (zh) 用於標靶定序之模型
Yu et al. BRWLDA: bi-random walks for predicting lncRNA-disease associations
US20250061972A1 (en) Molecular response and progression detection from circulating cell free dna
CA3204451A1 (fr) Systemes et procedes d'inference de variation du nombre de copies de sequencage du genome entier a faible couverture et de sequencage de l'exome entier conjoints a des fins de diagnostic cliniqu
Re et al. Cancer module genes ranking using kernelized score functions
Shutta et al. DRAGON: determining regulatory associations using graphical models on multi-omic networks
US20240076744A1 (en) METHODS AND SYSTEMS FOR mRNA BOUNDARY ANALYSIS IN NEXT GENERATION SEQUENCING
Yagin Machine learning approaches for multi-omics data integration in medicine
Liu et al. Survival time prediction of breast cancer patients using feature selection algorithm crystall
WO2025085824A1 (fr) Analyse multi-échelle de données de séquence d'acide ribonucléique pour prédire des réponses à des thérapies anticancéreuses
Wang et al. Computational models for pan-cancer classification based on multi-omics data
Haury et al. Increasing stability and interpretability of gene expression signatures
Adel et al. Bioinformatics analysis for immune hub genes in BLIS subtype of triple-negative breast cancer
Emmert-Streib Statistical diagnostics for cancer: analyzing high-dimensional data
Diaz-Herrera Methods to Integrate Genetic and Clinical Data for Disease Subtyping
Shende et al. RGE-GCN: Recursive Gene Elimination with Graph Convolutional Networks for RNA-seq based Early Cancer Detection
Kacar Dissecting Tumor Clonality in Liver Cancer: A Phylogeny Analysis Using Computational and Statistical Tools
Petescia et al. Cancer detection via one-shot learning: integrating gene expression and genomic mutation analysis
WO2025245396A1 (fr) Biopsie liquide d'arn et séquençage de nanopores
Gevaert A Bayesian network integration framework for modeling biomedical data

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 24880701

Country of ref document: EP

Kind code of ref document: A1