80 results about "Predictive biomarker" patented technology

The present disclosure relates generally to biomarker discovery and patient stratification, and more specifically to machine learning techniques for discovering relevant biomarkers using data collected as part of the standard-of-care (SoC), which can be used to identify a relevant patient population for a therapeutic with a known mechanism of action (MoA). An exemplary method for predicting activity of a molecular analyte of a patient comprises: training a first module of a machine learning model based on a plurality of medical images of a first cohort; training a second module of the machine learning model based on one or more molecular analyte data sets obtained from a second cohort; receiving a medical image from the patient; and predicting, using the trained first and second modules of the machine learning model, the activity of the molecular analyte from the medical image of the patient.

The present disclosure provides, among other things, methods for treating cancer comprising administering an effective dose of a WEE1 inhibitor such as Azenosertib, or a pharmaceutically acceptable salt thereof, to a subject selected to have a cancer associated with at least one alteration in the F-box and WD repeat domain containing 7 (FBXW7) gene.

This invention relates to a non-invasive predictive kit and method for the progression of benign prostatic hyperplasia (BPH) based on prostatic fluid. The invention provides the application of FGF9 as a non-invasive predictive biomarker for the progression of BPH based on prostatic fluid, wherein the concentration of FGF9 in prostatic fluid serves as an indicator of BPH progression. The invention also provides a method for detecting the concentration of FGF9 in prostatic fluid for non-disease diagnostic purposes. Compared with existing technologies, the non-invasive BPH detection method based on prostatic fluid of this invention has advantages such as non-invasiveness, accuracy, simplicity, practicality, and scalability, and is expected to be widely used in the clinical diagnosis and treatment of prostate diseases.

Disclosed herein are methods and compositions for quantifying distinct prognostic and predictive contributions of tumor epithelium vs. tumor microenvironment in colorectal cancer to optimize therapy.

The present disclosure provides, among other things, methods for treating cancer comprising administering an effective dose of Azenosertib to subjects selected to have a Cyclin E1 status above a predetermined threshold.

The present disclosure relates generally to biomarker discovery and patient stratification, and more specifically to machine learning techniques for discovering relevant biomarkers using data collected as part of the standard-of-care (SoC), which can be used to identify a relevant patient population for a therapeutic with a known mechanism of action (MoA). An exemplary method for predicting activity of a molecular analyte of a patient comprises: training a first module of a machine learning model based on a plurality of medical images of a first cohort; training a second module of the machine learning model based on one or more molecular analyte data sets obtained from a second cohort; receiving a medical image from the patient; and predicting, using the trained first and second modules of the machine learning model, the activity of the molecular analyte from the medical image of the patient.

The present disclosure provides, among other things, methods for treating cancer comprising administering an effective dose of azenosertib, or a pharmaceutically acceptable salt thereof, to subjects selected to have a homologous recombination repair deficiency (HRD).

Disclosed herein are methods of treating an individual having a cancer, of treating or identifying an individual having cancer for a treatment, or stratifying individuals having a cancer for a treatment based on a tumor mutational burden (TMB) score or a TMB score and a microsatellite instability assessment.

The present disclosure relates generally to biomarker discovery and patient stratification, and more specifically to machine learning techniques for discovering relevant biomarkers using data collected as part of the standard-of-care (SoC), which can be used to identify a relevant patient population for a therapeutic with a known mechanism of action (MoA). An exemplary method for predicting activity of a molecular analyte of a patient comprises: training a first module of a machine learning model based on a plurality of medical images of a first cohort; training a second module of the machine learning model based on one or more molecular analyte data sets obtained from a second cohort; receiving a medical image from the patient; and predicting, using the trained first and second modules of the machine learning model, the activity of the molecular analyte from the medical image of the patient.

The invention provides a human bladder cancer vedicetumab drug-resistant cell strain as well as a construction method and application thereof. The cell strain is named as a human bladder cancer drug-resistant cell strain T24-RC48, and the preservation number of the cell strain is CCTCC (China Center For Type Culture Collection) NO: C2024180. During construction, a method of continuously inducing at low concentration and gradually increasing the drug concentration and the treatment time of the RC48 is adopted, so that the formation of the RC48 drug-resistant cells is effectively induced, and the construction method is simple to operate and can effectively make up for the defects of the existing method. The human bladder transitional cell carcinoma RC48 drug-resistant cell strain T24-RC48 constructed by the invention can be used for researching a bladder cancer drug-resistant mechanism, promoting the development of predictive biomarkers, evaluating the antitumor activity of drugs and preparing a tumor cell model or a tumor animal model; a cell research model is provided for screening, researching and developing effective drugs and methods for overcoming bladder cancer drug resistance, and good application prospects are achieved.

Method for predicting severity of COVID-19 disease resulting from infection with SARS-COV-2 (severe acute respiratory syndrome coronavirus 2). The method uses a high dimensional approach to construct a comprehensive metabolic landscape of immune cells participating in the anti-viral response against SARS-CoV-2. Also encompassed within the invention are novel immune cell subsets exhibiting metabolic dysfunction that could serve as predictive biomarkers for COVID-19 severity or as targets for therapeutic interventions in COVID-19 disease.

The present invention relates to a method for predicting neurodegenerative decline and / or its severity for a patient, especially of cognitive impairment (CI). Strokes and Parkinson's disease are frequently associated with occurrence of long-term cognitive impairment or dementia with still incompletely resolved mechanisms. The discovery of diagnostic and predictive biomarkers thus remains a major challenge. The method of the invention uses radiomics corresponding to texture features extracted from a plurality of previously-acquired medical brain images and correlated with previously-acquired clinical and / or biological data. A classifier is trained beforehand for learning these radiomics, and then operated on radiomics computed from at least one brain image of a patient to generate a score representative of its risks of neurodegenerative decline. By applying this method on a cohort of 160 MCI and non-MCI patients, the inventors show that MCI patients could be early predicted with a mean accuracy of 88%. In the same way, the method was able to discriminate very early stages of cognitive decline in a Parkinson's disease population of 100 patients.

Methods and systems are provided for training a machine learning algorithm using at least one hardware processor to identify one or more predictive drug molecule features and / or predictive genetic biomarkers for cancer treatment. In some embodiments, the method uses at least one cancer drug discovery data set to train at least one learning algorithm in a predictive model, and uses a xenograft mouse model to validate the predictive model, and feeds back a biological response to the predictive model to further train the learning algorithm.

The invention relates to a method of predicting a subject´s response to anti-CD20 antibody, preferably ocrelizumab, therapy.

This disclosure provides a method for treating lymphoma, the method comprising administering a bispecific CD20xCD3 antibody to a patient in need, wherein the patient is selected based on an improvement in the level of circulating tumor (ct) DNA. In some embodiments, this disclosure provides a method for identifying lymphoma patients who may respond well to a therapy comprising a bispecific CD20xCD3 antibody.

Provided relates to the field of cytometry, specifically to flow cytometric methods and kits for improved diagnosis, prognosis and monitoring of tumors and other lesions involving immune cell infiltration. Further provided are embodiments of the subject matter which relate to compositions and methods providing high resolution quantitative means for immunophenotyping and immune modeling, and for identification of disease prognostic and therapy predictive biomarkers.

The present invention provides a method of treating a patient suffering from Parkinson's disease (PD) associated with wild type LRRK2, and a method of treating a patient suffering from Parkinson's disease (PD) associated with wild type LRRK2. The present invention recognizes that analysis of biomarkers of such patients allows for identification of patients who will respond to LRRK2 inhibitors. Accordingly, the invention provides methods of identifying PD patients who will respond to LRRK2 inhibitors and methods of treating such patients.

The invention relates to the technical field of biology, and provides a predictive biomarker for treating adverse reactions of tumor patients by using CCL5 as an immune checkpoint inhibitor and application of the predictive biomarker, and the predictive biomarker is the dynamic change of the CCL5 relative to a baseline proportion. The detection kit is used for detecting the proportion of CCL5. The dynamic change refers to the change of the CCL5 proportion before and after the immune checkpoint inhibitor is used; if the dynamic change is greater than or equal to 50% or continuously increased, the immune checkpoint inhibitor causes adverse reaction when treating the tumor patient. According to the method, high-risk patients can be identified through peripheral blood detection before irAEs have obvious clinical manifestations, so that a basis for advanced intervention is provided for clinicians, and the occurrence probability of serious adverse events is reduced.

The invention discloses application of FIGN protein in cytoplasm as a marker in preparation of a lung adenocarcinoma and / or breast cancer diagnosis product, and belongs to the field of biomedicine. According to the application of the FIGN protein in the cytoplasm as the marker in preparation of the lung adenocarcinoma and / or breast cancer diagnosis product, the lung adenocarcinoma and / or breast cancer diagnosis product comprises a product for detecting the expression level of the FIGN protein in the cytoplasm of a sample, and the sample is collected from lung glands and / or mammary glands to be diagnosed of a subject. The sensitivity of the diagnostic predictive biomarker and the diagnostic kit in breast cancer and lung adenocarcinoma tumor tissues is 88.89% and 87.87% respectively, the sensitivity of the diagnostic predictive biomarker and the diagnostic kit in normal breast and lung tissues is 92.22% and 90.00% respectively, a new tool and a new method are provided for early diagnosis of breast cancer, lung adenocarcinoma and the like, and the diagnostic predictive biomarker and the diagnostic kit have important clinical application value.

The present disclosure provides methods of treating lymphoma comprising administering a bispecific CD20xCD3 antibody to a patient in need thereof, wherein the patient is selected on the basis of exhibiting a modified level of circulating tumor (ct) DNA. In certain embodiments, the present disclosure provides methods of identifying a patient with lymphoma who is likely to respond favorably to therapy comprising a bispecific CD20xCD3 antibody.

The present invention relates to the use of FIGN protein in the cytoplasm as a marker in the preparation of a diagnostic product for lung adenocarcinoma and / or breast cancer, and is related to the biomedical field. The use of FIGN protein in the cytoplasm as a marker in the preparation of a diagnostic product for lung adenocarcinoma and / or breast cancer comprises a product for detecting the expression level of FIGN protein in the cytoplasm of a sample collected from the lung and / or breast of a subject to be diagnosed. The diagnostic predictive biomarker and diagnostic kit of the present invention have sensitivities of 88.89% and 87.87% in breast cancer and lung adenocarcinoma tumor tissues, respectively, and sensitivities of 92.22% and 90.00% in normal breast and lung tissues, respectively. These provide new tools and methods for the early diagnosis of breast cancer, lung adenocarcinoma, and other conditions, and have important clinical application value.

The invention discloses an application of a POSTN + fibroblast subgroup in screening and preparing a medicine for improving immune checkpoint blocking treatment drug resistance of a patient with head and neck squamous cell carcinoma. The action mechanism of small extracellular vesicles secreted by POSTN < + > fibroblasts in head and neck squamous cell carcinoma is studied, two fibroblast subtypes of POSTN <-> and POSTN < + > are identified through single-cell RNA sequencing, and the POSTN < + > subtype highly expresses FAP and other markers and is related to immune checkpoint blocking treatment drug resistance. Research finds that POSTN is enriched on the surface of sEVs secreted by POSTN + fibroblasts, and macrophages can be driven to be polarized to an M2 type by activating a BMP4 / BMPR2 / Smad signal channel. High expression of POSTN and FAP indicates that ICB treatment response of a patient is poor, and POSTN and FAP can be used as predictive biomarkers. The pathway can be blocked by down-regulating the POSTN, the ICB curative effect is improved, and a new target and a new strategy are provided for treatment of head and neck squamous cell carcinoma.

The invention provides a gout target biomarker screening and traditional Chinese medicine prediction method and device based on single cell sequencing in combination with medicinal and edible substances and network pharmacology. The method comprises the following steps: performing data quality control, preprocessing, clustering and grouping on a data set; screening differentially expressed genes through grouping comparison, and taking an intersection of the differentially expressed genes to obtain candidate genes; constructing a protein interaction PP I network, and identifying a potential biomarker treatment target; constructing a network pharmacology model, and performing traditional Chinese medicine or herbal medicine component prediction on the screened chemical small molecules to obtain candidate medicinal materials; according to the standard of homology of medicine and food, a potential traditional Chinese medicine with homology of medicine and food is provided for a gout treatment scheme. By combining with a biomarker screening technology of modern medicine, potential prediction markers are mined, and a theoretical basis and practical guidance are provided for individualized treatment of gout. A plurality of traditional Chinese medicine components with homology of medicine and food are screened through a network pharmacology method and become potential candidate medicines for treating gout.

The present disclosure provides, inter alia, methods for treating cancer comprising administering to a subject selected to have a cyclin E1 state above a predetermined threshold an effective dose of Asensertib.

The present disclosure relates generally to biomarker discovery and patient stratification, and more specifically to machine learning techniques for discovering relevant biomarkers using data collected as part of the standard-of-care (SoC), which can be used to identify a relevant patient population for a therapeutic with a known mechanism of action (MoA). An exemplary method for predicting activity of a molecular analyte of a patient comprises: training a first module of a machine learning model based on a plurality of medical images of a first cohort; training a second module of the machine learning model based on one or more molecular analyte data sets obtained from a second cohort; receiving a medical image from the patient; and predicting, using the trained first and second modules of the machine learning model, the activity of the molecular analyte from the medical image of the patient.

Potential prognostic biomarkers for CD26-targeted therapy were identified based on phase I study data of a humanized anti-CD26 monoclonal antibody YS110 against CD26-expressing tumors. Using boxplot analysis, scatter plot analysis, Pearson's product-moment correlation / Spearman's rank-difference correlation, bar graph analysis, and receiver operating characteristic (ROC), a correlation between soluble CD26 titer variation and tumor volume variation by YS110 administration, RECIST criteria evaluation, and progression-free survival (PFS) were examined. Further, mechanism of serum soluble CD26 titer variation was confirmed by in vitro experiments. As a result, serum soluble CD26 / DPP4 titer variation at an early stage of YS110 treatment was found for the first time as a predictive biomarker to evaluate a therapeutic effect.

The present disclosure relates generally to biomarker discovery and patient stratification, and more particularly to machine learning techniques for discovering related biomarkers using data collected as part of standard care (SoC), which may be used to identify related patient populations with therapeutic agents of known mechanisms of action (MoA). An exemplary method for predicting patient molecular analyte activity includes: training a first module of a machine learning model based on a plurality of medical images of a first queue; a second module to train the machine learning model based on one or more molecular analyte data sets obtained from a second queue; receiving a medical image from the patient; and predicting the activity of the molecular analyte from the medical image of the patient using the trained first and second modules of the machine learning model.

The present invention relates to a method of selecting a subject having cancer for treatment comprising: i) determining a KAT6A level of a biological sample of cancer from said subject; ii) selecting a subject for treatment; and iii) administering to the selected subject an amount of one of the following based on the KAT6A level: a) a lysine acetyltransferase 6A (KAT6A) inhibitor; b) a lysine acetyltransferase 6A (KAT6A) inhibitor and a cyclin dependent kinase 4 (CDK4) inhibitor; c) a lysine acetyltransferase 6A (KAT6A) inhibitor and an antiestrogen; and d) a lysine acetyltransferase 6A (KAT6A) inhibitor, a cyclin dependent kinase 4 (CDK4) inhibitor, and an antiestrogen, wherein the KAT6A level is determined as a high KAT6A level.

The invention relates to the technical field of biology, and provides a predictive biomarker for treating adverse reactions of tumor patients through an immune checkpoint inhibitor and application of the predictive biomarker, and the predictive biomarker is the dynamic change of the proportion of CX3CR1 + CD8 + T cells. The detection kit is used for detecting the proportion of CX3CR1 + CD8 + T cells. The dynamic change refers to the change of the CX3CR1 + CD8 + T cell proportion before and after the immune checkpoint inhibitor is used; if the dynamic change is greater than or equal to 50% or continuously increased, the immune checkpoint inhibitor causes adverse reaction when treating the tumor patient. According to the method, high-risk patients can be identified through peripheral blood detection before irAEs have obvious clinical manifestations, so that a basis for advanced intervention is provided for clinicians, and the occurrence probability of serious adverse events is reduced.

The present disclosure provides materials and methods for assessing and / or treating subjects having prostate cancer. In some embodiments, materials and methods for assessing a subject's tumor burden using a liquid biomarker, tumor-derived extracellular vesicle expressing a surface antigen, are provided. Provided are materials and methods for using the presence or absence of the biomarker to assess whether a subject should be treated with radiotherapy alone, or whether the subject would benefit from systemic therapy, either alone or in combination with radiotherapy.