66 results about "Cancer classification" patented technology

The present invention provides a process for classification of cancers and tissues of origin through the analysis of the expression patterns of specific microRNAs and nucleic acid molecules relating thereto. Classification according to a microRNA tree-based expression framework allows optimization of treatment, and determination of specific therapy.

Aspects of the invention relate to methods and compositions for characterizing or modulating the expression of metabolic mesenchymal genes. In some embodiments, methods for assessing the expression of metabolic mesenchymal genes and related gene signatures are provided that are useful for cancer classification, prognosis, diagnosis, or treatment selection.

A method for classifying a possible cancer from a magnetic resonance spectrographic (MRS) dataset includes extracting at least one feature from the MRS dataset as being identified with the possible cancer and embedding the extracted feature into a low dimensional space to form an embedded space. The method then clusters the embedded space into clusters representing a plurality of predetermined classes and spectrally decomposing the clusters to identify substantially significant independent metabolic signatures. The method then classifies the possible cancer as belong to one of at least two cancer classes based on the identified independent metabolic signatures.

An automatic classification method for distinguishing between indolent and clinically significant carcinoma using multiparametric MRI (mp-MRI) imaging is provided. By utilizing a convolutional neural network (CNN), which automatically extracts deep features, the hierarchical classification framework avoids deficiencies in current schemes in the art such as the need to provide handcrafted features predefined by a domain expert and the precise delineation of lesion boundaries by a human or computerized algorithm. This hierarchical classification framework is trained using previously acquired mp-MRI data with known cancer classification characteristics and the framework is applied to mp-MRI images of new patients to provide identification and computerized cancer classification results of a suspicious lesion.

Disclosed herein are classifier models, computer implemented systems, machine learning systems and methods thereof for classifying asymptomatic patients into a risk category for having or developing cancer and / or classifying a patient with an increased risk of having or developing cancer into an organ system-based malignancy class membership and / or into a specific cancer class membership.

A system for classifying a patient's cancer as belonging to one or more Cancer Modules of 1 of 15 different cancer types is provided. The Cancer Modules are useful to identify patient populations and individual patients demonstrating specific prognosis, risk of metastasis and / or recurrence, response or lack of response to drugs, and the like.

To provide a method for selecting a marker gene useful for cancer classification; a method for classifying cancer using the gene; a method for detecting cancer; a kit usable for the classification method or detection method; and a DNA array carrying the gene. According to the present invention, there can be obtained a gene, wherein expression of the above gene is altered independently from genes each of which expression is altered specifically during cell proliferation and expression level of the above gene is specifically altered depending on every type of cancer samples to be tested, whereby the classification or detection of cancer can be carried out conveniently and quickly without giving surgical treatment. Therefore, the present invention is useful for the diagnosis, the treatment, and the like of cancer.

The invention discloses a method and system for predicting cancer. The method comprises the following steps: carrying out difference analysis on the gene expression profile data of a cancer patient and a normal person to obtain difference genes; analyzing the gene expression profile data of the cancer patient and the normal person based on weighted gene co-expression network analysis to obtain a hub gene; processing the gene expression profile data of the difference genes through a variational auto-encoder algorithm to obtain dimension reduction data; and with the gene expression profile dataof the hub gene and the dimension reduction data as classification features of a cancer classifier of a preset type, conducting accurate classification of cancer patients and normal people through thecancer classifier. According to the method and the system for predicting cancer, the gene expression profile data of the hub gene obtained by weighted gene co-expression network analysis and the dimension reduction data processed by the variational auto-encoder are jointly used as the classification characteristics of the cancer classifier, so the accuracy of the cancer classifier is effectivelyimproved, and the purpose of efficiently predicting cancer is achieved.

The invention provides a screen method and screen device for protein markers for gastric cancer classification, and application of a screened protein marker. The screen method comprises steps of screening proteins meeting retaining conditions from a protein expression mass spectrometry database formed by multiple samples, and using the proteins as an effective protein set; performing twice dimension reducing processing on the effective protein set in sequence, so as to obtain a dimension-reduced protein set; performing clustering analysis on the dimension-reduced protein set, so as to obtain different types of protein markers. In the method, protein markers with remarkable high expression in cancer samples are screened out from a protein mass spectrometry database comprising a large quantity of gastric cancer samples, gastric cancer falls into different types of protein markers according to a relationship between different protein markers and survival rates, and the markers of different types have remarkable differences, helping classify gastric cancers more accurately.

The present invention relates to methods of classifying cancer cells based on the presence, absence or level of a tyrosine kinase or a phosphorylated tyrosine kinase. The present invention also relates to methods of treating cancer using cancer classification. The present invention further relates to methods of determining the effectiveness of a treatment for cancer using cancer classification.

The present invention provides a malignant cancer adjunctively therapeutic method which includes the three combined therapeutic regimens: reductive ion natural therapy, large dose vitamin C intravenous injection, and functional nutritional special prescription therapy. The functional nutritional special prescription therapy includes basic nutritional formula and functional formula and can greatly alleviate the suffering of cancer patients. By repairing and activating normal human cell ability, the malignant cancer adjunctively therapeutic method controls and inhibits the further development of cancer cells, formulates targeted therapeutic regimens according to cancer classification, and finds a new hopeful road for cancer patients.

The invention discloses a cancer grading prediction method and device, equipment and a storage medium, and the method comprises the steps: collecting a pathological image of a patient and corresponding grading labeling information, carrying out the preprocessing, and dividing the image into a plurality of image blocks; training a self-supervised learning model by using the image block of each pathological image; clustering the image block coding vectors by using a clustering algorithm, and clustering the image block coding vectors of each pathological image into a plurality of category areas; carrying out feature sampling on the image block coding vectors of each category region, and carrying out feature fusion on the sampled image block coding vectors to obtain image fusion features of each pathological image; training a cancer grading model by using the image fusion features with the category region information of each pathological image, wherein the cancer grading model is used for predicting cancer grading; and applying the trained model to a to-be-analyzed pathological image, and predicting cancer classification. According to the method, cancers can be accurately graded, diseases can be found in time, and a treatment scheme can be formulated.

The invention discloses a feature gene selecting and cancer classifying method which at least comprises the following steps of establishing a logistic regression model according to a super-parameter set and a to-be-processed gene data set; according to maximum likelihood estimation and logarithmic operation, expressing the logistic regression model as a loss function; establishing an SCAD-Net resolving model; according to the loss function and the SCAD-Net resolving model, obtaining an SNL model; calculating an iteration updating operator of the SCAD-Net; according to the iteration updating operator, calculating a gene regression coefficient of the SNL model through a coordinate gradient descent method; and according to the gene regression coefficient, performing feature gene selection andcancer classification. The feature gene selecting and cancer classifying method can effectively improve feature gene selecting and cancer classifying accuracy, thereby facilitating disease researching.

The invention provides a cancer subtype classification method based on a KAN network and multi-omics data, and the method comprises the steps: obtaining the multi-omics data, including genomics data, transcriptomics data and proteomics data, and constructing a test data set; carrying out feature extraction and integration on the multi-omics data by utilizing a Colmogolov-Arnod network model, and carrying out training to obtain a trained cancer typing model; in the model evaluation stage, a Monte Carlo discarding method is adopted to carry out multiple times of forward propagation so as to estimate the uncertainty of a model prediction result and improve the robustness of the model; and carrying out cancer typing prediction, and carrying out high-precision cancer typing on multi-omics data by using the trained Colmogolov-Arnod network model. According to the method, the problem of heterogeneity of multi-omics data can be effectively solved, the accuracy and robustness of cancer typing are improved, and the effect of personalized treatment is improved.

Biomarkers, particularly hypoxia-related genes, and methods using the biomarkers for molecular classification of disease are provided.

The invention discloses a method for classification of cancer in an individual having contracted cancer. The method of classification involves the determination of microsatellite status and a prognostic marker by examining gene expression patterns. The invention also relates to various methods of treatment of cancer. Additionally, the present invention concerns a pharmaceutical composition for treatment of cancer and uses of the present invention. The invention also relates to an assay for classification of cancer.

Aspects of the invention include methods for preparing an enriched sequencing library. In some embodiments, the methods involve preparing a sequencing library that is enriched for AT-rich sequences. In certain embodiments, the methods involve determining a presence or an absence of cancer, determining a cancer stage, monitoring cancer progression, and / or determining a cancer classification in a subject by analyzing an enriched sequencing library.

The invention discloses a cancer classification comparison learning method based on a twinborn network, and the method comprises the steps: obtaining a plurality of sample pathological section images and test pathological section images through collection equipment, carrying out the cancer type judgment of each sample pathological section image, carrying out the marking according to a judgment result, obtaining corresponding first marking data, and carrying out the classification comparison of the test pathological section images; the method comprises the following steps: respectively carrying out similar and heterogeneous random pairing on different sample pathological section images according to cancer categories to obtain a plurality of training pairs, creating a twin network, sequentially inputting each training pair into the twin network, and respectively learning similarity measurement between the pathological section images in different training pairs to obtain a trained twin network, and acquiring and using feature vectors with representation capability generated during twin network training and corresponding second annotation data to train a cancer classification prediction model, inputting all the test pathological section images into the cancer classification prediction model to obtain a plurality of classification prediction results, and visualizing the classification prediction results.

The invention belongs to the field of biological information, and discloses a cancer classification and characteristic gene selection method, which comprises the following steps of: establishment of a primary learner: establishing T logistic regression models and a spark group lasso regularized loss function solving model corresponding to the T logistic regression models, and outputting a secondary learner training set; establishing a secondary learner: establishing a multi-response regression model and a loss function solving model corresponding to L1 regularization, and outputting a training set prediction result; and a prognosis feature selection model: establishing a prognosis feature selection SGL model. According to the cancer classification and feature gene selection method, the three standards of prediction, stabilization and selection are met, the accuracy and stability of the model on cancer classification prediction are improved through stacking integration, oncogenes and cancer-related genes are accurately selected, and the interpretability of the model is enhanced; gene and gene pathway priori knowledge are fused, and the accuracy of cancer classification and the effectiveness of feature selection are improved.

The invention provides methods for classifying a cancer as susceptible to transmembrane prostate androgen induced (TMEPAI)-directed therapies, and methods for treating such cancers. The field of the invention pertains generally to medicine, pathology and oncology. More particularly, it addresses the treatment of breast cancer, such as triple-negative breast cancer, using a transmembrane prostate androgen induced (TMEPAI)-directed therapy.

The present invention relates to methods of classifying cancer cells based on the presence, absence or level of tyrosine kinase or a phophorylated tyrosine kinase. The present invention also related to methods of treating cancer using cancer classification. The present invention further related to methods of determining the effectiveness of a treatment for cancer using cancer classification.

Biomarkers, particularly hypoxia-related genes, and methods using the biomarkers for molecular detection and classification of disease are provided.

Methods for generating a sequencing library from a sample comprising a plurality of single-stranded DNA molecules are provided, along with methods of using the generated sequencing library for detecting cancer, determining cancer stage, monitoring cancer progression, and / or determining a cancer classification from a test sample obtained from a subject.

The invention discloses a cancer patient gene methylation feature screening method based on DDPG reinforcement learning. According to the method, a depth deterministic strategy gradient algorithm (DDPG) is combined with gene methylation data, and important features closely related to cancer classification are accurately screened out from massive gene methylation data. The system dynamically selects gene methylation features through effective exploration of a continuous state space and an action space, and optimizes a feature selection strategy through a reward mechanism of reinforcement learning. According to the method, the accuracy of a cancer classification model can be remarkably improved, and powerful support can be provided for early detection and personalized treatment of cancers by analyzing the screened features. According to the method, the challenge of high-dimensional gene data feature selection is effectively solved, the data processing efficiency in biomedical research is improved, and the method has wide application prospects and practical value.

Disclosed herein are classifier models, computer implemented systems, machine learning systems and methods thereof for classifying asymptomatic patients into a risk category for having or developing cancer and / or classifying a patient with an increased risk of having or developing cancer into an organ system-based malignancy class membership and / or into a specific cancer class membership.

Methods and systems for detecting cancer and / or determining a cancer tissue of origin are disclosed. In some embodiments, a multiclass cancer classifier is disclosed that is trained with a plurality of biological samples containing cfDNA fragments. The analytics system derives a feature vector for each sample, and the multiclass classifier predicts a probability likelihood for each of a plurality of tissue of origin (TOO) classes. In some embodiments, the plurality of TOO classes include hematological subtypes, including both hematological malignancies and precursor conditions. In one embodiment, non-cancer samples having high tissue signal are pruned from the training sample set. In another embodiment, the analytics system stratifies samples according to tissue signal and applies binary threshold cutoffs determined for each stratum.

The invention belongs to the technical field of deep learning and image classification, and relates to a lung cancer tissue classification method based on improved Swinin-Transformer, and the method specifically comprises the following steps: S1, preparing a data set: collecting lung full-view pathological tissue slice images to construct the data set, which comprises various lung cancer subtype tissue slices and normal lung tissue slices; the method is a multi-example learning method, a self-supervised comparative learning mode is adopted to compare feature differences between positive and negative samples, a double-flow channel structure is adopted to extract features under different amplification factors, each channel takes Swim-Transform as a main network framework, an EMA module is added between Swin Transform Block modules to enhance the capability of extracting multi-scale features, and the multi-scale feature extraction efficiency is improved. And carrying out feature fusion by adopting a feature weighted aggregation mode so as to carry out classification prediction on the whole image. According to the method, the final classification result is returned to the original image and displayed by the thermodynamic diagram, so that the purposes of full-view image cancer classification and focus area detection are achieved.

Systems and methods for identifying a diagnosis of a cancerous state for a somatic tumor specimen of a subject are provided.SOLUTION: The method receives sequencing information comprising an analysis of a plurality of nucleic acids from a somatic tumor specimen. The method identifies a plurality of features from the sequencing information including two or more of RNA, DNA, RNA splicing, viral, and copy number features. The method provides a first subset of features and a second subset of features from the identified plurality of features as input to a first classifier and a second classifier, respectively. The method generates two or more predictions of cancer status based at least in part on the identified plurality of features from the two or more classifiers. The method combines the two or more predictions with a final classifier to identify a diagnosis of cancer status for the subject's somatic tumor specimen.SELECTED DRAWING: Figure 1