14 results about "Cancer type" patented technology

Embodiments of the present application disclose a pan-cancer cell recognition model training method, device, equipment and storage medium. The method comprises selecting transcriptome test data of a plurality of preset cancer types according to a preset ratio of normal cells and malignant cells to construct an initial data set; obtaining a preset number of high variable genes in the transcriptome test data of the initial data set as training features to obtain a training set; based on a binary classification label, performing label annotation on the transcriptome test data in the training set to generate a binary classification label system test data set; taking the pre-training weight of a preset base model as an initialization parameter, mounting a binary classification head at the top layer of a transformer layer, and performing parameter fine-tuning on the preset base model based on the binary classification label system test data set to obtain a pan-cancer cell recognition model. The scheme of the embodiments of the present application can realize accurate identification of benign and malignant cells in pan-cancer single-cell transcriptome data.

Techniques for identifying a cancer type of a subject are described. An example method includes identifying sequence read data indicating sequences of DNA fragments of a sample obtained from a subject. Based on the sequence read data, endpoint positions of the DNA fragments with respect to a reference genome are identified. Further, input features are determined based on the endpoint positions of the DNA fragments with respect to the reference genome. The example method further includes predicting, using a classifier and based on the input features, a primary type of cancer of the subject.

Disclosed is a method of diagnosing cancer and predicting the type of cancer based on a single nucleotide variant in a cell-free nucleic acid including extracting nucleic acids from a biological sample to obtain sequence information, extracting cancer-specific single nucleotide variants through filtering based on aligned reads, calculating the regional mutation density of single nucleotide variants and the frequency of mutation signature of single nucleotide variants, and inputting the calculated values into a trained artificial intelligence model to analyze output values. This method is capable of exhibiting high sensitivity and accuracy compared to other methods of diagnosing cancer and predicting the type of cancer using genetic information of cell-free nucleic acids, and of ensuring the same level of sensitivity and accuracy as cancer-tissue-cell-based methods, and can be usefully applied to other analyses using single nucleotide variants in cell-free nucleic acids.

The present invention relates to a method for cancer diagnosis and cancer type prediction using methylated cell-free nucleic acid, more specifically, to a method for cancer diagnosis and cancer type prediction using a method of extracting methylated nucleic acid from a biological sample, obtaining sequence information, generating vectorized data of nucleic acid fragments based on aligned reads, and inputting the vectorized data into a trained artificial intelligence model to analyze calculated values. The method for cancer diagnosis and cancer type prediction using methylated cell-free nucleic acid according to the present invention is useful because it generates vectorized data and analyzes it using an AI algorithm, compared to a conventional method using a step of determining chromosome amount based on read count or a detection method using a distance concept between aligned reads, which utilizes values ​​related to reads as standardized values ​​one by one, and therefore can achieve the same effect even if the read coverage is low.

The application provides a human genome T5 series fragment for multi-cancer identification and use thereof. A set of human genome differential methylation regions for multi-cancer identification, referred to as T5 series fragments (T5-1, T5-2, T5-3, T5-4, T5-5, T5-6, T5-7, T5-8) is disclosed. On this basis, the application provides a multi-cancer methylation technology which can cover more than 20 high-incidence cancer types, has high sensitivity (≥90%) and high specificity (≤5% false positive rate), and can realize rapid and micro-sample detection.

The present application relates to the technical field of biological medicine, and particularly relates to a tumor immunogenic death biomimetic nanovesicle with high membrane breaking efficiency, a preparation method and application thereof.The tumor immunogenic death biomimetic nanovesicle with high membrane breaking efficiency comprises a tumor cell membrane and a photothermal reagent; the photothermal reagent is compound A or compound B.The biomimetic nanovesicle provided by the present application has a killing rate of more than 95% on various tumor cells, can be prepared into ICMs for different tumors by flexibly matching cell membranes of different cancer types, supports individualized treatment and combined immunotherapy, and provides an innovative scheme with high efficiency, wide spectrum and low toxicity for solid tumor treatment through synergistic action of targeted delivery and photothermal-induced cell membrane destruction, and has high clinical application potential.

Disclosed are a lymphoma cell-specific drug delivery system for the prevention or treatment of lymphoma and a production method therefor. The lymphoma cell-specific drug delivery system may be delivered into lymphoma cells in an improved manner compared to conventional single-target drug delivery systems, and is applicable to the delivery of various therapeutic drugs for the treatment of lymphoma through the application of a wide range of drugs and the same antibody functionalization strategy on the surface of different types of nanoparticles. In addition, the drug delivery system may be introduced into lymphoma as well as other cancer types by adjusting the type and mixing ratio of antibody, and may propose a method of introducing polymeric nucleic acid drugs having superior physiological stability and drug efficacy compared to conventional monomeric nucleic acid drugs, thereby enabling effective drug treatment of lymphoma which is highly resistant to intracellular drug delivery.

Tumors use a variety of mechanisms to avoid the host's anti-tumor immune response. Humoral immune suppression is one of the mechanisms. Tumors produce circulating factors that can suppress antibody or complement-mediated immune responses to enhance their own survival. Mesothelin is a cell surface protein that is overexpressed by several cancer types that are associated with a microenvironment that exhibits immune suppression. Anti-mesothelin antibodies often suffer from such immune suppression microenvironments. However, an alternatively formatted anti-mesothelin antibody is effective in killing mesothelin-expressing cancers, independent of the tumor microenvironment immune status.

This invention relates to a fusion protein that specifically binds to the extradomain B of fibronectin (EDB-FN) and transforming growth factor β (TGFβ), and its uses. More specifically, it relates to a fusion protein comprising a polypeptide that specifically binds to EDB-FN and a polypeptide that specifically binds to TGFβ, and its uses. The fusion protein of this invention achieves direct localization of TGFβ inhibition within the tumor microenvironment by immobilizing TGFβ, which is important for anti-tumor immune responses, in the extracellular matrix, ensuring local rather than systemic action. It not only exhibits excellent anti-tumor effects in various cancer types, but also, due to the rigidity of the extracellular matrix, demonstrates excellent anti-tumor effects in pancreatic cancer, where traditional TGFβ inhibitors are ineffective. Therefore, it can be usefully applied to the prevention or treatment of cancer.

The present application relates to the technical field of biology, to the field of genetic diagnosis, and in particular to a grading model for detecting the benign and malignant degree of tumor and application thereof. The present application provides a grading model for detecting the benign and malignant degree of tumor and application thereof, which is used for observing the change of imprinting genes of tumor at single cell and tissue levels, so as to judge the benign and malignant degree of tumor. Meanwhile, the change of expression of imprinting genes and non-imprinting genes can be combined, so that the cancer type and the benign and malignant degree can be more accurately judged.

This invention provides methods, systems, and computer-readable storage media for cancer screening. The cancer screening methods include: acquiring multi-source heterogeneous medical data from patients; preprocessing the multi-source heterogeneous medical data to generate structured medical data; constructing an atomic variable fact layer based on the structured medical data, which is used to categorize atomic variables according to preset medical classifications; constructing a patient early screening label system based on the atomic variable fact layer using preset label mapping rules, the patient early screening label system including label data for different cancer types, different medical classifications, and different label levels; using a risk assessment intelligent engine, performing risk assessment on the patient early screening label system using screening rule matching, generating risk assessment results and screening recommendations; and constructing a risk assessment knowledge graph based on the patient early screening label system, risk assessment results, and screening recommendations, the risk assessment knowledge graph including a positive early warning knowledge graph and a false negative identification knowledge graph.

The present invention relates to a method for diagnosing cancer and predicting cancer type using cell-free nucleic acid fragment end motif frequency and size, and more specifically, to a method for diagnosing cancer and predicting cancer type in which a nucleic acid is extracted from a biological sample, the end motif frequency of a nucleic acid fragment and the size of the nucleic acid fragment are derived on the basis of reads aligned by obtaining sequence information, and then a value calculated by generating the derived end motif frequency and size as vectorized data and post-processing same and then inputting the post-processed vectorized data to a learned artificial intelligence model is analyzed. A method for diagnosing cancer and predicting cancer type using the end motif frequency and size of a cell-free nucleic acid fragment according to the present invention generates vectorized data and analyzes same using an AI algorithm, and thus exhibits high sensitivity and accuracy even if read coverage is low. Therefore, the method is useful.

The present disclosure relates to polymeric compositions and methods for activating gamma delta T cells, specifically Vγ9Vδ2 T cells, in cancer immunotherapy. These compositions include a cell-targeting moiety and a polymer incorporating phosphoantigens (pAgs) for targeted delivery to tumor cells. The method involves administering an effective amount of these compositions to a subject, allowing controlled release of pAgs in the tumor microenvironment. This approach overcomes limitations of systemic pAg administration and can be used alone or with adoptive transfer of Vγ9Vδ2 T cells or PBMCs. The treatment may involve repeated administrations and is applicable to various cancer types. This disclosure also covers methods for synthesizing these compositions and their use in cancer treatment applications.

This invention relates to an AI-based early tumor screening system that couples the nucleosome localization cycle and mutation phase characteristics of cfDNA, belonging to the field of in vitro diagnostic technology. The system includes: a sample processing and nucleic acid extraction unit, which collects peripheral blood from subjects, purifies the plasma through two-stage centrifugation, extracts circulating cell-free DNA, and assesses its quality; a sequencing execution and data calibration unit, which constructs a library and performs whole-genome sequencing, removes abnormal fragments through quality control screening, removes repetitive sequences and corrects for biases after alignment with a human reference genome, and outputs standardized data; a core feature analysis and extraction unit, which identifies the nucleosome localization center, determines the orientation characteristics of DNA entanglement with histones, and integrates multimodal information to construct a core feature combination; and a model construction and risk assessment unit, which converts the features into a risk score and generates a screening report containing the risk level. This system achieves non-invasive, accurate, and efficient early tumor screening, covering a variety of common cancer types, and provides reliable support for early clinical diagnosis and treatment.