CN-116312789-B - Tumor malignancy evaluation method, electronic equipment and storage medium

CN116312789BCN 116312789 BCN116312789 BCN 116312789BCN-116312789-B

Abstract

The application discloses a method for evaluating malignancy of tumor, electronic equipment and a storage medium, wherein the method for evaluating malignancy of tumor comprises the following steps: the method comprises the steps of inputting a tumor sample to be tested into a comprehensive risk ratio index model, outputting a comprehensive risk ratio index according to the tumor sample to be tested by the comprehensive risk ratio index model, judging the malignancy degree of the tumor sample to be tested according to the comprehensive risk ratio index, and evaluating the malignancy degree of the tumor to be tested by only obtaining transcriptome data of the tumor to be tested of a patient.

Inventors

SUN KUN
HU DINGXUE
LIU XIAOYI

Assignees

深圳湾实验室

Dates

Publication Date: 20260508
Application Date: 20230331

Claims (5)

1. A processor-executable tumor malignancy evaluation program, characterized in that it when executed by a processor implements a tumor malignancy evaluation method comprising: inputting a tumor sample to be detected into a comprehensive risk ratio index model, wherein the tumor sample to be detected comprises transcriptome data of a tumor to be detected; the comprehensive risk ratio index model outputs a comprehensive risk ratio index according to the tumor sample to be detected; judging the malignancy degree of the tumor sample to be detected according to the comprehensive risk ratio index; the comprehensive risk ratio index model is constructed by the following method: Obtaining a plurality of tumor sample data and paracancer sample data corresponding to the tumor sample data, wherein the tumor sample data comprises first transcriptome data and patient prognosis information, the first transcriptome data is transcriptome data of a tumor sample, the paracancer sample data comprises second transcriptome data, and the second transcriptome data is transcriptome data of a paracancer sample; Screening for differentially expressed genes based on the first transcriptome data and the second transcriptome data; Dividing the tumor sample data into a training set and a testing set; obtaining the expression quantity of the differential expression genes in the training set; dividing the training set into a high expression level group and a low expression level group according to the expression level of the differential expression genes in the training set; Performing survival analysis on the high expression quantity group and the low expression quantity group to obtain a P value and an HR value corresponding to the differential expression gene, wherein the P value is the error probability; screening candidate genes from the training set according to the P value, wherein the candidate genes are the differential expression genes related to prognosis of a patient; Sequencing the candidate genes of each type from small to large according to the P value to obtain a significance sequence; selecting the first 40 of the candidate genes in each type of the saliency sequences as a prognosis-related gene, wherein the prognosis-related gene is the differentially expressed gene related to the prognosis of a patient, the types of the prognosis-related genes comprise a suspected protooncogene, a suspected up-regulating protecting gene, a suspected tumor suppressor gene and a suspected down-regulating protecting gene, the suspected protooncogene is the differentially expressed gene which is up-regulated in the tumor sample data and leads to a worse prognosis, the suspected up-regulating protecting gene is the differentially expressed gene which is up-regulated in the tumor sample data and leads to a better prognosis, the suspected tumor suppressor gene is the differentially expressed gene which is down-regulated in the tumor sample data and leads to a worse prognosis, and the suspected down-regulating protecting gene is the differentially expressed gene which is down-regulated in the tumor sample data and leads to a better prognosis; constructing a comprehensive risk ratio index model according to the prognosis related genes, wherein the calculation formula of the comprehensive risk ratio index is as follows: Wherein, the In order to integrate the risk ratio index(s), Is the first Said HR value corresponding to each of said prognostic-related genes, Is the first The method for acquiring the calculation coefficients corresponding to the prognosis related genes comprises the steps of acquiring the expression quantity of each prognosis related gene in all tumor sample data, determining a threshold value according to the expression quantity of each prognosis related gene in all tumor sample data, wherein the threshold value is the median of the expression quantity, acquiring the expression quantity of the prognosis related gene in the tumor sample to be detected, determining the calculation coefficients according to the threshold value, the type of the prognosis related gene and the expression quantity of the prognosis related gene in the tumor sample to be detected, wherein the calculation coefficients are 1 if the expression quantity of the prognosis related gene in the tumor sample to be detected is higher than the threshold value, and the calculation coefficients are 1 if the expression quantity of the prognosis related gene in the tumor sample to be detected is lower than the threshold value, and the calculation coefficients are-1 if the expression quantity of the prognosis related gene in the tumor sample to be detected is lower than the threshold value, and the calculation coefficients are inhibited by the threshold value; and verifying the comprehensive risk ratio index model through the test set.
2. The tumor malignancy evaluation program according to claim 1, wherein the acquiring a plurality of tumor sample data and paracancerous sample data corresponding to the tumor sample data comprises acquiring a plurality of tumor sample data including a plurality of cancer types and paracancerous sample data corresponding to the tumor sample data.
3. The tumor malignancy evaluation program according to claim 1, wherein screening for a differentially expressed gene based on the first transcriptome data and the second transcriptome data comprises screening for the differentially expressed gene from the first transcriptome data by DESeq2 software based on the first transcriptome data and the second transcriptome data.
4. An electronic device, comprising: at least one processor; at least one memory for storing at least one program; A tumor malignancy assessment procedure according to any one of claims 1 to 3 when at least one of said procedures is executed by at least one of said processors.
5. A computer-readable storage medium, in which a processor-executable program is stored, which when executed by a processor is for realizing the tumor malignancy evaluation program according to any one of claims 1 to 3.

Description

Tumor malignancy evaluation method, electronic equipment and storage medium Technical Field The application relates to the technical field of tumor malignancy evaluation, in particular to a tumor malignancy evaluation method, electronic equipment and a storage medium. Background Accurate medical treatment is currently recognized as the best treatment for cancer patients. In accurate medicine, the malignancy of the tumor has high guiding value for the selection of a treatment scheme and the evaluation of prognosis of a patient. The malignancy evaluation of the tumor is mainly carried out by grading the tumor according to the size of the primary tumor and the diffusion degree of the tumor in the body. Tumor staging can help clinicians to develop appropriate treatment regimens, predict patient prognosis, evaluate treatment efficacy of treatment regimens, etc. The current stage of a tumor is a stage obtained by different examination results of physical examination, imaging examination (X-ray, CT, etc.), laboratory examination (such as blood routine, urine routine, etc.), etc. Patient staging is primarily Tumor staging according to the TNM system, and is assessed by three dimensions for Tumor (Tumor), lymph node (Lymph Node), and distant Metastasis (Metastasis). The T stage is used for describing the development degree of the primary tumor, according to the size of the tumor, whether the growth part of the tumor is diffused into adjacent tissues or not can be divided into T0, T1, T2, T3 and T4, the larger the stage value is, the deeper the growth part of the tumor is, the evidence of lack of the primary tumor is represented by T0, the N stage is used for evaluating the situation of the lymph nodes diffused by the tumor and is divided into N0, N1, N2, N3 and N4, the larger the stage value is, the more the lymph nodes diffused by the tumor is represented by N0, the tumor is not diffused into the lymph nodes, the M stage is divided into M0 and M1, M0 represents that the tumor is not transferred into other parts, and M1 represents that the tumor is transferred into other parts. The TNM Stage values are synthesized to give overall Stage (Stage I, II, III, IV), and generally, the lower the overall Stage value is, the earlier the tumor is in, the better the prognosis is represented, and the higher the overall Stage value is, the more complex the tumor is in the later Stage, and the worse the prognosis is. The method has a certain guiding value for the treatment scheme and prognosis evaluation of cancer patients according to the malignancy degree evaluation of tumors, but mainly has three problems that the tumor staging method needs to carry out multiple inspections and needs to acquire the tumor tissues of the patients for inspection, the inspection is complex, the inspection cost is high and the time is long, the current tumor staging method carries out TNM stage judgment on the inspection result according to the experience of clinicians, the information of any tumor molecular level is not consulted, the qualitative rather than quantitative is preferred, the guiding capability of accurate medical treatment is limited, and the third point is that the survival condition of the patients is difficult to judge according to the tumor stage only for early tumor patients. Disclosure of Invention The present application aims to solve at least one of the technical problems existing in the prior art. Therefore, the application provides a tumor malignancy evaluation method, electronic equipment and a storage medium, which can solve the problems of complex examination, high cost, long time consumption, incapability of quantitatively analyzing the malignancy of the tumor and difficulty in evaluating the survival condition of early tumor patients in the existing tumor malignancy evaluation technology. According to the embodiment of the first aspect of the application, a tumor malignancy evaluation method comprises the steps of inputting a tumor sample to be tested into a comprehensive risk ratio index model, outputting a comprehensive risk ratio index according to the tumor sample by the comprehensive risk ratio index model, judging malignancy of the tumor sample to be tested according to the comprehensive risk ratio index, constructing the comprehensive risk ratio index model by the following steps of obtaining a plurality of tumor sample data and cancer side sample data corresponding to the tumor sample data, wherein the tumor sample data comprises first transcriptome data and patient prognosis information, the first transcriptome data is transcriptome data of the tumor sample, the cancer side sample data comprises second transcriptome data, the second transcriptome data is transcriptome data of the cancer side sample, selecting differential expression genes according to the first transcriptome data and the second transcriptome data, classifying the tumor sample data into a training set and a test set according to the comprehensiv