CN113851185B - Prognosis evaluation method for immunotherapy of non-small cell lung cancer patient - Google Patents
Prognosis evaluation method for immunotherapy of non-small cell lung cancer patient Download PDFInfo
- Publication number
- CN113851185B CN113851185B CN202111433361.1A CN202111433361A CN113851185B CN 113851185 B CN113851185 B CN 113851185B CN 202111433361 A CN202111433361 A CN 202111433361A CN 113851185 B CN113851185 B CN 113851185B
- Authority
- CN
- China
- Prior art keywords
- model
- patient
- prognosis
- tmb
- lung cancer
- 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.)
- Active
Links
Images
Classifications
-
- 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
- G16B5/00—ICT specially adapted for modelling or simulations in systems biology, e.g. gene-regulatory networks, protein interaction networks or metabolic networks
-
- C—CHEMISTRY; METALLURGY
- C12—BIOCHEMISTRY; BEER; SPIRITS; WINE; VINEGAR; MICROBIOLOGY; ENZYMOLOGY; MUTATION OR GENETIC ENGINEERING
- C12Q—MEASURING OR TESTING PROCESSES INVOLVING ENZYMES, NUCLEIC ACIDS OR MICROORGANISMS; COMPOSITIONS OR TEST PAPERS THEREFOR; PROCESSES OF PREPARING SUCH COMPOSITIONS; CONDITION-RESPONSIVE CONTROL IN MICROBIOLOGICAL OR ENZYMOLOGICAL PROCESSES
- C12Q1/00—Measuring or testing processes involving enzymes, nucleic acids or microorganisms; Compositions therefor; Processes of preparing such compositions
- C12Q1/68—Measuring or testing processes involving enzymes, nucleic acids or microorganisms; Compositions therefor; Processes of preparing such compositions involving nucleic acids
- C12Q1/6876—Nucleic acid products used in the analysis of nucleic acids, e.g. primers or probes
- C12Q1/6883—Nucleic acid products used in the analysis of nucleic acids, e.g. primers or probes for diseases caused by alterations of genetic material
- C12Q1/6886—Nucleic acid products used in the analysis of nucleic acids, e.g. primers or probes for diseases caused by alterations of genetic material for cancer
-
- 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
- G16B20/00—ICT specially adapted for functional genomics or proteomics, e.g. genotype-phenotype associations
- G16B20/50—Mutagenesis
-
- 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
-
- 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
-
- C—CHEMISTRY; METALLURGY
- C12—BIOCHEMISTRY; BEER; SPIRITS; WINE; VINEGAR; MICROBIOLOGY; ENZYMOLOGY; MUTATION OR GENETIC ENGINEERING
- C12Q—MEASURING OR TESTING PROCESSES INVOLVING ENZYMES, NUCLEIC ACIDS OR MICROORGANISMS; COMPOSITIONS OR TEST PAPERS THEREFOR; PROCESSES OF PREPARING SUCH COMPOSITIONS; CONDITION-RESPONSIVE CONTROL IN MICROBIOLOGICAL OR ENZYMOLOGICAL PROCESSES
- C12Q2600/00—Oligonucleotides characterized by their use
- C12Q2600/118—Prognosis of disease development
-
- C—CHEMISTRY; METALLURGY
- C12—BIOCHEMISTRY; BEER; SPIRITS; WINE; VINEGAR; MICROBIOLOGY; ENZYMOLOGY; MUTATION OR GENETIC ENGINEERING
- C12Q—MEASURING OR TESTING PROCESSES INVOLVING ENZYMES, NUCLEIC ACIDS OR MICROORGANISMS; COMPOSITIONS OR TEST PAPERS THEREFOR; PROCESSES OF PREPARING SUCH COMPOSITIONS; CONDITION-RESPONSIVE CONTROL IN MICROBIOLOGICAL OR ENZYMOLOGICAL PROCESSES
- C12Q2600/00—Oligonucleotides characterized by their use
- C12Q2600/156—Polymorphic or mutational markers
Abstract
The invention relates to the technical field of medical molecular biology, in particular to a prognosis evaluation method for immunotherapy of patients with non-small cell lung cancer. Compared with the prior art, the prognosis evaluation method for the immunotherapy of the patient with the non-small cell lung cancer TMB-H provided by the invention has the advantages that the sample of the patient with the non-small cell lung cancer TMB-H is sequenced, the prediction model containing 13 optimal characteristic genes is constructed based on the CART algorithm, the prognosis risk scoring is carried out on the patient with the non-small cell lung cancer TMB-H according to the prediction model, the TMB-H population is divided into a good prognosis group and a poor prognosis group, and the accuracy is up to 0.85.
Description
Technical Field
The invention relates to the technical field of medical molecular biology, in particular to a prognosis evaluation method for immunotherapy of patients with non-small cell lung cancer.
Background
The immunotherapy medicament can promote the function of the patient's own immune system to eliminate the tumor by inhibiting the immune escape of the tumor cells. At present, the immunotherapy has made breakthrough progress in the treatment of various advanced solid tumors, and particularly can effectively prolong the Overall survival time (OS) of patients, and has controllable adverse reactions. However, due to the lack of suitable clinical molecular markers, only 20% -30% of people who benefit from PD-1/PD-L1 immunotherapy drugs are benefited. Accurate measurement of TMB can predict the efficacy of immune checkpoint inhibitors, giving cancer patients the opportunity to obtain more accurate treatment. Previous clinical studies and transformation studies have shown that Tumor Mutation Burden (TMB) status based on tissue detection is associated with Objective Remission Rate (ORR), Progression-free survival (PFS), and OS, and is therefore considered to be an important marker for guided immunotherapy. It is generally believed that the effect of the immunodetection site inhibitor is better when the TMB value is higher (TMB-H). However, there are a number of reports indicating that there is a poor specificity when using TMB as an indicator to classify populations that benefit from immunotherapy, particularly in populations with TMB-H non-small cell lung cancer where there is a short OS after immunotherapy. Other markers are urgently needed to assist TMB to carry out secondary division of people, and the classification effect of the people benefiting from TMB-H immunotherapy is improved.
Disclosure of Invention
In view of the above-mentioned shortcomings of the background art, the present invention provides a method for prognosis evaluation of immunotherapy for patients with non-small cell lung cancer.
The technical scheme adopted by the invention is as follows: a prognostic evaluation method for immunotherapy of non-small cell lung cancer patients is characterized in that: the method comprises the following steps:
s1, carrying out gene targeted sequencing on the non-small cell lung cancer patient to obtain the gene variation condition;
s2, inputting the gene mutation list and prognosis condition of the patient into a supervised learning decision tree model, establishing a classification model based on a CART algorithm, creating a decision tree model, and screening out 13 optimal characteristic genes;
s3, constructing a prediction model formula I containing 13 optimal characteristic genes, and carrying out prognosis risk scoring on the non-small cell lung cancer TMB-H patient so as to predict the prognosis condition of the patient;
Wherein the content of the first and second substances,
to represent
Coefficient of one-way cox regression of the perturbation characteristic and time-to-live.
Preferably, the S1 is specifically: collecting a sample of a non-small cell lung cancer TMB-H patient to perform targeted deep sequencing and detecting the genetic variation condition of the panel.
Preferably, the S2 is specifically: the detected gene variation is used as a training characteristic, the total life cycle OS <12 months and the total life cycle OS >12 months are used as classification results of machine learning, a supervised learning decision tree model CART algorithm is used, and a decision tree model is created through four steps of characteristic selection, pruning, cross validation and model persistence.
Preferably, the feature selection is specifically: calculating the classification condition after branch selection is carried out through different characteristics by using the Gini coefficient shown in the formula II as a measurement standard, finding out the best classification characteristic as a root node, and repeating the steps until the tree building is finished, and creating a complex tree model;
Where K denotes the class, p is the probability of the kth class, the smaller Gini (p), the higher the purity and the better the feature.
Preferably, the pruning specifically comprises: the method is realized by minimizing the overall loss function of the decision tree shown in formula III, the complex tree model is retracted from bottom to top for non-leaf nodes, if the generalization performance can be improved by replacing subtrees corresponding to the nodes with leaf nodes, pruning is carried out, namely, father nodes are changed into new leaf nodes, so that the generated tree is simplified, and the over-fitting condition is avoided;
Where c (T) represents the degree of fit of the model to the training data and | T | represents the complexity of the model.
Preferably, the cross-validation specifically comprises: by an accuracy formula shown in a formula IV, randomly dividing an original data set into 5 parts, training a model by taking 4 parts as a training set each time, and verifying the model by taking the remaining 1 part as a verification set to obtain the accuracy of the verification set, performing the verification for 5 times in turn until all data are verified once and verified only once, circularly calculating the average value of the accuracy scores of each group of models, and taking the highest average value as an optimal model to evaluate the generalization capability of the models so as to select the models and parameters;
Wherein Accuracy represents the Accuracy, TP: number of correctly classified positive samples, TN: number of correctly classified negative samples, FP: number of negative examples misclassified, FN: number of samples of positive case that are misclassified.
Preferably, the 13 optimal characteristic genes are SMARCB1, TSC2, BAP1, SDHB, RIT1, ESR1, SOCS1, SH2B3, IDH2, MET, BRIP1, NTRK3 and FGFR 4.
Preferably, a sample of the TMB-H patient is subjected to targeted deep sequencing, gene variation is detected, the mutation conditions of 13 characteristic genes are brought into a prediction model to calculate the risk score of the TMB-H patient in the prognosis, and the patients are divided into a better prognosis group and a poorer prognosis group by taking a median as a distinguishing threshold.
Has the advantages that: compared with the prior art, the prognosis evaluation method for the immunotherapy of the patient with the non-small cell lung cancer provided by the invention comprises the steps of collecting a sample of the patient with the non-small cell lung cancer TMB-H, constructing a prediction model containing 13 optimal characteristic genes based on a CART algorithm, carrying out prognosis risk scoring on the patient with the non-small cell lung cancer TMB-H according to the prediction model, dividing the TMB-H population into a better prognosis group and a worse prognosis group, and achieving the accuracy rate of 0.85.
Drawings
FIG. 1 is a graph of a single-factor cox regression analysis of the prediction model of the present invention;
FIG. 2 is a schematic diagram showing the association between 13 gene mutations and overall survival;
FIG. 3 is a schematic diagram of DCR of different gene construction models for TMB-H population.
Detailed Description
In order to make the technical solutions of the present invention better understood, the present invention will be described in detail below with reference to the accompanying drawings and specific embodiments.
Example 1
Randomly selecting 155 patients in a TMB-H group, carrying out gene targeted sequencing on each patient sample, inputting a gene mutation list and a prognosis condition of each patient into a supervised learning decision tree model, and carrying out feature selection and pruning by using a Python (3.7.0) skear. Performing five-fold cross validation by using a cross _ val _ score function of a sklern model _ selection module, and calculating the accuracy of the model; carrying out model persistence by using a joblib module; the decision tree model was drawn using the grapeviz model, and the final decision tree model contained 13 optimal feature genes, including 9 negative predictive genes (SMARCB 1, TSC2, BAP1, SDHB, RIT1, ESR1, SOCS1, SH2B3, IDH 2) and 4 positive predictive genes (MET, BRIP1, NTRK3, FG)FR 4); constructing a prediction model (formula 1) containing 13 optimal characteristic genes according to the screened 13 optimal characteristic genes,
(formula 1), a one-way cox regression analysis was performed (see FIG. 1). The results show that there is a significant association of 13 gene mutations with overall survival (p)<0.05）；
The method comprises the steps of carrying out targeted deep sequencing on a sample of a TMB-H patient, detecting panel gene variation, substituting mutation conditions of 13 characteristic genes into a prediction model to calculate a risk score of the TMB-H patient after prognosis, taking a median as a distinguishing threshold, dividing the patient into a group with high risk and a group with low risk of prognosis (shown in figure 2), and displaying that the survival effect of the TMB-H group with low risk after receiving immunotherapy is obviously better than that of the TMB-H group with high risk and the TMB-L group.
Comparative example
The model is respectively constructed by 9 negative genes, 4 positive genes and 13 comprehensive genes to divide TMB-H population, and the benefit conditions (DCR) of the population after receiving immunotherapy are compared, as shown in figure 3, the results show that the prognosis of different risk populations divided by the negative 9 genes, the positive 4 genes and the comprehensive 13 genes has obvious difference, and the clinical benefit difference of the comprehensive 13 gene classified population is most obvious.
Finally, it should be noted that the above-mentioned description is only a preferred embodiment of the present invention, and those skilled in the art can make various similar representations without departing from the spirit and scope of the present invention.
Claims (4)
1. A method for the prognostic evaluation of immunotherapy for non-small cell lung cancer patients, characterized by comprising the steps of:
s1, carrying out gene targeted sequencing on the non-small cell lung cancer patient to obtain the gene variation condition;
s2, inputting the gene mutation list and the prognosis condition into a supervised learning decision tree model, establishing a classification model based on a CART algorithm, creating a decision tree model, and screening out 13 optimal characteristic genes;
s3, constructing a prediction model containing 13 optimal characteristic genes shown in formula I, and carrying out prognosis risk scoring on the non-small cell lung cancer TMB-H patient so as to predict the prognosis condition of the patient;
Wherein the content of the first and second substances,
to represent
Coefficient of single-factor cox regression of the perturbation characteristic and the survival time;
wherein, the S2 specifically is: the detected gene variation is used as a training characteristic, the total life cycle OS <12 months and the total life cycle OS >12 months are used as classification results of machine learning, a supervised learning decision tree model CART algorithm is used, and a decision tree model is created through four steps of characteristic selection, pruning, cross validation and model persistence; the feature selection specifically comprises: calculating the classification condition after branch selection is carried out through different characteristics by using the Gini coefficient shown in the formula II as a measurement standard, finding out the best classification characteristic as a root node, and repeating the steps until the tree building is finished, and creating a complex tree model;
Wherein K represents the category, p is the probability of the kth category, and the smaller Gini (p), the higher the purity and the better the characteristics;
the pruning specifically comprises the following steps: the method is realized by minimizing the overall loss function of the decision tree shown in formula III, the complex tree model is retracted from bottom to top for non-leaf nodes, if the generalization performance can be improved by replacing subtrees corresponding to the nodes with leaf nodes, pruning is carried out, namely, father nodes are changed into new leaf nodes, so that the generated tree is simplified, and the over-fitting condition is avoided;
Wherein c (T) represents the degree of fit of the model to the training data, | T | represents the complexity of the model;
the cross validation specifically comprises: by an accuracy formula shown in a formula IV, randomly dividing an original data set into 5 parts, training a model by taking 4 parts as a training set each time, and verifying the model by taking the remaining 1 part as a verification set to obtain the accuracy of the verification set, performing the verification for 5 times in turn until all data are verified once and verified only once, circularly calculating the average value of the accuracy scores of each group of models, and taking the highest average value as an optimal model to evaluate the generalization capability of the models so as to select the models and parameters;
Wherein Accuracy represents the Accuracy, TP: number of correctly classified positive samples, TN: number of correctly classified negative samples, FP: number of negative examples misclassified, FN: number of samples of positive case that are misclassified.
2. The method according to claim 1, wherein S1 is specifically defined as follows: collecting a sample of a patient with non-small cell lung cancer TMB-H to perform targeted deep sequencing and detecting the genetic variation condition.
3. The method of claim 1, wherein the method comprises the steps of: the 13 optimal characteristic genes are SMARCB1, TSC2, BAP1, SDHB, RIT1, ESR1, SOCS1, SH2B3, IDH2, MET, BRIP1, NTRK3 and FGFR 4.
4. The method of claim 1, wherein the method comprises the steps of: carrying out targeted deep sequencing on a sample of a TMB-H patient, detecting panel gene variation, substituting mutation conditions of 13 characteristic genes into a prediction model to calculate the risk score of the TMB-H patient after prognosis, and dividing the patient into a group with good prognosis and a group with poor prognosis by taking a median as a distinguishing threshold.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111433361.1A CN113851185B (en) | 2021-11-29 | 2021-11-29 | Prognosis evaluation method for immunotherapy of non-small cell lung cancer patient |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111433361.1A CN113851185B (en) | 2021-11-29 | 2021-11-29 | Prognosis evaluation method for immunotherapy of non-small cell lung cancer patient |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113851185A CN113851185A (en) | 2021-12-28 |
| CN113851185B true CN113851185B (en) | 2022-04-19 |
Family
ID=78982240
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111433361.1A Active CN113851185B (en) | 2021-11-29 | 2021-11-29 | Prognosis evaluation method for immunotherapy of non-small cell lung cancer patient |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113851185B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114999653B (en) * | 2022-06-17 | 2023-06-20 | 中国医学科学院肿瘤医院 | Training method and prediction device of prediction model of non-small cell lung cancer immunotherapy curative effect |
| CN115620894B (en) * | 2022-09-20 | 2023-05-02 | 贵州医科大学第二附属医院 | Lung cancer immune curative effect prediction system, device and storage medium based on gene mutation |
| CN115938579A (en) * | 2022-11-30 | 2023-04-07 | 常州国药医学检验实验室有限公司 | Characteristic combination and Cox proportion risk model for predicting survival rate of non-small cell lung cancer patients |
| CN116844685B (en) * | 2023-07-03 | 2024-04-12 | 广州默锐医药科技有限公司 | Immunotherapeutic effect evaluation method, device, electronic equipment and storage medium |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2014163445A1 (en) * | 2013-04-05 | 2014-10-09 | 연세대학교 산학협력단 | Method for manufacturing gastric cancer prognosis prediction model |
| WO2017074036A2 (en) * | 2015-10-26 | 2017-05-04 | 주식회사 싸이퍼롬 | Method and system for selecting customized drug using genomic nucleotide sequence variation information and survival information of cancer patient |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090062144A1 (en) * | 2007-04-03 | 2009-03-05 | Nancy Lan Guo | Gene signature for prognosis and diagnosis of lung cancer |
| EP2156187A4 (en) * | 2007-06-15 | 2010-07-21 | Biosite Inc | Methods and compositions for diagnosis and/or prognosis of ovarian cancer and lung cancer |
| US20110256545A1 (en) * | 2010-04-14 | 2011-10-20 | Nancy Lan Guo | mRNA expression-based prognostic gene signature for non-small cell lung cancer |
-
2021
- 2021-11-29 CN CN202111433361.1A patent/CN113851185B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2014163445A1 (en) * | 2013-04-05 | 2014-10-09 | 연세대학교 산학협력단 | Method for manufacturing gastric cancer prognosis prediction model |
| WO2017074036A2 (en) * | 2015-10-26 | 2017-05-04 | 주식회사 싸이퍼롬 | Method and system for selecting customized drug using genomic nucleotide sequence variation information and survival information of cancer patient |
Non-Patent Citations (3)
| Title |
|---|
| 556例非手术男性肺癌预后分析;杜佳等;《检验医学与临床》;20170414(第07期);全文 * |
| EGFR和KRAS突变对手术切除NSCLC患者预后预测价值分析;薛洋等;《中华肿瘤防治杂志》;20130928(第18期);全文 * |
| TCGA数据库基因突变信息结合机器学习软件RapidMiner构建肝细胞癌患者复发模型;祁亮等;《中国肝脏病杂志(电子版)》;20180920(第03期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113851185A (en) | 2021-12-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113851185B (en) | Prognosis evaluation method for immunotherapy of non-small cell lung cancer patient | |
| EP3201812B1 (en) | Predictive test for aggressiveness or indolence of prostate cancer from mass spectrometry of blood-based sample | |
| CN112735513B (en) | Construction method of tumor immune checkpoint inhibitor treatment effectiveness evaluation model based on DNA methylation spectrum | |
| CN116640847A (en) | Cancer evolution detection and diagnosis | |
| US20210102262A1 (en) | Systems and methods for diagnosing a disease condition using on-target and off-target sequencing data | |
| WO2022170909A1 (en) | Drug sensitivity prediction method, electronic device and computer-readable storage medium | |
| US20210358626A1 (en) | Systems and methods for cancer condition determination using autoencoders | |
| CN109658980A (en) | A kind of screening and application of excrement gene marker | |
| WO2023197825A1 (en) | Multi-cancer early screening model construction method and detection device | |
| CN110273003A (en) | A kind of Papillary Renal Cell Carcinoma patient prognosis recurrence detects the foundation of mark tool and its risk evaluation model | |
| CN111748633A (en) | Characteristic miRNA expression profile combination and head and neck squamous cell carcinoma early prediction method | |
| CN111763738A (en) | Characteristic mRNA expression profile combination and liver cancer early prediction method | |
| CN106415563A (en) | Systems and methods for predicting a smoking status of an individual | |
| CN111944902A (en) | Early prediction method of renal papillary cell carcinoma based on lincRNA expression profile combination characteristics | |
| CN111733251A (en) | Characteristic miRNA expression profile combination and early prediction method of renal clear cell carcinoma | |
| CN110373458A (en) | A kind of kit and analysis system of thalassemia detection | |
| US20230242992A1 (en) | Methods of predicting cancer progression | |
| CN111733252A (en) | Characteristic miRNA expression profile combination and early gastric cancer prediction method | |
| Madjar | Survival models with selection of genomic covariates in heterogeneous cancer studies | |
| CN111793692A (en) | Characteristic miRNA expression profile combination and lung squamous carcinoma early prediction method | |
| Wang et al. | Improved estimation of cell type-specific gene expression through deconvolution of bulk tissues with matrix completion | |
| EP4318493A1 (en) | Artificial-intelligence-based method for detecting tumor-derived mutation of cell-free dna, and method for early diagnosis of cancer, using same | |
| CN111944901A (en) | Characteristic mRNA expression profile combination and renal papillary cell carcinoma early prediction method | |
| Kariotis | Unsupervised machine learning of high dimensional data for patient stratification | |
| CN111876485A (en) | Characteristic mRNA expression profile combination and head and neck squamous cell carcinoma early prediction method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP03 | Change of name, title or address | ||
| CP03 | Change of name, title or address |
Address after: Room 135, Floor 1, Building 3, No. 96, Longchuanwu Road, Donghu Street, Linping District, Hangzhou City, Zhejiang Province, 310000 Patentee after: Qiuzhen Medical Technology (Zhejiang) Co.,Ltd. Address before: 100000 101 / F, building 3, No. 156 Jinghai 4th Road, Beijing Economic and Technological Development Zone, Daxing District, Beijing Patentee before: CHOSENMED TECHNOLOGY (BEIJING) Co.,Ltd. |