Construction and application of cancer prediction model

Abstract

The construction and application of a cancer prediction model. Specifically, a model for cancer prediction is developed, which involves cancer prediction regarding whether a tissue is cancerous; and a cancer prediction system based on the cancer prediction model is developed. The cancer prediction system provides an auxiliary diagnosis result for efficiently and accurately determining whether a tissue to be tested is cancerous.

Description

Construction and application of cancer prediction models Technical Field

[0001] This invention relates to the field of cancer detection, and more specifically, to the construction and application of cancer prediction models. Background Technology

[0002] The development of malignant tumors involves progressing from normal tissue to precancerous lesions, eventually transforming into malignant tumors. The precancerous stage of most malignant tumors is relatively long and may be reversible. Early diagnosis of precancerous lesions is clinically significant for disease intervention, preventing disease progression and improving patients' quality of life. With the continuous development and advancement of clinical diagnostic technologies, numerous diagnostic methods are now available, such as pathogen biological examination, cytological examination, endoscopy, biopsy pathology diagnosis, and gene testing; these technologies have significantly improved the early diagnosis rate of precancerous lesions.

[0003] However, these diagnostic methods still have a certain rate of missed diagnoses and misdiagnoses. Currently, pathological diagnosis is the gold standard for most precancerous lesions of tumors, but the number of cells in precancerous lesions is relatively small and dispersed, and the cell morphology may be similar to normal cells or cells in benign lesions. Therefore, it is quite difficult to detect and diagnose precancerous lesion cells in tissue specimens.

[0004] Therefore, there is an urgent need in this field to develop a new, more accurate, and efficient method or device for cancer auxiliary diagnosis. Summary of the Invention

[0005] This invention provides a novel method and device for auxiliary cancer diagnosis.

[0006] In a first aspect of the present invention, a method for constructing a cancer prediction model is provided, comprising the steps of:

[0007] (s1) Process the third-generation sequencing data and RNA sequencing (RNA-seq) data of cancer tissue samples, adjacent normal tissue samples, and normal tissue samples to obtain reference GTF files of full-length RNA transcripts and tumor-specific RNA transcripts (Tu-SRT).

[0008] (s2) Provide training, testing and validation set data for model construction, the data including expression information (or quantitative results) of full-length RNA transcripts obtained from RNA-seq data based on the reference GTF file after RNA sequencing; the expression information includes the expression information of the tumor-specific RNA transcripts;

[0009] The expression information of the tumor-specific RNA transcripts includes the expression information of tumor-specific RNA transcripts from cancer-positive samples and the expression information of tumor-specific RNA transcripts from cancer-negative samples.

[0010] (s3) The training set data is used to train machine learning models selected from the following group: Random Forest, Decision Tree, XGBoost, LightGBM, and CatBoost; thereby obtaining the hyperparameters of the machine learning models and the trained machine learning models; and

[0011] (s4) Using the test set and validation set data, the prediction results of the machine learning model are scored using the following scoring metrics: AUC value, accuracy, sensitivity and specificity; the machine learning model whose score meets the expected value is used as the cancer prediction model.

[0012] In another preferred embodiment, the expression information of the transcript is the TPM (Transcripts Per Million) value of the transcript expression.

[0013] In another preferred embodiment, the validation set data and the training set and test set data are derived from different queue samples.

[0014] In another preferred embodiment, the machine learning model is the LightGBM model.

[0015] In another preferred embodiment, the expression information of the transcript is represented by a TPM (Transcript per million) value.

[0016] In another preferred embodiment, in step (s3), the training set is used to train machine learning models selected from the following group: Random Forest model, Decision Tree model, XGBoost model, LightGBM model, and CatBoost model; thereby obtaining the hyperparameters of the five machine learning models respectively, and obtaining five trained machine learning models;

[0017] Furthermore, in step (s4), the prediction results of the five trained machine learning models are scored using the test set and validation set, employing the following scoring metrics: AUC value, accuracy, sensitivity, and specificity; the machine learning model with the highest score is selected as the cancer prediction model.

[0018] In another preferred embodiment, the cancer-positive sample is a cancer tissue sample.

[0019] In another preferred embodiment, the cancer sample includes a cancer tissue sample, a cancer cell sample, or a combination thereof.

[0020] In another preferred embodiment, the cancer samples include samples of n different cancers, where n is a positive integer ≥10.

[0021] In another preferred embodiment, n ≥ 15; more preferably, n is 20-100; even more preferably, n is 20-50.

[0022] In another preferred embodiment, the cancer is selected from the group consisting of: adrenocortical carcinoma, urothelial carcinoma of the bladder, invasive breast carcinoma, squamous cell carcinoma and adenocarcinoma of the cervix, cholangiocarcinoma, colon cancer, diffuse large B-cell lymphoma, esophageal cancer, multifocal glioma, head and neck squamous cell carcinoma, chromophobe renal carcinoma, clear cell renal carcinoma, papillary renal carcinoma, acute myeloid leukemia, low-grade glioma of the brain, hepatocellular carcinoma, lung adenocarcinoma, lung squamous cell carcinoma, mesothelioma, ovarian serous cystadenocarcinoma, pancreatic cancer, pheochromocytoma and paraganglioma, prostate cancer, rectal adenocarcinoma, sarcoma, melanoma of the skin, gastric cancer, testicular cancer, thyroid cancer, thymic cancer, endometrial cancer, uterine sarcoma, uveal melanoma, or combinations thereof.

[0023] In another preferred embodiment, the cancer-negative sample is an adjacent normal tissue sample and / or a normal tissue sample.

[0024] In another preferred embodiment, step (s1) includes: establishing a full-length transcript reference GTF file by processing third-generation sequencing data and filtering transcript annotations; the GTF file is used for quantifying RNAseq transcripts obtained from sample RNA sequencing; and

[0025] By comparing RNAseq transcript expression information from different tissue samples, the types of tumor-specific RNA transcripts were identified, and the expression information of each tumor-specific RNA transcript in each cancer sample was obtained.

[0026] In another preferred embodiment, the expression information of the transcript includes the expression information of the transcript itself.

[0027] In another preferred embodiment, step (s1) includes the following steps:

[0028] (a) Collect third-generation sequencing data and RNA-seq data of cancer tissue and adjacent normal tissue samples from different tumor sources, as well as normal tissue samples, and generate non-redundant transcriptome GTF files.

[0029] (b) Optimize non-redundant transcriptome GTF files, wherein for a certain cancer / tissue RNA-seq, if all splicing sites of a transcript are detected in ≥m samples, the transcript is retained, where m is 1-90%, preferably 2-50%;

[0030] (c) Each transcript was compared with the reference transcriptome (GENCODE v.35). The transcripts were mainly divided into four groups: fully spliced, partially spliced, novel within the catalog, and novel outside the catalog. After filtering, a reference GTF file for full-length RNA transcripts was established.

[0031] Specifically, for all incompletely spliced ​​matching transcripts, these transcripts are filtered out from the entire transcriptome;

[0032] Unqualified novel transcripts, both in-directory and out-of-directory, are filtered out (e.g., those with Cage peaks and polyA sites annotated with SQANTI3 are filtered out if there are 16 or more adenines within 20 bases downstream of the annotated transcription termination site).

[0033] For similar transcripts, the longest transcript is retained, and other transcripts are filtered out;

[0034] (d) Based on the reference GTF file for full-length RNA transcripts, full-length transcripts are quantified from the RNA-seq data of tissue samples to obtain the expression information of full-length RNA transcripts in tissue samples.

[0035] (e) By comparison, RNA transcripts that show significant differences in expression information between cancer tissue samples, adjacent normal tissue samples, and normal tissue samples are obtained, thereby obtaining the tumor-specific RNA transcripts.

[0036] In another preferred embodiment, the significant difference is that it is expressed in tumor tissue but not expressed or expressed at very low levels in adjacent or normal tissue.

[0037] In another preferred embodiment, step (d) includes:

[0038] The Salmon software was used to align the short reads of RNA-seq obtained from RNA-seq sequencing to the transcript library corresponding to the GTF file, and the expression level of transcripts in each sample was measured in the form of TPM (Transcript per million) to obtain the transcript expression information of the sample.

[0039] In another preferred embodiment, the types of tumor-specific RNA transcripts are obtained through the following steps:

[0040] (a) Obtain sequencing data (including sequencing of third-generation sequencing, second-generation sequencing or a combination thereof) from biopsy tissue samples in the population to be tested;

[0041] (b) By processing third-generation sequencing data and filtering transcript annotations, a full-length transcript reference GTF file is established; the GTF file is used to quantify RNAseq transcripts obtained from second-generation sequencing of tissue samples.

[0042] (c) The RNA-seq short read sequences are aligned to the transcript library obtained by long read sequencing, and the expression level of each transcript in each sample is measured in the form of TPM (Transcript per million) to generate transcript expression information of the test tissue; the transcript expression information includes the expression information of tumor-specific RNA transcripts of the test tissue.

[0043] In a second aspect of the invention, a reference GTF file for a full-length RNA transcript is provided, obtained by comprising the following steps:

[0044] (i) Collect third-generation sequencing data and RNA-seq sequencing data of cancer tissue and adjacent normal tissue samples from different tumor sources, and generate non-redundant transcriptome GTF files.

[0045] (ii) Optimize non-redundant transcriptome GTF files, wherein, for a certain cancer / tissue RNA-seq, if all splicing sites of a transcript are detected in ≥m samples, the transcript is retained, where m is 1-90%, preferably 2-50%;

[0046] (iii) Each transcript was compared with the reference transcriptome (GENCODE v.35). The transcripts were mainly divided into four groups: fully spliced, partially spliced, novel in-directory, and novel out-of-directory. After filtering, a reference GTF file for full-length RNA transcripts was established.

[0047] Specifically, for all incompletely spliced ​​matching transcripts, these transcripts are filtered out from the entire transcriptome;

[0048] Unqualified novel transcripts, both in-directory and out-of-directory, are filtered out (e.g., those with Cage peaks and polyA sites annotated with SQANTI3 are filtered out if there are 16 or more adenines within 20 bases downstream of the annotated transcription termination site).

[0049] For similar transcripts, the longest transcript is retained, and other transcripts are filtered out.

[0050] In another preferred embodiment, the full splice matching, incomplete splice matching, in-catalog novel, and out-of-catalog novel are respectively: a transcript that is completely identical to a known isoform in the reference transcriptome database compared to the reference transcriptome; a transcript that is completely contained by a known transcript but has fewer exons than the known transcript, and whose intron sequences completely correspond to the known transcript; a transcript that shows a known splice site but presents a new splice pattern or exon combination; and a transcript that has at least one splice site that is not annotated in existing databases.

[0051] In a third aspect of the invention, a method for determining the expression information of full-length RNA transcripts is provided, comprising the steps of:

[0052] (i) Based on the reference GTF file for full-length RNA transcripts described in the second aspect of the present invention, full-length transcript quantification is performed on RNA-seq data of tissue samples to obtain full-length RNA transcript expression information.

[0053] In another preferred embodiment, the full-length RNA transcript expression information includes the expression information of the full-length RNA transcript expression profile.

[0054] In a fourth aspect of the invention, a cancer prediction system is provided, the system comprising:

[0055] (a) An input module configured to input full-length RNA transcript expression information of the sample to be tested;

[0056] (b) Evaluation module (or prediction module): The evaluation module is configured to input the expression information of the full-length RNA transcript into a cancer prediction model constructed using the method described in the first aspect of the present invention, thereby obtaining a cancer prediction result for the sample to be tested; and

[0057] (c) Output module, which is configured to output the prediction result.

[0058] In another preferred embodiment, the system further includes (a0) a preprocessing module configured to analyze and determine the full-length RNA transcript expression information of the test sample using the method described in the third aspect of the present invention, based on the RNA-seq sequencing information of the test sample.

[0059] In another preferred embodiment, the system further includes (d) a control module configured to control the operation of the modules.

[0060] In another preferred embodiment, the system further includes (e) a storage module configured to store data including: model hyperparameters, prediction probabilities, and preset reference thresholds.

[0061] In another preferred embodiment, the judgment in the prediction module includes:

[0062] The expression information of the full-length RNA transcript is input into the cancer prediction model to obtain the prediction result, which includes the prediction probability. When the prediction probability in the prediction result is greater than or equal to the preset reference threshold for cancer prediction, it is judged as positive, that is, the sample to be tested is a cancer sample; otherwise, it is judged as negative, that is, the sample to be tested is a non-cancer sample.

[0063] In a fifth aspect of the invention, a computer storage medium is provided for storing a computer program corresponding to the algorithm of the cancer prediction model constructed by the method described in the first aspect of the invention.

[0064] In a sixth aspect of the present invention, a method for auxiliary diagnosis of cancer is provided, comprising the steps of:

[0065] (a) Provide data: Provide RNA sequencing information for the sample to be tested;

[0066] (b) Data preprocessing: For the sequencing information, analyze and determine the expression information of full-length RNA transcripts of the sample to be tested, or use the method described in the third aspect of the present invention to analyze and determine the expression information of full-length RNA transcripts of the sample to be tested;

[0067] (c) Analysis and Evaluation: The expression information of the full-length RNA transcripts is input into the cancer prediction model constructed using the method described in the first aspect of this invention to obtain the evaluation results of the sample to be tested; and

[0068] (d) Output results: Output the evaluation results.

[0069] In another preferred embodiment, the sample to be tested is selected from the group consisting of cell samples, tissue samples, or combinations thereof.

[0070] In another preferred embodiment, the method is an in vitro method.

[0071] In another preferred embodiment, the method is non-diagnostic and non-therapeutic.

[0072] It should be understood that, within the scope of this invention, the above-described technical features of this invention and the technical features specifically described below (such as in the embodiments) can be combined with each other to form new or preferred technical solutions. Due to space limitations, they will not be described in detail here. Attached Figure Description

[0073] Figure 1 shows a schematic diagram of the cancer prediction model in Example 2; in the figure, "Feat" refers to a feature.

[0074] Figure 2 shows the ROC curves of the cancer prediction model generated from the LightGBM model on the training, test, and validation sets.

[0075] Figure 3 shows a schematic diagram of a prediction module of an example of the present invention.

[0076] Figure 4 shows a schematic diagram of a process for cancer prediction in a population to be tested according to an example of the present invention. Detailed Implementation

[0077] Through extensive and in-depth research, the inventors, based on third-generation sequencing and second-generation sequencing (including RNA-seq) results from tumor tissue, adjacent normal tissue, and / or normal tissue samples, quantified RNA transcripts to determine the expression information of full-length RNA transcripts in tissue samples, and based on this, discovered tumor-specific RNA transcripts. A model for cancer prediction was developed based on these tumor-specific RNA transcripts, and a system (or device) for cancer prediction was developed based on this model. The cancer prediction model or system of this invention has high predictive accuracy and can be used for early clinical auxiliary diagnosis. Based on this, the present invention was completed.

[0078] the term

[0079] To facilitate a clearer understanding of this disclosure, certain terms are first defined. As used herein, unless otherwise expressly specified herein, each of the following terms shall have the meaning given below. Other definitions are set forth throughout the application.

[0080] The term “about” can refer to a value or composition within an acceptable margin of error for a particular value or composition as determined by a person skilled in the art, depending in part on how the value or composition is measured or determined. For example, as used herein, the expression “about 100” includes all values ​​between 99 and 101 (e.g., 99.1, 99.2, 99.3, 99.4, etc.).

[0081] As used herein, the terms “containing” or “including (comprise)” can be open-ended, semi-closed, or closed. In other words, the terms also include “consistently made of” or “composed of”.

[0082] As used herein, unless otherwise stated, any concentration range, percentage range, proportion range, or integer range shall be understood to include any integer value within the range and, where appropriate, its fractional value (e.g., one-tenth and one-hundredth of an integer).

[0083] As used herein, the term “and / or” refers to and covers any and all possible combinations of one or more of the related listed items.

[0084] As used in this article, “transcription expression information,” “transcription quantification results,” “transcription expression level,” and “transcription expression value” have the same meaning and can be used interchangeably. They all refer to the expression level of each transcript in the sample, measured in TPM (Transcript per million), by aligning the RNA-seq short read sequence of the tissue sample to the transcript library corresponding to the GTF file constructed in this invention.

[0085] As used in this article, "full-length RNA transcript" and "full-length transcript" have the same meaning and can be used interchangeably. Both refer to the complete RNA molecule produced from a gene, including all parts of the coding and non-coding regions. It contains a series of information such as the 5' untranslated region (5'UTR), exons, introns (which are cut out in mature mRNA but retained in the full-length transcript), and the 3' untranslated region (3'UTR).

[0086] Tumor-specific RNA transcripts

[0087] Tumor-specific RNA transcripts (Tumor-SRTs or Tu-SRTs) are defined as those found only in tumor samples and not in normal samples (or present in very low amounts in normal samples). The SRTs for different types of tumors identified by RNA-seq are determined based on the following criteria:

[0088] i) Transcripts with a TPM>0.5 in more than 5% of samples in a certain type of tumor are considered to be expressed in that tumor type, and the median value of the samples with TPM>0.5 is used as their expression level;

[0089] ii) The expression level of transcripts in normal tissues is divided into two cases: if at least 3 transcripts with TPM > 0.5 are observed in all normal tissues (except testes) in the GTEx dataset and in adjacent normal tissues in the TCGA dataset, the maximum value is used to represent the expression level. If fewer than 3 transcripts with TPM > 0.5 are observed, the median value is used to represent the expression level.

[0090] iii) The expression level of the transcript in the tumor was at least 10 times that of the maximum expression level observed in all normal tissues (except the testes) and adjacent normal tissues.

[0091] Based on the above calculation method, this invention identified 44,673 tumor tissue-specific RNA transcripts. These specific RNA transcripts are highly expressed only in tumors, and are not expressed or are expressed at very low levels in normal tissues and adjacent normal tissues (the above list of 44,673 tumor tissue-specific RNA transcripts was calculated by the inventors and is unique to this invention).

[0092] The present invention provides a method for quantifying full-length RNA transcripts in tissue samples.

[0093] The method for quantifying full-length RNA transcripts in tissue samples according to the present invention includes the following steps:

[0094] (St1): 177 tumor tissue specimens from patients with hepatocellular carcinoma, colorectal cancer, ovarian cancer, breast cancer, nasopharyngeal carcinoma, neuroendocrine tumors, gastric cancer, gastrointestinal stromal tumors, renal cancer, and cervical cancer were collected. RNA was extracted from the collected tissues and PacBio Iso-seq third-generation sequencing was performed. The raw PacBio sequencing data were processed using the Iso-Seq workflow.

[0095] (St2): Collected third-generation PacBio and ONT transcriptome sequencing data from 21 cancer tissue samples (including esophageal cancer, lung cancer, glioblastoma, leukemia, lymphoma, melanoma, myeloma, and sarcoma) and 153 normal tissue samples (including adipose tissue, adrenal gland, brain, breast, heart, liver, lung, muscle, ovary, pancreas, testis, fibroblasts, GM12878, H1, H9, HEK293T, and WTC11 cells) from public databases.

[0096] (St3): FASTQ sequences from PacBio and ONT data were aligned using minimap2 and processed using a standard pipeline to obtain merged GTF transcriptomes. Full-length transcripts from all samples were merged into non-redundant transcriptome GTF files using gffcompare software.

[0097] (St4): If all splicing sites of a transcript are detected in at least 5 samples in TCGA and GTEx for a certain cancer / tissue RNA-seq in the merged GTF file, then the transcript is retained.

[0098] (St5): Using SQANTI3 and gffcompare software, these transcripts were compared with the reference transcriptome (GENCODE v.35). The transcripts were mainly divided into four groups: fully spliced ​​matched, partially spliced ​​matched, novel within the catalog, and novel outside the catalog. All partially spliced ​​matched transcripts, which may be the result of RNA degradation and incomplete reverse transcription, were filtered out from the entire transcriptome.

[0099] (St6): Cage peaks and polyA sites were annotated using SQANTI3. For novel transcripts both in-directory and out-of-directory, transcripts with 16 or more adenines within 20 bases downstream of the annotated transcription termination site were filtered.

[0100] (St7): The full-length transcript sequence was obtained using the gffread software based on the transcript location provided by the GTF. ORFs in the transcripts from the third-generation sequencing data were predicted using GeneMark. When the stop codon was located more than 50 nucleotides upstream of the last exon-exon splicing site, the predicted transcript would induce meaningless mediated decay.

[0101] (St8): Transposon elements from the entire human hg38 genome were downloaded from the UCSC Genome Browser, and BEDTools software was used to determine whether transcripts overlapped with TEs within a TSS ± ​​100 bp. Similar transcripts were merged according to the following criteria: i) A maximum of three exon differences were allowed. ii) Differences per exon did not exceed four bases. iii) The maximum allowed dissimilarity for transcription start and termination sites was 100. iv) For coding transcripts, it was ensured that there were no differences in ORFs between transcripts.

[0102] (St9): For similar transcripts, the longest one is retained and other transcripts are filtered out. A reference GTF file containing 1,069,895 full-length RNA transcripts is created for full-length transcript quantification of RNAseq data from tissue samples.

[0103] (St10): During data processing, Salmon software can be used to create an index for the GTF file containing 1,069,895 full-length RNA transcripts obtained above.

[0104] (St11): By aligning short reads of RNA-seq to the transcript library and measuring the expression level of transcripts in each sample in the form of TPM (Transcript per million), a quantitative method for quantifying the expression profile of full-length RNA transcripts in samples using RNA-seq data was developed.

[0105] Cancer prediction models based on machine learning

[0106] This invention's machine learning-based cancer prediction model relies on the common biological characteristics (tumor-specific RNA transcripts, Tumor-SRTs) of cancer cells in different tissues. Machine learning is used to set positive and negative thresholds to construct the prediction model. By comparing the expression results of specific transcripts in cancerous tissues with adjacent and normal tissues, the training and validation models are continuously optimized and improved for diagnosing whether a patient has cancer. The cancer prediction system device uses the cancer prediction model to predict whether a patient has cancer based on the tumor-specific transcript (SRT) data expressed in the patient's tissues.

[0107] Machine learning, a branch of artificial intelligence, uses statistical and computer science methods to enable computer systems to learn from data and automatically improve. It analyzes and identifies patterns and regularities in data to make predictions and decisions. In the field of oncology, it can analyze patient data such as clinical symptoms, medical imaging, laboratory tests, and histopathology to discover new patterns and correlations between variables and generate predictive models. By applying machine learning techniques, the field of oncology diagnosis can extract valuable information from large amounts of complex data, helping doctors provide more accurate and faster diagnostic results and improving treatment outcomes and survival rates for cancer patients.

[0108] Machine learning models were used to construct the final model of this invention during the model building process. These machine learning models include: Random Forest model, Decision Tree model, XGBoost model, LightGBM model, and CatBoost model.

[0109] Cancer auxiliary diagnosis of the present invention

[0110] This invention provides several applications of the cancer-assisted diagnostic model, including the development of cancer-assisted diagnostic software, devices, or systems. Figure 4 shows a schematic flowchart of cancer prediction for a population to be tested based on the cancer-assisted diagnostic model of this invention.

[0111] As shown in Figure 4, the first step is to obtain the full-length transcript expression information of the target population. This involves: obtaining biopsy tissue samples from the target population; establishing a full-length transcript reference GTF file through third-generation sequencing data processing and transcript annotation filtering; using this file to quantify RNA-seq transcripts from the tissue samples; aligning short-read RNA-seq sequences to a transcript library already obtained through long-read sequencing; and measuring the expression level of transcripts in each sample using TPM (Transcript per million) to generate the full-length RNA transcript expression information of the target tissue. This transcript expression information includes tumor-specific RNA transcripts from the target tissue.

[0112] The expression information of the full-length RNA transcript is input into a pre-trained cancer prediction model. The cancer prediction model outputs a prediction value indicating that the tested tissue is cancerous. If the prediction value is greater than a preset prediction threshold, the tested tissue is determined to be positive, including or containing cancerous tissue; if it is less than the preset prediction threshold, the tested tissue is determined to be negative. The preset prediction threshold can be set to 50%, and this invention does not limit the specific value of the preset prediction threshold.

[0113] In another preferred embodiment, the cancer-aided diagnostic device, software, or system of the present invention includes modules selected from the group consisting of: an input module, a preprocessing module, a prediction module (or an evaluation module), and an output module.

[0114] In another preferred embodiment, the cancer-aided diagnostic system of the present invention makes predictions based on specific RNA transcript (SRT) data expressed in the patient's tissue to be tested, and is used to diagnose whether the patient has cancer, with objective predictive indicators.

[0115] The technical solution of this invention is based on a pre-trained cancer-aided diagnostic model that predicts the probability of a sample tissue being cancerous based on its genetic information, including Tu-SRT (tumor-specific transcripts). All these feature variables are obtained by analyzing tumor and normal tissue samples using long-read and short-read RNA sequencing technologies, integrating third-generation RNA sequencing data from various normal and cancerous human tissues and cells, and analyzing tumor-specific RNA transcripts from a large amount of case data. Five models—Random Forest, Decision Tree, XGBoost, LightGBM, and CatBoost—are used to obtain hyperparameters for each feature using grid search. The roc_auc of the five models under their hyperparameters is compared, and the model with the highest roc_auc and its hyperparameters are selected to obtain five trained tumor prediction models, with the optimal model among the five being identified. This provides the probability of a sample being diagnosed as cancer, serving as a highly objective outcome indicator.

[0116] Furthermore, the system is independent of pathologists, requires less human intervention, and can provide standardization and consistency, offering pathologists highly stable tumor auxiliary diagnosis. This reduces the burden on physicians and improves work efficiency, demonstrating high clinical translational value and market potential.

[0117] It should be noted that, in the apparatus or device of this application, the storage medium (computer-readable medium) used to store the model or algorithm of the present invention can be a computer-readable signal medium or a non-transitory computer-readable storage medium, or any combination thereof. A non-transitory computer-readable storage medium can be, for example,, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a non-transitory computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof.

[0118] In this application, a non-transitory computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in connection with an instruction execution system, apparatus, or device. In this application, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can also be any computer-readable medium other than a non-transitory computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination thereof.

[0119] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device.

[0120] The main advantages of this invention include:

[0121] (a) This prediction system can help doctors provide more accurate and faster cancer diagnosis results, improve diagnostic efficiency, and has good clinical application value and market prospects.

[0122] The present invention will be further illustrated below with reference to specific embodiments. It should be understood that these embodiments are for illustrative purposes only and are not intended to limit the scope of the invention. Experimental methods in the following embodiments, unless otherwise specified, are generally performed under conventional conditions, such as those described in Sambrook et al., Molecular Cloning: A Laboratory Manual (New York: Cold Spring Harbor Laboratory Press, 1989), or as recommended by the manufacturer. Unless otherwise stated, percentages and parts are weight percentages and parts by weight.

[0123] Example 1: Construction of GTF files and screening of tumor-specific RNA transcripts

[0124] 1.1 Data Acquisition

[0125] We collected 177 tumor tissue specimens from patients with hepatocellular carcinoma, colorectal cancer, ovarian cancer, breast cancer, nasopharyngeal carcinoma, neuroendocrine tumors, gastric cancer, gastrointestinal stromal tumors, renal cancer, and cervical cancer. After extracting RNA from the collected tissues, we performed PacBio Iso-seq third-generation sequencing and second-generation sequencing (including RNA-seq) (this part of the data was generated by the inventors through sequencing). The raw PacBio sequencing data was processed using the Iso-Seq workflow.

[0126] We collected third-generation PacBio and ONT transcriptome sequencing data and second-generation sequencing data (including RNA-seq) from 21 cancer tissue samples (including esophageal cancer, lung cancer, glioblastoma, leukemia, lymphoma, melanoma, myeloma, and sarcoma) and 153 normal tissue samples (including adipose tissue, adrenal gland, brain, breast, heart, liver, lung, muscle, ovary, pancreas, testis, fibroblasts, GM12878, H1, H9, HEK293T, and WTC11 cells) from public databases.

[0127] 1.2 Building GTF Files

[0128] FASTQ sequences from PacBio and ONT data were aligned using minimap2 and then processed using a standard pipeline to obtain merged GTF transcriptomes. Full-length transcripts from all samples were merged into non-redundant transcriptome GTF files using gffcompare software.

[0129] Non-redundant transcriptome GTF files were optimized using various methods to obtain optimized merged GTF files. In this optimized merged GTF file, if at least five samples in TCGA and GTEx for a certain cancer / tissue RNA-seq dataset showed all splicing sites of the transcript, then that transcript was retained.

[0130] These transcripts were compared with the reference transcriptome (GENCODE v.35) using SQANTI3 and gffcompare software. The transcripts were mainly divided into four groups: fully spliced, partially spliced, novel in the catalog, and novel out of the catalog.

[0131] Fully spliced-matched transcripts are those that are completely identical to known isoforms in the database. Partially spliced-matched transcripts are those that are completely contained within known transcripts but have fewer exons than known transcripts, and whose intron sequences completely correspond to known transcripts. Novel transcripts within the catalog show known splicing sites but exhibit new splicing patterns or exon combinations. Novel transcripts outside the catalog refer to transcripts with at least one splicing site that is not annotated in existing databases.

[0132] All incomplete splice-matched transcripts, which may be the result of RNA degradation and incomplete reverse transcription, should be filtered out from the entire transcriptome.

[0133] Cage peaks and polyA sites were annotated using SQANTI3. For novel transcripts both in-directory and out-of-directory, transcripts with 16 or more adenines within 20 bases downstream of the annotated transcription termination site were filtered.

[0134] The full-length sequences of transcripts were obtained using the gffread software based on the transcript locations provided by GTF. GeneMark was used to predict ORFs in the transcripts from the third-generation sequencing data. Transcripts predicted to induce meaningless mediated decay when the stop codon was located more than 50 nucleotides upstream of the last exon-exon splicing site were filtered out from the entire transcriptome.

[0135] Transposon elements from the entire human hg38 genome were downloaded from the UCSC Genome Browser, and BEDTools software was used to determine whether transcripts overlapped with TEs within a TSS ± ​​100 bp. Similar transcripts were merged according to the following criteria: i) a maximum of three exon differences were allowed. ii) differences per exon did not exceed four bases. iii) the maximum allowed dissimilarity for transcription start and termination sites was 100. iv) for coding transcripts, it was ensured that there were no differences in ORFs between transcripts.

[0136] For similar transcripts, the longest one is retained and other transcripts are filtered out, thus creating a reference GTF file containing 1,069,895 full-length RNA transcripts (containing 1,069,895 transcripts), which is used for full-length transcript quantification of tissue sample RNAseq data (this newly generated GTF file is unique to the inventor based on his own sequencing data and analysis of public data).

[0137] During data processing, Salmon software can be used to create an index on the GTF file containing 1,069,895 full-length RNA transcripts obtained above (creating an index based on the newly generated GTF file is unique to this invention), thereby establishing a transcript library.

[0138] The RNA-seq short read sequences of the above samples (data sources include public databases and second-generation sequencing data obtained from the above self-test) were aligned to the transcript library, and the expression levels of 1,069,895 transcripts in each sample were measured in the form of TPM (Transcript per million). A quantitative method for quantifying the expression profile of full-length RNA transcripts in samples using RNA-seq data was developed.

[0139] 1.3 Obtaining tumor-specific RNA transcripts

[0140] Transcript quantification was performed on RNA-seq data from 33 TCGA tumors and 28 normal tissues in a public database. The inventors developed the FLIBase database based on full-length RNA transcripts, creating a comprehensive resource library of full-length transcript information for both human cancer and normal tissues. This database covers multiple cancer types and different normal tissue types, identifies a large number of unannotated tumor-specific RNA transcripts, and provides a panoramic view of tissue-specific RNA transcripts in different normal tissues.

[0141] The FLIBase of this invention has significant advantages in discovering a large number of previously unannotated isoforms and tumor-specific RNA transcripts. Using this database to conduct in-depth mining and research on the cancer transcriptome at the transcript level can help obtain new insights into the precision diagnosis and treatment of cancer.

[0142] The tumor-specific RNA transcripts (Tumor-SRTs) described in this invention are RNA transcripts that show significant differences in transcript quantification (including the TPM value of transcripts) between cancer tissues, adjacent normal tissues, and normal tissues; that is, transcripts expressed in cancer tissues but not expressed or expressed at very low levels in adjacent normal tissues and normal tissues. A total of 44,673 tumor-specific RNA transcripts were obtained in this invention.

[0143] Example 2: Construction of a Cancer Prediction Model

[0144] 2.1 Training and Test Set Sample Data

[0145] Sample data sources: The sample data includes RNAseq data (negative) of 33 types of cancer tissues (positive) and adjacent normal tissues (negative) from the TCGA dataset in the public database, and normal tissues from the GTEx and GEO public databases, as shown in Tables 1 and 2.

[0146] Table 1. Number of cancer tissue and adjacent normal tissue samples for 33 types of cancer in the TCGA dataset from the public database.

[0147] Table 2. Number of samples of each normal tissue type in the public databases GTX and GEO datasets.

[0148] 2.2 Model Construction

[0149] The sample data in section 2.1 is divided into a training set and a test set in a 3:1 ratio, with the test set and training set data being independent of each other.

[0150] The expression information or quantitative results (represented by TPM) of 44,673 tumor-specific RNA transcripts from each sample in the training set were input into the machine learning model for training to obtain a cancer prediction model.

[0151] Hyperparameter determination: Hyperparameters of the machine learning model were determined using a grid search based on the expression information of tumor-specific RNA transcripts. During the grid search, each parameter combination underwent cross-validation, such as 5-fold cross-validation, with ROC AUC as the scoring function.

[0152] The machine learning models used for training include: Random Forest, Decision Tree, XGBoost, LightGBM, and CatBoost. Finally, five cancer prediction models were obtained after training on these five machine learning models (corresponding to Random Forest, Decision Tree, XGBoost, LightGBM, and CatBoost models, respectively).

[0153] In this training set, cancer tissue samples from the TCGA dataset are used as positive samples, while adjacent normal tissue samples and all normal tissue samples from GTEx are used as negative samples (i.e., adjacent normal tissue samples and all normal tissue samples from GTEx are considered as normal tissue samples).

[0154] Figure 1 shows a schematic diagram of the cancer prediction model in this embodiment. The cancer prediction model can predict whether a tumor is cancerous or not. It obtains features from tumor-specific RNA transcripts based on a set of cancer feature names and inputs them into a cancer classifier. The cancer classifier is pre-constructed with information such as the classifier name and classifier parameters, including pre-determined hyperparameters. The cancer classifier determines whether a tumor is cancerous or not. If the predicted value output by the cancer classifier is greater than a cancer prediction threshold, it is judged as cancer; if it is less than the cancer prediction threshold, it is judged as non-cancer.

[0155] 2.3 Model Validation

[0156] The machine learning models for the five cancer prediction methods obtained above were validated on the test and validation sets and evaluated based on four metrics: AUC, accuracy, sensitivity, and specificity. The model with the highest score was selected as the cancer prediction model.

[0157] Specifically, the cancer prediction model was evaluated using test set (see description in 2.2) and validation set data, respectively.

[0158] The validation set consists of RNA-seq sequencing data of cancer tissues and adjacent normal tissues of 33 types of cancer obtained from the public databases GEO and dbGAP independent datasets, and full-length RNA transcript expression information determined according to the GTF file obtained in Example 1, as shown in Table 3.

[0159] Table 3. Sample data of cancer tissue and adjacent normal tissue for 33 types of cancer from the public databases GEO and dbGAP.

[0160] In this validation dataset, all cancer tissue samples from the GEO and dbGAP datasets are considered positive samples, and all adjacent normal tissue samples are considered negative samples.

[0161] The cancer prediction model was scored on both the test and validation sets, and the final cancer prediction model was determined to be the one trained on the LightGBM model (Table 4). The test results or scores of the cancer prediction model (or tumor diagnosis model) trained on the LightGBM model are shown in Table 5 and Figure 2.

[0162] Table 4 Selection of Cancer Prediction Models

[0163] Table 5 shows the accuracy of the cancer prediction model trained using LightGBM.

[0164] The results show that the accuracy on the test set is 0.9897, sensitivity is 0.9978, specificity is 0.9665, and AUC is 0.9995. Using the validation set, the AUC is 0.8703, the accuracy is 0.8420, and when the threshold is 0.99, the sensitivity is 0.887 and the specificity is 0.603, further demonstrating the effectiveness of the model.

[0165] After establishing the cancer prediction model, it is possible to predict whether the subject has cancer based on the full-length RNA transcript expression information (including tumor SRT) and the cancer prediction model.

[0166] Example 3: Cancer-Assisted Diagnostic Devices and Systems

[0167] Based on the cancer auxiliary diagnosis model constructed in this invention, a cancer auxiliary diagnosis system and software have been developed.

[0168] In addition to the input and output modules, the aforementioned cancer auxiliary diagnostic system also includes a preprocessing module and a prediction module.

[0169] The preprocessing module is configured to quantify the expression values ​​of full-length RNA transcripts in the test samples.

[0170] Figure 3 shows a schematic diagram of a prediction module of an example of the present invention. This module extracts features from the sample to be predicted based on feature data reading and inputs them into a cancer prediction model. The parameters of the prediction model are pre-set in the model or system. The prediction model predicts the probability of whether the input sample is cancer and its threshold.

[0171] The prediction module is configured to perform the following operations: in response to the received full-length RNA transcript expression information of the tissue to be tested, input it into a pre-trained cancer prediction model to obtain the prediction result.

[0172] Taking cancer as an example, after inputting the expression information of the full-length RNA transcript of the tissue to be tested into the cancer prediction model, candidate prediction results are obtained, including prediction probability and preset reference threshold. When the prediction probability in the prediction results is greater than or equal to the preset probability threshold, it is judged as positive and used to characterize the target sample as cancer.

[0173] Figure 3 shows a schematic diagram of a cancer prediction system according to an example of the present invention predicting whether a disease is cancer.

[0174] When performing cancer prediction, the program generates a cancer test set, reads the optimal cancer classifier and its hyperparameters from the configuration file, and makes predictions, outputting the probability that the sample is cancer-positive, denoted as Cancer_prob. Simultaneously, this module uses the trained classifier to predict on the training set and calculates the threshold, denoted as threshold, that maximizes the f1_score of the prediction results for the training set. Cases where Cancer_prob ≥ threshold are considered positive, and those where it is below are considered negative.

[0175] The following is relevant information about the development system or equipment:

[0176] System Name: Machine Learning-Based Specific RNA Transcript Tumor Diagnostic System

[0177] Hardware environment for development

[0178] CPU AMD Ryzen 7 6800U with Radeon Graphics

[0179] 64GB RAM (2100MHz)

[0180] The operating system used to develop this software

[0181] Distributor ID: Ubuntu

[0182] Description: Ubuntu 22.04.3LTS

[0183] Release: 22.04

[0184] Codename: jammy

[0185] Software development environment / tools: Vim 8.2

[0186] Programming language: Python 3.

[0187] The output module of the system, software, or device of the present invention is used to output the probability that the sample to be tested is cancer based on the prediction result of the cancer prediction module.

[0188] discuss

[0189] Tumor pathology diagnosis is currently one of the gold standards for diagnosing many types of tumors, boasting high accuracy. Through tumor pathology diagnosis, the nature and origin of the tumor can be clearly identified, and its stage and type can be determined, along with its degree of differentiation. By observing and analyzing the histological characteristics, grade, and stage of the tumor, patient survival rates and recurrence risks can be predicted, providing important references for treatment decisions and patient management, thereby guiding individualized treatment strategies. However, tumor pathology diagnosis involves a degree of subjectivity, requiring a high level of professional knowledge and experience from physicians. Different pathologists may interpret and judge the same tissue specimen differently. This can lead to inconsistencies in diagnosis between different hospitals and specialists, affecting the comparability of treatment decisions and outcomes. Therefore, those skilled in the art recognize the need to obtain more tissue-specific biomarkers or biological characteristics at the molecular biological level to improve diagnostic accuracy.

[0190] In the human genome, over 95% of genes have more than one transcript, and the same gene often expresses different transcripts in different tissues or disease states. These different transcripts differ in structure and function. This transcript diversity is particularly evident in different tissues, cell types, and disease states, especially in human cancer research, where transcript expression patterns exhibit significant tissue and pathological state preferences. Specific RNA transcripts (SRTs) are transcripts of genes specifically expressed in a particular tissue or disease. Tumor-specific RNA transcripts not only promote cancer development and progression, becoming highly promising therapeutic targets, but are also considered a source of immunogenic neoantigens. Tissue-specific transcripts show great potential in treatment, maximizing efficacy in target tissues and minimizing safety risks to unrelated tissues.

[0191] With the continuous development of high-throughput RNA sequencing technology and significant improvements in computational analysis methods, researchers are now able to conduct more in-depth analyses of transcriptional regulatory mechanisms under normal physiological and pathological conditions, and are expected to identify new transcripts. Although short-read RNA-seq technology has been widely used in transcriptomics research, it has inherent limitations in reconstructing transcripts, especially when multiple transcriptomic isoforms of the same gene share exons, making accurate differentiation and identification difficult. Considering the high complexity of the transcriptome and the aforementioned challenges, the task of comprehensively reconstructing all transcripts relying solely on short-read data is particularly arduous. In contrast, long-read sequencing (LR-Seq), also known as third-generation sequencing technology, including Pacific Biosciences (PacBio) and Oxford Nanopore Technologies (ONT), has advantages due to its ability to generate longer reads (>10kb), accurately capturing full-length isoforms. Third-generation sequencing technology promotes comprehensive and accurate characterization of transcript structure by eliminating the need for transcript assembly. Third-generation sequencing technology, thanks to its high accuracy in capturing complete transcriptomic isoforms, provides a comprehensive molecular basis for studying the transcriptomic characterization of tissues and cancers. Currently, numerous studies, including our own, have also used long-read RNA sequencing of tissue and tumor samples to discover unannotated tissue- and tumor-specific transcripts.

[0192] Tumor-specific RNA transcripts, expressed in tumors but not in normal tissues or expressed at very low levels in normal tissues, are called tumor SRTs (tu-SRTs). In the complex biological processes of cancer, tumor cells exhibit a series of unique transcriptomic patterns. Tumor-specific RNA transcripts play a crucial role in regulating tumor biological behavior; their presence is significantly correlated with the clinical outcomes of various cancers, and their specific expression characteristics in tumor tissues can be used for tumor diagnosis.

[0193] Therefore, this invention analyzes tumor and normal tissue samples using long-read and short-read RNA sequencing technologies, and integrates third-generation RNA sequencing data from various normal and cancerous human tissues and cells, identifying a large number of previously unannotated tumor-specific RNA transcripts in a large sample set. These results lay a solid scientific foundation for further research and implementation of precision RNA diagnostic and therapeutic strategies.

[0194] All documents mentioned in this invention are incorporated herein by reference as if each document were individually incorporated by reference. Furthermore, it should be understood that after reading the foregoing teachings of this invention, those skilled in the art can make various alterations or modifications to this invention, and these equivalent forms also fall within the scope defined by the appended claims.

Claims

1. A method for constructing a cancer prediction model, characterized in that, Including the following steps: (s1) Process the third-generation sequencing data and RNA sequencing (RNA-seq) data of cancer tissue samples, adjacent normal tissue samples, and normal tissue samples to obtain reference GTF files of full-length RNA transcripts and tumor-specific RNA transcripts (Tu-SRT). (s2) Provide training set, test set and validation set data for model construction, the data including expression information of full-length RNA transcripts obtained from RNA-seq data based on the reference GTF file after RNA sequencing; the expression information includes expression information of the tumor-specific RNA transcripts; The expression information of the tumor-specific RNA transcripts includes the expression information of tumor-specific RNA transcripts from cancer-positive samples and the expression information of tumor-specific RNA transcripts from cancer-negative samples. (s3) The training set data is used to train machine learning models selected from the following group: Random Forest, Decision Tree, XGBoost, LightGBM, and CatBoost; thereby obtaining the hyperparameters of the machine learning models and the trained machine learning models; and (s4) Using the test set and validation set data, the prediction results of the machine learning model are scored using the following scoring metrics: AUC value, accuracy, sensitivity and specificity; the machine learning model whose score meets the expected value is used as the cancer prediction model.

2. The method as described in claim 1, characterized in that, The transcript expression information includes the transcript expression level as measured in TPM (Transcript per million).

3. The method as described in claim 1, characterized in that, The cancer samples include samples of n different cancers, where n is a positive integer ≥10; preferably, n≥15; more preferably, n is 20-100; and even more preferably, n is 20-50.

4. The method as described in claim 1, characterized in that, Step (s1) includes the following steps: (a) Collect third-generation sequencing data and RNA-seq data of cancer tissue and adjacent normal tissue samples from different tumor sources, as well as normal tissue samples, and generate non-redundant transcriptome GTF files. (b) Optimize the non-redundant transcriptome GTF file, wherein, for a certain cancer / tissue RNA-seq, if all splicing sites of the transcript are detected in ≥m samples, the transcript is retained, where m is 1-90%, preferably 2-50%; (c) Each transcript was compared with the reference transcriptome (GENCODE v.35). The transcripts were mainly divided into four groups: fully spliced, partially spliced, novel within the catalog, and novel outside the catalog. After filtering, a reference GTF file for full-length RNA transcripts was established. Specifically, for all incompletely spliced ​​matching transcripts, these transcripts are filtered out from the entire transcriptome; Unqualified novel transcripts, both in-directory and out-of-directory, are filtered out (e.g., those with Cage peaks and polyA sites annotated with SQANTI3 are filtered out if there are 16 or more adenines within 20 bases downstream of the annotated transcription termination site). For similar transcripts, the longest transcript is retained, and other transcripts are filtered out; (d) Based on the reference GTF file for full-length RNA transcripts, the full-length transcripts of the tissue sample RNA-seq data are quantified to obtain the expression information of the full-length RNA transcripts of the tissue sample. (e) By comparison, RNA transcripts that show significant differences in expression information between cancer tissue samples, adjacent normal tissue samples, and normal tissue samples are obtained, thereby obtaining the tumor-specific RNA transcripts.

5. A reference GTF file for full-length RNA transcripts, characterized in that, It is obtained by the following steps: (i) Collect third-generation sequencing data and RNA-seq data of cancer tissue and adjacent normal tissue samples from different tumor sources, as well as normal tissue samples, and generate non-redundant transcriptome GTF files. (ii) Optimize the non-redundant transcriptome GTF file, wherein, for a certain cancer / tissue RNA-seq, if all splicing sites of the transcript are detected in ≥m samples, the transcript is retained, where m is 1-90%, preferably 2-50%; (iii) Each transcript was compared with the reference transcriptome (GENCODE v.35). The transcripts were mainly divided into four groups: fully spliced, partially spliced, novel in-directory, and novel out-of-directory. After filtering, a reference GTF file for full-length RNA transcripts was established. Specifically, for all incompletely spliced ​​matching transcripts, these transcripts are filtered out from the entire transcriptome; Unqualified novel transcripts, both in-directory and out-of-directory, are filtered out (e.g., those with Cage peaks and polyA sites annotated with SQANTI3 are filtered out if there are 16 or more adenines within 20 bases downstream of the annotated transcription termination site). For similar transcripts, the longest transcript is retained, and other transcripts are filtered out.

6. A method for determining the expression information of full-length RNA transcripts, characterized in that, Including the following steps: (i) Based on the reference GTF file for full-length RNA transcripts as described in claim 5, full-length transcript quantification is performed on RNA-seq data of tissue samples to obtain full-length RNA transcript expression information.

7. A cancer prediction system, characterized in that, The system includes: (a) An input module configured to input full-length RNA transcript expression information of the sample to be tested; (b) Evaluation module: The evaluation module is configured to input the expression information of the full-length RNA transcript into the cancer prediction model constructed using the method of claim 1, thereby obtaining a cancer prediction result for the sample to be tested; and (c) Output module, which is configured to output the prediction result.

8. The system as described in claim 7, characterized in that, The system further includes (a0) a preprocessing module configured to analyze and determine the full-length RNA transcript expression information of the test sample based on the RNA-seq sequencing information of the test sample.

9. The system as described in claim 7, characterized in that, The judgments in the prediction module include: The expression information of the full-length RNA transcript is input into the cancer prediction model to obtain the prediction result, which includes the prediction probability. When the prediction probability in the prediction result is greater than or equal to the preset reference threshold for cancer prediction, it is judged as positive, that is, the sample to be tested is a cancer sample; otherwise, it is judged as negative, that is, the sample to be tested is a non-cancer sample.

10. A computer storage medium, characterized in that, The storage medium is used to store the computer program corresponding to the algorithm of the cancer prediction model constructed by the method of claim 1.

Images