CN115851951A - Construction of early liver cancer detection model containing multiple groups of chemical marker compositions and kit - Google Patents
Construction of early liver cancer detection model containing multiple groups of chemical marker compositions and kit Download PDFInfo
- Publication number
- CN115851951A CN115851951A CN202211599809.1A CN202211599809A CN115851951A CN 115851951 A CN115851951 A CN 115851951A CN 202211599809 A CN202211599809 A CN 202211599809A CN 115851951 A CN115851951 A CN 115851951A
- Authority
- CN
- China
- Prior art keywords
- marker
- liver cancer
- detection
- model
- fragment
- 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.)
- Pending
Links
- 201000007270 liver cancer Diseases 0.000 title claims abstract description 78
- 208000014018 liver neoplasm Diseases 0.000 title claims abstract description 78
- 239000003550 marker Substances 0.000 title claims abstract description 64
- 238000001514 detection method Methods 0.000 title claims abstract description 57
- 238000010276 construction Methods 0.000 title claims abstract description 17
- 239000000203 mixture Substances 0.000 title claims abstract description 17
- 239000000126 substance Substances 0.000 title claims abstract description 10
- 239000012634 fragment Substances 0.000 claims abstract description 39
- 108010047956 Nucleosomes Proteins 0.000 claims abstract description 23
- 210000001623 nucleosome Anatomy 0.000 claims abstract description 23
- 238000004458 analytical method Methods 0.000 claims abstract description 21
- 230000011987 methylation Effects 0.000 claims abstract description 21
- 238000007069 methylation reaction Methods 0.000 claims abstract description 21
- 238000012216 screening Methods 0.000 claims abstract description 20
- 238000012163 sequencing technique Methods 0.000 claims abstract description 16
- 238000013145 classification model Methods 0.000 claims abstract description 7
- 238000010801 machine learning Methods 0.000 claims abstract description 7
- 210000004369 blood Anatomy 0.000 claims description 27
- 239000008280 blood Substances 0.000 claims description 27
- 239000012474 protein marker Substances 0.000 claims description 22
- 102000013529 alpha-Fetoproteins Human genes 0.000 claims description 20
- 108010026331 alpha-Fetoproteins Proteins 0.000 claims description 20
- 230000007067 DNA methylation Effects 0.000 claims description 16
- 238000000034 method Methods 0.000 claims description 12
- 108090000623 proteins and genes Proteins 0.000 claims description 9
- 102000004169 proteins and genes Human genes 0.000 claims description 9
- 238000012164 methylation sequencing Methods 0.000 claims description 8
- 108010094028 Prothrombin Proteins 0.000 claims description 5
- 102100027378 Prothrombin Human genes 0.000 claims description 5
- 230000002159 abnormal effect Effects 0.000 claims description 5
- 229940039716 prothrombin Drugs 0.000 claims description 5
- 238000000338 in vitro Methods 0.000 claims description 3
- 230000000694 effects Effects 0.000 abstract description 5
- 238000012070 whole genome sequencing analysis Methods 0.000 abstract description 4
- 206010073071 hepatocellular carcinoma Diseases 0.000 description 8
- 239000000523 sample Substances 0.000 description 8
- 206010028980 Neoplasm Diseases 0.000 description 7
- 231100000844 hepatocellular carcinoma Toxicity 0.000 description 7
- 238000013467 fragmentation Methods 0.000 description 5
- 238000006062 fragmentation reaction Methods 0.000 description 5
- 210000004027 cell Anatomy 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 230000035945 sensitivity Effects 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 201000011510 cancer Diseases 0.000 description 3
- 230000004083 survival effect Effects 0.000 description 3
- ISAKRJDGNUQOIC-UHFFFAOYSA-N Uracil Chemical compound O=C1C=CNC(=O)N1 ISAKRJDGNUQOIC-UHFFFAOYSA-N 0.000 description 2
- OPTASPLRGRRNAP-UHFFFAOYSA-N cytosine Chemical compound NC=1C=CNC(=O)N=1 OPTASPLRGRRNAP-UHFFFAOYSA-N 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000003745 diagnosis Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000001973 epigenetic effect Effects 0.000 description 2
- 238000011528 liquid biopsy Methods 0.000 description 2
- 230000004807 localization Effects 0.000 description 2
- 210000002966 serum Anatomy 0.000 description 2
- 238000000967 suction filtration Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 102000004506 Blood Proteins Human genes 0.000 description 1
- 108010017384 Blood Proteins Proteins 0.000 description 1
- 208000005623 Carcinogenesis Diseases 0.000 description 1
- 201000009030 Carcinoma Diseases 0.000 description 1
- 208000017667 Chronic Disease Diseases 0.000 description 1
- 206010008909 Chronic Hepatitis Diseases 0.000 description 1
- 238000007400 DNA extraction Methods 0.000 description 1
- 230000004543 DNA replication Effects 0.000 description 1
- 206010073306 Exposure to radiation Diseases 0.000 description 1
- 206010016654 Fibrosis Diseases 0.000 description 1
- 206010019695 Hepatic neoplasm Diseases 0.000 description 1
- 101000648539 Homo sapiens Transmembrane protein 59-like Proteins 0.000 description 1
- 206010058467 Lung neoplasm malignant Diseases 0.000 description 1
- 208000008589 Obesity Diseases 0.000 description 1
- 102100028863 Transmembrane protein 59-like Human genes 0.000 description 1
- 108010063628 acarboxyprothrombin Proteins 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000006907 apoptotic process Effects 0.000 description 1
- 230000036952 cancer formation Effects 0.000 description 1
- 231100000504 carcinogenesis Toxicity 0.000 description 1
- 230000033077 cellular process Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 239000003153 chemical reaction reagent Substances 0.000 description 1
- 210000000349 chromosome Anatomy 0.000 description 1
- 230000007882 cirrhosis Effects 0.000 description 1
- 208000019425 cirrhosis of liver Diseases 0.000 description 1
- 238000002790 cross-validation Methods 0.000 description 1
- 229940104302 cytosine Drugs 0.000 description 1
- 230000006866 deterioration Effects 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 238000013399 early diagnosis Methods 0.000 description 1
- 230000002255 enzymatic effect Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000014509 gene expression Effects 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 208000006454 hepatitis Diseases 0.000 description 1
- 238000012165 high-throughput sequencing Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 201000005202 lung cancer Diseases 0.000 description 1
- 208000020816 lung neoplasm Diseases 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 239000003147 molecular marker Substances 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000017074 necrotic cell death Effects 0.000 description 1
- 235000020824 obesity Nutrition 0.000 description 1
- 230000001575 pathological effect Effects 0.000 description 1
- 210000005259 peripheral blood Anatomy 0.000 description 1
- 239000011886 peripheral blood Substances 0.000 description 1
- 230000035935 pregnancy Effects 0.000 description 1
- 239000000047 product Substances 0.000 description 1
- 239000002096 quantum dot Substances 0.000 description 1
- 238000007674 radiofrequency ablation Methods 0.000 description 1
- 230000022532 regulation of transcription, DNA-dependent Effects 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 238000002271 resection Methods 0.000 description 1
- 230000000405 serological effect Effects 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
- 210000001519 tissue Anatomy 0.000 description 1
- 210000004881 tumor cell Anatomy 0.000 description 1
- 239000000439 tumor marker Substances 0.000 description 1
- 238000002604 ultrasonography Methods 0.000 description 1
- 229940035893 uracil Drugs 0.000 description 1
- 238000010200 validation analysis Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Landscapes
- Measuring Or Testing Involving Enzymes Or Micro-Organisms (AREA)
- Investigating Or Analysing Biological Materials (AREA)
Abstract
The invention discloses construction of an early liver cancer detection model containing a multi-group chemical marker composition and a kit thereof, belonging to the technical field of biological detection. The single-index classification models respectively constructed by the marker compositions relevant to liver cancer detection are integrated with the constructed liver cancer early screening machine learning model, so that the detection accuracy is improved. Fragment group marker analysis and nucleosome imprinting marker analysis are carried out by using sequencing data of cfDNA methylation, low-depth whole genome sequencing is not required to be carried out independently, and the prediction effect is improved. The kit can detect the marker combination required to be detected by the liver cancer early screening multigroup model, the accuracy of the detection result is improved, and the kit has great clinical value.
Description
Technical Field
The invention belongs to the technical field of biological detection, and particularly relates to construction of an early liver cancer detection model containing a multi-group chemical marker composition and a kit thereof.
Background
Liver cancer is one of the common malignant tumors, and the mortality rate is high and secondary to lung cancer. The incidence and mortality of liver cancer in the past years show a descending trend, but the survival rate of liver cancer patients is still lower and is obviously lower than the total relative survival rate of all malignant tumors in China. Liver cancer is developed gradually on the basis of chronic diseases such as chronic hepatitis or cirrhosis, and is a multi-factor and multi-step development and deterioration process. At present, the morbidity and mortality of liver cancer are higher than the average level in the world, but the early detection rate of liver cancer is lower. If liver cancer is diagnosed by early screening, 5-year survival rate can be obviously improved after comprehensive treatment such as liver tumor resection or radiofrequency ablation. The detection and monitoring of the high risk group of liver cancer is helpful for the early discovery, early diagnosis and early treatment of liver cancer, and is the key for improving the curative effect of liver cancer.
Currently, the combination of ultrasound and Alpha-fetoprotein (AFP) detection is still the most widely used liver cancer detection technology. However, serum AFP has many factors, and is not only affected by other physiological or pathological factors such as diseases and pregnancy, but also directly related to the tumor volume of liver cancer. Particularly, 30-40% of liver cancer patients clinically belong to AFP negative, so that certain misdiagnosis rate and missed diagnosis rate exist. Meanwhile, the ultrasonic examination is easily influenced by the experience of operators and the obesity of patients, the sensitivity to early liver cancer is low, and the missed diagnosis rate is still high.
However, imaging tests such as CT and MRI have the risk of radiation exposure due to high equipment price, are difficult to popularize and popularize, and cannot meet the detection requirements.
Disclosure of Invention
The first purpose of the present invention is to provide a multigroup chemical marker composition, which combines a protein marker, a DNA methylation marker, a fragment group marker and a nucleosome imprinting marker with higher sensitivity and specificity, so as to solve the technical problems of false negative detection result and inaccurate detection result caused by the prior art that only alpha fetoprotein is used for detection.
The second objective of the present invention is to provide a multigroup chemical marker composition, and the combined use of the marker composition eliminates the need of performing low-depth whole genome sequencing alone, thereby saving detection cost and improving detection effects that cannot be achieved by a single index.
The third purpose of the invention is to provide a construction method of an early liver cancer detection model, which constructs single index classification models aiming at markers respectively and calculates AUC values of the models for distinguishing liver cancer from non-liver cancer; the liver cancer early screening machine learning model constructed by the marker-integrated composition is obviously superior to a single-index classification model, and the accuracy of liver cancer detection is improved.
The invention is realized by the following technical scheme:
a multigenomic marker composition comprising a combination of a protein marker, a DNA methylation marker, a fragment group marker, and a nucleosome imprinted marker;
the protein marker comprises a combination of one or more of alpha-fetoprotein, alpha-fetoprotein heteroplasmon AFP-L3, and abnormal prothrombin DCP;
the DNA methylation marker is a fragment with the length of 80-200bp in plasma used for calculating the methylation level of the methylation marker;
the fragment group marker is the ratio of short fragments to long fragments in cfDNA; wherein the short fragment length is a cfDNA fragment between 80bp and 150 bp; the long fragment length is a cfDNA fragment between 150bp and 200 bp.
The alpha fetoprotein heteroplasmon AFP-L3 is specific to liver cancer cells and correspondingly increases along with the enhancement of canceration degree, so the AFP-L3 accounts for the percentage of AFP (AFP-L3%) which is commonly used as the detection index of primary liver cancer.
DCP is also called PIVKA-II, and is abnormal prothrombin specifically produced along with liver cancer.
Alpha-fetoprotein heteroplasmon AFP-L3 and abnormal prothrombin DCP are used as supplements of AFP, and the DCP has a certain diagnostic value for liver cancer negative to AFP. Therefore, for serum AFP negative population, the detection accuracy of early liver cancer can be improved by means of the combined action of AFP-L3, DCP and AFP.
A kit for detecting early liver cancer comprises the multi-group chemical marker composition.
A construction method of an early liver cancer detection model comprises the following steps:
s1, detecting protein markers: carrying out protein marker concentration detection on an isolated blood sample to obtain a protein marker detection value;
s2, sequencing: performing targeted methylation sequencing on the blood cfDNA to obtain sequencing data;
s3, marker comparison: comparing the sequencing data to the hg19 human genome to obtain the methylation level of each DNA methylation marker, the fragment group marker and the nucleosome imprinting marker result of the detection sample;
s4, characteristic value acquisition and analysis: constructing single index classification models by using the marker compositions, and respectively comparing AUC values of the models for distinguishing liver cancer from non-liver cancer;
s5, model construction: and (3) taking the models with obvious difference and higher AUC value as input values of model construction to construct and obtain the early liver cancer detection model.
The significant difference is that the detection value of the marker has a significant difference in the process of screening the marker. Higher AUC values refer to the selection of AUC values during the screening process ranked top50 (methylation), nucleosome imprinting (top 20), fragment group markers (top 10).
Among liquid biopsies, blood free DNA (cfDNA) is most widely used. cfDNA comes from the process of apoptosis or necrosis, is released into the blood, and is free of highly fragmented DNA outside the cells. The cfDNA contains circulating tumor DNA (ctDNA) which is the most important analysis object, i.e., tumor genomic DNA fragments released into blood by tumor cells and circulating in the whole body along with blood. Compared with the traditional tumor marker, the cancer-related segmented omics characteristics, nucleosome imprinting characteristics, DNA methylation markers and the like in the blood free DNA show higher sensitivity and specificity. Therefore, through high-throughput sequencing, specific genetic information and epigenetic information in a tumor genome are mined, various markers are comprehensively used, and a multiomic-based combined detection technology is established, so that higher sensitivity and specificity than those of ultrasonic combined AFP can be provided, and the method is expected to become an accurate, economic, convenient and practical detection technical means suitable for a wide range of people.
An apparatus for constructing an early liver cancer detection model, comprising:
s1, a protein marker detection module: the quantitative detection device is used for carrying out the quantitative detection of the concentration of the protein marker and obtaining the quantitative detection data of the protein marker;
s2, a sequencing module for extracting cfDNA from the liver cancer sample and the non-liver cancer sample and performing targeted methylation sequencing to obtain sequencing data;
s3, a marker comparison module for comparing the sequencing data result to a reference genome;
s4, a characteristic value acquisition and analysis module for obtaining the methylation level of the DNA methylation marker, the result of the fragment group marker and the result of the nucleosome imprinting marker, and screening the input value which is obvious in difference among the markers and high in AUC value and is used as the model construction;
and S5, a model construction module for inputting the characteristic values obtained by the screening module into a model to construct a machine learning model for early screening of the liver cancer.
A computer readable medium comprises a stored program, and when the program runs, the apparatus where the readable medium is located is controlled to execute the construction method of the early liver cancer detection model.
Compared with the prior art, the invention at least has the following technical effects:
the method comprises the steps of detecting protein markers related to liver cancer, performing targeted methylation sequencing on cfDNA in peripheral blood of a human body, screening out multiple molecular marker characteristics (DNA methylation molecular markers, fragment group markers and nucleosome imprinting markers) related to the liver cancer, respectively constructing single-index classification models, and calculating AUC values of the respective models for distinguishing liver cancer from non-liver cancer. The liver cancer early screening machine learning model constructed by integrating the four markers has an AUC value of 0.980 for distinguishing liver cancer from non-liver cancer, is obviously superior to a single-index classification model, and improves the accuracy of liver cancer detection.
The invention also provides a multi-group chemical marker composition, wherein the DNA methylation marker is used as an epigenetic index; the nucleosome imprinting marker and the fragment group marker are used as a whole genome sequencing index; the combined protein marker is used as the protein marker index for combination, is suitable for the liver cancer detection liquid biopsy method, and has accurate detection rate.
The method realizes protein marker analysis, DNA methylation marker analysis, fragment group marker analysis and nucleosome imprinting marker analysis by using sequencing data of cfDNA methylation, does not need to perform low-depth whole genome sequencing independently, saves the detection cost and improves the prediction effect which cannot be achieved by a single index.
The kit provided by the invention can detect marker combinations required to be detected by a liver cancer early screening multigroup chemical model, and the detection result improves the accuracy of detecting liver cancer, thereby having great clinical value.
Drawings
FIG. 1 is a AUC curve for distinguishing liver cancer from non-liver cancer for a model constructed solely using a combination of 50 DNA methylation markers as in example Table 1;
FIG. 2 is a AUC curve for distinguishing liver cancer from non-liver cancer using a model constructed separately from combinations of the segment group markers in Table 2 of the examples;
fig. 3 is an AUC curve for distinguishing liver cancer from non-liver cancer of a model constructed separately by using the combinations of nucleosome imprinted markers in table 2 of the examples.
FIG. 4 is the AUC curve for differentiating liver cancer from non-liver cancer of the model constructed by the combination of protein markers in the example;
FIG. 5 is the AUC curve for differentiating liver cancer from non-liver cancer in the liver cancer early-screening model constructed comprehensively by integrating 4 markers in the example.
Detailed Description
Embodiments of the present invention will be described in detail with reference to the following examples, but those skilled in the art will understand that the following examples are merely illustrative of the present invention and should not be construed as limiting the scope of the present invention, and that the specific conditions not specified in the examples are carried out according to conventional conditions or conditions suggested by the manufacturer, and that the reagents or equipment used are not specified by the manufacturer, and are all conventional products available through commercial purchase.
Example (b):
according to the construction method of the early liver cancer detection model, firstly, a protein marker in blood needs to be detected, and a protein concentration result is obtained. The method for measuring a blood protein is not particularly limited.
1. Extraction and targeted methylation sequencing of blood cfDNA:
the specific operation steps of extracting the blood cfDNA are carried out by combining a vacuum suction filtration pump according to the operation instruction of a free DNA extraction kit (suction filtration method), the extracted cfDNA is subjected to DNA quality and content detection by using a Qubit fluorescence quantifier, the NEBNext Enzymatic Methyl-seq kit is adopted to carry out conversion from cytosine to uracil and construction of a methylation sequencing library, the constructed library is hybridized with a customized probe to form a targeted methylation sequencing library, and then on-machine sequencing is carried out.
2. Analysis of sequencing data:
raw data off-line low quality sequences (phred 33 score < = 20) as well as linker sequences and polyA/T sequences in read were first filtered using fastQC. And (3) replying the filtered high-quality reads to the hg19 human genome by using BSMAP, and screening the reads with higher replying quality. Remove PCR duplication by picard and then select reads that are attached back to the target genomic region (the region corresponding to the DNA methylation marker) by samtools and calculate the methylation level of each DNA methylation marker, the fragmentation group short-to-long fragment ratio and the nucleosome imprinting result.
2.1 for blood cfDNA methylation calculations, fragments between 80-200bp in length in plasma were used to calculate methylation levels of methylation markers. cfDNA methylation is a very stable biological feature for early tumor detection. And carrying out difference analysis and AUC analysis. Differential methylation sites of top50 are selected as candidate sites and incorporated into a subsequent early liver cancer prediction model, and specific data are shown in table 1.
TABLE 1cfDNA methylation top50 site AUC results
2.2 for nucleosome imprinting calculations, since the main form of cfDNA in blood is DNA protected by a single nucleosome, nucleosome localization changes are accompanied by a shift in gene expression pattern, similar to methylation patterns, which play an important role in transcriptional regulation, DNA replication and repair, etc. in a variety of cellular processes and tumorigenesis development. The tumor therefore has a characteristic nucleosomal imprinting score.
Nucleosome localization varies with cell type and therefore also contains cfDNA tissue origin information. The occupancy rate of nucleosomes is calculated by using software DNAPOS3, and after difference analysis and AUC analysis, a top20 nucleosome region with obvious difference and highest AUC value is obtained by screening and is included in a subsequent early liver cancer prediction model, and the data is shown in Table 2.
TABLE 2 nucleosome imprinting Top20 site AUC results
2.3 for the ratio calculation of the fragmentation group short and long fragments, the ratio of the short to long fragments in cfDNA is used, the short fragment refers to the cfDNA fragment with the length between 80bp to 150bp in the template, the long fragment refers to the cfDNA fragment with the length between 150bp to 200bp in the template. And for the target region, counting the number of short segments and long segments in the target region, and obtaining the ratio of the short segments to the long segments. Difference analysis and AUC analysis are carried out through the result of the fragmentation group analysis, the positions of top10 chromosome fragment regions with obvious difference and the highest AUC value are obtained by screening and are included in a subsequent early liver cancer prediction model, and the data are shown in Table 3.
TABLE 3 fragmentation group top10 site AUC results
2.4 for the serological protein results, the protein markers were subjected to differential analysis and AUC analysis, and all the AUC results of the protein markers were included in the subsequent early liver cancer screening model, and the data are shown in Table 4.
TABLE 4 protein marker AUC results
| Protein markers | AUC_SCORE |
| AFP | 0.797 |
| AFP-L3％ | 0.677 |
| DCP | 0.678 |
Test examples
A total of 96 ex vivo plasma samples from hepatocellular carcinoma patients and 96 ex vivo plasma samples from enrolled healthy volunteers were used.
The training and validation set ratios were 7, and 50 cross-validation analyses were performed.
Different types of markers or marker compositions are respectively used for constructing a machine learning model for detecting the hepatocellular carcinoma in-vitro blood sample in a training set, and the accuracy of the model for predicting the hepatocellular carcinoma in-vitro blood sample is evaluated in an independent verification set sample.
As shown in the results of fig. 1, the AUC values of the models constructed from the combinations of 50 all blood cfDNA methylation markers in table 1 above, which distinguished blood from that of hepatocellular carcinoma patients, were 0.939 (95% ci.
As shown in the results of fig. 2, the AUC for differentiating the blood for health examination and the blood for hepatocellular carcinoma patients constructed by all the blood cfDNA fragment set markers in table 2 above was 0.808 (95% ci.
As shown in the results of FIG. 3, the AUC values for differentiating blood of a physical examination from blood of a hepatocellular carcinoma patient constructed by all the combinations of the nucleosomal imprinted markers in Table 2 above were 0.863 (95% CI: 0.792-0.937).
As shown in the results of FIG. 4, the AUC value of the model constructed from all the protein marker combinations (alpha-fetoprotein, alpha-fetoprotein variant AFP-L3 and abnormal prothrombin DCP) for distinguishing the blood of the healthy body examination from the blood of the hepatoma cell carcinoma patients was 0.820 (95% CI: 0.731-0.890).
As shown in the results of FIG. 5, the AUC value of the comprehensive machine learning model constructed by combining the cfDNA methylation marker, the nucleosome imprinted marker, the fragmentation group marker and the protein marker in distinguishing the blood of the healthy physical examination from the blood of the hepatocellular carcinoma patient is as high as 0.980 (95% CI: 0.916-0.996).
Finally, it should be noted that: the above description is only a preferred embodiment of the present invention, and is not intended to limit the scope of the present invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (5)
1. A multigenomic marker composition comprising a combination of a protein marker, a DNA methylation marker, a fragment set marker, and a nucleosome imprinting marker;
the protein marker comprises a combination of one or more of alpha-fetoprotein, alpha-fetoprotein heteroplasmon AFP-L3, and abnormal prothrombin DCP;
the DNA methylation marker is a fragment with the length of 80-200bp in plasma used for calculating the methylation level of the methylation marker;
the fragment group marker is the ratio of short fragments to long fragments in cfDNA; wherein the short fragment length is a cfDNA fragment between 80bp and 150 bp; the long fragment length is a cfDNA fragment between 150bp and 200 bp.
2. A kit for early liver cancer detection, comprising the multi-panel chemical marker composition of claim 1.
3. A method for constructing an early liver cancer detection model is characterized by comprising the following steps:
s1, detecting protein markers: carrying out protein marker concentration detection on the in vitro blood sample to obtain a protein marker detection value;
s2, sequencing: performing targeted methylation sequencing on the blood cfDNA to obtain sequencing data;
s3, marker comparison: comparing the sequencing data to the hg19 human genome to obtain the methylation level, fragment group markers and nucleosome imprinting marker results of each DNA methylation marker of the detection sample;
s4, characteristic value acquisition and analysis: respectively constructing a single index classification model by using the marker composition of claim 1, and respectively comparing AUC values of the respective models for distinguishing liver cancer from non-liver cancer;
s5, model construction: and (3) taking the models with obvious difference and higher AUC value as input values of model construction to construct and obtain the early liver cancer detection model.
4. An apparatus for constructing an early liver cancer detection model, comprising:
s1, a protein marker detection module: the quantitative detection device is used for carrying out the quantitative detection of the concentration of the protein marker and obtaining the quantitative detection data of the protein marker;
s2, a sequencing module for extracting cfDNA from the liver cancer sample and the non-liver cancer sample and performing targeted methylation sequencing to obtain sequencing data;
s3, a marker comparison module for comparing the sequencing data result to a reference genome;
s4, a characteristic value obtaining and analyzing module for obtaining the methylation level of the DNA methylation marker, the fragment group marker and the nucleosome imprinting marker result, and screening the input value which has obvious difference and higher AUC value in the marker and is used as the model construction;
and S5, a model construction module for inputting the characteristic values obtained by the screening module into a model and constructing a machine learning model for early screening of the liver cancer.
5. A computer readable medium, wherein the computer readable medium comprises a stored program, and when the program runs, the apparatus in which the computer readable medium is located is controlled to execute the method for constructing an early liver cancer detection model according to claim 3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211599809.1A CN115851951A (en) | 2022-12-12 | 2022-12-12 | Construction of early liver cancer detection model containing multiple groups of chemical marker compositions and kit |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211599809.1A CN115851951A (en) | 2022-12-12 | 2022-12-12 | Construction of early liver cancer detection model containing multiple groups of chemical marker compositions and kit |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115851951A true CN115851951A (en) | 2023-03-28 |
Family
ID=85672590
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211599809.1A Pending CN115851951A (en) | 2022-12-12 | 2022-12-12 | Construction of early liver cancer detection model containing multiple groups of chemical marker compositions and kit |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115851951A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116403637A (en) * | 2023-06-08 | 2023-07-07 | 深圳市睿法生物科技有限公司 | Model construction method of liver cirrhosis marker |
| CN116597902A (en) * | 2023-04-24 | 2023-08-15 | 浙江大学 | Method and device for screening multiple groups of chemical biomarkers based on drug sensitivity data |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20210017605A1 (en) * | 2019-05-31 | 2021-01-21 | Guardant Health, Inc. | Methods and systems for improving patient monitoring after surgery |
| CN112410422A (en) * | 2020-10-30 | 2021-02-26 | 深圳思勤医疗科技有限公司 | Method for predicting tumor risk value based on fragmentation pattern |
| CN112599197A (en) * | 2020-12-23 | 2021-04-02 | 北京吉因加医学检验实验室有限公司 | Method and device for evaluating cancer risk based on plasma DNA fragment analysis |
| EP3940086A1 (en) * | 2019-03-11 | 2022-01-19 | Cancer Hospital Chinese Academy of Medical Sciences | Kit for early screening of liver cell cancer and preparation method and use thereof |
| CN114317762A (en) * | 2022-03-16 | 2022-04-12 | 北京莱盟君泰国际医疗技术开发有限公司 | Three-marker composition for detecting early liver cancer and kit thereof |
| CN114592066A (en) * | 2021-11-30 | 2022-06-07 | 杭州翱锐基因科技有限公司 | Novel combined marker for early detection of multi-target liver cancer and application thereof |
| CN114596918A (en) * | 2022-03-11 | 2022-06-07 | 苏州吉因加生物医学工程有限公司 | Method and device for detecting mutation |
| CN114657247A (en) * | 2022-02-28 | 2022-06-24 | 北京莱盟君泰国际医疗技术开发有限公司 | DNA methylation biomarker or combination for early liver cancer detection and application thereof |
| WO2022144407A1 (en) * | 2020-12-29 | 2022-07-07 | Belgian Volition Srl | Circulating transcription factor analysis |
| WO2022226231A1 (en) * | 2021-04-21 | 2022-10-27 | Helio Health Inc. | Liver cancer methylation and protein markers and their uses |
| CN115287353A (en) * | 2022-01-24 | 2022-11-04 | 南京世和医疗器械有限公司 | Methylation marker derived from free DNA of liver cancer plasma and application thereof |
-
2022
- 2022-12-12 CN CN202211599809.1A patent/CN115851951A/en active Pending
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP3940086A1 (en) * | 2019-03-11 | 2022-01-19 | Cancer Hospital Chinese Academy of Medical Sciences | Kit for early screening of liver cell cancer and preparation method and use thereof |
| US20210017605A1 (en) * | 2019-05-31 | 2021-01-21 | Guardant Health, Inc. | Methods and systems for improving patient monitoring after surgery |
| CN112410422A (en) * | 2020-10-30 | 2021-02-26 | 深圳思勤医疗科技有限公司 | Method for predicting tumor risk value based on fragmentation pattern |
| CN112599197A (en) * | 2020-12-23 | 2021-04-02 | 北京吉因加医学检验实验室有限公司 | Method and device for evaluating cancer risk based on plasma DNA fragment analysis |
| WO2022144407A1 (en) * | 2020-12-29 | 2022-07-07 | Belgian Volition Srl | Circulating transcription factor analysis |
| WO2022226231A1 (en) * | 2021-04-21 | 2022-10-27 | Helio Health Inc. | Liver cancer methylation and protein markers and their uses |
| CN114592066A (en) * | 2021-11-30 | 2022-06-07 | 杭州翱锐基因科技有限公司 | Novel combined marker for early detection of multi-target liver cancer and application thereof |
| CN115287353A (en) * | 2022-01-24 | 2022-11-04 | 南京世和医疗器械有限公司 | Methylation marker derived from free DNA of liver cancer plasma and application thereof |
| CN114657247A (en) * | 2022-02-28 | 2022-06-24 | 北京莱盟君泰国际医疗技术开发有限公司 | DNA methylation biomarker or combination for early liver cancer detection and application thereof |
| CN114596918A (en) * | 2022-03-11 | 2022-06-07 | 苏州吉因加生物医学工程有限公司 | Method and device for detecting mutation |
| CN114317762A (en) * | 2022-03-16 | 2022-04-12 | 北京莱盟君泰国际医疗技术开发有限公司 | Three-marker composition for detecting early liver cancer and kit thereof |
Non-Patent Citations (3)
| Title |
|---|
| LEI CHEN等: "Genome-scale profiling of circulating cell-free DNA signatures for early detection of hepatocellular carcinoma in cirrhotic patients", CELL RES, vol. 31, no. 5, pages 589 - 592, XP037441893, DOI: 10.1038/s41422-020-00457-7 * |
| 吴彤: "基于cfDNA全基因组测序技术的肝癌早诊早筛模型研究", 万方平台 * |
| 杨智彬等: "肝脏疾病的表观遗传学研究进展", 肝脏, vol. 22, no. 05, pages 381 - 384 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116597902A (en) * | 2023-04-24 | 2023-08-15 | 浙江大学 | Method and device for screening multiple groups of chemical biomarkers based on drug sensitivity data |
| CN116597902B (en) * | 2023-04-24 | 2023-12-01 | 浙江大学 | Method and device for screening multiple groups of chemical biomarkers based on drug sensitivity data |
| CN116403637A (en) * | 2023-06-08 | 2023-07-07 | 深圳市睿法生物科技有限公司 | Model construction method of liver cirrhosis marker |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20080206756A1 (en) | Biomarker panel for colorectal cancer | |
| JP2019022495A (en) | Using size and number aberrations in plasma dna for detecting cancer | |
| CN115851951A (en) | Construction of early liver cancer detection model containing multiple groups of chemical marker compositions and kit | |
| JP5209272B2 (en) | Liver cancer-related gene and method for determining liver cancer risk | |
| CN107326065A (en) | A kind of screening technique of genetic marker thing and its application | |
| WO2022161076A1 (en) | Methylation markers for detection of benign/malignant pulmonary nodules or combination thereof, and application thereof | |
| CN107435062B (en) | Peripheral blood gene marker for discriminating benign and malignant pulmonary nodules and application thereof | |
| CN109616198A (en) | It is only used for the choosing method of the special DNA methylation assay Sites Combination of the single cancer kind screening of liver cancer | |
| CN117165688A (en) | Marker for urothelial cancer and application thereof | |
| CN115820860A (en) | Method for screening non-small cell lung cancer marker based on methylation difference of enhancer, marker and application thereof | |
| CN117363733B (en) | Application of detection primer probe group for PER1 and LOX double-gene methylation joint diagnosis in preparation of bladder cancer diagnosis reagent | |
| CN114107502A (en) | Upper urinary tract epithelial cancer diagnosis marker and application thereof | |
| CN112280867A (en) | Early warning method for liver cancer, detection kit for early warning and detection method | |
| CN111968702A (en) | Early malignant tumor screening system based on circulating tumor DNA | |
| CN111778335A (en) | tsRNA marker and probe for detecting cancer tissue and paracarcinoma tissue of pancreatic cancer and application of tsRNA marker and probe | |
| CN115287353A (en) | Methylation marker derived from free DNA of liver cancer plasma and application thereof | |
| CN114107514A (en) | miRNA molecular marker for colorectal cancer diagnosis and kit thereof | |
| CN106282366A (en) | A kind of molecular marked compound relevant to carcinoma of prostate and application thereof | |
| WO2023063049A1 (en) | Method for creating biomarker set for detecting cancer | |
| KR102602100B1 (en) | Method for discovering disease biomarker through comparison of disease and normal tissue specific epigenome with normal body fluid epigenome | |
| CN116287252B (en) | Application of long-chain non-coding RNA APCDD1L-DT in preparation of pancreatic cancer detection products | |
| CN113278697B (en) | Lung cancer diagnostic kit based on peripheral blood internal gene methylation | |
| US11807908B2 (en) | Genetic markers used for identifying benign and malignant pulmonary micro-nodules and the application thereof | |
| WO2024066941A1 (en) | Composition for detecting bladder cancer, kit, and use thereof | |
| JP7024957B2 (en) | Methods for predicting the presence or absence of metastatic metastasis of colorectal cancer and kits used for it |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20230328 |
|
| RJ01 | Rejection of invention patent application after publication |