CN115440375A - Colorectal cancer prediction system and application thereof - Google Patents
Colorectal cancer prediction system and application thereof Download PDFInfo
- Publication number
- CN115440375A CN115440375A CN202211073050.3A CN202211073050A CN115440375A CN 115440375 A CN115440375 A CN 115440375A CN 202211073050 A CN202211073050 A CN 202211073050A CN 115440375 A CN115440375 A CN 115440375A
- Authority
- CN
- China
- Prior art keywords
- acid
- colorectal cancer
- biomarker
- biomarkers
- sulfate
- 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
- 206010009944 Colon cancer Diseases 0.000 title claims abstract description 160
- 208000001333 Colorectal Neoplasms Diseases 0.000 title claims abstract description 155
- 239000000090 biomarker Substances 0.000 claims abstract description 136
- 210000002700 urine Anatomy 0.000 claims abstract description 40
- WGNAKZGUSRVWRH-UHFFFAOYSA-N p-cresol sulfate Chemical compound CC1=CC=C(OS(O)(=O)=O)C=C1 WGNAKZGUSRVWRH-UHFFFAOYSA-N 0.000 claims description 38
- IWDCLRJOBJJRNH-UHFFFAOYSA-N p-cresol Chemical compound CC1=CC=C(O)C=C1 IWDCLRJOBJJRNH-UHFFFAOYSA-N 0.000 claims description 30
- 238000001514 detection method Methods 0.000 claims description 25
- -1 5-hydroxyindole glucoside Chemical class 0.000 claims description 22
- 238000007637 random forest analysis Methods 0.000 claims description 20
- AOKCDAVWJLOAHG-UHFFFAOYSA-N 4-(methylamino)butyric acid Chemical compound C[NH2+]CCCC([O-])=O AOKCDAVWJLOAHG-UHFFFAOYSA-N 0.000 claims description 18
- KKADPXVIOXHVKN-UHFFFAOYSA-N 4-hydroxyphenylpyruvic acid Chemical compound OC(=O)C(=O)CC1=CC=C(O)C=C1 KKADPXVIOXHVKN-UHFFFAOYSA-N 0.000 claims description 18
- XUWHAWMETYGRKB-UHFFFAOYSA-N piperidin-2-one Chemical compound O=C1CCCCN1 XUWHAWMETYGRKB-UHFFFAOYSA-N 0.000 claims description 18
- AEMOLEFTQBMNLQ-AQKNRBDQSA-N D-glucopyranuronic acid Chemical compound OC1O[C@H](C(O)=O)[C@@H](O)[C@H](O)[C@H]1O AEMOLEFTQBMNLQ-AQKNRBDQSA-N 0.000 claims description 17
- 229940097042 glucuronate Drugs 0.000 claims description 17
- JFLIEFSWGNOPJJ-JTQLQIEISA-N N(2)-phenylacetyl-L-glutamine Chemical compound NC(=O)CC[C@@H](C(O)=O)NC(=O)CC1=CC=CC=C1 JFLIEFSWGNOPJJ-JTQLQIEISA-N 0.000 claims description 16
- FDWFFCURSPACFQ-QMMMGPOBSA-N (2s)-2-[(2-phenylacetyl)amino]propanoic acid Chemical compound OC(=O)[C@H](C)NC(=O)CC1=CC=CC=C1 FDWFFCURSPACFQ-QMMMGPOBSA-N 0.000 claims description 15
- OZQCZEAFOVHVSC-NSHDSACASA-N (2s)-4-methylsulfanyl-2-[(2-phenylacetyl)amino]butanoic acid Chemical compound CSCC[C@@H](C(O)=O)NC(=O)CC1=CC=CC=C1 OZQCZEAFOVHVSC-NSHDSACASA-N 0.000 claims description 15
- ZTAVORUYXADUPD-KCJUWKMLSA-N (2s,3r)-3-hydroxy-2-[(2-phenylacetyl)amino]butanoic acid Chemical compound C[C@@H](O)[C@@H](C(O)=O)NC(=O)CC1=CC=CC=C1 ZTAVORUYXADUPD-KCJUWKMLSA-N 0.000 claims description 13
- 238000004458 analytical method Methods 0.000 claims description 13
- 238000007477 logistic regression Methods 0.000 claims description 13
- LRFVTYWOQMYALW-UHFFFAOYSA-N 9H-xanthine Chemical compound O=C1NC(=O)NC2=C1NC=N2 LRFVTYWOQMYALW-UHFFFAOYSA-N 0.000 claims description 12
- PYUSHNKNPOHWEZ-YFKPBYRVSA-N N-formyl-L-methionine Chemical compound CSCC[C@@H](C(O)=O)NC=O PYUSHNKNPOHWEZ-YFKPBYRVSA-N 0.000 claims description 10
- DTVCHTPRFHXPKU-UHFFFAOYSA-N 1h-indol-3-ol;sulfuric acid Chemical compound OS(O)(=O)=O.C1=CC=C2C(O)=CNC2=C1 DTVCHTPRFHXPKU-UHFFFAOYSA-N 0.000 claims description 9
- BVZASAZPMFMKCN-UHFFFAOYSA-N 3-(hydroxyamino)benzoic acid Chemical compound ONC1=CC=CC(C(O)=O)=C1 BVZASAZPMFMKCN-UHFFFAOYSA-N 0.000 claims description 9
- 238000007405 data analysis Methods 0.000 claims description 9
- 229930182478 glucoside Natural products 0.000 claims description 9
- UYPYRKYUKCHHIB-UHFFFAOYSA-N trimethylamine N-oxide Chemical compound C[N+](C)(C)[O-] UYPYRKYUKCHHIB-UHFFFAOYSA-N 0.000 claims description 9
- FFOQSERFAKGHPB-UHFFFAOYSA-N 1H-indol-6-ol sulfuric acid Chemical compound S(=O)(=O)(O)O.OC1=CC=C2C=CNC2=C1 FFOQSERFAKGHPB-UHFFFAOYSA-N 0.000 claims description 8
- QBRBSVCIHKXBNP-UHFFFAOYSA-N 2-(diaminomethylideneamino)-2,3-dimethylpentanoic acid Chemical compound CC(C(C(=O)O)(NC(=N)N)C)CC QBRBSVCIHKXBNP-UHFFFAOYSA-N 0.000 claims description 8
- PTSRBZOZSRJCKX-JTQLQIEISA-N N-Phenylacetylglutamic acid Chemical compound OC(=O)CC[C@@H](C(O)=O)NC(=O)CC1=CC=CC=C1 PTSRBZOZSRJCKX-JTQLQIEISA-N 0.000 claims description 8
- AYFVYJQAPQTCCC-UHFFFAOYSA-N Threonine Natural products CC(O)C(N)C(O)=O AYFVYJQAPQTCCC-UHFFFAOYSA-N 0.000 claims description 8
- 239000004473 Threonine Substances 0.000 claims description 8
- HXXOZPLLGYOEMB-UHFFFAOYSA-N n-(1-aminopentyl)acetamide Chemical compound CCCCC(N)NC(C)=O HXXOZPLLGYOEMB-UHFFFAOYSA-N 0.000 claims description 7
- ZCRPDIISGMDRTM-LBPRGKRZSA-N (2s)-3-(1h-imidazol-5-yl)-2-[(2-phenylacetyl)amino]propanoic acid Chemical compound C([C@@H](C(=O)O)NC(=O)CC=1C=CC=CC=1)C1=CNC=N1 ZCRPDIISGMDRTM-LBPRGKRZSA-N 0.000 claims description 6
- CYRKYXZJUIBBJX-UHFFFAOYSA-N N-4-hydroxyphenylacetylglutamic acid Chemical compound OC(=O)CCC(C(O)=O)NC(=O)CC1=CC=C(O)C=C1 CYRKYXZJUIBBJX-UHFFFAOYSA-N 0.000 claims description 6
- USSFUVKEHXDAPM-UHFFFAOYSA-N Nicotinamide N-oxide Chemical compound NC(=O)C1=CC=C[N+]([O-])=C1 USSFUVKEHXDAPM-UHFFFAOYSA-N 0.000 claims description 6
- DFPAKSUCGFBDDF-ZQBYOMGUSA-N [14c]-nicotinamide Chemical compound N[14C](=O)C1=CC=CN=C1 DFPAKSUCGFBDDF-ZQBYOMGUSA-N 0.000 claims description 6
- PIEPQKCYPFFYMG-UHFFFAOYSA-N tris acetate Chemical compound CC(O)=O.OCC(N)(CO)CO PIEPQKCYPFFYMG-UHFFFAOYSA-N 0.000 claims description 6
- 229940075420 xanthine Drugs 0.000 claims description 6
- MIISCXSXGSYQNJ-UHFFFAOYSA-N CC(C(=O)O)(CC)NC(=N)N Chemical compound CC(C(=O)O)(CC)NC(=N)N MIISCXSXGSYQNJ-UHFFFAOYSA-N 0.000 claims description 5
- FNHVSHKKUKMXJJ-VIFPVBQESA-N (2s)-3-hydroxy-2-[(2-phenylacetyl)amino]propanoic acid Chemical compound OC[C@@H](C(O)=O)NC(=O)CC1=CC=CC=C1 FNHVSHKKUKMXJJ-VIFPVBQESA-N 0.000 claims description 4
- HCQNSJKEUUTUJW-UHFFFAOYSA-N CC(C(CC1=CC=CC=C1)=O)S(O)(=O)=O Chemical compound CC(C(CC1=CC=CC=C1)=O)S(O)(=O)=O HCQNSJKEUUTUJW-UHFFFAOYSA-N 0.000 claims description 3
- MQWMHIZABNPALP-UHFFFAOYSA-N CC(C1=CC=CC=C1)(NC(C)=O)S(O)(=O)=O Chemical compound CC(C1=CC=CC=C1)(NC(C)=O)S(O)(=O)=O MQWMHIZABNPALP-UHFFFAOYSA-N 0.000 claims description 3
- 239000002253 acid Substances 0.000 claims description 3
- HZPMSKASVBBGIP-UHFFFAOYSA-N 1-[(2-phenylacetyl)amino]ethanesulfonic acid Chemical compound C1(=CC=CC=C1)CC(=O)NC(C)S(=O)(=O)O HZPMSKASVBBGIP-UHFFFAOYSA-N 0.000 claims description 2
- 239000003795 chemical substances by application Substances 0.000 claims description 2
- 238000000034 method Methods 0.000 abstract description 18
- 239000002207 metabolite Substances 0.000 abstract description 17
- 238000003745 diagnosis Methods 0.000 abstract description 9
- 230000009467 reduction Effects 0.000 description 60
- 239000000523 sample Substances 0.000 description 22
- 239000003153 chemical reaction reagent Substances 0.000 description 11
- 230000008859 change Effects 0.000 description 8
- 238000002705 metabolomic analysis Methods 0.000 description 8
- 230000001431 metabolomic effect Effects 0.000 description 8
- 238000011160 research Methods 0.000 description 8
- 238000012216 screening Methods 0.000 description 8
- 238000001294 liquid chromatography-tandem mass spectrometry Methods 0.000 description 7
- DFPAKSUCGFBDDF-UHFFFAOYSA-N Nicotinamide Chemical compound NC(=O)C1=CC=CN=C1 DFPAKSUCGFBDDF-UHFFFAOYSA-N 0.000 description 6
- 208000029742 colonic neoplasm Diseases 0.000 description 5
- 229960003966 nicotinamide Drugs 0.000 description 5
- 239000011570 nicotinamide Substances 0.000 description 5
- 238000012706 support-vector machine Methods 0.000 description 5
- 239000013068 control sample Substances 0.000 description 4
- 230000002503 metabolic effect Effects 0.000 description 4
- 210000002966 serum Anatomy 0.000 description 4
- 238000010811 Ultra-Performance Liquid Chromatography-Tandem Mass Spectrometry Methods 0.000 description 3
- 150000001413 amino acids Chemical group 0.000 description 3
- 230000008901 benefit Effects 0.000 description 3
- 210000004369 blood Anatomy 0.000 description 3
- 239000008280 blood Substances 0.000 description 3
- 201000010099 disease Diseases 0.000 description 3
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 3
- 235000005152 nicotinamide Nutrition 0.000 description 3
- 238000007619 statistical method Methods 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- IJGRMHOSHXDMSA-UHFFFAOYSA-N Atomic nitrogen Chemical compound N#N IJGRMHOSHXDMSA-UHFFFAOYSA-N 0.000 description 2
- 102100024504 Bone morphogenetic protein 3 Human genes 0.000 description 2
- KHEUJAKHWLIQCV-UHFFFAOYSA-N CC(C(CC1=CC=CC=C1)=O)(N)S(O)(=O)=O Chemical compound CC(C(CC1=CC=CC=C1)=O)(N)S(O)(=O)=O KHEUJAKHWLIQCV-UHFFFAOYSA-N 0.000 description 2
- 206010064571 Gene mutation Diseases 0.000 description 2
- 101000762375 Homo sapiens Bone morphogenetic protein 3 Proteins 0.000 description 2
- 101000995332 Homo sapiens Protein NDRG4 Proteins 0.000 description 2
- 101150105104 Kras gene Proteins 0.000 description 2
- 208000015634 Rectal Neoplasms Diseases 0.000 description 2
- QAOWNCQODCNURD-UHFFFAOYSA-L Sulfate Chemical compound [O-]S([O-])(=O)=O QAOWNCQODCNURD-UHFFFAOYSA-L 0.000 description 2
- 230000000875 corresponding effect Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 2
- 230000002550 fecal effect Effects 0.000 description 2
- HNDVDQJCIGZPNO-UHFFFAOYSA-N histidine Natural products OC(=O)C(N)CC1=CN=CN1 HNDVDQJCIGZPNO-UHFFFAOYSA-N 0.000 description 2
- 238000004949 mass spectrometry Methods 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 230000011987 methylation Effects 0.000 description 2
- 238000007069 methylation reaction Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 239000000047 product Substances 0.000 description 2
- 108090000623 proteins and genes Proteins 0.000 description 2
- 206010038038 rectal cancer Diseases 0.000 description 2
- 201000001275 rectum cancer Diseases 0.000 description 2
- 238000000611 regression analysis Methods 0.000 description 2
- CCEKAJIANROZEO-UHFFFAOYSA-N sulfluramid Chemical group CCNS(=O)(=O)C(F)(F)C(F)(F)C(F)(F)C(F)(F)C(F)(F)C(F)(F)C(F)(F)C(F)(F)F CCEKAJIANROZEO-UHFFFAOYSA-N 0.000 description 2
- 230000004083 survival effect Effects 0.000 description 2
- 239000000107 tumor biomarker Substances 0.000 description 2
- HSINOMROUCMIEA-FGVHQWLLSA-N (2s,4r)-4-[(3r,5s,6r,7r,8s,9s,10s,13r,14s,17r)-6-ethyl-3,7-dihydroxy-10,13-dimethyl-2,3,4,5,6,7,8,9,11,12,14,15,16,17-tetradecahydro-1h-cyclopenta[a]phenanthren-17-yl]-2-methylpentanoic acid Chemical compound C([C@@]12C)C[C@@H](O)C[C@H]1[C@@H](CC)[C@@H](O)[C@@H]1[C@@H]2CC[C@]2(C)[C@@H]([C@H](C)C[C@H](C)C(O)=O)CC[C@H]21 HSINOMROUCMIEA-FGVHQWLLSA-N 0.000 description 1
- 125000003088 (fluoren-9-ylmethoxy)carbonyl group Chemical group 0.000 description 1
- 238000009007 Diagnostic Kit Methods 0.000 description 1
- 108010015031 Glycochenodeoxycholic Acid Proteins 0.000 description 1
- 206010028980 Neoplasm Diseases 0.000 description 1
- 125000002015 acyclic group Chemical group 0.000 description 1
- 150000003862 amino acid derivatives Chemical class 0.000 description 1
- 125000003277 amino group Chemical group 0.000 description 1
- 239000000427 antigen Substances 0.000 description 1
- 108091007433 antigens Proteins 0.000 description 1
- 102000036639 antigens Human genes 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000003613 bile acid Substances 0.000 description 1
- 238000011088 calibration curve Methods 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 230000000052 comparative effect Effects 0.000 description 1
- 150000001875 compounds Chemical class 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 238000006731 degradation reaction Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 238000001647 drug administration Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000013210 evaluation model Methods 0.000 description 1
- 210000003608 fece Anatomy 0.000 description 1
- 239000007850 fluorescent dye Substances 0.000 description 1
- 150000008131 glucosides Chemical class 0.000 description 1
- GHCZAUBVMUEKKP-GYPHWSFCSA-N glycochenodeoxycholic acid Chemical compound C([C@H]1C[C@H]2O)[C@H](O)CC[C@]1(C)[C@@H]1[C@@H]2[C@@H]2CC[C@H]([C@@H](CCC(=O)NCC(O)=O)C)[C@@]2(C)CC1 GHCZAUBVMUEKKP-GYPHWSFCSA-N 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000000338 in vitro Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 150000002500 ions Chemical class 0.000 description 1
- 238000004811 liquid chromatography Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 230000036210 malignancy Effects 0.000 description 1
- 238000001819 mass spectrum Methods 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 229910052757 nitrogen Inorganic materials 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000001575 pathological effect Effects 0.000 description 1
- QKFJKGMPGYROCL-UHFFFAOYSA-N phenyl isothiocyanate Chemical compound S=C=NC1=CC=CC=C1 QKFJKGMPGYROCL-UHFFFAOYSA-N 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000004451 qualitative analysis Methods 0.000 description 1
- 238000004445 quantitative analysis Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 150000003384 small molecules Chemical class 0.000 description 1
- 239000000243 solution Substances 0.000 description 1
- 238000013179 statistical model Methods 0.000 description 1
- 239000006228 supernatant Substances 0.000 description 1
- 238000012418 validation experiment Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16B—BIOINFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR GENETIC OR PROTEIN-RELATED DATA PROCESSING IN COMPUTATIONAL MOLECULAR BIOLOGY
- G16B5/00—ICT specially adapted for modelling or simulations in systems biology, e.g. gene-regulatory networks, protein interaction networks or metabolic networks
- G16B5/20—Probabilistic models
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
- G01N33/48—Biological material, e.g. blood, urine; Haemocytometers
- G01N33/50—Chemical analysis of biological material, e.g. blood, urine; Testing involving biospecific ligand binding methods; Immunological testing
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
- G01N33/48—Biological material, e.g. blood, urine; Haemocytometers
- G01N33/50—Chemical analysis of biological material, e.g. blood, urine; Testing involving biospecific ligand binding methods; Immunological testing
- G01N33/64—Chemical analysis of biological material, e.g. blood, urine; Testing involving biospecific ligand binding methods; Immunological testing involving ketones
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
- G01N33/48—Biological material, e.g. blood, urine; Haemocytometers
- G01N33/50—Chemical analysis of biological material, e.g. blood, urine; Testing involving biospecific ligand binding methods; Immunological testing
- G01N33/68—Chemical analysis of biological material, e.g. blood, urine; Testing involving biospecific ligand binding methods; Immunological testing involving proteins, peptides or amino acids
- G01N33/6803—General methods of protein analysis not limited to specific proteins or families of proteins
- G01N33/6806—Determination of free amino acids
- G01N33/6812—Assays for specific amino acids
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
- G01N33/48—Biological material, e.g. blood, urine; Haemocytometers
- G01N33/50—Chemical analysis of biological material, e.g. blood, urine; Testing involving biospecific ligand binding methods; Immunological testing
- G01N33/68—Chemical analysis of biological material, e.g. blood, urine; Testing involving biospecific ligand binding methods; Immunological testing involving proteins, peptides or amino acids
- G01N33/6803—General methods of protein analysis not limited to specific proteins or families of proteins
- G01N33/6806—Determination of free amino acids
- G01N33/6812—Assays for specific amino acids
- G01N33/6815—Assays for specific amino acids containing sulfur, e.g. cysteine, cystine, methionine, homocysteine
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
- G01N33/48—Biological material, e.g. blood, urine; Haemocytometers
- G01N33/50—Chemical analysis of biological material, e.g. blood, urine; Testing involving biospecific ligand binding methods; Immunological testing
- G01N33/82—Chemical analysis of biological material, e.g. blood, urine; Testing involving biospecific ligand binding methods; Immunological testing involving vitamins or their receptors
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16B—BIOINFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR GENETIC OR PROTEIN-RELATED DATA PROCESSING IN COMPUTATIONAL MOLECULAR BIOLOGY
- G16B40/00—ICT specially adapted for biostatistics; ICT specially adapted for bioinformatics-related machine learning or data mining, e.g. knowledge discovery or pattern finding
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/50—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for simulation or modelling of medical disorders
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Physics & Mathematics (AREA)
- Hematology (AREA)
- Immunology (AREA)
- Urology & Nephrology (AREA)
- Chemical & Material Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Biotechnology (AREA)
- Pathology (AREA)
- Analytical Chemistry (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Medicinal Chemistry (AREA)
- Food Science & Technology (AREA)
- Biochemistry (AREA)
- Microbiology (AREA)
- General Physics & Mathematics (AREA)
- Public Health (AREA)
- Cell Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Biophysics (AREA)
- Epidemiology (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Proteomics, Peptides & Aminoacids (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Evolutionary Biology (AREA)
- Primary Health Care (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- Probability & Statistics with Applications (AREA)
- Physiology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioethics (AREA)
- Artificial Intelligence (AREA)
Abstract
The invention provides a colorectal cancer prediction system and application thereof, wherein a metabonomics method is utilized, and a series of biomarkers capable of predicting colorectal cancer occurrence risk in early stage are screened out by analyzing metabolites with significant difference in urine of colorectal cancer patients and normal persons, and a group of biomarkers is further screened out from the biomarkers to construct a colorectal cancer diagnosis model, so that the colorectal cancer prediction system can be used for conveniently, non-invasively and efficiently predicting whether an individual suffers from colorectal cancer, and meets clinical requirements.
Description
The application is a divisional application with the application number of 202210658811.5, the application date of 2022, 6 months and 10 days, and the title of the application is 'a colorectal cancer prediction system and application thereof'.
Technical Field
The invention relates to the field of medicine, in particular to a method for screening biomarkers of colorectal cancer by utilizing metabonomics and diagnosing the colorectal cancer, and particularly relates to a prediction system for predicting colorectal cancer occurrence risk by detecting urine samples and application thereof.
Background
Metabolomics (Metabolomics) is a discipline for the qualitative and quantitative analysis of small molecule metabolites with relative molecular weights less than 1000 in the body. The physiological and pathological conditions of the organism can be reflected through metabonomic analysis, and the difference between different individuals can be distinguished. With the development of mass spectrometry technology, liquid chromatography and mass spectrometry (LC-MS) have become the most important research tools in metabonomics research. At present, metabonomics has been widely used and clinically diagnosed, mainly to find metabolic markers related to disease diagnosis and treatment.
Colorectal cancer (CRC) is one of the most common malignancies worldwide and in our country. Prevention and treatment of colorectal cancer has advanced in a long-term basis and clinical practice, but overall five-year survival rates remain low, due to the lack of effective biomarkers that can early predict the risk of CRC development. Therefore, early discovery and early treatment are also the key to improving overall survival of colorectal cancer.
At present, the diagnosis of colorectal cancer is mainly based on enteroscopy and imaging. In the course of research and discovery of cancer biomarkers, omics (Omics) technology based on system biology also plays an important role. Biomarkers discovered based on the research results of genomics and proteomics have been applied to cancer research, for example, a gene diagnosis in vitro diagnostic kit for detecting KRAS gene mutation and BMP3/NDRG4 gene methylation of colorectal cancer, namely a KRAS gene mutation and BMP3/NDRG4 gene methylation and fecal occult blood combined detection kit (PCR fluorescent probe method-colloidal gold method), is approved by the national drug administration and marketed 11/9/2020 and is applied to screening of colorectal cancer high-risk population with poor enteroscope compliance.
A large number of research results from metabolomics research in recent years are being found more and more widely in various academic journals. In 2014, cross et al performed a metabolomic study of serum for 254 colorectal cancer patients and matched 254 disease-free control populations. No screening of 447 serum metabolites identified led to a direct correlation between specific determinations of which serum metabolites and risk of rectal cancer, but an interesting finding was that glycochenodeoxycholate content in bile acid and risk of rectal cancer were significantly positively correlated in the female population. In another metabolomic study for colorectal cancer, long et al first performed a non-targeted metabolomic study of the sera of 30 CRC patients and 30 healthy control humans. The few studies on early discovery and early warning of CRC above theoretically demonstrate the feasibility of finding CRC-related metabolic biomarkers through metabolomic techniques. However, the sample types required by the metabolic biomarkers for colorectal cancer reported at present are blood samples, and the gene detection for colorectal cancer risk requires a fecal sample, so that the method has no advantages in noninvasive and simple sample collection.
Therefore, there is an urgent need to find a biomarker which can be used for conveniently and rapidly sampling without wound and can be used for early predicting whether an individual has colorectal cancer risk, so that the colorectal cancer risk can be more efficiently evaluated.
Disclosure of Invention
Aiming at the problems in the prior art, the invention provides a biomarker for detecting colorectal cancer, by utilizing a metabonomics method, a series of biomarkers capable of early predicting colorectal cancer (CRC) occurrence risk are screened out by analyzing metabolites with significant difference in urine of colorectal cancer patients and normal people, and a group of biomarkers is further screened out from the biomarkers to construct a colorectal cancer diagnosis model, so that the biomarker can be used for conveniently, non-invasively and efficiently predicting whether an individual suffers from colorectal cancer, and clinical requirements are met.
In one aspect, the invention provides the use of a biomarker selected from one or more of the following: 2-piperidone, 3-hydroxyaminobenzoic acid, 3-hydroxyindole sulfate, 4-hydroxyphenylacetyl glutamine, 4-hydroxyphenylpyruvic acid, 5-hydroxyindole glucoside, 6-hydroxyindole sulfate, dimethylguanidinium valeric acid, N-acetyl-pentanediamine, N-formylmethionine, nicotinamide-N-oxide, N-methyl-4-aminobutyric acid, p-cresol glucuronate, p-cresol sulfate, phenylacetylalanine, phenylacetylglutamic acid, phenylacetylglutamine, phenylacetylhistidine, phenylacetylmethionine, phenylacetylserine, phenylacetaminoethanesulfonic acid, phenylacetylthreonine, trimethylamine-N-oxide, xanthine, tris (hydroxymethyl) aminomethane acetate.
Through non-targeted metabonomics research, two groups of urine samples of a healthy group and a colorectal cancer patient group are analyzed by using a UPLC-MS/MS high performance liquid chromatography-tandem mass spectrometry combined method, metabolites with significant differences between a colorectal cancer sample and a control sample are respectively screened by using random forest, PLS-DA, difference test and SVM, the metabolites with significant differences screened in the four statistical analysis methods are selected, and finally 26 urine metabolites are obtained and used as biomarkers for efficiently predicting whether an individual has colorectal cancer or not.
In some embodiments, the biomarker for predicting whether the individual is a colorectal cancer reagent may be a biomarker for preparing a detection reagent for a detection target, such as a sample pretreatment reagent, an antigen or an antibody, and other biological reagents and kits suitable for detecting the biomarker; can also be developed into a standardized reagent or a kit and the like suitable for the detection of the biomarkers LC-UV or LC-MS.
In some ways, the biomarker of the present invention is obtained by screening urine samples, and is particularly suitable for developing a urine detection reagent or kit for colorectal cancer prediction, and the like.
In some embodiments, when the selected biomarker is an amino acid or an amino acid derivative or contains an amino group, such as 4-hydroxyphenylacetylglutamyl, N-acetyl-pentanediamine, N-formylmethionine, N-methyl-4-aminobutyric acid, phenylacetylalanine, phenylacetglutamic acid, phenylacethistidine, phenylacetmethionine, phenylacetserine, phenylacetylethanesulfonic acid, or phenylacetthreonine, the agent or kit for detecting the biomarker can be prepared by combining an amino acid analysis method such as the PITC method, the AQC method, the OPA method, or the FMOC method, and is suitable for use in an amino acid analyzer or LC-UV.
Further, the detecting the biomarker in the urine is detecting the existence or relative abundance or concentration of the biomarker in the urine sample of the individual.
In some embodiments, it is preferred to express the relative abundance as the chromatographic peak area of the biomarker in the detection profile obtained by high performance liquid chromatography-tandem mass spectrometry. For example, if the average peak area of a biomarker in a control sample (an individual not suffering from colon cancer) is 500 and the average peak area in a colon cancer sample is 3000, the abundance of the biomarker in the colon cancer sample is 6 times that in the control sample.
Further, the biomarker is selected from one or more of: 4-hydroxyphenylpyruvic acid, dimethylguanidinopentanoic acid, N-methyl-4-aminobutyric acid, nicotinamide, p-cresol glucuronate, p-cresol sulfate, phenylacetylalanine, phenylacetylglutamine, phenylacetylmethionine, and phenylacetylthreonine.
By examining the concentration differences of the biomarkers in the urine of colorectal cancer patients and normal persons, and sorting according to the fold of difference, 10 biomarkers with the largest fold change between colorectal cancer patients and normal controls (theoretically, the compounds with the largest fold change may be the most effective markers) are further selected from 26 biomarkers, and can be used for more effectively distinguishing or predicting the risk of colorectal cancer or constructing a diagnostic model of colorectal cancer.
Further, the reagent is used for detecting biomarkers in urine.
The invention screens urine for biomarkers of colorectal cancer, the biomarkers have significant difference in urine of patients with colon cancer and patients with non-colon cancer, and by collecting urine samples, the biomarkers in urine of individuals can be detected to predict or assist in diagnosing whether the individuals have colorectal cancer or have the possibility of colorectal cancer, or the biomarkers in urine of a certain population can be detected, and the population can be further classified into a colorectal cancer group or a non-colorectal cancer group. Compared with blood and feces, urine collection has the characteristics of non-invasiveness and simplicity, and the urine biomarker has great advantages and prospects when used for preparing a colorectal cancer diagnostic reagent or diagnosing colorectal cancer.
In another aspect, the present invention provides a kit or chip for predicting whether an individual is colorectal cancer, the kit or chip comprising a detection reagent for a biomarker as described above.
Further, the reagent is used for detecting biomarkers in urine.
In a further aspect, the present invention provides a biomarker combination for predicting whether an individual is colorectal cancer, the biomarker combination comprising the following biomarkers: 4-hydroxyphenylpyruvic acid, dimethylguanidinopropionic acid, N-methyl-4-aminobutyric acid, nicotinamide, p-cresol glucuronate, p-cresol sulfate, phenylacetylalanine, phenylacetylglutamine, phenylacetylmethionine, and phenylacetylthreonine.
Further, the biomarker combination comprises the following biomarkers: 2-piperidone, 3-hydroxyaminobenzoic acid, 3-hydroxyindole sulfate, 4-hydroxyphenylacetyl glutamine, 4-hydroxyphenylpyruvic acid, 5-hydroxyindole glucoside, 6-hydroxyindole sulfate, dimethylguanidinium valeric acid, N-acetyl-pentanediamine, N-formylmethionine, nicotinamide-N-oxide, N-methyl-4-aminobutyric acid, p-cresol glucuronate, p-cresol sulfate, phenylacetylalanine, phenylacetylglutamic acid, phenylacetylglutamine, phenylacetylhistidine, phenylacetylmethionine, phenylacetylserine, phenylacetaminoethanesulfonic acid, phenylacetylthreonine, trimethylamine-N-oxide, xanthine, tris (hydroxymethyl) aminomethane acetate.
In yet another aspect, the invention provides a system for predicting whether an individual is colorectal cancer, the system comprising a data analysis module; the data analysis module is used for analyzing the detection value of the biomarker, wherein the biomarker is one or more selected from the following: 2-piperidone, 3-hydroxyaminobenzoic acid, 3-hydroxyindole sulfate, 4-hydroxyphenylacetylglutamine, 4-hydroxyphenylpyruvic acid, 5-hydroxyindole glucoside, 6-hydroxyindole sulfate, dimethylguanidinopropionic acid, N-acetyl-pentanediamine, N-formylmethionine, nicotinamide-N-oxide, N-methyl-4-aminobutyric acid, p-cresol glucuronate, p-cresol sulfate, phenylacetylalanine, phenylacetglutamic acid, phenylacetglutamine, phenylacethistidine, phenylacetmethionine, phenylacetserine, phenylacetylethanesulfonic acid, phenylacetthreonine, trimethylamine-N-oxide, xanthine, and tris (hydroxymethyl) aminomethane acetate.
Further, the biomarker is selected from one or more of: 4-hydroxyphenylpyruvic acid, dimethylguanidinopropionic acid, N-methyl-4-aminobutyric acid, nicotinamide, p-cresol glucuronate, p-cresol sulfate, phenylacetylalanine, phenylacetylglutamine, phenylacetylmethionine, phenylacetylthreonine, 3-hydroxyaminobenzoic acid, 5-hydroxyindoxyl glucoside, phenylacetylglutamic acid, phenylacetylhistidine, 2-piperidone, N-formylmethionine, phenylacetamidoethanesulfonic acid, 3-hydroxyindoxyl sulfate, 6-hydroxyindoxyl sulfate, trimethylamine-N-oxide.
Further, the biomarker is selected from one or more of: 4-hydroxyphenylpyruvic acid, dimethylguanidinopentanoic acid, N-methyl-4-aminobutyric acid, nicotinamide, p-cresol glucuronate, p-cresol sulfate, phenylacetylalanine, phenylacetylglutamine, phenylacetylmethionine, and phenylacetylthreonine.
Further, the detection value of the biomarker is a detection value for detecting a biomarker in urine.
Further, the biomarker is detected by detecting the presence or absence or relative abundance or concentration of the biomarker in a urine sample of the individual.
Further, the data analysis module adopts a random forest or logistic regression equation to construct a model for analysis.
Further, the data analysis module calculates a predictive value for predicting whether the individual is colorectal cancer by substituting the detected value of the biomarker into a logistic regression equation, thereby evaluating whether the individual is colorectal cancer.
Further, the logistic regression equation is:
z = 4-hydroxyphenylpyruvic acid 0.037986+ dimethylguanidinopentanoic acid 0.4818-N-methyl-4-aminobutyric acid 1.0077-nicotinamide 1.525-p-cresol glucuronate 0.0353-p-cresol sulfate 0.021798-phenylacetylalanine 0.1902+ phenylacetylglutamine 0.858-phenylacetylmethionine 0.118805+ phenylacetylthreonine 0.59727+0.7486;
wherein e is the base of the natural logarithm; p represents a predictive value for predicting whether an individual is colorectal cancer.
e is the base of the natural logarithm, is an infinite acyclic fractional number with a value of 2.71828 \ 8230 \8230; \8230, defined as: when n->Infinity, (1 + 1/n) n Limit of (2)
)。
Wherein, the biomarker name represents the relative abundance of the corresponding biomarker in the urine sample, namely the peak area of the biomarker in the detection map obtained by high performance liquid chromatography-tandem mass spectrometry.
Further, when P is greater than 0.5, the individual is predicted to have a high likelihood of colorectal cancer; when p is less than 0.5, the likelihood of predicting that the individual is colorectal cancer is low.
In a further aspect, the present invention provides the use of a system as described above for constructing a detection model for predicting a probability value of whether an individual is colorectal cancer.
The invention has the beneficial effects that:
1. screening 26 brand new biomarkers capable of early predicting colorectal cancer (CRC) occurrence risk;
2. screening 2, 3, 5, 10, 20 and 26 biomarkers to construct a random forest diagnosis model of the colorectal cancer, and finding that the model for constructing the colorectal cancer by adopting the 10 biomarkers is optimal;
3. comparing a random forest model constructed by 10 biomarkers with a logistic regression model, finding that the logistic regression model can further improve the detection accuracy and can be used for more efficiently predicting whether an individual suffers from colorectal cancer, wherein the AUC value reaches 0.957;
4. only need collect the sample through the urine and detect, it is noninvasive and more convenient, compare through serum or excrement and urine sample detection, have bigger advantage and prospect.
Drawings
FIG. 1 is a flowchart of screening for biomarkers in urine by metabolomics as in example 1;
FIG. 2 is the structural formula of 3-hydroxyindole sulfate in example 1;
FIG. 3 is the structural formula of 4-hydroxyphenylacetylglutamyl in example 1;
FIG. 4 is the structural formula of 5-hydroxyindole glucoside in example 1;
FIG. 5 is the structural formula of phenylacetylglutamic acid in example 1;
FIG. 6 is the structural formula of phenylacetylhistidine in example 1;
FIG. 7 is the structural formula of phenylacetyl methionine in example 1;
FIG. 8 is the structural formula of phenylacetylthreonine in example 1;
fig. 9 is a comparative diagram of prediction accuracy in constructing a colorectal cancer diagnosis model by selecting 2, 3, 5, 10, 20, 26 biomarkers from the 26 biomarkers in example 2, respectively;
FIG. 10 is a ROC curve for the model of whether colorectal cancer was predicted constructed in example 2;
FIG. 11 is an analytical profile of the random forest model for predicting whether colorectal cancer is present or absent in example 2;
FIG. 12 is a ROC curve of the logistic regression model constructed in example 2 to predict whether colorectal cancer is present;
FIG. 13 is an analysis graph of the logistic regression model for predicting whether colorectal cancer is present or absent in example 2;
FIG. 14 shows the result of accuracy evaluation of the colorectal cancer model prediction in example 3.
Detailed Description
The invention will be described in further detail below with reference to the drawings and examples, which are intended to facilitate the understanding of the invention without limiting it in any way. The reagents used in this example were all known products and were obtained by purchasing commercially available products.
Example 1 Metabolic omics screening for biomarkers of colorectal cancer in urine
In this example, two groups of urine samples of healthy and colorectal cancer patients were first analyzed by non-targeted metabonomics studies using UPLC-MS/MS ultra performance liquid chromatography-tandem mass spectrometry. Secondly, metabolites with significant difference between the colorectal cancer sample and a control sample are respectively screened by four statistical methods of random forest, PLS-DA, volcano and SVM, the metabolites with significant difference screened by the four statistical analysis methods are selected, finally 26 urine metabolites are obtained to be used as biomarkers, and the roles of the biomarkers in the diagnosis or differentiation of colorectal cancer are verified (a flow chart is shown in figure 1).
The method comprises the following specific steps:
1. experimental methods
(1) Sample collection
Urine samples were collected from patients with colorectal cancer and control individuals (non-colorectal cancer individuals), 50 cases each. Wherein the patient with colorectal cancer is an individual who is confirmed to have colorectal cancer through enteroscopy.
(2) Sample processing
According to the proportion of 1. From each sample, 4 100. Mu.L portions of the supernatant were transferred to 4 sample plates, blown dry with nitrogen, and the reconstituted solution was added for subsequent LC-MS/MS detection.
(3) LC-MS/MS detection and data processing
Extracting m/z ions from original mass spectrum data obtained by LC-MS/MS detection, searching a database to retrieve and identify metabolites, checking chromatographic peak integration of the metabolites to obtain peak areas, performing data normalization and missing value filling, and performing subsequent biographical analysis on an obtained data matrix, wherein the obtained data matrix comprises random forest, PLS-DA (partial least squares), volcano (volcanic chart) and SVM (support vector machine), and a ranking list of the different metabolites which are most effective for sample grouping between colorectal cancer samples and control samples is respectively screened. Finally, the metabolites screened in all four methods were selected as biomarkers for colorectal cancer.
2. Results of the experiment
32, 41, 35 and 52 differential metabolites were screened by random forest, PLS-DA, differential test and SVM, respectively, wherein 26 metabolites, namely 26 biomarkers, were screened in the four data analysis methods, as shown in Table 1.
TABLE 1, 25 colorectal cancer biomarkers
Example 2: colorectal cancer prediction model
This example uses the single biomarker or combination of biomarkers selected in example 1 to establish a predictive or diagnostic model for colorectal cancer. These models are used to distinguish colorectal cancer from non-colorectal cancer, or to screen a population for colorectal cancer patients, or to predict whether an individual is a colorectal cancer patient or the likelihood that an individual will have colorectal cancer, as follows.
1. Single biomarker
R language software is applied to process the data. According to the grouping of colorectal cancer patients and non-colorectal cancer crowds, the concentration change of 26 biomarkers in urine samples of the colorectal cancer patients and the non-colorectal cancer crowds is judged, all detection results are subjected to LASSO regression analysis to establish a mathematical model for predicting whether an individual has colorectal cancer, and the effectiveness of the regression model is evaluated by adopting a calibration curve and an ROC curve method.
The analysis results show that 26 biomarkers have obvious correlation with whether colorectal cancer is suffered, and the analysis results are shown in tables 2 and 3.
TABLE 2 comparison of the results of the correlation test of the 26 biomarkers with the presence or absence of colorectal cancer
TABLE 3 results of ROC analysis of Single biomarkers
The correlation between the concentration change of the 26 biomarkers and whether the patients suffer from colorectal cancer can be distinguished by OR values, p-values and the like in table 2, and can also be distinguished by AUC values and the like in table 3, wherein the OR values and the AUC values are most intuitive and obvious. The higher the OR value, the more the effect on the indicator is, the more pronounced the indicator exposure is, for persons suffering from colorectal cancer compared to non-colorectal cancer. The higher the AUC value, the more accurately the biomarker can distinguish the colorectal cancer population from the non-colorectal cancer population.
As can be seen from table 2, the concentration changes of the 26 biomarkers have obvious correlation with whether colorectal cancer is suffered, wherein the correlation of phenylacetylglutamine is highest, the OR value reaches 2.36, and the OR value reaches 1.82 after phenylacetylthreonine.
As can be seen from Table 3, when the concentration change of any one of the 26 biomarkers is independently adopted to distinguish the colorectal cancer population from the non-colorectal cancer population, the AUC value can reach over 0.63, and the accuracy is high, wherein the AUC value is phenylacetylglutamine at the highest, the AUC value reaches 0.7876, p-cresol glucuronate at the next and the AUC value reaches 0.7836.
2. Combination of multiple biomarkers
Although a single biomarker can be used for distinguishing colorectal cancer from non-colorectal cancer urine samples or predicting colorectal cancer, the combination of multiple biomarkers is generally more accurate in distinguishing or predicting colorectal cancer.
However, a single biomarker with higher accuracy in predicting colorectal cancer does not necessarily play a larger role in the combination when combined with other one or more biomarkers, and the more the number of biomarkers is, the higher the accuracy of prediction (AUC value) of the combination is, and thus a large number of validation experiments are required.
Since the AUC and OR values of the biomarkers are biased toward evaluating the relative importance of the variables in the statistical model and are not suitable for use in constructing the model for the preferred variables, this example preferably uses 2, 3, 5, 10, 20, 26 biomarkers with the highest Fold difference in concentration in the urine samples of colorectal cancer and non-colorectal cancer for constructing the diagnostic model for colorectal cancer, and the concentration Fold difference of the 26 biomarkers in the urine samples of colorectal cancer and non-colorectal cancer (Fold Change, fold Change = the expression mean of the disease sample divided by the expression mean of the normal sample), ranked from high to low, and the results are shown in table 4.
Table 4, concentration fold difference ranking of 26 biomarkers in colorectal and non-colorectal cancer urine samples
According to the concentration difference multiples of the 26 biomarkers in the urine samples of colorectal cancer and non-colorectal cancer provided in table 4, 2, 3, 5, 10, 20 and 26 biomarkers in the 26 biomarkers are selected respectively in the embodiment, and a colorectal cancer diagnosis model is constructed through random forests.
Wherein the 2 biomarkers are two biomarkers (p-cresol sulfate and phenylacetyl threonine) ranked in the 1 st and the 2 nd in table 4, and the constructed random forest model has an information gain ratio (GINI coefficient) of the p-cresol sulfate of 25.31 and an average descent precision (meanDeseraceAccuracy) of 21.17; the GINI coefficient of phenylacetyl threonine was 24.22, and the average reduction accuracy was 16.71.
The 3 biomarkers are three biomarkers ranked from 1 st to 3 rd in table 4, and in the constructed random forest model, the GINI coefficient of p-cresol sulfate is 15.43, and the average reduction precision is 16.37; the GINI coefficient of phenylacetyl threonine is 15.75, and the average reduction precision is 15.04; the GINI coefficient of N-methyl-4-aminobutyric acid was 18.33, and the average reduction accuracy was 24.42.
The 5 biomarkers are five biomarkers ranked from 1 st to 5 th in table 4, and in the constructed random forest model, the GINI coefficient of p-cresol sulfate is 7.86, and the average reduction precision is 10.99; the GINI coefficient of phenylacetyl threonine is 6.39, and the average reduction precision is 5.58; the GINI coefficient of the N-methyl-4-aminobutyric acid is 13.73, and the average reduction precision is 25.36; the GINI coefficient of 4-hydroxyphenylpyruvic acid is 10.43, and the average reduction precision is 45.38; the GINI coefficient of phenylacetylmethionine was 11.05, and the average falling accuracy was 18.74.
The 10 biomarkers are ten biomarkers ranked from 1 st to 10 th in table 4, and in the constructed random forest model, the GINI coefficient of p-cresol sulfate is 3.64, and the average reduction precision is 7.56; the GINI coefficient of phenylacetyl threonine is 2.46, and the average reduction precision is 4.80; the GINI coefficient of the N-methyl-4-aminobutyric acid is 8.04, and the average reduction precision is 18.60; the GINI coefficient of 4-hydroxyphenylpyruvic acid is 6.25, and the average reduction precision is 12.60; the GINI coefficient of the phenylacetyl methionine is 6.26, and the average reduction precision is 12.85; the GINI coefficient of the p-cresol glucuronate is 5.20, and the average reduction precision is 11.07; the GINI coefficient of nicotinamide is 6.56, and the average degradation precision is 12.51; the GINI coefficient of the phenylacetylalanine is 3.18, and the average reduction precision is 6.30; the GINI coefficient of the phenylacetylglutamine is 4.47, and the average reduction precision is 6.83; the GINI coefficient of dimethylguanidinopentanic acid was 3.43 with an average drop of 9.16.
The 20 biomarkers are 20 biomarkers ranked from 1 st to 20 th in table 4, and in the constructed random forest model, the GINI coefficient of p-cresol sulfate is 2.36, and the average reduction precision is 6.21; the GINI coefficient of phenylacetyl threonine is 1.73, and the average reduction precision is 4.02; the GINI coefficient of the N-methyl-4-aminobutyric acid is 5.92, and the average reduction precision is 16.23; the GINI coefficient of 4-hydroxyphenylpyruvic acid is 4.10, and the average reduction precision is 9.28; the GINI coefficient of the phenylacetyl methionine is 3.79, and the average reduction precision is 10.13; the GINI coefficient of the p-cresol glucuronate is 3.77, and the average reduction precision is 9.49; the nicotinamide GINI coefficient is 4.67, and the average reduction precision is 11.61; the GINI coefficient of the phenylacetylalanine is 2.26, and the average reduction precision is 5.84; the GINI coefficient of the phenylacetylglutamine is 2.67, and the average reduction precision is 7.71; the GINI coefficient of the dimethylguanidinopentanoic acid is 2.00, and the average reduction precision is 7.77; the GINI coefficient of the 3-hydroxyaminobenzoic acid is 2.03, and the average reduction precision is 4.32; the GINI coefficient of 5-hydroxyindole glucoside is 2.69, and the average reduction precision is 5.66; the GINI coefficient of phenylacetylglutamic acid is 1.59, and the average reduction precision is 4.38; the GINI coefficient of the phenylacetyl histidine is 1.62, and the average reduction precision is 4.96; the GINI coefficient of the 2-piperidone is 1.57, and the average reduction precision is 1.85; the GINI coefficient of the N-formyl methionine is 1.45, and the average reduction precision is 2.81; the GINI coefficient of the phenylacetyl amino ethanesulfonic acid is 1.28, and the average reduction precision is 0.79; the GINI coefficient of the 3-hydroxyindole sulfate is 1.41, and the average reduction precision is 3.51; the GINI coefficient of the 6-hydroxyindole sulfate is 1.57, and the average reduction precision is 1.93; the GINI coefficient of trimethylamine-N-oxide was 1.02, and the average falling accuracy was 2.61.
The 26 biomarkers are the 26 biomarkers ranked from 1 st to 26 th in table 4, and in the constructed random forest model, the GINI coefficient of p-cresol sulfate is 1.69, and the average reduction precision is 7.04; the GINI coefficient of phenylacetyl threonine is 1.04, and the average reduction precision is 2.80; the GINI coefficient of the N-methyl-4-aminobutyric acid is 3.57, and the average reduction precision is 12.93; the GINI coefficient of 4-hydroxyphenyl pyruvic acid was 2.45, and the average falling accuracy was 5.50; the GINI coefficient of the phenylacetyl methionine is 2.68, and the average reduction precision is 7.68; the GINI coefficient of the p-cresol glucuronate is 2.61, and the average reduction precision is 8.31; the nicotinamide GINI coefficient is 2.56, and the average reduction precision is 8.02; the GINI coefficient of the phenylacetylalanine is 1.47, and the average reduction precision is 4.84; the GINI coefficient of the phenylacetylglutamine is 1.83, and the average reduction precision is 5.74; the GINI coefficient of the dimethylguanidinopentanic acid is 1.34, and the average reduction precision is 3.76; the GINI coefficient of the 3-hydroxyaminobenzoic acid is 1.14, and the average reduction precision is 4.11; the GINI coefficient of 5-hydroxyindolylglucoside was 1.76, the average reduction precision was 4.39; the GINI coefficient of phenylacetylglutamic acid is 0.88, and the average reduction precision is 3.11; the GINI coefficient of the phenylacetyl histidine is 1.00, and the average reduction precision is 4.79; the GINI coefficient of the 2-piperidone is 1.20, and the average reduction precision is 1.80; the GINI coefficient of the N-formyl methionine is 0.79, and the average reduction precision is 2.15; the GINI coefficient of the phenylacetyl amino ethanesulfonic acid is 0.58, and the average reduction precision is 2.70; the GINI coefficient of the 3-hydroxyindole sulfate is 0.96, and the average reduction precision is 3.64; the GINI coefficient of the 6-hydroxyindole sulfate is 0.73, and the average reduction precision is 2.70; the GINI coefficient of trimethylamine-N-oxide is 0.74, and the average reduction precision is 2.33; the GINI coefficient of the 4-hydroxyphenylacetylglutamine is 0.83, and the average reduction precision is 4.61; the GINI coefficient of the N-acetyl-pentanediamine is 2.22, and the average reduction precision is 7.72; the GINI coefficient of the tris acetate is 2.48, and the average reduction precision is 8.06; the GINI coefficient of xanthine is 2.70, and the average reduction precision is 8.67; the nicotinamide-N-oxide has a GINI coefficient of 8.21 and an average reduction precision of 16.94; phenylacetylserine had a GINI coefficient of 2.01 and an average reduction accuracy of 7.16.
The AUC values and 95% CL confidence intervals were calculated for the 6 random forest diagnostic models constructed using 2, 3, 5, 10, 20, 26 biomarkers as described above, respectively, and the results are shown in FIG. 9.
As can be seen from fig. 9, the AUC value of the model constructed by selecting the two top-ranked biomarkers from the 26 biomarkers can only reach 0.922, the 95% cl confidence interval is 0.718-0.999, the AUC value gradually increases with the increase of the number of the selected biomarkers, the 95% cl confidence interval gradually decreases, when 10 biomarkers are selected to construct the diagnostic model of colorectal cancer, the AUC value reaches 0.935, the 95% cl confidence interval is 0.842-0.998, and when the biomarker species number further increases to 20 or 26, the space for the AUC to continue to increase is very limited, and the confidence interval becomes large; in addition, compared with 20 and 26 biomarkers, 10 biomarkers are adopted to construct the model, so that the number of variables can be reduced, and the complexity of the model can be reduced. Therefore, the 10 top-ranked biomarkers in table 4 are preferably used to construct a diagnostic model of colorectal cancer, which not only achieves very good prediction accuracy, but also is simpler and more convenient.
The detection values of the biomarkers in the urine samples of 42 clinically known colorectal cancer patients and 42 non-colorectal cancer patients are used as a total data set, and are analyzed by a random forest model of 10 biomarkers, the analysis map is shown in fig. 11, as can be seen from fig. 11, when the random forest model constructed by using 10 biomarkers is used for predicting colorectal cancer, certain errors (of course, the errors are difficult to avoid) exist, 37 of the 42 colorectal cancer patients are detected, 5 of the 42 non-colorectal cancer patients are assigned to the colorectal cancer patient area, and the accuracy is 88%. FIG. 11 shows that when the predicted value P is greater than 0.5, the likelihood of predicting an individual to be colorectal cancer is high; when the predicted value p is less than 0.5, the likelihood of predicting that the individual is colorectal cancer is low.
Adopting 10 biomarkers in the top 10 of the Fold Change ranking, performing multifactorial regression analysis, and establishing a logistic regression evaluation model for predicting whether an individual has colorectal cancer:
z = 4-hydroxyphenylpyruvic acid 0.037986+ dimethylguanidinopentanoic acid 0.4818-N-methyl-4-aminobutyric acid 1.0077-nicotinamide 1.525-p-cresol glucuronate 0.0353-p-cresol sulfate 0.021798-phenylacetylalanine 0.1902+ phenylacetylglutamine 0.858-phenylacetylmethionine 0.118805+ phenylacetylthreonine 0.59727+0.7486;
wherein e is the base of the natural logarithm; p represents a predictor of whether an individual is predicted to be colorectal cancer; the biomarker name represents the relative abundance of the corresponding biomarker in the urine sample, namely the peak area of the biomarker in a detection map obtained by high performance liquid chromatography-tandem mass spectrometry.
The ROC curve of the logistic regression model for predicting whether an individual has colorectal cancer provided in this example is shown in fig. 12, and the AUC value reaches 0.957, which is significantly improved compared with the random forest model of 10 biomarkers.
Using the logistic regression model for predicting whether an individual has colorectal cancer, 50 patients with colorectal cancer and 50 patients with non-colorectal cancer, which are clinically known, were analyzed as a total data set, and the results of the analysis are shown in FIG. 13 and Table 5, where
TABLE 5 prediction of individual colorectal cancer model analysis results
As can be seen from fig. 13 and table 5, the logistic regression assessment model for predicting whether an individual has colorectal cancer constructed by 10 biomarkers was used for analysis, 45 of 50 patients with colorectal cancer were detected, and 5 of 50 patients with non-colorectal cancer were classified into colorectal cancer patients, and the accuracy rate was up to 90% or more, and the accuracy was improved.
As can also be seen from fig. 13, when P is 0.5, it can be regarded as a cut-off point for judgment, and when P is greater than 0.5, it is predicted that the possibility that the individual is colorectal cancer is high; when p is less than 0.5, the individual is predicted to have a low likelihood of colorectal cancer.
Example 3: assessment of whether to predict colorectal cancer model
This example was conducted to evaluate the accuracy of clinical application of the model for predicting colorectal cancer constructed in example 2, wherein the 42 patients with colorectal cancer and 42 patients with non-colorectal cancer were used as a total data set, 8 patients with CRC and normal persons (non-CRC patients) were randomly selected from the data set, urine samples were taken, and the relative abundance of 10 biomarkers in the model was measured according to the sample processing method in example 1, thereby calculating the predicted value P from the model to predict whether the individual has colorectal cancer, and the results are shown in fig. 14.
As can be seen from fig. 14, 8 patients with colorectal cancer were all detected, and one of 8 normal persons was predicted to be colorectal cancer with an accuracy of 93.75%.
Although the present invention is disclosed above, the present invention is not limited thereto. Various changes and modifications may be effected therein by one skilled in the art without departing from the spirit and scope of the invention as defined in the appended claims.
Claims (10)
1. A system for predicting whether an individual is colorectal cancer, the system comprising a data analysis module; the data analysis module is used for analyzing the detection value of the biomarker, wherein the biomarker is one or more selected from the following: 2-piperidone, 3-hydroxyaminobenzoic acid, 3-hydroxyindole sulfate, 4-hydroxyphenylacetylglutamine, 4-hydroxyphenylpyruvic acid, 5-hydroxyindole glucoside, 6-hydroxyindole sulfate, dimethylguanidinopropionic acid, N-acetyl-pentanediamine, N-formylmethionine, nicotinamide-N-oxide, N-methyl-4-aminobutyric acid, p-cresol glucuronate, p-cresol sulfate, phenylacetylalanine, phenylacetglutamic acid, phenylacetglutamine, phenylacethistidine, phenylacetmethionine, phenylacetserine, phenylacetylethanesulfonic acid, phenylacetthreonine, trimethylamine-N-oxide, xanthine, and tris (hydroxymethyl) aminomethane acetate.
2. The system of claim 1, wherein the biomarker is selected from one or more of the following: 4-hydroxyphenylpyruvic acid, dimethylguanidinopentanoic acid, N-methyl-4-aminobutyric acid, nicotinamide, p-cresol glucuronate, p-cresol sulfate, phenylacetylalanine, phenylacetylglutamine, phenylacetylmethionine, phenylacetylthreonine, 3-hydroxyaminobenzoic acid, 5-hydroxyindole glucoside, phenylacetylglutamic acid, phenylacetylhistidine, 2-piperidone, N-formylmethionine, phenylacetylaminoethanesulfonic acid, 3-hydroxyindole sulfate, 6-hydroxyindole sulfate, trimethylamine-N-oxide.
3. The system of claim 2, wherein the biomarker is selected from one or more of the following: 4-hydroxyphenylpyruvic acid, dimethylguanidinopropionic acid, N-methyl-4-aminobutyric acid, nicotinamide, p-cresol glucuronate, p-cresol sulfate, phenylacetylalanine, phenylacetylglutamine, phenylacetylmethionine, and phenylacetylthreonine.
4. The system of claim 3, wherein the detection of the biomarker is a detection of a biomarker in the urine.
5. The system of claim 4, wherein the biomarker is detected as the presence or relative abundance or concentration of the biomarker in a urine sample from the individual.
6. The system of claim 5, wherein the data analysis module employs a random forest or logistic regression equation to build a model for analysis.
7. The system of claim 6, wherein the data analysis module evaluates whether the individual is colorectal cancer by substituting the detected values of the biomarkers into a logistic regression equation to calculate a predictive value that predicts whether the individual is colorectal cancer.
8. Use of the system of any one of claims 1 to 7 for constructing a detection model for predicting a probability value of whether an individual is colorectal cancer.
9. Use of a biomarker for the preparation of an agent for predicting whether an individual is colorectal cancer, wherein the biomarker is selected from one or more of: 2-piperidone, 3-hydroxyaminobenzoic acid, 3-hydroxyindole sulfate, 4-hydroxyphenylacetyl glutamine, 4-hydroxyphenylpyruvic acid, 5-hydroxyindole glucoside, 6-hydroxyindole sulfate, dimethylguanidinium valeric acid, N-acetyl-pentanediamine, N-formylmethionine, nicotinamide-N-oxide, N-methyl-4-aminobutyric acid, p-cresol glucuronate, p-cresol sulfate, phenylacetylalanine, phenylacetylglutamic acid, phenylacetylglutamine, phenylacetylhistidine, phenylacetylmethionine, phenylacetylserine, phenylacetaminoethanesulfonic acid, phenylacetylthreonine, trimethylamine-N-oxide, xanthine, tris (hydroxymethyl) aminomethane acetate.
10. The use of claim 9, wherein the biomarker is selected from one or more of: 4-hydroxyphenylpyruvic acid, N-methyl-4-aminobutyric acid, p-cresol sulfate, phenylacetyl methionine and phenylacetyl threonine.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211073050.3A CN115440375A (en) | 2022-06-10 | 2022-06-10 | Colorectal cancer prediction system and application thereof |
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210658811.5A CN114758719B (en) | 2022-06-10 | 2022-06-10 | Colorectal cancer prediction system and application thereof |
| CN202211073050.3A CN115440375A (en) | 2022-06-10 | 2022-06-10 | Colorectal cancer prediction system and application thereof |
Related Parent Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210658811.5A Division CN114758719B (en) | 2022-06-10 | 2022-06-10 | Colorectal cancer prediction system and application thereof |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115440375A true CN115440375A (en) | 2022-12-06 |
Family
ID=82336377
Family Applications (2)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211073050.3A Pending CN115440375A (en) | 2022-06-10 | 2022-06-10 | Colorectal cancer prediction system and application thereof |
| CN202210658811.5A Active CN114758719B (en) | 2022-06-10 | 2022-06-10 | Colorectal cancer prediction system and application thereof |
Family Applications After (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210658811.5A Active CN114758719B (en) | 2022-06-10 | 2022-06-10 | Colorectal cancer prediction system and application thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (2) | CN115440375A (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116519954B (en) * | 2023-06-28 | 2023-10-27 | 杭州广科安德生物科技有限公司 | Colorectal cancer detection model construction method, colorectal cancer detection model construction system and biomarker |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA2856167A1 (en) * | 2011-11-11 | 2013-05-16 | Metabolon, Inc. | Biomarkers for bladder cancer and methods using the same |
| CN107064508A (en) * | 2017-04-21 | 2017-08-18 | 深圳大学 | Aid in colorectal cancer early diagnosis and molecular marker and its application of Prognosis scoveillance |
| CN109557311B (en) * | 2018-12-13 | 2022-02-15 | 中南大学湘雅医院 | Colorectal cancer diagnosis marker, colorectal cancer detection product and application thereof |
| US11840720B2 (en) * | 2019-12-23 | 2023-12-12 | Metabolomic Technologies Inc. | Urinary metabolomic biomarkers for detecting colorectal cancer and polyps |
| CN114839298B (en) * | 2019-12-28 | 2024-06-07 | 中精普康(北京)医药科技有限公司 | Biomarker for detecting colorectal cancer or adenoma and method thereof |
| KR102343240B1 (en) * | 2020-03-27 | 2021-12-23 | 서울대학교산학협력단 | Biomarker composition for predicition of cetuximab treatment effects in colorectal cancer |
-
2022
- 2022-06-10 CN CN202211073050.3A patent/CN115440375A/en active Pending
- 2022-06-10 CN CN202210658811.5A patent/CN114758719B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN114758719A (en) | 2022-07-15 |
| CN114758719B (en) | 2022-10-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3151665B1 (en) | Methods and systems for determining autism spectrum disorder risk | |
| CN110196335A (en) | Biomarker relevant to renal function and its application method | |
| US20170059581A1 (en) | Methods for diagnosis and prognosis of inflammatory bowel disease using cytokine profiles | |
| US20150056605A1 (en) | Identification of blood based metabolite biomarkers of pancreatic cancer | |
| US20180100858A1 (en) | Protein biomarker panels for detecting colorectal cancer and advanced adenoma | |
| EP3257953B1 (en) | Methods of identification, assessment, prevention and therapy of lung diseases and kits thereof including gender-based disease identification, assessment, prevention and therapy | |
| Moledina et al. | Identification and validation of urinary CXCL9 as a biomarker for diagnosis of acute interstitial nephritis | |
| WO2015164616A1 (en) | Biomarkers for detection of tuberculosis | |
| CN114758719B (en) | Colorectal cancer prediction system and application thereof | |
| CN114755422B (en) | Biomarker for colorectal cancer detection and application thereof | |
| WO2016123058A1 (en) | Biomarkers for detection of tuberculosis risk | |
| CN115684451A (en) | Esophageal squamous carcinoma lymph node metastasis diagnosis marker based on metabonomics and application thereof | |
| WO2015153860A1 (en) | Glomerular filtration rate biomarkers and uses thereof | |
| US20230402131A1 (en) | Biomarker and diagnosis system for colorectal cancer detection | |
| WO2016182967A1 (en) | Biomarkers for detection of tuberculosis risk | |
| Vessby et al. | AGPAT1 as a novel colonic biomarker for discriminating between ulcerative colitis with and without primary sclerosing cholangitis | |
| CN115372628B (en) | Metabolic marker related to transthyretin amyloidosis and application thereof | |
| CN112255333B (en) | Ovarian tumor urine metabolic marker and application thereof | |
| US20240230622A9 (en) | Methods and Systems for Determining Autism Spectrum Disorder Risk | |
| US20240133865A1 (en) | Methods and Systems for Determining Autism Spectrum Disorder Risk | |
| WO2024064322A2 (en) | Methods of assessing tobacco use status | |
| CN117330760A (en) | Plasma exosome marker for early diagnosis of pancreatic cancer and application | |
| WO2023211771A1 (en) | Methods for sample quality assessment | |
| CA3233138A1 (en) | Lung cancer prediction and uses thereof | |
| CN117214276A (en) | Application of plasma lipid molecules in lung cancer diagnosis |
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 | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: 310000 room 701-6, building 2, Zijin Qizhen building, No. 859 Shixiang West Road, Sandun Town, Xihu District, Hangzhou City, Zhejiang Province Applicant after: Kailaipu Technology Co.,Ltd. Address before: 310000 room 701-6, building 2, Zijin Qizhen building, No. 859 Shixiang West Road, Sandun Town, Xihu District, Hangzhou City, Zhejiang Province Applicant before: HANGZHOU CALIBRA DIAGNOSTICS CO.,LTD. |