CN114250288B - Use of DNA methylation profiles and prepulse inhibition profiles in schizophrenia diagnosis - Google Patents

Use of DNA methylation profiles and prepulse inhibition profiles in schizophrenia diagnosis Download PDF

Info

Publication number
CN114250288B
CN114250288B CN202111281022.6A CN202111281022A CN114250288B CN 114250288 B CN114250288 B CN 114250288B CN 202111281022 A CN202111281022 A CN 202111281022A CN 114250288 B CN114250288 B CN 114250288B
Authority
CN
China
Prior art keywords
dna methylation
prepulse inhibition
schizophrenia
model
individual
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202111281022.6A
Other languages
Chinese (zh)
Other versions
CN114250288A (en
Inventor
张晓斌
杜向东
田晴
殷光中
朱峰
王传跃
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Suzhou Guangji Hospital
Original Assignee
Suzhou Guangji Hospital
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Suzhou Guangji Hospital filed Critical Suzhou Guangji Hospital
Priority to CN202111281022.6A priority Critical patent/CN114250288B/en
Publication of CN114250288A publication Critical patent/CN114250288A/en
Application granted granted Critical
Publication of CN114250288B publication Critical patent/CN114250288B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • C—CHEMISTRY; METALLURGY
    • C12—BIOCHEMISTRY; BEER; SPIRITS; WINE; VINEGAR; MICROBIOLOGY; ENZYMOLOGY; MUTATION OR GENETIC ENGINEERING
    • C12Q—MEASURING OR TESTING PROCESSES INVOLVING ENZYMES, NUCLEIC ACIDS OR MICROORGANISMS; COMPOSITIONS OR TEST PAPERS THEREFOR; PROCESSES OF PREPARING SUCH COMPOSITIONS; CONDITION-RESPONSIVE CONTROL IN MICROBIOLOGICAL OR ENZYMOLOGICAL PROCESSES
    • C12Q1/00—Measuring or testing processes involving enzymes, nucleic acids or microorganisms; Compositions therefor; Processes of preparing such compositions
    • C12Q1/68—Measuring or testing processes involving enzymes, nucleic acids or microorganisms; Compositions therefor; Processes of preparing such compositions involving nucleic acids
    • C12Q1/6876—Nucleic acid products used in the analysis of nucleic acids, e.g. primers or probes
    • C12Q1/6883—Nucleic acid products used in the analysis of nucleic acids, e.g. primers or probes for diseases caused by alterations of genetic material
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01H—MEASUREMENT OF MECHANICAL VIBRATIONS OR ULTRASONIC, SONIC OR INFRASONIC WAVES
    • G01H17/00—Measuring mechanical vibrations or ultrasonic, sonic or infrasonic waves, not provided for in the preceding groups
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/243—Classification techniques relating to the number of classes
    • G06F18/24323—Tree-organised classifiers
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • 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
    • G16B15/00—ICT specially adapted for analysing two-dimensional or three-dimensional molecular structures, e.g. structural or functional relations or structure alignment
    • 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
    • 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
    • G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/50—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for simulation or modelling of medical disorders
    • C—CHEMISTRY; METALLURGY
    • C12—BIOCHEMISTRY; BEER; SPIRITS; WINE; VINEGAR; MICROBIOLOGY; ENZYMOLOGY; MUTATION OR GENETIC ENGINEERING
    • C12Q—MEASURING OR TESTING PROCESSES INVOLVING ENZYMES, NUCLEIC ACIDS OR MICROORGANISMS; COMPOSITIONS OR TEST PAPERS THEREFOR; PROCESSES OF PREPARING SUCH COMPOSITIONS; CONDITION-RESPONSIVE CONTROL IN MICROBIOLOGICAL OR ENZYMOLOGICAL PROCESSES
    • C12Q2600/00—Oligonucleotides characterized by their use
    • C12Q2600/154—Methylation markers

Landscapes

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Physics & Mathematics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Medical Informatics (AREA)
  • Public Health (AREA)
  • General Health & Medical Sciences (AREA)
  • Chemical & Material Sciences (AREA)
  • Data Mining & Analysis (AREA)
  • Theoretical Computer Science (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Pathology (AREA)
  • Biomedical Technology (AREA)
  • General Engineering & Computer Science (AREA)
  • Organic Chemistry (AREA)
  • Spectroscopy & Molecular Physics (AREA)
  • Primary Health Care (AREA)
  • General Physics & Mathematics (AREA)
  • Epidemiology (AREA)
  • Databases & Information Systems (AREA)
  • Evolutionary Biology (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Proteomics, Peptides & Aminoacids (AREA)
  • Biophysics (AREA)
  • Biotechnology (AREA)
  • Analytical Chemistry (AREA)
  • Evolutionary Computation (AREA)
  • Molecular Biology (AREA)
  • Genetics & Genomics (AREA)
  • Wood Science & Technology (AREA)
  • Zoology (AREA)
  • Artificial Intelligence (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Software Systems (AREA)
  • Microbiology (AREA)
  • Biochemistry (AREA)
  • Immunology (AREA)
  • Mathematical Physics (AREA)
  • Probability & Statistics with Applications (AREA)
  • Physiology (AREA)

Abstract

The invention discloses the application of DNA methylation characteristics and prepulse inhibition characteristics in schizophrenia diagnosis, uses the DNA methylation characteristics and the prepulse inhibition characteristics as clinical biomarkers for the first time, is jointly applied to diagnosis and identification of first-onset schizophrenia, ultra-high risk groups and healthy groups, has the advantages of objectivity, accuracy, effectiveness and the like, has very good application prospect in clinic, and lays a foundation for early identification and intervention of schizophrenia.

Description

Use of DNA methylation profiles and prepulse inhibition profiles in schizophrenia diagnosis
Technical Field
The invention belongs to the technical field of biomedicine, and particularly relates to application of DNA methylation characteristics and prepulse inhibition characteristics in schizophrenia diagnosis.
Background
Schizophrenia (SCH) is a serious psychotic disorder characterized by abnormal social behaviors and is a complex psychotic disorder whose etiology has not yet been clarified. The main clinical manifestations of the disease include various disorders of perception, thinking, emotion, behavior, etc., and the incoordination of mental activities, reducing social participation degree, and lack of motivation. Schizophrenic patients also tend to have additional mental health problems, such as anxiety, depressive states, and the like. Seriously affecting the physical function and the quality of life of the patient. Symptoms associated with schizophrenic patients generally appear and progress gradually from puberty. Epidemiological investigation shows that the worldwide lifetime prevalence of schizophrenia is about 1%, and it is estimated that 700-800 million patients with schizophrenia exist in China, so that treatment and rehabilitation costs and social and household burdens are enormous each year.
Most patients with schizophrenia have many abnormalities in perception, thinking, speech, behavior and other aspects (also called "subclinical state") in a period before the first onset, which is called the Prodromal stage of schizophrenia (Prodromal stage), and common symptoms in this period include: suspicion, thoughts, depression, anxiety, mood swings, irritability, memory disorders, inattention, changes in self, other people and external perception, and sleep disorders, physical discomfort, etc. People with prodromal stage manifestations are more likely to develop schizophrenia, such people are currently called "Ultra High Risk (UHR)", the proportion of the schizophrenic Ultra high risk people to be transformed into schizophrenia in the follow-up period of 1-2 years is higher, and the transformation rate can reach 9% -76%. For patients with First-onset schizophrenia (FES), prevention of recurrence after successful treatment is even more important.
Although some stricter diagnosis standards such as DSM-5 and ICD-10 exist internationally, and some common diagnosis standards such as Chinese mental disorder classification and diagnosis standard CCMD-3 exist domestically, the current diagnosis method for schizophrenia mainly depends on doctors to make comprehensive judgment according to the detailed disease history and mental symptoms of patients and then according to the onset age, disease period, disease course and the like of the patients, and the diagnosis results have larger difference due to different subjective experiences of the doctors, so the current diagnosis method for schizophrenia has the problems of strong subjectivity, lack of objective diagnosis indexes and the like. In recent years, in order to make diagnosis of schizophrenia more objective, reduce human factors and improve the consistency and accuracy of diagnosis, researchers around the world are constantly dedicated to searching biomarkers of schizophrenia and establishing effective detection methods in order to improve the consistency and accuracy of diagnosis of schizophrenia.
Disclosure of Invention
In view of this, the present invention aims to overcome the technical defects existing in the current field for diagnosing schizophrenia, improve the accuracy and consistency of schizophrenia diagnosis, make schizophrenia diagnosis more objective, and reduce subjective errors caused by human factors.
The above purpose of the invention is realized by the following technical scheme:
in a first aspect the invention provides the use of a DNA methylation profile, and/or a prepulse inhibition profile, as a biomarker in the manufacture of a product for diagnosing schizophrenia.
Further, the application comprises the application of the DNA methylation characteristic and/or the prepulse inhibition characteristic as a biomarker in the preparation of products for diagnosing the first schizophrenia;
preferably, the DNA methylation signature comprises 900 DNA methylation signature sites;
<xnotran> , 900 DNA cg25224760, cg25122934, cg25783352, cg00693060, cg23195763, cg25176297, cg18516940, cg22030766, cg21163478, cg15153114, cg03515346, cg16210324, cg18561199, cg24344143, cg03803284, cg23243856, cg27400655, cg13748287, cg14044124, cg12390678, cg18889956, cg07746811, cg25799064, cg15796941, cg24727290, cg10924691, cg11631427, cg26369259, cg22594586, cg01511844, cg15782771, cg18065318, cg25672411, cg23147317, cg18718234, cg15430422, cg22910549, cg06759901, cg25242729, cg22879458, cg25920734, cg25763426, cg20592447, cg04570624, cg20793712, cg25929589, cg04008557, cg10294363, cg23879228, cg12904004, cg04584468, cg24025893, cg17173330, cg01758041, cg17681524, cg24399801, cg07745707, cg25567990, cg10164186, cg21686797, cg17250082, cg13054419, cg25122125, cg13384409, cg27475680, cg26619156, cg24982343, cg17391741, cg11080430, cg24981400, cg19940644, cg20781380, cg20901993, cg13850825, cg02160684, cg24365551, cg22027671, cg16541340, cg15126273, cg21239409, cg18003231, cg24766555, cg25178683, cg21351992, cg11508828, cg24913623, cg16522885, cg18411015, cg22930950, cg17058296, cg27175294, cg19129200, cg12285326, cg11321371, cg24172989, cg20927425, cg10482356, cg04739228, cg14892768, cg22790758, cg02860199, cg11688731, cg20795889, cg06107159, cg17877898, cg16781264, cg06508379, cg15525341, cg27389290, cg27613174, cg26095809, cg10733080, cg14427074, cg13245883, cg24371156, cg16356539, cg01997461, cg17036570, cg23464565, cg27259382, cg24554865, cg26473110, cg10120112, cg23856267, cg05283486, cg25818522, cg24451839, cg21362233, cg09311571, cg19136704, cg20100445, cg17365824, cg22007638, cg14478036, cg27124109, cg01367037, cg23976937, cg00419512, cg13918430, cg14700479, cg14617167, cg26765871, cg13088598, cg02172133, cg19011911, cg17195231, cg26315559, cg11623950, cg26202181, cg21722655, cg06065611, cg26124670, cg27652200, cg01573019, </xnotran> cg17830740, cg19506491, cg26030037, cg17717125, cg22643214, cg17569754, cg11202345, cg20471798, cg26686249, cg18944640, cg22064182, cg17215601, cg 27295, cg02237470, cg26862091, cg13823585, cg09315290, cg23180925, cg 24242424242424946, cg19733221, cg24748771, cg22894329, cg13042714 cg23563927, cg 08134034068, cg 25414174, cg20965876, cg25139963, cg 20851051097, cg 10594947, cg 27002, cg 125397327, cg 12541719227, cg 2535773577357727, cg 25357756329238, cg 33547756329238, cg 337756329235775632357735, cg 335477563243547735, 32435477563243cgs, cg 33547756325632563243547735, 324354775477547735, 3277547754775477547756325632547735, cg 33325632547735, 3243cgfcGC4354775432547735, 32563254775477547729, 3256325632563256325632563256325632543256325632563256325632563256325427, 325632563256325432545632563256325427, cgc cg22079361, cg14609682, cg21518713, cg11002709, cg17031944, cg01811230, cg21378920, cg19362632, cg16260889, cg09319649, cg08057037, cg02100464, cg27272679, cg14880340, cg24013954, cg 249504, cg22013228, cg18301955, cg 52175, cg05587552, cg 23523551, cg 56242, cg 06889, cg07108214, cg 238478847843, cg12858166, cg 11868868809, cg 15215282731, cg05393023, cg 02384023, cg03538137, cg12265130, cg 4884607, cg 00532927766, cg 0332924776, cg 32357727, cg 32927727, cg 33320520, cg 3327, cg 3332920532920520, cg 32357727, cg 320520 g, cg 320532053205323527, cg 32357727, 32533205320520, cg 320535, cg03538137, cg 320532053205320520, cg 32320535, cg 3253320535, cg 323232320520, cg 32320535, phag, phagus, 320535 cGC3232323232320535, phagus, cg24964635, cg25621420, cg02203528, cg17654766, cg24957609, cg20296990, cg17426070, cg14776168, cg04744810, cg22270828, cg00934864, cg04756223, cg18116174, cg10286969, cg04641380, cg21778244, cg19251740, cg16619193, cg26837906, cg19229071, cg19851029, cg 858657, cg06202930, cg10588705, cg04900856, cg 35109109762, cg 26220020033, cg26259271, cg 0460837, cg 9393005, cg 63634, 27159443, cg 3434804, cg 19934871, cg 0805392, cg 0807746, cg 047746, cg 1557746, cg 18746, cg18793005, cg 63634, cg 15659443, cg 34559, cg 3455804, cg 19955871, cg 080779, cg 779, cg 087746, cg 7746, etc cg27173374, cg26643617, cg 169993936, cg01894875, cg07349169, cg19988408, cg08205921, cg00459299, cg05061471, cg14648186, cg11812015, cg14504291, cg21040513, cg16629408, cg09370941, cg18328477, cg18266383, cg17876742, cg17730591, cg 43011775190, cg 17333, cg 34007025, cg07072638, cg10390228, cg14998917, cg19564077, cg12251779, cg03024403, cg 13719613719628, cg 37408, cg 35199, cg09650487, cg 173987, cg 68124966, cg 1739633, cg 2159191933, cg 679, cg 67043, cg 8891 cg21896553, cg02812534, cg18443412, cg08501989, cg24257454, cg10880459, cg05665447, cg12331332, cg 1697902, cg16316042, cg04535320, cg13996738, cg00608943, cg13676583, cg18160999, cg21675569, cg01217923, cg13651234, cg25197240, cg21548152, cg 772073, cg 14376, cg 41688, cg13426198, cg 84011782, cg 176572, cg16178855, cg00369126, cg15381380, cg 74660, cg 51158158158317, cg 01124644, cg 36851243, cg 0382928570, cg 0392284, cg 2404865353, cg 24092650, cg 24064899, cg 24064048, cg 240161 cg00234363, cg16385933, cg09888026, cg07957070, cg18582505, cg19132701, cg12808194, cg10121816, cg19691425, cg01926051, cg19324027, cg16470919, cg12320972, cg02131013, cg08774990, cg06050385, cg10967622, cg15937259, cg18623931, cg19484548, cg11002033, cg05682017, cg 144240, cg05197515, cg 01438471, cg08877624, cg22252041, cg 05384, cg 179538383869, cg 11078940, cg22138494, cg13565624, cg 10206647133, cg 10291385 04, cg 124124124201892, cg 44493, cg 448373, cg 298373, cg 298333, cg0533, cg 05201493 494, cg05, cg25370362, cg02477579, cg06468646, cg02414586, cg02483627, cg13505944, cg09084892, cg07237023, cg00232772, cg09200468, cg02581147, cg01428397, cg10157558, cg08464954, cg21403762, cg06037240, cg05919900, cg00867317, cg 15945, cg14473016, cg11297423, cg04305319, cg07322293, cg18793773, cg 00515612, cg07870479, cg 1627874747, cg11605394, cg13096007, cg08091867, cg 24911, cg 2409113, cg001699, cg 00169977, cg 20658957, cg 20695917, cg 0581977, cg 09729716, cg 0972979, cg 72977, cg 0981978, cg 0972978, cg 973 cg07599136, cg15887150, cg03005121, cg08510930, cg01072942, cg19212949, cg09528372, cg01831459, cg15044205, cg08967338, cg07848764, cg03644971, cg02894527, cg01360325, cg00700866, cg18504368, cg05141656, cg02263704, cg00524443, cg 234560, cg 09340340485, cg18279180, cg 174473, cg15701419, cg 17584462, cg 08848, cg12290190, cg17084361, cg 56154025, cg 23961, cg 161161122, cg06538872, cg 175672, cg 22117, cg 211211211211260, cg 4484361, cg 591540, cg 5625557961, cg 007161122, cg 598829, cg 598872, cg17569, cn179, cg 032458, cg 592119, cg 59211458, cg 592113, cg 5989458, cg 59893, cg 59891, cg 03963 cg20226150, cg21455883, cg07938869, cg20336788, cg06814654, cg20643659, cg05271612, cg00576340, cg12161959, cg11369706, cg04425202, cg11703939, cg03114004, cg01705612, cg 06011711783, cg12388760, cg01771651, cg 01107640, cg10691323, cg 4141414156, cg 01937046, cg17344560, cg 036909, cg 096757, cg01606576, cg 05932, cg 46156156610, cg 0706670490, cg06458679, cg15565231, cg04734610, cg 26750, cg 047404747, cg 041449, cg 1449, cg 76769, cg 13076049, cg 13076632, cg 13088632, 13003632, 94, cg 03632, etc. 049 cg 43586, cg12402427, cg10703338, cg12394910, cg11036189, cg13515074, cg10440450, cg20355084, cg10075524, cg08071164, cg07678448, cg08193100, cg05016746, cg05580671, cg05718343, cg07431064, cg02843332, cg 08741841842, cg05497345, cg02540504, cg 582438, cg00369658, cg04181189, cg02404489, cg00338113, cg00770663, cg00031362, cg00082739, cg00107488, cg 00223089, cg 00230346, cg00230381, cg00321703, cg 00400419, cg 005004004043, cg 1345965, cg 00759363, cg 856, cg 00759363 856, cg 002363,65, <xnotran> cg00771653, cg00787055, cg00814990, cg00838379, cg00934564, cg00948102, cg01102220, cg01148568, cg01158804, cg01261775, cg01372572, cg01385063, cg01422467, cg01479738, cg01508386, cg01566396, cg01585372, cg01727923, cg02039058, cg02068505, cg02173970, cg02278803, cg02292206, cg02447937, cg02481842, cg02484210, cg02545393, cg02641277, cg02642822, cg02650286, cg02685016, cg02708898, cg02724747, cg02741655, cg02794096, cg02800362, cg02803629, cg02873991, cg02916932, cg02921122, cg03031823, cg03110787, cg03123782, cg03131097, cg03145322, cg03201507, cg03223467, cg03303025, cg03447137, cg03505995, cg03550508, cg03553910, cg03600697, cg03608224, cg03619332, cg03643709, cg03741350, cg03764027, cg03799192, cg03847642, cg03849780, cg03864121, cg03880355, cg03892062, cg04001842, cg04059695, cg04101729, cg04113225, cg04201335, cg04201365, cg04251616, cg04294058, cg04477962, cg04514292, cg04555107, cg04619882, cg04791145, cg04832450, cg04833648, cg04843801, cg04889960, cg04925085, cg04939919, cg04962756, cg04967200, cg05031519, cg05116088, cg05119778, cg05221370, cg05269534, cg05282641, cg05333753, cg05341567, cg05369351, cg05399718, cg05470179, cg05529874, cg05571437, cg05572751, cg05607935, cg05625951, cg05659199, cg05899224, cg05949034, cg05971212, cg05977964, cg05978571, cg06100147, cg06185734, cg06250386, cg06307176, cg06508886, cg06527318, cg06550214, cg06588466, cg06589239, cg06613034, cg06627532, cg06760899, cg06807379, cg06813554, cg06909254, cg07008701, cg07078225, cg07119973, cg07176514, cg07177889, cg07245558, cg07310500, cg07346747, cg07372520, cg07403258, cg07618581, cg07747241, cg07754486, cg07850987, cg07936305, cg07939245, cg07972159, cg08088948, cg08104023, cg08141194, cg08305707, cg08362804, cg08371190, cg08578136, cg08611508, cg08616234, cg08791782, cg08817937, cg08864042, cg08894540, cg08915378, cg08944086, cg08951822, cg08955275, cg09050775, cg09147024, </xnotran> cg09163921, cg09173939, cg09250965, cg09262552, cg09382942, cg09444206, cg09460462, cg09465855, cg09514717, cg09524686, cg09528462, cg09615620, cg09619883, cg09631044, cg09678035, cg 092198, cg09694764, cg09726046, cg09747638, cg09802873, cg09806262, cg 0998988, cg10033694, cg10052615, cg10158249, cg10163338, cg10169976, cg10214132, cg10247383, cg 43071, cg 88141, cg 10410541, cg 10410526, cg 1087357, cg 1017735, cg 11669976, cg 1024732, cg 1164705, cg 1164153, cg 116779, cg 110779, cg 1167791,779,779,779,779, cg 116779,110779,779,779,779,779, cg 116779,779,779,779,779, cg 116779,779,779,779,7793,779, cg 1167793,773,773,773,773,773, cg 0351773, cg11854579, cg11873026, cg11995137, cg11999199, cg12005153, cg12092351, cg12099459, cg12105770, cg12107522, cg12154434, cg12192122, cg12228478, cg12332083, cg12470114, cg12472085, cg12500602, cg12507168, cg12508336, cg12553110, cg12595444, cg12666921, cg12832751, cg12841061, cg12884605, cg13013644, cg13248789, cg13254556, cg 82132635, cg13318914, cg 12892921, cg12841061, cg12884605, cg13013644, cg13248789, cg13254556 cg13413789, cg13435263, cg13443092, cg13455586, cg13456654, cg13471352, cg13476139, cg13621410, cg13629807, cg13647660, cg13708908, cg13714987, cg13728439, cg13731422, cg13749070, cg13779963, cg13807254, cg13962664, cg13962718, cg13994177, cg13999554, cg 14099551, cg14036868, cg 22836, cg14125353, cg 14116, cg14221825, cg14280583;
preferably, the prepulse inhibition feature comprises a myoelectric change percentage;
more preferably, the calculation formula of the myoelectricity change percentage (%) is: percent myoelectric change (%) = (1-S2/S1) × 100%;
wherein S1 is the myoelectric amplitude of the prepulse inhibition only containing the startling stimulation, and S2 is the myoelectric amplitude of the prepulse inhibition simultaneously containing the prepulse stimulation;
most preferably, the startle stimulus is white noise, with a duration of 40ms and a sound pressure level of 100dB;
most preferably, the front stimulus is white noise divided into 3ms lead left or right channel, duration 150ms, sound pressure level 65dB.
In a specific embodiment of the invention, the DNA methylation features are obtained by identifying DNA methylation differential site data obtained by methylation site detection analysis based on an Illumina Infinium methylation epic bead chip (850 k) methylation chip by a bisulfite method, and performing further processing analysis, wherein the processing comprises performing deletion value processing, high-deviation variable removal, normalization, standardization, feature dimension reduction and feature selection processing on the extracted data, so as to improve the generalization capability of the model, and the rfe function in the R software is used for feature selection of DNA methylation by a multi-recursive feature elimination method. rfe first fits the model to all features using the bag tree algorithm. Each feature is ranked according to its importance to the model. In each iteration of feature selection, the ranked features are retained, the model is readjusted and performance is evaluated. Each set of features was finally selected based on 10-fold cross-validation.
In a specific embodiment of the present invention, the pre-pulse suppression features are measured by using a human startle reflex system (a system for customizing the natural rumbling grand human startle reflex) in an auditory sound-insulation shielding room which maintains certain brightness and temperature, sound materials used in the present invention are all generated by using "randn ()" in the MATLAB library, the sampling rate is 48kHz, the sound materials include background sound, front stimulus and startle stimulus, and the statistical index includes myoelectric change percentage (%) = (1-S2/S1) × 100%; myoelectric maximum latency; myoelectric maximum response rate; the attention level was continued. Wherein, 500ms before stimulation is recorded as baseline S0; only startle stimulation was recorded as S1, while pro-stimulation was recorded as S2; sustained level of attention includes, but is not limited to, the time of continuous staring at a cross.
Further, the application comprises the application of the DNA methylation characteristic and/or the prepulse inhibition characteristic as a biomarker in the preparation of products for diagnosing the schizophrenia in the high risk group;
preferably, the DNA methylation signature comprises 4 DNA methylation signature sites;
more preferably, the 4 DNA methylation signature sites include cg25376875, cg27415006, cg09543727, cg00213281;
preferably, the pre-pulse suppression feature is the aforementioned pre-pulse suppression feature.
Further, the application comprises the application of the DNA methylation characteristics and/or the prepulse inhibition characteristics as biomarkers in the preparation of products for differential diagnosis of patients with the first schizophrenia, the high risk group of schizophrenia and the healthy group;
preferably, the DNA methylation signature comprises 10 DNA methylation signature sites;
more preferably, the 10 DNA methylation signature sites include cg01511844, cg23076086, cg01807407, cg15782771, cg04538470, cg04218099, cg10297617, cg14240820, cg25929589, cg10315533;
preferably, the pre-pulse suppression feature is the aforementioned pre-pulse suppression feature.
In a second aspect the invention provides a diagnostic device for assessing the risk of a test individual for developing first-onset schizophrenia.
Further, the diagnostic apparatus includes:
(1) The detection unit comprises a reagent for detecting the DNA methylation characteristics of the individual to be detected, and/or equipment for detecting the prepulse inhibition characteristics of the individual to be detected and sound materials;
preferably, the subject to be tested is a non-drug-administered subject;
preferably, the DNA methylation signature is 900 DNA methylation signatures according to the first aspect of the invention;
preferably, the pre-pulse suppression feature is the pre-pulse suppression feature of the first aspect of the invention;
(2) The analysis unit is used for analyzing the detection result obtained by the detection unit and evaluating the risk of suffering from schizophrenia of the individual to be detected;
preferably, the analysis unit further comprises a DNA methylation model containing DNA methylation characteristics and/or a prepulse inhibition model containing prepulse inhibition characteristics, which are obtained by adopting random forest algorithm modeling;
more preferably, the analysis unit further comprises a step of obtaining a final simulation value by using 10-fold cross validation on the DNA methylation model and the prepulse inhibition model, and constructing a combined model containing the DNA methylation characteristics and the prepulse inhibition characteristics based on the final simulation value.
A third aspect of the invention provides a diagnostic device for assessing whether an individual to be tested is a group at high risk for schizophrenia.
Further, the diagnostic apparatus includes:
(1) The detection unit comprises a reagent for detecting the DNA methylation characteristics of the individual to be detected, and/or equipment for detecting the prepulse inhibition characteristics of the individual to be detected and a sound material;
preferably, the subject to be tested is a non-drug-administered subject;
preferably, the DNA methylation signature is 4 DNA methylation signatures according to the first aspect of the invention;
preferably, the pre-pulse suppression feature is the pre-pulse suppression feature of the first aspect of the invention;
(2) The analysis unit is used for analyzing the detection result obtained by the detection unit and evaluating the risk of the schizophrenia of the individual to be detected;
preferably, the analysis unit further comprises a random forest algorithm modeling unit for obtaining a DNA methylation model containing DNA methylation characteristics and/or a prepulse inhibition model containing prepulse inhibition characteristics;
more preferably, the analysis unit further comprises a step of obtaining a final simulation value by using 10-fold cross validation on the DNA methylation model and the prepulse inhibition model, and a step of constructing a combined model containing the DNA methylation characteristics and the prepulse inhibition characteristics based on the final simulation value.
In a fourth aspect of the invention, a diagnostic device for assessing the risk of schizophrenia in an individual to be tested is provided.
Further, the diagnostic apparatus includes:
(1) The detection unit comprises a reagent for detecting the DNA methylation characteristics of the individual to be detected, and/or equipment for detecting the prepulse inhibition characteristics of the individual to be detected and a sound material;
preferably, the detection unit is used for detecting the DNA methylation characteristics and prepulse inhibition characteristics of the first schizophrenia patient, the schizophrenia super-high risk group and the healthy group;
preferably, the subject to be tested is a non-drug-administered subject;
preferably, the DNA methylation signature is 10 DNA methylation signatures according to the first aspect of the invention;
preferably, the pre-pulse suppression feature is the pre-pulse suppression feature of the first aspect of the invention;
(2) The analysis unit is used for analyzing the detection result obtained by the detection unit and evaluating the risk of the schizophrenia of the individual to be detected;
preferably, the analysis unit further comprises a DNA methylation model containing DNA methylation characteristics and/or a prepulse inhibition model containing prepulse inhibition characteristics, which are obtained by adopting random forest algorithm modeling;
more preferably, the analysis unit further comprises a step of obtaining a final simulation value by using 10-fold cross validation on the DNA methylation model and the prepulse inhibition model, and constructing a combined model containing the DNA methylation characteristics and the prepulse inhibition characteristics based on the final simulation value.
A fifth aspect of the invention provides a system for early detection and risk prediction of schizophrenia.
Further, the system comprises the following modules:
(1) The test module is used for detecting the DNA methylation characteristics and the prepulse inhibition characteristics of the first schizophrenia patients, the high risk groups and the healthy groups of schizophrenia of the three groups of people;
(2) The acquisition and preprocessing module is used for acquiring DNA methylation characteristics and/or prepulse inhibition characteristics of the three groups of people by applying a DNA methylation chip analysis technology and a prepulse inhibition measurement technology, preprocessing the DNA methylation characteristics and/or prepulse inhibition characteristic data and extracting data applicable to machine learning;
(3) The data analysis module is used for carrying out missing value processing, high deviation variable removal, normalization, standardization, feature dimension reduction and feature selection processing on the DNA methylation feature data and/or prepulse inhibition feature data processed by the acquisition and preprocessing module;
preferably, the feature selection process comprises a selection process of DNA methylation features;
more preferably, the selection process of the DNA methylation characteristics comprises the selection of the characteristics by a multivariate recursive characteristic elimination method by using an rfe function in R software;
most preferably, the rfe function first fits the model to all features using a bag tree algorithm, each feature sorts the model according to its importance, in each iteration of feature selection, the sorted features are retained, the model is readjusted and the performance is evaluated, each group of features is finally selected based on 10-fold cross validation;
(4) The learning classification module is used for training a model by using DNA methylation characteristic data and/or prepulse inhibition characteristic data obtained by processing and analyzing by the data analysis module, classifying the three groups of people by using a random forest method, and constructing the model for identifying and diagnosing the three groups of people;
(5) And the classification performance evaluation module is used for comparing the classification effect of the model constructed on the basis of the DNA methylation characteristics and/or the prepulse inhibition characteristics based on the results of the learning classification module, and calculating the accuracy, the sensitivity, the specificity, the positive prediction value, the negative prediction value and the AUC value of the area under the ROC curve to evaluate the model.
Further, the model for carrying out differential diagnosis on the first schizophrenia patient, the schizophrenia super-high risk group and the healthy group, which is obtained by analyzing and evaluating the classification performance evaluation module, comprises a DNA methylation characteristic and/or a prepulse inhibition characteristic;
preferably, the DNA methylation signature is 10 DNA methylation signatures described in the first aspect of the invention;
preferably, the pre-pulse suppression feature is the pre-pulse suppression feature described in the first aspect of the invention.
A sixth aspect of the invention provides a computer-readable storage medium.
Further, the computer readable storage medium comprises a stored computer program which, when executed by a processor, implements the diagnostic apparatus of the second aspect of the invention, the diagnostic apparatus of the third aspect of the invention, the diagnostic apparatus of the fourth aspect of the invention, and/or the system of the fifth aspect of the invention.
Schizophrenia has a lack of objective biological indicators for clinical practice in the field due to the complexity of the etiology and heterogeneity of the symptoms, and in the present invention, DNA methylation, one of the common forms of epigenetic regulation, is an indicator based on genes and affected by environmental events; prepulse Inhibition (PPI), one of the internal manifestations of schizophrenia, is closely related to the typical behavioral symptoms of the disease, and carries with it the genetic burden of the disease. The diagnosis model containing the specific DNA methylation characteristics and/or the prepulse inhibition characteristics is obtained through analysis, screening and verification, can be used for diagnosis and identification of schizophrenia, and has better diagnosis efficiency.
Compared with the prior art, the invention has the advantages and beneficial effects that:
the invention firstly uses the DNA methylation characteristic and the prepulse inhibition characteristic as clinical biomarkers, is jointly applied to diagnosis and identification of the first schizophrenia, the ultra-high risk group of schizophrenia and the healthy group, has the advantages of objectivity, accuracy, effectiveness and the like, has very good application prospect in clinic, lays a foundation for early identification and intervention of schizophrenia, and provides support for development of accurate medical strategies.
Drawings
Embodiments of the invention are described in detail below with reference to the attached drawing figures, wherein:
FIG. 1 shows a technical roadmap for the present invention;
FIG. 2 is a schematic diagram showing a test paradigm for pre-pulse suppression according to the present invention;
FIG. 3 shows ROC plots of DNA methylation model, PPI model, combined signature (DNA methylation signature and PPI signature combined) model for diagnosis of first-onset schizophrenia, where FPR, falls Positive Rate, false Positive Rate, abscissa; ordinate TPR: true Positive Rate, true Rate;
FIG. 4 is a graph showing the probability distribution of the first schizophrenia among healthy population, wherein the abscissa represents the DNA methylation model simulation values ranging from 0 to 100%, and larger values represent higher probability of the individual being the first schizophrenia patient; the ordinate represents the PPI model simulation value, the numerical range is from 0 to 100 percent, and the larger the numerical value is, the higher the probability that the individual is the patient with the first schizophrenia is; a triangle CON, representing that the individual is really a healthy population; circular FES, representing individuals who are truly first schizophrenia patients;
FIG. 5 shows ROC plots of DNA methylation model, PPI model, combined signature (DNA methylation signature and PPI signature combined) model for diagnosis of the ultra-high risk group, where FPR, falls Positive Rate, false Positive Rate, abscissa; ordinate TPR: true Positive Rate, true Rate;
FIG. 6 is a graph showing the probability distribution of the ultra-high risk group to distinguish healthy groups, wherein the abscissa represents the DNA methylation model simulation value, the range of the numerical value is from 0 to 100%, and the larger the numerical value is, the higher the probability of the individual being the ultra-high risk group is; the ordinate represents a PPI model simulation value, the numerical range is from 0 to 100%, and the larger the numerical value is, the higher the probability that the individual is an ultra-high risk group is; a triangle CON, representing that the individual is really a healthy population; a circular UHR represents that the individual is really an ultra-high risk group;
FIG. 7 shows a diagram of UMAP (unified expressed application and project) of three populations based on DNA methylation models, wherein the abscissa is the two-dimensional principal component of DNA methylation features calculated by the UMAP feature dimension reduction algorithm; triangles represent CON, healthy control population; squares represent UHR, ultra high risk group; circles indicate FES, the first schizophrenia patient.
Detailed Description
The invention is further illustrated below with reference to specific examples, which are intended to be purely exemplary of the invention and are not to be interpreted as limiting the same. As will be understood by those of ordinary skill in the art: various changes, modifications, substitutions and alterations can be made to the embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the claims and their equivalents. The following examples are examples of experimental methods in which specific conditions are not specified, and the detection is usually carried out according to conventional conditions or according to conditions recommended by the manufacturers.
Example construction of diagnostic model for schizophrenia and verification of diagnostic efficacy thereof
In the study, a total of 31 patients with first-onset schizophrenia, 34 patients with a very high risk for schizophrenia, and 26 healthy controls were included. Subject DNA methylation data was collected by Illumina methylation epic methylation chip and PPI data was collected by perceptual spatial separation paradigm. After DNA methylation data are normalized and normalized, features are screened by a recursive feature elimination method. A model is constructed by combining DNA methylation characteristics, prepulse inhibition characteristics and characteristics of the two groups respectively, three groups of crowds are distinguished by 10-fold cross validation by applying a random forest algorithm, and a specific technical route diagram is shown in figure 1.
1. Study object
A total of 3 groups of subjects were enrolled in the study: 31 patients (First-epidemic schizohrena, FES) with First onset of drug-free schizophrenia, 34 patients (Ultra high risk, UHR) and 26 patients (Health control, CON) in each case. The first schizophrenia patient group and the ultra-high risk group are recruited from the clinic or the inpatient department of the Beijing diazepam hospital affiliated to the first medical university; healthy control populations were recruited from staff, reading students, and society. The ethical issues associated with this study have been reviewed by the ethical committee of the Beijing stabilized hospital affiliated with the university of capital medicine. All subjects were informed of the benefit and risk of participation in the study and signed an informed consent.
Grouping standard: a shared part: voluntarily sign an informed consent and inform the study protocol; right handedness, age between 18-55 years; the cultural degree of the junior middle school and above is normal in intelligence test (IQ is more than or equal to 75); normal hearing, no hearing system disease; no history of alcohol and drug abuse; family history of neurologic disease (except cerebrovascular accident); there is currently no history of well-diagnosed neurological and other severe somatic diseases. FES: those who meet DSM-5 diagnostic criteria for schizophrenia with a course of < 3 years and have not been treated with systemic antipsychotic agents. UHR: and the SIPS screening prodromal stage risk syndrome standard is met. CON: the DSM-5 is compliant with no psychiatric disorder criteria.
Exclusion criteria: severe abnormality of physical examination and biochemical index in laboratory or electroencephalogram and electrocardiogram; pregnant or lactating women, women likely to be pregnant during follow-up; those who cannot discontinue use of the drug for other somatic diseases; the blood is participated in other scientific research treatments, blood donations or blood-sampled persons as subjects within 3 months; extreme excitement, impulsivity, non-compliant authors; the investigator believes that the subject will have suicide or violence during the study; the patients who receive electric convulsion or magnetic stimulation treatment within 6 months. FES: other psychiatric disorders than schizophrenia, which are not currently well-defined; those currently or once treated with antipsychotics, antidepressants, central stimulants, or mood stabilizers. UHR, CON: a person now or previously diagnosed with a psychotic disorder; now or previously diagnosed as a mental disorder caused by an organic or somatic disease of the brain or caused by a psychoactive substance; those currently or once treated with antipsychotics, antidepressants, central stimulants, or mood stabilizers.
2. Experimental methods
(1) General demographic and clinical data collection
Inquiring general demographic data of the testee by a main test in a form of a homemade questionnaire, wherein the general demographic data comprises the age, the sex, the race, the cultural degree, the handedness, the smoking and drinking conditions, the personal history, the family history and the like of the testee; if the subject is a patient, the patient will also be asked for clinical data (e.g., PANSS scale, age of onset, medication, etc.); if The subject is a super high risk group, a psychiatric risk syndrome institutional Interview (The Structured Interview for psychopathology-ask Syndromes, SIPS) will also be conducted. Was tested by 2 clinicians trained strictly and qualified to perform a consistency assessment.
(2) Assessment of cognitive function
The cognitive dimensions tested included: speed of information processing, attention/alertness, working memory, word learning, visual learning, reasoning and problem solving, social cognition. Testing was performed by 3 strictly trained pilot trials. In order to avoid the fatigue of the tested person, the person can have a rest for 5 to 10 minutes in the middle.
(3) Prepulse suppression measurement
(1) Experimental equipment: a system for customizing the shock reflex of a human being in great distance with heaven sound.
(2) The experimental environment is as follows: the method is carried out in a hearing sound insulation shielding room, and certain brightness and temperature are kept.
(3) Sound materials: the desired sound material was generated using "randn ()" in the MATLAB function library, with a sampling rate of 48kHz. The generated gaussian noise is passed through a 512-order low-pass digital filter with a cutoff frequency of 10kHz to obtain broadband noise as background noise. In addition, a pre-stimulus sound having a length of 150ms of the broadband noise and a startle sound having a length of 40ms of the broadband noise are generated. In order to avoid the energy splash phenomenon, each sound stimulus is filtered after the introduction of the pre-pulse stimulus sound and the startle stimulus sound. The sound signal is input to the Sennheiser HD 600 headphones by means of a sound card (Audio CODEC' 97) and presented to the subject. Sound pressure correction was performed using a sound pressure corrector (Larson Davis, AUDit and System 824). The following are the sound specific parameters, a) background sound: white noise, which is divided into a left sound channel or a right sound channel leading 3ms, duration 15s and sound pressure level 60dB; b) Pre-stimulation: white noise which is divided into a left sound channel or a right sound channel leading 3ms, lasting time 150ms and sound pressure level 65dB; c) Frightening and stimulating: white noise, duration 40ms,100dB.
(4) The test flow comprises the following steps: order to sit on the examination chair, 2 Ag/AgCl electrodes are pasted 1.5cm below and outside the pupil of the right eye to record the electrical activity of the orbicularis oculi muscle, and the electrode is pasted as the ground wire on the right mastoid. The eye is 60cm from the eye tracker display. The muscles of the whole body are relaxed, the patient keeps clear-headed as much as possible in the experiment process, and the patient keeps the head fixed as much as possible while watching the screen with two eyes. Firstly, learning all sound materials, wherein each sound material is learned for 3 times, the same guide words are given to all the tested persons, the tested persons need to distinguish a left sound channel or a right sound channel to be led by background sound and forward stimulus, monocular 3-point scale eye movement calibration is carried out on the tested persons, the tested persons order to be noticed to look at a front cross, and the test is started.
(5) The test paradigm is: the pre-stimulation duration is 150ms, divided into left-leading and right-leading. The front stimulus and background sounds (left-leading and right-leading) exhibited 2 states of perceptual spatial separation (front stimulus left-leading, background sound right-leading; front stimulus right-leading, background sound left-leading), each state being repeated 5 times. The pre-and startle stimuli are separated by 120ms. The number of trials with only startling stimulation was 7. See figure 2 in particular.
(6) And (3) statistical indexes are as follows: recording as baseline S0 500ms before stimulation; only startle stimulation was recorded as S1, while pro-stimulation was recorded as S2; calculating the myoelectricity change percentage (%) = (1-S2/S1) × 100%; myoelectric maximum latency; myoelectric maximum response rate; sustained attention level (e.g., sustained time to stare at the cross).
(4) Illumina Infinium methylation EPIC Beadchip (850 k) methylation chip detection
The Illumina 850k DNA methylation chip (the chip is purchased from Illumina company) adopts a bisulfite method to identify methylation sites, reaches single base resolution, can detect the methylation state of about 853,307 CpG sites in a human whole genome, not only maintains the comprehensive coverage of CpG islands and gene promoter regions, but also particularly strengthens the probe coverage of enhancer regions (333,265 probes are newly added to cover enhancers from ENCODE and FANTOM5 plans) and gene coding regions. The specific experimental procedures are as follows:
(1) and (3) sample quality inspection: and (4) extracting DNA. For genomic DNA, the amount was determined by spectrophotometry, and the sample was adjusted to a standard concentration of 50 ng/. Mu.L, 20. Mu.L, and then electrophoresed on 0.8% agarose gel. The main band of the sample electrophoresis is clear, is usually not less than 10kb, has no obvious degradation, has a total amount of more than 5 mu L, and can be used for downstream methylation chip experiments.
(2) And (3) sulfite conversion: the conversion of the subphobic acid salt was performed according to the Zymo EZ DNA Methylation Kit optimization method recommended by Illumina official.
(3) DNA amplification: MSA3 plates were prepared, DNA was denatured to single strands by adding 0.1N NaOH to the samples, neutralized and added with whole genome amplification reagents and incubated overnight at 37 ℃ constant temperature.
(4) DNA fragmentation, precipitation, resuspension: DNA fragmentation: and performing enzymolysis treatment on the amplified product to obtain fragmented DNA. DNA precipitation: the DNA fragment was precipitated by centrifugation at 4 ℃ with the addition of isopropanol. DNA resuspension: after the precipitated DNA was air-dried, a hybridization buffer was added to redissolve the DNA precipitate.
(5) Hybridization of DNA to chip: the resuspended DNA sample was hybridized to the prepared chip and placed in a hybridization oven overnight. In the hybridization process, the fragmented DNA is denatured and annealed to 50 bases of a specific site (attached to beads of a chip).
(6) Chip cleaning, single base extension and dyeing: washing off the DNA which is not hybridized and non-specifically hybridized, using the captured DNA as a template, carrying out single-base extension reaction on the chip, and adding a detectable fluorescent group on the chip, thereby distinguishing the methylation status of the sample. Coating a chip: and putting the reacted chip into XC4 reagent, wrapping a layer of viscous transparent liquid on the surface of the chip, and drying the chip in a vacuum environment for 1 hour, so as to coat the chip and protect the signal stability for a long time.
(7) Chip scanning and data extraction: downloading a corresponding manifest file in advance, putting the processed chip into a scanner, exciting a fluorescent group of a single-base extension product on the chip by using laser, acquiring fluorescence emitted by the fluorescent group by the scanner, generating original data, and recording the storage position of a scanning result. The data obtained from this were directly introduced into the R package ChAMP software for analysis, and the methylation level data of each site of each sample was obtained.
(5) DNA methylation differential site analysis
The original signal value and the Detection P information of each site are obtained by introducing a ChAMP package into a methylation matrix through R software (R version 3.6.3). The specific experimental procedures are as follows:
(1) and (3) data quality control: the method comprises site quality control and individual quality control. The Detection P of more than 95% of individuals with sites required by site quality control is less than 0.05, the beacon count is not less than 3, and sites on X, Y chromosomes and SNP are removed; individual quality control requires that the Detection P of an individual in more than 95% of sites is less than 0.05. Second, prior to lot correction, the study removed samples representing either small lots (< 5 samples) or unbalanced lots with "slide" and "position" as lot variables.
(2) Normalization processing: on Illumina DNA methylation microarrays, probes are designed with two different designs (referred to as type I probes and type II probes) with different hybridization chemistries, which means that probes from these two different designs will show different distributions and this is not related to differences in biological properties (e.g., cpG density) by type I and type II probes. The most significant difference between the methylation profiles of type I and type II probes is that the type II probe profile exhibits a reduced dynamic range. Based on the data after quality control filtering, probe type bias (probe type bias) was corrected using BMIQ (beta-mixture quality normalization) to obtain methylation level (beta value) which can be finally used for difference analysis.
(3) Batch effect, cell type and other confounding factor correction: the specific process is as follows,
a correcting the technical difference by sva package ComBat algorithm and using an empirical Bayesian method to correct the batch effect. In this study, "slide" and "position" are used as batch variables. Beta values are converted by log before using ComBatt adjustment and then reconverted to beta values after ComBatt adjustment.
b since blood is composed of multiple cell types, and given the high degree of cell type specificity of DNA methylation, analysis of differential methylation sites that are not driven by potential variations in cell type composition also typically requires correction for cell type heterogeneity. The RefbaseEWAS method infers the sample-specific cell type proportion in a constrained multiple regression format by reference to the DNA methylation profile database of the major cell types in blood, and uses this as a covariate to calculate phenotypically-related changes that are not driven by the influence of cell type composition, correcting the methylation matrix.
c for smoking status, the study extrapolated DNA methylated smoking scores based on DNA methylation profiles of sites known to be associated with smoking status according to the methods in the documents Elliott R, tillin T, mcradle W L, et al. This method is based on the generation of a weighted score at 183 DNA methylation sites, where the weights are taken from previous studies (Zeilinger S, kuhnel B, klopp N, et al.Tobacco scoring leads to extensive genome-genes in DNA methylation [ J ]. PloS one,2013,8 (5): e 63812.). Finally, age, gender and smoking scores are used as confounding factors to correct.
(4) Differential methylation site (DMP) analysis: and (3) carrying out differential methylation site analysis by using an R software Limma package, wherein the Limma adopts modulated t-statistics and empirical Bayes methods to test the significance of the differential sites, and calculates a corrected P value aiming at a multiple hypothesis test problem. The default screening criteria for significantly different CpG sites are: adjust.p.value <0.05.
(6) Machine learning model discrimination of study subjects based on DNA methylation and PPI
(1) Data applicable to machine learning, PPI assessment, DNA methylation data are extracted.
(2) Selecting characteristics: in order to improve the classification accuracy, the extracted data is subjected to missing value processing, high deviation variable removal, normalization, standardization, feature dimension reduction and feature selection processing, and the generalization capability of the model is improved, and the rfe function in the R software is used for feature selection of DNA methylation through a multi-element recursive feature elimination method. rfe first fits the model to all features using the bag tree algorithm. Each feature is ordered according to its importance to the model. In each iteration of feature selection, the ranked features are retained, the model is readjusted and performance is evaluated. The final selection for each set of features was based on 10-fold cross-validation.
(3) Constructing a model: after data processing such as feature selection is completed, the extracted data is used for training a model, the used method comprises a Random Forest (RF) method, and the research uses program packages such as random forest in R software to construct an auxiliary diagnosis model of schizophrenia.
(4) And (3) model evaluation: the model was evaluated using the accuracy, sensitivity, specificity, positive predictive value, negative predictive value, area under the ROC curve.
3. Results of the experiment
(1) Demographic and clinical characteristics
A total of 91 subjects were collected from this study, including 31 first non-drug-administered schizophrenic patients, 34 at high risk, and 26 healthy controls. The three groups of people have no obvious difference in age, sex and educational age. On the smoking scores, two-by-two comparisons showed significant differences between the healthy control and the other two groups (P <0.05 after Bonferroni correction), which was corrected for in subsequent further DNA methylation analyses (see table 1);
in the aspect of cognitive function assessment, compared with the first schizophrenia patient, the healthy control has statistical significance on the difference of all dimensions of the cognitive function, and compared with the ultra-high risk group, the healthy control has statistical significance on the difference of working memory and the total cognitive score. The difference between patients with the first schizophrenia and the ultra-high risk group has statistical significance in attention to alertness, working memory, visual learning, reasoning, problem solving and cognition summary score (see table 1);
on PPI (PSS-PPI) separated in perceptual space, the differences between healthy control and the first schizophrenia patients and the super-high risk group are statistically significant, and no significant difference is found between the first schizophrenia patients and the super-high risk group (see Table 1).
TABLE 1 general demographic characteristics, MCCB cognitive function assessment, PPI assessment results for first-onset schizophrenia patients, ultra-high risk groups and healthy subjects
Figure BDA0003330925760000191
Figure BDA0003330925760000201
FES: first-onset, drug-naive schizophrenic patients; UHR: a population at ultra-high risk; CON: a healthy control; p value: analysis of variance or chi-square test; a. checking a chi-square; under the conditions of Gender: sex; age: age; onstet: the age of onset; edu: the age of education; smoking: smoking scoring; and (4) SOP: the information processing speed; AV: attention to alertness; WM: working memory; VBL: learning words; VSL: visual learning; RPS: reasoning and problem solving; and (3) SC: social cognition; OCV: a total cognitive score; PANSS: positive and negative symptom scales; p Score positive scale Score; n Score: a negative scale score; g Score general psychopathology scale Score; PSS _ PPI: perceptually spatially separating the PPI; NA: not applicable to
(2) Machine learning model based on DNA methylation and PPI to distinguish first-onset patients from healthy population
A machine learning model based on DNA methylation and PPI is constructed by adopting a random forest algorithm. Marking the FES group as 1 and the CON group as 0, respectively modeling by using a random forest algorithm based on DNA methylation and PPI, wherein DNA methylation data is subjected to threshold value of P <0.05 after correction, screening 18696 differential methylation sites, and screening 900 characteristic sites (900 DNA methylation characteristic sites are listed in detail in the invention content part) for modeling through characteristic processing. And respectively adopting 10-fold Cross Validation (10-fold Cross Validation,10-fold CV) to obtain a final simulation value for the DNA methylation model and the PPI model, and constructing a characteristic combination model based on the DNA methylation simulation value and the PPI simulation value. Finally, respectively drawing ROC curves (ROC curves) aiming at the DNA methylation model, the PPI model and the feature combination model, and drawing a probability distribution diagram of the first-onset schizophrenia differentiation healthy population by taking the DNA methylation simulation value as an abscissa and the PPI simulation value as an ordinate (see figures 3 and 4). The results showed that the accuracy of the DNA methylation model, the PPI model and the combined feature model was 82.5%, 93.0% and 94.7%, respectively, and the Area Under the ROC curve (ROC Area Under cutters, AUC) was 90.3%, 98.8% and 98.6%, respectively. In general, the DNA methylation model did not perform as well as the PPI and combined signature models in the FES versus CON groups, and the combined signature model consisting of DNA methylation signatures and PPI signatures combined was the most effective in diagnosing first schizophrenia (see table 2).
(3) Machine learning model based on DNA methylation and PPI (pulse-beat noise)
And (3) marking the UHR group as 1, marking the CON group as 0, respectively modeling by using a random forest algorithm based on DNA methylation and PPI, wherein the DNA methylation data takes corrected P <0.05 as a threshold value, screening 47376 differential methylation sites altogether, and screening 4 characteristic sites altogether through characteristic processing (4 DNA methylation characteristic sites are cg25376875, cg27415006, cg09543727 and cg00213281 respectively) for modeling. And respectively adopting 10-fold Cross Validation (10-fold Cross Validation,10-fold CV) to obtain a final simulation value for the DNA methylation model and the PPI model, and simultaneously constructing a characteristic combination model based on the DNA methylation simulation value and the PPI simulation value. Finally, respectively drawing ROC curves (ROC curves) aiming at the DNA methylation model, the PPI model and the feature combination model, and drawing a probability distribution diagram (shown in figure 5 and figure 6) of the ultra-high risk population distinguishing healthy population by taking the DNA methylation simulation value as an abscissa and the PPI simulation value as an ordinate. The results showed that the accuracy of the DNA methylation model, the PPI model and the combined feature model was 88.3%, 90.0% and 96.6%, respectively, and the Area Under the ROC curve was (ROC Area Under Curvrs, AUC) 96.7%, 98.3% and 99.0%, respectively. In general, the DNA methylation model distinguished the UHR group from the CON group by performing slightly weaker than the PPI model and the combined signature model, which was the best diagnostic efficacy for the first ultra-high risk group (see table 2).
(4) Machine learning model based on DNA methylation and PPI to distinguish three groups of people
Aiming at three groups of people including an FES group, an UHR group and a CON group, respectively based on DNA methylation and PPI, random forest algorithm modeling is utilized, wherein DNA methylation data takes corrected P <0.05 as a threshold value, 28245 differential methylation sites are screened out altogether, 10 characteristic sites are obtained through characteristic processing (the 10 DNA methylation characteristic sites are cg01511844, cg23076086, cg01807407, cg15782771, cg 38045470, cg04218099, cg10297617, cg14240820, cg 25958929 and cg 10315533) for modeling. And respectively adopting 10-fold Cross Validation (10-fold Cross Validation,10-fold CV) to obtain a final simulation value for the DNA methylation model and the PPI model, and simultaneously constructing a characteristic combination model based on the DNA methylation simulation value and the PPI simulation value. Three sets of population UMAP maps based on DNA methylation models were generated using the Uniform Manifold Approximation and Projection (UMAP) algorithm (see FIG. 7). The results showed that the accuracy of the DNA methylation model, the PPI model and the combined feature model was 79.1%, 44.0% and 79.1%, respectively. In general, the PPI model is much inferior to the DNA methylation model and the combined signature model, which have relatively good differentiation effects on three groups of people (first schizophrenia patient, ultra-high risk group, healthy group) (see table 3).
TABLE 2 machine learning model based on DNA methylation and PPI to differentiate patients with schizophrenia from healthy, at-risk and healthy populations
Figure BDA0003330925760000221
The model simulation values are all 0.5 as a demarcation value to calculate accuracy, sensitivity, specificity, positive prediction value and negative prediction value. The FES vs CON representation model distinguishes patients with first schizophrenia from healthy people; UHR vs CON expression model for distinguishing ultra-high risk group from healthy group
TABLE 3 machine learning model based on DNA methylation and PPI to distinguish three groups of people
Figure BDA0003330925760000222
Figure BDA0003330925760000231
The vertical columns represent the real number of the three groups of the crowd CON, UHR and FES, and the horizontal rows represent the number of the crowd CON, UHR and FES which are distinguished into the three groups of the crowd after being predicted by a machine learning model
The above description of the embodiments is only intended to illustrate the method of the invention and its core idea. It should be noted that it would be apparent to those skilled in the art that various modifications and variations can be made in the present invention without departing from the spirit of the invention, and these modifications and variations also fall within the scope of the claims of the present invention.

Claims (6)

  1. The application of the combination of the DNA methylation characteristic and the prepulse inhibition characteristic as a biomarker in the preparation of products for diagnosing the first schizophrenia;
    the DNA methylation characteristic is a combination of 900 DNA methylation characteristic sites; a combination of 900 DNA methylation signature sites was used for random forest modeling;
    the 900 characteristic sites of DNA methylation are cg25224760, cg25122934, cg25783352, cg00693060, cg23195763, cg25176297, cg1851694, cg22030766, cg21163478, cg15153114, cg03515346, cg16210324, cg18561199, cg24344143, cg03803284, cg 43856, cg27400655, cg13748287, cg14044124, cg12390678, cg18889956, cg07746811, cg 259064, cg15796941, cg24727290, cg10924691, cg11631427, cg26369259, cg 942251841841841841841844, 586 157317, cg 65317, cg 651801801801, cg 6722, cg 3049122, cg 3043043049149, cg 3049120, cg 919122, 30447, cg06759901, cg25242729, cg22879458, cg25920734, cg25763426, cg20592447, cg04570624, cg20793712, cg25929589, cg04008557, cg10294363, cg23879228, cg12904004, cg04584468, cg24025893, cg17173330, cg01758041, cg17681524, cg24399801, cg07745707, cg25567990, cg10164186, cg21686797, cg17250082, cg13054419, cg25122125, cg 8484409, cg27475680, cg 269156, cg 24234983, cg 91741, cg 110430, cg 4098551400, cg 01981021644, cg 6081021825, cg 60209825, cg 6092825 825,825,825,825,825,825,825, cg22027671, cg16541340, cg15126273, cg21239409, cg18003231, cg 24555, cg25178683, cg21351992, cg11508828, cg24913623, cg16522885, cg18411015, cg22930950, cg17058296, cg27175294, cg19129200, cg12285326, cg11321371, cg 24198989, cg20927425, cg10482356, cg 047328, cg14892768, cg22790758, cg 02802899, cg11688731, cg20795889, cg 06106159, cg17877898, cg16781264, cg 0683838379, cg 171252525252558, cg 004259258, cg 02899, cg 613188204315046, cg 108373246, cg 65778, cg 72357731416520 g, cg 729720, cg 729735, cg 723577317727, cg 729735, cg 727737327727, cg 17563277563732778, cg 72978, cg 267756373277563732778, cg 72978, cg 3277317731773181988, cg 72977, cg 32773132773181988, cg 32773132778, cg 72977, cg 32775632479, cg 988, cg 7256373277563732775637327756373277563732773181988, cg 988, cg 7297cgc, <xnotran> cg19506491, cg26030037, cg17717125, cg22643214, cg17569754, cg11202345, cg20471798, cg26686249, cg18944640, cg22064182, cg17215601, cg27289295, cg02237470, cg26862091, cg13823585, cg09315290, cg23180925, cg24524946, cg19733221, cg24748771, cg22894329, cg13042714, cg23563927, cg08134068, cg25418474, cg20965876, cg25139963, cg20851097, cg10554947, cg27022602, cg25603927, cg12571055, cg10555383, cg04950413, cg07768486, cg26110834, cg21059366, cg24132991, cg19854991, cg26616258, cg23671319, cg04538470, cg07343706, cg23892310, cg22871908, cg02677877, cg24694879, cg01699425, cg24953213, cg27465618, cg25267487, cg10851774, cg02348488, cg18885125, cg25739742, cg00064261, cg09694403, cg18063493, cg15049549, cg23881601, cg08331138, cg23201527, cg26916621, cg22933195, cg22908033, cg04190450, cg24693635, cg17138984, cg16611213, cg09500174, cg09439920, cg15028904, cg24247231, cg06520003, cg00356723, cg27643917, cg25902889, cg15709265, cg22079361, cg14609682, cg21518713, cg11002709, cg17031944, cg01811230, cg21378920, cg19362632, cg16260889, cg09319649, cg08057037, cg02100464, cg27272679, cg14880340, cg24013954, cg24957704, cg22013228, cg18301955, cg10452175, cg05587552, cg23572751, cg05156242, cg06884029, cg07108214, cg23847843, cg12858166, cg11868809, cg15282731, cg05393023, cg02384255, cg03538137, cg12265130, cg13848607, cg16254946, cg27141176, cg06045225, cg11568925, cg12062504, cg10926330, cg26930230, cg22332577, cg24836607, cg02098075, cg26924679, cg14650228, cg11384205, cg00847359, cg13525067, cg16482175, cg13036702, cg19120496, cg13857168, cg22413912, cg09358961, cg05328885, cg23062115, cg20563131, cg18394235, cg09756436, cg06642177, cg19308620, cg20728314, cg01142417, cg19802477, cg01072259, cg08722290, cg22910769, cg10117603, cg00551487, cg08314949, cg09941712, cg06525127, cg01035812, cg17942689, cg19172429, cg05842490, cg18594106, cg05612346, cg17389077, cg24964635, </xnotran> <xnotran> cg25621420, cg02203528, cg17654766, cg24957609, cg20296990, cg17426070, cg14776168, cg04744810, cg22270828, cg00934864, cg04756223, cg18116174, cg10286969, cg04641380, cg21778244, cg19251740, cg16619193, cg26837906, cg19229071, cg19851029, cg01858657, cg06202930, cg10588705, cg04900856, cg10935762, cg26220033, cg26259271, cg15560837, cg18793005, cg15663074, cg27159443, cg07134804, cg19977871, cg26945392, cg08040115, cg04855546, cg18038737, cg17714225, cg08638514, cg27173374, cg26643617, cg16993936, cg01894875, cg07349169, cg19988408, cg08205921, cg00459299, cg05061471, cg14648186, cg11812015, cg14504291, cg21040513, cg16629408, cg09370941, cg18328477, cg18266383, cg17876742, cg17730591, cg11775190, cg17343033, cg07340025, cg07072638, cg10390228, cg14998917, cg19564077, cg12251779, cg03024403, cg13719628, cg15137408, cg17335199, cg09650487, cg12298697, cg12468966, cg09603833, cg04369787, cg16467919, cg21544091, cg11488893, cg21896553, cg02812534, cg18443412, cg08501989, cg24257454, cg10880459, cg05665447, cg12331332, cg16937902, cg16316042, cg04535320, cg13996738, cg00608943, cg13676583, cg18160999, cg21675569, cg01217923, cg13651234, cg25197240, cg21548152, cg01772073, cg14382976, cg24241688, cg13426198, cg01841782, cg17936572, cg16178855, cg00369126, cg15381380, cg13174660, cg15851317, cg12401644, cg24365633, cg03828570, cg11590902, cg24052284, cg13692650, cg05064489, cg24055461, cg13789353, cg00234363, cg16385933, cg09888026, cg07957070, cg18582505, cg19132701, cg12808194, cg10121816, cg19691425, cg01926051, cg19324027, cg16470919, cg12320972, cg02131013, cg08774990, cg06050385, cg10967622, cg15937259, cg18623931, cg19484548, cg11002033, cg05682017, cg14429240, cg05197515, cg01438434, cg08877624, cg22252041, cg05637384, cg17953869, cg10718940, cg22138494, cg13565624, cg06647133, cg10220104, cg26291385, cg10249373, cg22044892, cg12483005, cg27229471, cg25370362, </xnotran> cg02477579, cg06468646, cg02414586, cg02483627, cg13505944, cg09084892, cg07237023, cg00232772, cg09200468, cg02581147, cg01428397, cg10157558 558, cg08464954, cg21403762, cg06037240, cg05919900, cg00867317, cg 02215915945, cg14473016, cg11297423, cg 04319, cg 07293, cg18793773, cg 15615600512, cg07870479, cg 16278747474394, cg 11696394, cg 080969124911, cg24013, cg001699, cg 001587, cg 20695917, cg 20695535, cg 079197779, cg 0797969, cg 07979, cg 0797779, cg 97779, cg 078197779, cg 0797779 cg15887150, cg03005121, cg08510930, cg01072942, cg19212949, cg09528372, cg01831459, cg15044205, cg08967338, cg07848764, cg03644971, cg02894527, cg01360325, cg00700866, cg18504368, cg05141656, cg02263704, cg00524443, cg23402560, cg09340485, cg18279180, cg17424473, cg15701419, cg17509462, cg 08502848, cg12290190, cg17084361, cg 5625, cg00723961, cg 83557122, cg 531618872, cg 17733, cg 22117, cg07044458, cg 08044260, cg 03961, cg 70963, cg 7072963, cg 202090, cg 03963, cg 70557, cg 032733, cg 202419672, cg 22180, cg 221458, cg07044458, cg 5944260, cg 08059963, cg 03961, cg 20289963, cg 202090 cg21455883, cg07938869, cg20336788, cg06814654, cg20643659, cg05271612, cg00576340, cg12161959, cg11369706, cg04425202, cg11703939, cg 14004, cg01705612, cg11706083, cg12388760, cg01771651, cg10701640, cg 9110641323, cg09414156, cg01627046, cg17344560, cg 039809, cg09936757, cg 60606576, cg05933932, cg 07046610, cg07066790, cg06458679, cg15565231, cg 04467310, cg 26750, cg 04747, cg 0474569, cg 1441449, cg 1447646, cg 036404659, cg 03632,32659, cg 0343632,632, cg 034331632,632,632,632,323167, cg 03433167, cg 034331632,632,3265, cg 03649, cg 034331632, cg12402427, cg10703338, cg12394910, cg11036189, cg13515074, cg10440450, cg20355084, cg10075524, cg08071164, cg07678448, cg08193100, cg05016746, cg05580671, cg05718343, cg07431064, cg02843332, cg 081842, cg05497345, cg02540504, cg 01245838, cg00369658, cg04181189, cg02404489, cg00338113, cg00770663, cg00031362, cg 00000082739, cg00107488, cg00203089, cg00223046, cg00230381, cg 00321717403, cg 00400419, cg 0045904653, cg 0055904653, cg 13465, cg 007363,007363,00765, cg 7165, cg 007363,, <xnotran> cg00787055, cg00814990, cg00838379, cg00934564, cg00948102, cg01102220, cg01148568, cg01158804, cg01261775, cg01372572, cg01385063, cg01422467, cg01479738, cg01508386, cg01566396, cg01585372, cg01727923, cg02039058, cg02068505, cg02173970, cg02278803, cg02292206, cg02447937, cg02481842, cg02484210, cg02545393, cg02641277, cg02642822, cg02650286, cg02685016, cg02708898, cg02724747, cg02741655, cg02794096, cg02800362, cg02803629, cg02873991, cg02916932, cg02921122, cg03031823, cg03110787, cg03123782, cg03131097, cg03145322, cg03201507, cg03223467, cg03303025, cg03447137, cg03505995, cg03550508, cg03553910, cg03600697, cg03608224, cg03619332, cg03643709, cg03741350, cg03764027, cg03799192, cg03847642, cg03849780, cg03864121, cg03880355, cg03892062, cg04001842, cg04059695, cg04101729, cg04113225, cg04201335, cg04201365, cg04251616, cg04294058, cg04477962, cg04514292, cg04555107, cg04619882, cg04791145, cg04832450, cg04833648, cg04843801, cg04889960, cg04925085, cg04939919, cg04962756, cg04967200, cg05031519, cg05116088, cg05119778, cg05221370, cg05269534, cg05282641, cg05333753, cg05341567, cg05369351, cg05399718, cg05470179, cg05529874, cg05571437, cg05572751, cg05607935, cg05625951, cg05659199, cg05899224, cg05949034, cg05971212, cg05977964, cg05978571, cg06100147, cg06185734, cg06250386, cg06307176, cg06508886, cg06527318, cg06550214, cg06588466, cg06589239, cg06613034, cg06627532, cg06760899, cg06807379, cg06813554, cg06909254, cg07008701, cg07078225, cg07119973, cg07176514, cg07177889, cg07245558, cg07310500, cg07346747, cg07372520, cg07403258, cg07618581, cg07747241, cg07754486, cg07850987, cg07936305, cg07939245, cg07972159, cg08088948, cg08104023, cg08141194, cg08305707, cg08362804, cg08371190, cg08578136, cg08611508, cg08616234, cg08791782, cg08817937, cg08864042, cg08894540, cg08915378, cg08944086, cg08951822, cg08955275, cg09050775, cg09147024, cg09163921, </xnotran> cg09173939, cg09250965, cg09262552, cg09382942, cg09444206, cg09460462, cg09465855, cg09514717, cg09524686, cg09528462, cg09615620, cg09619883, cg 09091044, cg09678035, cg09682198, cg09694764, cg09726046, cg09747638, cg09802873, cg09806262, cg09983708, cg10033694, cg10052615, cg 1015863249, cg10163338, cg 10197696, cg 14110232, cg10247383, cg 10371, cg 103694 cg10488141, cg10488637, cg10549357, cg10587782, cg10589249, cg10730208, cg10758986, cg10803722, cg10841956, cg10844118, cg10973146, cg10989690, cg11021611, cg11029191, cg11046887, cg11051139, cg11187110, cg11251399, cg11466109, cg11466321, cg11585769, cg11611011, cg11625897, cg11673867, cg 11709009009009065, cg11770888, cg 118369, cg11854579 cg11873026, cg11995137, cg11999199, cg12005153, cg12092351, cg12099459, cg12105770, cg12107522, cg12154434, cg12192122, cg12228478, cg12332083, cg12470114, cg12472085, cg12500602, cg12507168, cg12508336, cg 53125110, cg12595444, cg12666921, cg12832751, cg12841061, cg12884605, cg13013644, cg13248789, cg13254556, cg13282635, cg13318914, cg12832751, cg12841061, cg12884605, cg13013644, cg 132635 cg13413789, cg13435263, cg13443092, cg13455586, cg13456654, cg13471352, cg13476139, cg13621410, cg13629807, cg13647660, cg13708908, cg13714987, cg13728439, cg13731422, cg13749070, cg13779963, cg13807254, cg13962664, cg13962718, cg13994177, cg 13999599554, cg14019951, cg14036868, cg 22836, cg14125353, cg 14116, cg14221825, cg14280583;
    the prepulse inhibition characteristic is myoelectric change percentage;
    the calculation formula of the myoelectricity change percentage (%) is as follows: percent myoelectric change (%) = (1-S2/S1) × 100%;
    wherein S1 is the myoelectric amplitude of the prepulse inhibition only containing the startling stimulation, and S2 is the myoelectric amplitude of the prepulse inhibition simultaneously containing the prepulse stimulation;
    the startle stimulus is white noise, the duration is 40ms, and the sound pressure level is 100dB;
    the front stimulus is white noise, and is divided into a left channel or a right channel leading by 3ms, a duration of 150ms and a sound pressure level of 65dB.
  2. The combination of DNA methylation characteristics and prepulse inhibition characteristics is used as a biomarker for preparing products for diagnosing the high risk group of schizophrenia;
    the DNA methylation characteristic is a combination of 4 DNA methylation characteristic sites; a combination of 4 DNA methylation characteristic sites is used for random forest modeling;
    the 4 DNA methylation characteristic sites are cg25376875, cg27415006, cg09543727 and cg00213281;
    the pre-pulse suppression feature is the pre-pulse suppression feature recited in claim 1.
  3. The combination of the DNA methylation characteristic and the prepulse inhibition characteristic is used as a biomarker for preparing products for differential diagnosis of patients with first schizophrenia, the ultra-high risk group of schizophrenia and healthy groups;
    the DNA methylation characteristic is a combination of 10 DNA methylation characteristic sites; a combination of 10 DNA methylation signature sites was used for random forest modeling;
    the 10 DNA methylation characteristic sites are cg01511844, cg23076086, cg01807407, cg15782771, cg04538470, cg04218099, cg10297617, cg14240820, cg25929589 and cg10315533;
    the pre-pulse suppression feature is the pre-pulse suppression feature recited in claim 1.
  4. 4. A diagnostic device for assessing the risk of a subject for developing first-onset schizophrenia, the diagnostic device comprising:
    (1) The detection unit comprises a reagent for detecting the DNA methylation characteristics of the individual to be detected, equipment for detecting the prepulse inhibition characteristics of the individual to be detected and sound materials;
    the individual to be tested is a patient who is not used with the medicine;
    the DNA methylation signature is a combination of 900 DNA methylation signature sites as described in claim 1; a combination of 900 DNA methylation signature sites was used for random forest modeling;
    the pre-pulse suppression feature is the pre-pulse suppression feature of claim 1;
    (2) The analysis unit is used for analyzing the detection result obtained by the detection unit and evaluating the risk of the first schizophrenia of the individual to be detected;
    the analysis unit further comprises a DNA methylation model containing DNA methylation characteristics and a prepulse inhibition model containing prepulse inhibition characteristics, which are obtained by adopting random forest algorithm modeling;
    the analysis unit also comprises a step of obtaining a final simulation value by adopting 10-fold cross validation on the DNA methylation model and the prepulse inhibition model, and a combined model containing the DNA methylation characteristics and the prepulse inhibition characteristics is constructed based on the final simulation value.
  5. 5. A diagnostic device for evaluating whether an individual to be tested is a group at high risk for schizophrenia, the diagnostic device comprising:
    (1) The detection unit comprises a reagent for detecting the DNA methylation characteristics of the individual to be detected, equipment for detecting the prepulse inhibition characteristics of the individual to be detected and sound materials;
    the individual to be tested is a patient who is not used;
    the DNA methylation signature is a combination of 4 DNA methylation signature sites as described in claim 2; a combination of 4 DNA methylation characteristic sites is used for random forest modeling;
    the pre-pulse suppression feature is the pre-pulse suppression feature of claim 1;
    (2) The analysis unit is used for analyzing the detection result obtained by the detection unit and evaluating whether the individual to be detected is the high risk group of schizophrenia or not;
    the analysis unit further comprises a DNA methylation model containing DNA methylation characteristics and a prepulse inhibition model containing prepulse inhibition characteristics, which are obtained by adopting random forest algorithm modeling;
    the analysis unit also comprises a step of obtaining a final simulation value by adopting 10-fold cross validation on the DNA methylation model and the prepulse inhibition model, and a combined model containing the DNA methylation characteristics and the prepulse inhibition characteristics is constructed based on the final simulation value.
  6. 6. A diagnostic device for assessing the risk of schizophrenia in an individual to be tested, said diagnostic device comprising:
    (1) The detection unit comprises a reagent for detecting the DNA methylation characteristics of the individual to be detected, equipment for detecting the prepulse inhibition characteristics of the individual to be detected and sound materials;
    the detection unit is used for detecting the DNA methylation characteristics and the prepulse inhibition characteristics of a first schizophrenia patient, a schizophrenia super-high risk group and a healthy group;
    the individual to be tested is a patient who is not used;
    the DNA methylation signature is a combination of 10 DNA methylation signature sites as described in claim 3; a combination of 10 DNA methylation signature sites was used for random forest modeling;
    the pre-pulse suppression feature is the pre-pulse suppression feature of claim 1;
    (2) The analysis unit is used for analyzing the detection result obtained by the detection unit and evaluating the risk of the schizophrenia of the individual to be detected;
    the analysis unit further comprises a DNA methylation model containing DNA methylation characteristics and a prepulse inhibition model containing prepulse inhibition characteristics, which are obtained by adopting random forest algorithm modeling;
    the analysis unit also comprises a step of obtaining a final simulation value by adopting 10-fold cross validation on the DNA methylation model and the prepulse inhibition model, and a combined model containing the DNA methylation characteristics and the prepulse inhibition characteristics is constructed based on the final simulation value.
CN202111281022.6A 2021-11-01 2021-11-01 Use of DNA methylation profiles and prepulse inhibition profiles in schizophrenia diagnosis Active CN114250288B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111281022.6A CN114250288B (en) 2021-11-01 2021-11-01 Use of DNA methylation profiles and prepulse inhibition profiles in schizophrenia diagnosis

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111281022.6A CN114250288B (en) 2021-11-01 2021-11-01 Use of DNA methylation profiles and prepulse inhibition profiles in schizophrenia diagnosis

Publications (2)

Publication Number Publication Date
CN114250288A CN114250288A (en) 2022-03-29
CN114250288B true CN114250288B (en) 2022-12-06

Family

ID=80792275

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111281022.6A Active CN114250288B (en) 2021-11-01 2021-11-01 Use of DNA methylation profiles and prepulse inhibition profiles in schizophrenia diagnosis

Country Status (1)

Country Link
CN (1) CN114250288B (en)

Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110063732A (en) * 2019-04-15 2019-07-30 北京航空航天大学 For schizophrenia early detection and Risk Forecast System

Family Cites Families (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2015095930A1 (en) * 2013-12-23 2015-07-02 Stephanie Fryar-Williams Mental illness model and mental illness risk assessment test for schizophrenic psychosis
CN105506074B (en) * 2016-03-01 2019-02-15 张理义 A kind of lncRNA marker and kit for schizophrenia diagnosis
CN106222243B (en) * 2016-05-24 2021-04-23 张理义 circRNA marker, kit and gene chip for schizophrenia diagnosis
CN109223006A (en) * 2018-10-26 2019-01-18 首都医科大学附属北京安定医院 A kind of schizophrenia diagnosis system
WO2021028844A2 (en) * 2019-08-13 2021-02-18 Tata Consultancy Services Limited System and method for assessing the risk of schizophrenia
CN112168187A (en) * 2020-09-29 2021-01-05 首都医科大学附属北京安定医院 Diagnostic index, diagnostic model and diagnostic system for schizophrenia
CN112877419A (en) * 2021-01-20 2021-06-01 武汉大学 DNA methylation marker for predicting schizophrenia occurrence risk, screening method and application

Patent Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110063732A (en) * 2019-04-15 2019-07-30 北京航空航天大学 For schizophrenia early detection and Risk Forecast System

Also Published As

Publication number Publication date
CN114250288A (en) 2022-03-29

Similar Documents

Publication Publication Date Title
Sun et al. Fall risk prediction in multiple sclerosis using postural sway measures: a machine learning approach
Stuart et al. Comparison of self-report and structured clinical interview in the identification of depression
CN107003317B (en) Biomarker and its application in cerebral injury
Escudero et al. Early detection and characterization of Alzheimer's disease in clinical scenarios using Bioprofile concepts and K-means
JP3581319B2 (en) Brain activity automatic judgment device
US20090006001A1 (en) Empirical quantitative approaches for psychiatric disorders phenotypes
CN108634931B (en) Eye movement analyzer suitable for testing cognitive function damage of epileptic
Taboada-Crispi et al. Quantitative EEG tomography of early childhood malnutrition
CN118155787A (en) Medical data processing method and system based on Internet big data
González-Cebrián et al. Diagnosis of myalgic encephalomyelitis/chronic fatigue syndrome with partial least squares discriminant analysis: relevance of blood extracellular vesicles
Manjur et al. Detecting Autism Spectrum Disorder and Attention Deficit Hyperactivity Disorder Using Multimodal Time-Frequency Analysis with Machine Learning Using the Electroretinogram from Two Flash Strengths
CN114250288B (en) Use of DNA methylation profiles and prepulse inhibition profiles in schizophrenia diagnosis
WO2023240056A1 (en) System and method for mental diagnosis using eeg
Saengmolee et al. Consumer-grade brain measuring sensor in people with long-term kratom consumption
Hubers et al. Artificial intelligence-based classification of motor unit action potentials in real-world needle EMG recordings
CN114334122A (en) Cognitive assessment system suitable for clinical dementia risk screening
EP4051104A1 (en) Method to determine cognitive impairment
Gross et al. Machine Learning-Based Detection of High Trait Anxiety Using Frontal Asymmetry Characteristics in Resting-State EEG Recordings
CN111415745A (en) Calculation method for prompting Alzheimer disease risk of elderly men by androgen
La Grutta et al. Breathprinting in childhood asthma
JP2020525765A (en) IL-10, S100B and H-FABP markers and the use of the markers in the detection of traumatic brain injury
CN116908470A (en) Marker and kit for diagnosing schizophrenia or predicting curative effect of medicine
Deepthi et al. Study On Early Detection Of Autism Using Genetic And Kinematic Biomarker
Kumar et al. A survey on Neuropsychiatric Tools and Machine Learning Approaches used in the Diagnosis of Depression
JADHAV et al. A Method to Predict Comorbid Conditions

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant