{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T00:59:27Z","timestamp":1774313967802,"version":"3.50.1"},"reference-count":85,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2021,2,25]],"date-time":"2021-02-25T00:00:00Z","timestamp":1614211200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100004359","name":"Swedish Research Council","doi-asserted-by":"publisher","award":["2017-01861"],"award-info":[{"award-number":["2017-01861"]}],"id":[{"id":"10.13039\/501100004359","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Genet."],"abstract":"<jats:p>Autism spectrum disorder (ASD) is a heterogeneous neuropsychiatric disorder with a complex genetic background. Analysis of altered molecular processes in ASD patients requires linear and nonlinear methods that provide interpretable solutions. Interpretable machine learning provides legible models that allow explaining biological mechanisms and support analysis of clinical subgroups. In this work, we investigated several case-control studies of gene expression measurements of ASD individuals. We constructed a rule-based learning model from three independent datasets that we further visualized as a nonlinear gene-gene co-predictive network. To find dissimilarities between ASD subtypes, we scrutinized a topological structure of the network and estimated a centrality distance. Our analysis revealed that autism is the most severe subtype of ASD, while pervasive developmental disorder-not otherwise specified and Asperger syndrome are closely related and milder ASD subtypes. Furthermore, we analyzed the most important ASD-related features that were described in terms of gene co-predictors. Among others, we found a strong co-predictive mechanism between <jats:italic>EMC4<\/jats:italic> and <jats:italic>TMEM30A<\/jats:italic>, which may suggest a co-regulation between these genes. The present study demonstrates the potential of applying interpretable machine learning in bioinformatics analyses. Although the proposed methodology was designed for transcriptomics data, it can be applied to other omics disciplines.<\/jats:p>","DOI":"10.3389\/fgene.2021.618277","type":"journal-article","created":{"date-parts":[[2021,2,25]],"date-time":"2021-02-25T05:11:18Z","timestamp":1614229878000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":15,"title":["Interpretable Machine Learning Reveals Dissimilarities Between Subtypes of Autism Spectrum Disorder"],"prefix":"10.3389","volume":"12","author":[{"given":"Mateusz","family":"Garbulowski","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Karolina","family":"Smolinska","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Klev","family":"Diamanti","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gang","family":"Pan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Khurram","family":"Maqbool","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lars","family":"Feuk","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jan","family":"Komorowski","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2021,2,25]]},"reference":[{"key":"ref1","first-page":"509","article-title":"The Kendall rank correlation","volume-title":"Encyclopedia of measurement and statistics.","author":"Abdi","year":"2007"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"2422","DOI":"10.3390\/app8122422","article-title":"A machine learning approach for the classification of kidney cancer subtypes using mirna genome data","volume":"8","author":"Ali","year":"2018","journal-title":"Appl. Sci."},{"key":"ref3","doi-asserted-by":"publisher","first-page":"e16715","DOI":"10.1371\/journal.pone.0016715","article-title":"Autism and increased paternal age related changes in global levels of gene expression regulation","volume":"6","author":"Alter","year":"2011","journal-title":"PLoS One"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"601","DOI":"10.3389\/fnins.2016.00601","article-title":"Variation in gene expression in autism spectrum disorders: an extensive review of transcriptomic studies","volume":"10","author":"Ansel","year":"2017","journal-title":"Front. Neurosci."},{"key":"ref57","author":"Anyango","year":"2016"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"466","DOI":"10.1016\/j.socnet.2005.11.005","article-title":"A graph-theoretic perspective on centrality","volume":"28","author":"Borgatti","year":"2006","journal-title":"Soc. Networks"},{"key":"ref6","author":"Bornel\u00f6v","year":"2012"},{"key":"ref7","first-page":"711","article-title":"Unsupervised knowledge discovery in medical databases using relevance networks","author":"Butte","year":"1999","journal-title":"Proc. AMIA Symp."},{"key":"ref8","doi-asserted-by":"publisher","first-page":"2363","DOI":"10.1093\/bioinformatics\/btq431","article-title":"A framework for oligonucleotide microarray preprocessing","volume":"26","author":"Carvalho","year":"2010","journal-title":"Bioinformatics"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"1027","DOI":"10.1093\/brain\/awaa025","article-title":"Two distinct neuroanatomical subtypes of schizophrenia revealed using machine learning","volume":"143","author":"Chand","year":"2020","journal-title":"Brain"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"3215","DOI":"10.4049\/jimmunol.1002710","article-title":"Human TMEM30a promotes uptake of antitumor and bioactive choline phospholipids into mammalian cells","volume":"186","author":"Chen","year":"2011","journal-title":"J. Immunol."},{"key":"ref11","doi-asserted-by":"publisher","first-page":"2884","DOI":"10.1111\/jcmm.13583","article-title":"NDAMDA: network distance analysis for Mi RNA-disease association prediction","volume":"22","author":"Chen","year":"2018","journal-title":"J. Cell. Mol. Med."},{"key":"ref12","author":"Clayden","year":"2020"},{"key":"ref13","doi-asserted-by":"crossref","first-page":"719","DOI":"10.1111\/1469-7610.00488","article-title":"Autism spectrum disorders at 20 and 42 months of age: stability of clinical and ADI-R diagnosis","volume":"40","author":"Cox","year":"1999","journal-title":"J. Child Psychol. Psychiatry"},{"key":"ref14","author":"Dong","year":"2018"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"1","DOI":"10.18637\/jss.v085.i12","article-title":"rmcfs: an R package for Monte Carlo feature selection and interdependency discovery","volume":"85","author":"Drami\u0144ski","year":"2018","journal-title":"J. Stat. Softw."},{"key":"ref16","doi-asserted-by":"publisher","first-page":"110","DOI":"10.1093\/bioinformatics\/btm486","article-title":"Monte Carlo feature selection for supervised classification","volume":"24","author":"Drami\u0144ski","year":"2008","journal-title":"Bioinformatics"},{"key":"ref17","doi-asserted-by":"publisher","first-page":"124","DOI":"10.1016\/j.bbi.2008.08.001","article-title":"Altered gene expression and function of peripheral blood natural killer cells in children with autism","volume":"23","author":"Enstrom","year":"2009","journal-title":"Brain Behav. Immun."},{"key":"ref18","doi-asserted-by":"crossref","first-page":"283","DOI":"10.21136\/CMJ.1976.101401","article-title":"Distance in graphs","volume":"26","author":"Entringer","year":"1976","journal-title":"Czechoslov. Math. J."},{"key":"ref19","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s13040-020-00217-8","article-title":"Merging microarray studies to identify a common gene expression signature to several structural heart diseases","volume":"13","author":"Fajarda","year":"2020","journal-title":"BioData Min."},{"key":"ref20","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41525-019-0093-8","article-title":"Exome sequencing of 457 autism families recruited online provides evidence for autism risk genes","volume":"4","author":"Feliciano","year":"2019","journal-title":"NPJ Genom. Med."},{"key":"ref21","doi-asserted-by":"publisher","first-page":"49","DOI":"10.1186\/s13229-016-0110-z","article-title":"Blood\u2013brain barrier and intestinal epithelial barrier alterations in autism spectrum disorders","volume":"7","author":"Fiorentino","year":"2016","journal-title":"Mol. Autism."},{"key":"ref22","doi-asserted-by":"publisher","first-page":"e273","DOI":"10.1038\/tp.2013.51","article-title":"Redox metabolism abnormalities in autistic children associated with mitochondrial disease","volume":"3","author":"Frye","year":"2013","journal-title":"Transl. Psychiatry"},{"key":"ref23","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41389-019-0157-8","article-title":"DeepCC: a novel deep learning-based framework for cancer molecular subtype classification","volume":"8","author":"Gao","year":"2019","journal-title":"Oncogenesis"},{"key":"ref24","article-title":"R. ROSETTA: an interpretable machine learning framework","volume":"625905","author":"Garbulowski","year":"2020","journal-title":"bioRxiv"},{"key":"ref25","doi-asserted-by":"publisher","first-page":"307","DOI":"10.1093\/bioinformatics\/btg405","article-title":"affy\u2014analysis of Affymetrix GeneChip data at the probe level","volume":"20","author":"Gautier","year":"2004","journal-title":"Bioinformatics"},{"key":"ref26","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41598-017-10361-7","article-title":"High predictive values of RBC membrane-based diagnostics by biophotonics in an integrated approach for autism spectrum disorders","volume":"7","author":"Giacometti","year":"2017","journal-title":"Sci. Rep."},{"key":"ref27","doi-asserted-by":"publisher","first-page":"22","DOI":"10.1016\/j.ygeno.2007.09.003","article-title":"Gene expression changes in children with autism","volume":"91","author":"Gregg","year":"2008","journal-title":"Genomics"},{"key":"ref28","doi-asserted-by":"publisher","first-page":"59","DOI":"10.3389\/fncel.2020.00059","article-title":"Cell type-specific gene network-based analysis depicts the heterogeneity of autism spectrum disorder","volume":"14","author":"Guan","year":"2020","journal-title":"Front. Cell. Neurosci."},{"key":"ref29","doi-asserted-by":"publisher","first-page":"470","DOI":"10.1126\/science.aao3099","article-title":"The ER membrane protein complex is a transmembrane domain insertase","volume":"359","author":"Guna","year":"2018","journal-title":"Science"},{"key":"ref30","doi-asserted-by":"publisher","first-page":"985083","DOI":"10.1155\/2015\/985083","article-title":"Effects of trace metal profiles characteristic for autism on synapses in cultured neurons","volume":"2015","author":"Hagmeyer","year":"2015","journal-title":"Neural Plast."},{"key":"ref31","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41598-019-48160-x","article-title":"An integrated transcriptomic analysis of autism spectrum disorder","volume":"9","author":"He","year":"2019","journal-title":"Sci. Rep."},{"key":"ref32","doi-asserted-by":"publisher","first-page":"147","DOI":"10.1007\/s11064-017-2370-1","article-title":"Implication of endoplasmic reticulum stress in autism spectrum disorder","volume":"43","author":"Kawada","year":"2018","journal-title":"Neurochem. Res."},{"key":"ref33","doi-asserted-by":"publisher","first-page":"133664","DOI":"10.1016\/j.neulet.2018.06.033","article-title":"Blood-brain barrier regulation in psychiatric disorders","volume":"726","author":"Kealy","year":"2018","journal-title":"Neurosci. Lett."},{"key":"ref34","doi-asserted-by":"publisher","first-page":"996","DOI":"10.1101\/gr.229102","article-title":"The human genome browser at UCSC","volume":"12","author":"Kent","year":"2002","journal-title":"Genome Res."},{"key":"ref35","doi-asserted-by":"publisher","first-page":"3095","DOI":"10.3390\/ijms16023095","article-title":"Neuron membrane trafficking and protein kinases involved in autism and ADHD","volume":"16","author":"Kitagishi","year":"2015","journal-title":"Int. J. Mol. Sci."},{"key":"ref1002","first-page":"3","article-title":"Rough sets: A tutorial","author":"Komorowski","year":"1999","journal-title":"Rough fuzzy hybridization: A new trend in decision-making"},{"key":"ref36","doi-asserted-by":"publisher","first-page":"e49475","DOI":"10.1371\/journal.pone.0049475","article-title":"Characteristics and predictive value of blood transcriptome signature in males with autism spectrum disorders","volume":"7","author":"Kong","year":"2012","journal-title":"PLoS One"},{"key":"ref37","doi-asserted-by":"publisher","first-page":"63","DOI":"10.1016\/j.artmed.2015.11.001","article-title":"The feature selection bias problem in relation to high-dimensional gene data","volume":"66","author":"Krawczuk","year":"2016","journal-title":"Artif. Intell. Med."},{"key":"ref38","doi-asserted-by":"publisher","first-page":"S194","DOI":"10.1186\/s12859-016-1038-1","article-title":"A comparative evaluation of data-merging and meta-analysis methods for reconstructing gene-gene interactions","volume":"17","author":"Lagani","year":"2016","journal-title":"BMC Bioinform."},{"key":"ref39","doi-asserted-by":"publisher","first-page":"e1001969","DOI":"10.1371\/journal.pbio.1001969","article-title":"A conserved endoplasmic reticulum membrane protein complex (EMC) facilitates phospholipid transfer from the ER to mitochondria","volume":"12","author":"Lahiri","year":"2014","journal-title":"PLoS Biol."},{"key":"ref40","doi-asserted-by":"publisher","first-page":"559","DOI":"10.1186\/1471-2105-9-559","article-title":"WGCNA: an R package for weighted correlation network analysis","volume":"9","author":"Langfelder","year":"2008","journal-title":"BMC Bioinform."},{"key":"ref41","doi-asserted-by":"publisher","first-page":"e1003118","DOI":"10.1371\/journal.pcbi.1003118","article-title":"Software for computing and annotating genomic ranges","volume":"9","author":"Lawrence","year":"2013","journal-title":"PLoS Comput. Biol."},{"key":"ref42","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"LeCun","year":"2015","journal-title":"Nature"},{"key":"ref43","doi-asserted-by":"publisher","first-page":"882","DOI":"10.1093\/bioinformatics\/bts034","article-title":"The sva package for removing batch effects and other unwanted variation in high-throughput experiments","volume":"28","author":"Leek","year":"2012","journal-title":"Bioinformatics"},{"key":"ref44","author":"Lenzerini","year":"2002"},{"key":"ref45","doi-asserted-by":"publisher","first-page":"1720","DOI":"10.1038\/s41380-018-0081-x","article-title":"A comparative study of the genetic components of three subcategories of autism spectrum disorder","volume":"24","author":"Li","year":"2019","journal-title":"Mol. Psychiatry"},{"key":"ref46","doi-asserted-by":"publisher","first-page":"325","DOI":"10.1093\/bib\/bbw113","article-title":"A review on machine learning principles for multi-view biological data integration","volume":"19","author":"Li","year":"2018","journal-title":"Brief. Bioinform."},{"key":"ref47","doi-asserted-by":"publisher","first-page":"2","DOI":"10.1186\/s40364-017-0082-y","article-title":"Machine learning and systems genomics approaches for multi-omics data","volume":"5","author":"Lin","year":"2017","journal-title":"Biomark. Res."},{"key":"ref48","doi-asserted-by":"publisher","first-page":"508","DOI":"10.1016\/S0140-6736(18)31129-2","article-title":"Autism spectrum disorder","volume":"392","author":"Lord","year":"2018","journal-title":"Lancet"},{"key":"ref49","doi-asserted-by":"publisher","first-page":"479","DOI":"10.1038\/s41596-019-0251-6","article-title":"Machine learning workflows to estimate class probabilities for precision cancer diagnostics on DNA methylation microarray data","volume":"15","author":"Maros","year":"2020","journal-title":"Nat. Protoc."},{"key":"ref50","doi-asserted-by":"publisher","first-page":"477","DOI":"10.1016\/j.ajhg.2007.12.009","article-title":"Structural variation of chromosomes in autism spectrum disorder","volume":"82","author":"Marshall","year":"2008","journal-title":"Am. J. Hum. Genet."},{"key":"ref51","doi-asserted-by":"publisher","first-page":"321","DOI":"10.1007\/s11060-019-03376-9","article-title":"Prediction of lower-grade glioma molecular subtypes using deep learning","volume":"146","author":"Matsui","year":"2020","journal-title":"J. Neuro-Oncol."},{"key":"ref52","author":"Molnar","year":"2020"},{"key":"ref53","doi-asserted-by":"publisher","first-page":"1030","DOI":"10.3389\/fonc.2020.01030","article-title":"Integrated multi-omics analyses in oncology: a review of machine learning methods and tools","volume":"10","author":"Nicora","year":"2020","journal-title":"Front. Oncol."},{"key":"ref54","doi-asserted-by":"publisher","first-page":"e26","DOI":"10.1371\/journal.pcbi.0040026","article-title":"Co-regulation of metabolic genes is better explained by flux coupling than by network distance","volume":"4","author":"Notebaart","year":"2008","journal-title":"PLoS Comput. Biol."},{"key":"ref55","doi-asserted-by":"publisher","first-page":"47","DOI":"10.9758\/cpn.2017.15.1.47","article-title":"Predicting autism spectrum disorder using blood-based gene expression signatures and machine learning","volume":"15","author":"Oh","year":"2017","journal-title":"Clin. Psychopharmacol. Neurosci."},{"key":"ref56","author":"\u00d8hrn","year":"1997"},{"key":"ref58","doi-asserted-by":"publisher","first-page":"690","DOI":"10.1002\/art.40428","article-title":"Identification of three rheumatoid arthritis disease subtypes by machine learning integration of synovial histologic features and RNA sequencing data","volume":"70","author":"Orange","year":"2018","journal-title":"Arthritis Rheumatol."},{"key":"ref59","doi-asserted-by":"publisher","first-page":"489","DOI":"10.2174\/1871527317666180706123229","article-title":"Role of the immune system in autism spectrum disorders (ASD)","volume":"17","author":"Ormstad","year":"2018","journal-title":"CNS Neurol. Disord. Drug Targets"},{"key":"ref60","doi-asserted-by":"publisher","first-page":"296","DOI":"10.1016\/j.neubiorev.2019.03.012","article-title":"Changing conceptualizations of regression: what prospective studies reveal about the onset of autism spectrum disorder","volume":"100","author":"Ozonoff","year":"2019","journal-title":"Neurosci. Biobehav. Rev."},{"key":"ref61","doi-asserted-by":"publisher","first-page":"341","DOI":"10.1007\/BF01001956","article-title":"Rough sets","volume":"11","author":"Pawlak","year":"1982","journal-title":"Int. J. Comput. Inf. Sci."},{"key":"ref1001","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/S0020-0255(02)00197-4","article-title":"Rough sets and intelligent data analysis","volume":"147","author":"Pawlak","year":"2002","journal-title":"Inf. Sci."},{"key":"ref62","doi-asserted-by":"publisher","first-page":"28","DOI":"10.1016\/j.ins.2006.06.006","article-title":"Rough sets: some extensions","volume":"177","author":"Pawlak","year":"2007","journal-title":"Inf. Sci."},{"key":"ref63","doi-asserted-by":"publisher","first-page":"1347","DOI":"10.1056\/NEJMra1814259","article-title":"Machine learning in medicine","volume":"380","author":"Rajkomar","year":"2019","journal-title":"N. Engl. J. Med."},{"key":"ref64","doi-asserted-by":"publisher","first-page":"W193","DOI":"10.1093\/nar\/gkm226","article-title":"g: Profiler\u2014a web-based toolset for functional profiling of gene lists from large-scale experiments","volume":"35","author":"Reimand","year":"2007","journal-title":"Nucleic Acids Res."},{"key":"ref65","doi-asserted-by":"publisher","first-page":"42200","DOI":"10.1109\/ACCESS.2020.2976199","article-title":"Explainable machine learning for scientific insights and discoveries","volume":"8","author":"Roscher","year":"2020","journal-title":"IEEE Access"},{"key":"ref66","doi-asserted-by":"publisher","first-page":"290","DOI":"10.1038\/mp.2010.136","article-title":"Mitochondrial dysfunction in autism spectrum disorders: a systematic review and meta-analysis","volume":"17","author":"Rossignol","year":"2012","journal-title":"Mol. Psychiatry"},{"key":"ref67","author":"Roy","year":"2014"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1162\/99608f92.5a8a3a3d","article-title":"Why are we using black box models in AI when we don\u2019t need to? A lesson from an explainable AI competition","author":"Rudin","year":"2019","journal-title":"Harvard Data Sci. Rev."},{"key":"ref69","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1016\/j.pharmthera.2018.05.007","article-title":"Autism spectrum disorder: classification, diagnosis and therapy","volume":"190","author":"Sharma","year":"2018","journal-title":"Pharmacol. Ther."},{"key":"ref70","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1186\/1866-1955-4-4","article-title":"Mechanism of nitrogen metabolism-related parameters and enzyme activities in the pathophysiology of autism","volume":"4","author":"Shmais","year":"2012","journal-title":"J. Neurodev. Disord."},{"key":"ref71","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41598-020-58290-2","article-title":"Machine learning and network analyses reveal disease subtypes of pancreatic cancer and their molecular characteristics","volume":"10","author":"Sinkala","year":"2020","journal-title":"Sci. Rep."},{"key":"ref72","doi-asserted-by":"publisher","first-page":"855","DOI":"10.1038\/s41598-020-58290-2","article-title":"Rough sets: past, present, and future","volume":"17","author":"Skowron","year":"2018","journal-title":"Nat. Comput."},{"key":"ref1003","author":"Smolinska","year":"2021"},{"key":"ref73","doi-asserted-by":"crossref","first-page":"397","DOI":"10.1007\/0-387-29362-0_23","article-title":"Limma: linear models for microarray data","volume-title":"Bioinformatics and computational biology solutions using R and bioconductor","author":"Smyth","year":"2005"},{"key":"ref74","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1159\/000323189","article-title":"The neurobiology of lipid metabolism in autism spectrum disorders","volume":"18","author":"Tamiji","year":"2010","journal-title":"Neurosignals"},{"key":"ref75","doi-asserted-by":"publisher","first-page":"585","DOI":"10.1111\/jcpp.12499","article-title":"Heritability of autism spectrum disorders: a meta-analysis of twin studies","volume":"57","author":"Tick","year":"2016","journal-title":"J. Child Psychol. Psychiatry"},{"key":"ref76","first-page":"373","author":"Tsumoto","year":"2002"},{"key":"ref82","doi-asserted-by":"crossref","first-page":"1219","DOI":"10.1001\/jamapsychiatry.2015.2079","article-title":"Association of symptom network structure with the course of depression","volume":"72","author":"van Borkulo","year":"2015","journal-title":"JAMA psychiatry"},{"key":"ref77","doi-asserted-by":"publisher","first-page":"172","DOI":"10.1097\/00004583-200402000-00012","article-title":"Specifying PDD-NOS: a comparison of PDD-NOS, Asperger syndrome, and autism","volume":"43","author":"Walker","year":"2004","journal-title":"J. Am. Acad. Child Adolesc. Psychiatry"},{"key":"ref78","doi-asserted-by":"publisher","first-page":"1611","DOI":"10.1007\/s10803-008-0541-2","article-title":"Examining the validity of autism spectrum disorder subtypes","volume":"38","author":"Witwer","year":"2008","journal-title":"J. Autism Dev. Disord."},{"key":"ref79","doi-asserted-by":"publisher","first-page":"349","DOI":"10.3389\/fnins.2019.00349","article-title":"Neurological diseases with autism spectrum disorder: role of ASD risk genes","volume":"13","author":"Xiong","year":"2019","journal-title":"Front. Neurosci."},{"key":"ref80","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41419-018-0938-6","article-title":"Disruption of Tmem30a results in cerebellar ataxia and degeneration of Purkinje cells","volume":"9","author":"Yang","year":"2018","journal-title":"Cell Death Dis."},{"key":"ref81","author":"You","year":"2020"}],"container-title":["Frontiers in Genetics"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fgene.2021.618277\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,2,25]],"date-time":"2021-02-25T05:11:30Z","timestamp":1614229890000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fgene.2021.618277\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,2,25]]},"references-count":85,"alternative-id":["10.3389\/fgene.2021.618277"],"URL":"https:\/\/doi.org\/10.3389\/fgene.2021.618277","relation":{},"ISSN":["1664-8021"],"issn-type":[{"value":"1664-8021","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,2,25]]},"article-number":"618277"}}