Repository logo
 
Publication

Identification of biological mechanisms underlying a multidimensional ASD phenotype using machine learning

2020-01-28Journal article Open access
Simple item page
dc.contributor.authorAsif, Muhammad
dc.contributor.authorMartiniano, Hugo F.M.C.
dc.contributor.authorMarques, Ana Rita
dc.contributor.authorSantos, João Xavier
dc.contributor.authorVilela, Joana
dc.contributor.authorRasga, Celia
dc.contributor.authorOliveira, Guiomar
dc.contributor.authorCouto, Francisco M.
dc.contributor.authorVicente, Astrid M.
dc.date.accessioned2021-03-04T18:58:25Z
dc.date.available2021-03-04T18:58:25Z
dc.date.issued2020-01-28
dc.description.abstractThe complex genetic architecture of Autism Spectrum Disorder (ASD) and its heterogeneous phenotype makes molecular diagnosis and patient prognosis challenging tasks. To establish more precise genotype-phenotype correlations in ASD, we developed a novel machine-learning integrative approach, which seeks to delineate associations between patients' clinical profiles and disrupted biological processes, inferred from their copy number variants (CNVs) that span brain genes. Clustering analysis of the relevant clinical measures from 2446 ASD cases in the Autism Genome Project identified two distinct phenotypic subgroups. Patients in these clusters differed significantly in ADOS-defined severity, adaptive behavior profiles, intellectual ability, and verbal status, the latter contributing the most for cluster stability and cohesion. Functional enrichment analysis of brain genes disrupted by CNVs in these ASD cases identified 15 statistically significant biological processes, including cell adhesion, neural development, cognition, and polyubiquitination, in line with previous ASD findings. A Naive Bayes classifier, generated to predict the ASD phenotypic clusters from disrupted biological processes, achieved predictions with a high precision (0.82) but low recall (0.39), for a subset of patients with higher biological Information Content scores. This study shows that milder and more severe clinical presentations can have distinct underlying biological mechanisms. It further highlights how machine-learning approaches can reduce clinical heterogeneity by using multidimensional clinical measures, and establishes genotype-phenotype correlations in ASD. However, predictions are strongly dependent on patient's information content. Findings are therefore a first step toward the translation of genetic information into clinically useful applications, and emphasize the need for larger datasets with very complete clinical and biological information.pt_PT
dc.description.sponsorshipThe work was supported by Portuguese Fundação para a Ciência e Tecnologia (FCT) through funding to BioISI (Ref: UID/MULTI/04046/2013), LASIGE Research Unit (Ref: UID/CEC/00408/2019), and to DeST: Deep Semantic Tagger project (Ref: PTDC/CCI-BIO/28685/2017). M.A., A.R.M., J.X.S., and J.V. were the recipients of BioSys PhD programme fellowship from FCT (Portugal) with references PD/BD/52485/2014, PD/BD/113773/2015, PD/BD/114386/2016, and PD/BD/\131390/2017, respectively. C.R. is the recipient of a grant from FCT (Ref: POCI01-0145-FEDER-016428). Patients and parents were genotyped in the context of the Autism Genome Project (AGP), funded by NIMH, HRB, MRC, Autism Speaks, Hilibrand Foundation, Genome Canada, OGI, and CIHR. We acknowledge the families who participated in these projects.pt_PT
dc.description.versioninfo:eu-repo/semantics/publishedVersionpt_PT
dc.identifier.citationTransl Psychiatry. 2020 Jan 28;10(1):43. doi: 10.1038/s41398-020-0721-1.pt_PT
dc.identifier.doi10.1038/s41398-020-0721-1pt_PT
dc.identifier.issn2158-3188
dc.identifier.urihttp://hdl.handle.net/10400.18/7319
dc.language.isoengpt_PT
dc.peerreviewedyespt_PT
dc.publisherSpringer Naturept_PT
dc.relationLARGE-SCALE INFORMATICS SYSTEMS LABORATORY
dc.relation.publisherversionhttps://www.nature.com/articles/s41398-020-0721-1pt_PT
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/4.0/pt_PT
dc.subjectAutismpt_PT
dc.subjectAutism Spectrum Disorder (ASD)pt_PT
dc.subjectNeurodevelopmental Disorderpt_PT
dc.subjectASD Phenotypept_PT
dc.subjectPerturbações do Desenvolvimento Infantil e Saúde Mentalpt_PT
dc.titleIdentification of biological mechanisms underlying a multidimensional ASD phenotype using machine learningpt_PT
dc.typejournal article
dspace.entity.typePublication
oaire.awardTitleLARGE-SCALE INFORMATICS SYSTEMS LABORATORY
oaire.awardURIinfo:eu-repo/grantAgreement/FCT/6817 - DCRRNI ID/UID%2FCEC%2F00408%2F2019/PT
oaire.awardURIinfo:eu-repo/grantAgreement/FCT/3599-PPCDT/PTDC%2FCCI-BIO%2F28685%2F2017/PT
oaire.citation.issue1pt_PT
oaire.citation.startPage43pt_PT
oaire.citation.titleTranslational Psychiatrypt_PT
oaire.citation.volume10pt_PT
oaire.fundingStream6817 - DCRRNI ID
oaire.fundingStream3599-PPCDT
project.funder.identifierhttp://doi.org/10.13039/501100001871
project.funder.identifierhttp://doi.org/10.13039/501100001871
project.funder.nameFundação para a Ciência e a Tecnologia
project.funder.nameFundação para a Ciência e a Tecnologia
rcaap.embargofctAcesso de acordo com página web do editor da revista.pt_PT
rcaap.rightsopenAccesspt_PT
rcaap.typearticlept_PT
relation.isProjectOfPublication277abb5a-b0b6-40b3-ab6e-eaa1448d58e4
relation.isProjectOfPublication9ed21d2b-8ca8-4010-8e79-7452970cd135
relation.isProjectOfPublication.latestForDiscovery9ed21d2b-8ca8-4010-8e79-7452970cd135

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Identification of biological mechanisms underlying.pdf
Size:
733.55 KB
Format:
Adobe Portable Document Format
Download

Collections

DPSPDNT - Artigos em revistas internacionais