Show simple item record

dc.contributor.authorVitsios, D
dc.contributor.authorPetrovski, S
dc.date.accessioned2020-11-17T03:20:01Z
dc.date.available2020-11-17T03:20:01Z
dc.date.issued2020-05-07
dc.identifierpii: S0002-9297(20)30108-7
dc.identifier.citationVitsios, D. & Petrovski, S. (2020). Mantis-ml: Disease-Agnostic Gene Prioritization from High-Throughput Genomic Screens by Stochastic Semi-supervised Learning.. Am J Hum Genet, 106 (5), pp.659-678. https://doi.org/10.1016/j.ajhg.2020.03.012.
dc.identifier.issn0002-9297
dc.identifier.urihttp://hdl.handle.net/11343/251473
dc.description.abstractAccess to large-scale genomics datasets has increased the utility of hypothesis-free genome-wide analyses. However, gene signals are often insufficiently powered to reach experiment-wide significance, triggering a process of laborious triaging of genomic-association-study results. We introduce mantis-ml, a multi-dimensional, multi-step machine-learning framework that allows objective assessment of the biological relevance of genes to disease studies. Mantis-ml is an automated machine-learning framework that follows a multi-model approach of stochastic semi-supervised learning to rank disease-associated genes through iterative learning sessions on random balanced datasets across the protein-coding exome. When applied to a range of human diseases, including chronic kidney disease (CKD), epilepsy, and amyotrophic lateral sclerosis (ALS), mantis-ml achieved an average area under curve (AUC) prediction performance of 0.81-0.89. Critically, to prove its value as a tool that can be used to interpret exome-wide association studies, we overlapped mantis-ml predictions with data from published cohort-level association studies. We found a statistically significant enrichment of high mantis-ml predictions among the highest-ranked genes from hypothesis-free cohort-level statistics, indicating a substantial improvement over the performance of current state-of-the-art methods and pointing to the capture of true prioritization signals for disease-associated genes. Finally, we introduce a generic mantis-ml score (GMS) trained with over 1,200 features as a generic-disease-likelihood estimator, outperforming published gene-level scores. In addition to our tool, we provide a gene prioritization atlas that includes mantis-ml's predictions across ten disease areas and empowers researchers to interactively navigate through the gene-triaging framework. Mantis-ml is an intuitive tool that supports the objective triaging of large-scale genomic discovery studies and enhances our understanding of complex genotype-phenotype associations.
dc.languageeng
dc.publisherElsevier BV
dc.titleMantis-ml: Disease-Agnostic Gene Prioritization from High-Throughput Genomic Screens by Stochastic Semi-supervised Learning.
dc.typeJournal Article
dc.identifier.doi10.1016/j.ajhg.2020.03.012
melbourne.affiliation.departmentMedicine and Radiology
melbourne.source.titleAmerican Journal of Human Genetics
melbourne.source.volume106
melbourne.source.issue5
melbourne.source.pages659-678
dc.rights.licenseCC BY
melbourne.elementsid1448374
melbourne.openaccess.pmchttp://www.ncbi.nlm.nih.gov/pmc/articles/PMC7212270
melbourne.contributor.authorPetrovski, Slave
dc.identifier.eissn1537-6605
melbourne.accessrightsOpen Access


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record