Skip to content
DraconiticResearch
Search Sources API
203,234 studies31 sourcesUpdated 41 min ago
Peer-reviewedCC BYBriefings in bioinformatics

Integrating multi-omics data through deep learning with applications to autism risk gene prioritization.

  • Shengtong Han1
  • Di Wang2
  • Wenhui Sheng3
  • Nathanael Chu4
4 affiliations
  1. 1Department of Community Dental Sciences, School of Dentistry, Marquette University, 1801 West Wisconsin Avenue, 53233 WI, United States.
  2. 2Foxconn, Milwaukee, WI, United States.
  3. 3Department of Mathematical and Statistical Sciences, Marquette University, 1313 West Wisconsin Avenue, 53233 WI, United States.
  4. 4Department of Computer Science, Liberty University, 1971 University Boulevard, 24515 VA, United States.
Read full textPDFDOICite

Abstract

Autism spectrum disorder (ASD) is a highly heritable neurodevelopmental disorder. Advances in genetic research, particularly whole-exome sequencing studies, have identified an increasing number of ASD risk genes, especially through large-effect rare variant analyses. However, current rare-variant studies still have limited power to recover the full spectrum of ASD risk genes, leaving a substantial gap between known genes and the estimated genetic architecture of ASD. To address this challenge, we developed Deep-MOTIFs (Multi-Omics inTegratIon For autiSm), a Bayesian-guided positive-unlabeled deep learning framework for multi-omics integration that combines genetic, transcriptomic, and protein-interaction evidence for genome-wide ASD risk-gene prioritization. Deep-MOTIFs achieved stronger performance than existing methods across held-out ASD gene prediction, top-ranked prioritization, positive-label efficiency, and label-noise robustness analyses. Functional enrichment and genome-wide decile analyses further supported the biological relevance of the top-ranked candidates, showing convergence on ASD-related phenotypic annotations and synaptic, neurodevelopmental, and chromatin-regulatory mechanisms. Together, these results support Deep-MOTIFs as a robust framework for ASD risk-gene prioritization under incomplete supervision. Source code is available at: https://github.com/shan-team/Deep-MOTIFs.

Related

  1. MSIPep: A pipeline for immunogenic peptide identification and prioritization integrating immunopeptidomics and transcriptomics data
    Peng Liu, Siwen Zhang, Manman Lu +6
    BMC GenomicsPeer-reviewedCC BY-NC-ND 4.0Genetics & genomicsCrossref
  2. Integrating Genomic Annotations and Traits Dependencies for single-nucleotide polymorphisms Prioritization with Causal Concept Bottleneck Models
    F. De Santis, D. Malpetti, F. Gualdi +1
    bioRxivPreprintCC BY-NC-NDFull textBioinformatics & computational biologybioRxiv
  3. Integrating nested species distribution models and multicriteria prioritization into an open-access geoportal for tropical forest restoration
    R. J. Herrera-Feijoo, J. Morales-Barbero, B. Torres +1
    bioRxivPreprintCC BY-NCFull textPlant biologybioRxiv
  4. A heterogeneous biomedical knowledge network framework for rare disease drug candidate prioritization: integrating Orphadata and DisGeNET via gene-bridge harmonization
    D. Ramani
    bioRxivPreprintCC BYFull textSystems & synthetic biologybioRxiv
  5. Smart Agriculture Through Internet of Things and Machine Learning: A Survey of Monitoring Techniques, Methods and Applications
    Ado Adamou Abba Ari, Emmanuel Baba, Hamayadji Abdoul Aziz +3
    IET Wireless Sensor SystemsPeer-reviewedCC BY-NC-ND1 citedPlant biologyHAL

Cite

BibTeXRIS
BibTeX
@article{han2026integrating,
  title = {{Integrating multi-omics data through deep learning with applications to autism risk gene prioritization.}},
  author = {Shengtong Han and Di Wang and Wenhui Sheng and Nathanael Chu},
  journal = {Briefings in bioinformatics},
  year = {2026},
  month = sep,
  doi = {10.1093/bib/bbag588},
  url = {https://europepmc.org/article/MED/42932847},
  note = {CC BY},
}
RIS
TY  - JOUR
TI  - Integrating multi-omics data through deep learning with applications to autism risk gene prioritization.
AU  - Shengtong Han
AU  - Di Wang
AU  - Wenhui Sheng
AU  - Nathanael Chu
PY  - 2026
DA  - 2026/09/01
JO  - Briefings in bioinformatics
DO  - 10.1093/bib/bbag588
UR  - https://europepmc.org/article/MED/42932847
AB  - Autism spectrum disorder (ASD) is a highly heritable neurodevelopmental disorder. Advances in genetic research, particularly whole-exome sequencing studies, have identified an increasing number of ASD risk genes, especially through large-effect rare variant analyses. However, current rare-variant studies still have limited power to recover the full spectrum of ASD risk genes, leaving a substantial gap between known genes and the estimated genetic architecture of ASD. To address this challenge, we developed Deep-MOTIFs (Multi-Omics inTegratIon For autiSm), a Bayesian-guided positive-unlabeled deep learning framework for multi-omics integration that combines genetic, transcriptomic, and protein-interaction evidence for genome-wide ASD risk-gene prioritization. Deep-MOTIFs achieved stronger performance than existing methods across held-out ASD gene prediction, top-ranked prioritization, positive-label efficiency, and label-noise robustness analyses. Functional enrichment and genome-wide decile analyses further supported the biological relevance of the top-ranked candidates, showing convergence on ASD-related phenotypic annotations and synaptic, neurodevelopmental, and chromatin-regulatory mechanisms. Together, these results support Deep-MOTIFs as a robust framework for ASD risk-gene prioritization under incomplete supervision. Source code is available at: https://github.com/shan-team/Deep-MOTIFs.
SN  - 1467-5463
SN  - 1477-4054
ER  -