| Title: | A foundation model for learning genetic associations from brain imaging phenotypes |
| Journal: | Bioinformatics Advances |
| Published: | 26 Dec 2024 |
| Pubmed: | https://pubmed.ncbi.nlm.nih.gov/40917653/ |
| DOI: | https://doi.org/10.1093/bioadv/vbaf196 |
Publication 16442
WARNING: the interactive features of this website use CSS3, which your browser does not support. To use the full features of this website, please update your browser.
Abstract
Motivation: Due to the intricate etiology of neurological disorders, finding interpretable associations between multiomics features can be challenging using standard approaches.</p>
Results: We propose COMICAL, a contrastive learning approach using multiomics data to generate associations between genetic markers and brain imaging-derived phenotypes. COMICAL jointly learns omics representations utilizing transformer-based encoders with custom tokenizers. Our modality-agnostic approach uniquely identifies many-to-many associations via self-supervised learning schemes and cross-modal attention encoders. COMICAL discovered several significant associations between genetic markers and imaging-derived phenotypes for a variety of neurological disorders in the UK Biobank, as well as prediction of diseases and unseen clinical outcomes from learned representations.</p>
Availability and Implementation: The source code of COMICAL along with pretrained weights, enabling transfer learning, is available at https://github.com/IBM/comical.</p>
4 Authors
- Diego Machado Reyes
- Myson Burch
- Laxmi Parida
- Aritra Bose
Enabling scientific discoveries that improve human health