Back

A Multimodal Foundation Model for Discovering Genetic Associations with Brain Imaging Phenotypes

Machado Reyes, D.; Burch, M. C.; PARIDA, L.; Bose, A.

2024-11-04 genetic and genomic medicine
10.1101/2024.11.02.24316653 medRxiv
Show abstract

Due to the intricate etiology of neurological disorders, finding interpretable associations between multi-omics features can be challenging using standard approaches. We propose COMICAL, a contrastive learning approach leveraging multi-omics data to generate associations between genetic markers and brain imaging-derived phenotypes. COMICAL jointly learns omic representations utilizing transformer-based encoders with custom tokenizers. Our modality-agnostic approach uniquely identi-fies 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 predicting across diseases and unseen clinical outcomes from the learned representations. Source code of COMICAL along with pre-trained weights, enabling transfer learning is available at https://github.com/IBM/comical.

Matching journals

The top 11 journals account for 50% of the predicted probability mass.

1
Bioinformatics
1204 papers in training set
Top 2%
11.5%
2
Briefings in Bioinformatics
354 papers in training set
Top 2%
5.3%
3
Nature Communications
5641 papers in training set
Top 28%
5.3%
4
Artificial Intelligence in the Life Sciences
13 papers in training set
Top 0.1%
5.3%
5
Scientific Reports
3612 papers in training set
Top 19%
5.0%
6
Bioinformatics Advances
203 papers in training set
Top 1%
4.7%
7
Patterns
78 papers in training set
Top 0.4%
3.9%
8
npj Digital Medicine
118 papers in training set
Top 2%
3.1%
9
Genome Medicine
183 papers in training set
Top 2%
3.1%
10
Frontiers in Psychiatry
87 papers in training set
Top 0.9%
2.4%
11
Nature Neuroscience
252 papers in training set
Top 3%
2.3%
50% of probability mass above
12
Nature Computational Science
55 papers in training set
Top 0.4%
2.3%
13
Frontiers in Genetics
230 papers in training set
Top 2%
2.1%
14
Nature Machine Intelligence
70 papers in training set
Top 1%
2.1%
15
Communications Medicine
113 papers in training set
Top 2%
1.7%
16
iScience
1154 papers in training set
Top 19%
1.6%
17
IEEE/ACM Transactions on Computational Biology and Bioinformatics
38 papers in training set
Top 0.7%
1.5%
18
PLOS ONE
5266 papers in training set
Top 52%
1.5%
19
PLOS Computational Biology
1863 papers in training set
Top 15%
1.5%
20
Nature Biomedical Engineering
47 papers in training set
Top 0.8%
1.5%
21
Imaging Neuroscience
282 papers in training set
Top 3%
1.5%
22
Human Genetics and Genomics Advances
84 papers in training set
Top 1%
1.3%
23
Genome Biology
637 papers in training set
Top 7%
1.3%
24
Cell Genomics
172 papers in training set
Top 3%
1.1%
25
GigaScience
212 papers in training set
Top 4%
1.1%
26
Medical Image Analysis
35 papers in training set
Top 0.6%
1.1%
27
Human Brain Mapping
329 papers in training set
Top 4%
1.1%
28
IEEE Journal of Biomedical and Health Informatics
37 papers in training set
Top 1%
1.0%
29
Nature Medicine
125 papers in training set
Top 3%
1.0%
30
European Journal of Human Genetics
58 papers in training set
Top 1.0%
1.0%