Integrating Genomic Annotations and Traits Dependencies for single-nucleotide polymorphisms Prioritization with Causal Concept Bottleneck Models
- 1IDSIA - USI, SUPSI
Abstract
Predicting common traits from single-nucleotide polymorphism (SNPs) data is challenging due to polygenicity, small effect sizes, and the presence of potentially mediated or spurious cross-trait associations. We propose a modeling approach that combines genomic annotations with known cross-trait relations by leveraging Causally Reliable Concept Bottleneck Models (C2BM), a deep learning architecture that factors the joint trait distribution over a graph of interpretable concepts. This design allows trait predictions to leverage information from other observed traits in addition to genomic inputs. Furthermore, the interpretable architecture of the model enables us to investigate how specific trait-trait relationships influence SNP-level predictions. We evaluate the approach on a multi-trait GWAS dataset covering five traits and show that C2BM improves predictions when ground-truth labels for related traits are available. Moreover, by analyzing variations in how trait-trait relationships influence predictions, we postulate that such differences may reflect the presence or absence of shared genetic mechanisms or indirect effects. Accepted at the CIBB 2026 conference (https://cibb2026.teralab.ai/)
Related
- Inferring Geographic Origin of White‐Tailed Deer ( Odocoileus virginianus ) Using Single Nucleotide Polymorphisms in a Region Experiencing Long‐Term Effects of Chronic Wasting Disease
- MSIPep: A pipeline for immunogenic peptide identification and prioritization integrating immunopeptidomics and transcriptomics data
- Integrating multi-omics data through deep learning with applications to autism risk gene prioritization.
- Integrating nested species distribution models and multicriteria prioritization into an open-access geoportal for tropical forest restoration
- A heterogeneous biomedical knowledge network framework for rare disease drug candidate prioritization: integrating Orphadata and DisGeNET via gene-bridge harmonization
BibTeX
@misc{santis2026integrating,
title = {{Integrating Genomic Annotations and Traits Dependencies for single-nucleotide polymorphisms Prioritization with Causal Concept Bottleneck Models}},
author = {F. De Santis and D. Malpetti and F. Gualdi and F. Mangili},
howpublished = {bioRxiv},
year = {2026},
month = sep,
doi = {10.64898/2026.09.04.749112},
url = {https://www.biorxiv.org/content/10.64898/2026.09.04.749112v1},
note = {CC BY-NC-ND},
}
RIS
TY - UNPB
TI - Integrating Genomic Annotations and Traits Dependencies for single-nucleotide polymorphisms Prioritization with Causal Concept Bottleneck Models
AU - F. De Santis
AU - D. Malpetti
AU - F. Gualdi
AU - F. Mangili
PY - 2026
DA - 2026/09/04
PB - bioRxiv
DO - 10.64898/2026.09.04.749112
UR - https://www.biorxiv.org/content/10.64898/2026.09.04.749112v1
AB - Predicting common traits from single-nucleotide polymorphism (SNPs) data is challenging due to polygenicity, small effect sizes, and the presence of potentially mediated or spurious cross-trait associations. We propose a modeling approach that combines genomic annotations with known cross-trait relations by leveraging Causally Reliable Concept Bottleneck Models (C2BM), a deep learning architecture that factors the joint trait distribution over a graph of interpretable concepts. This design allows trait predictions to leverage information from other observed traits in addition to genomic inputs. Furthermore, the interpretable architecture of the model enables us to investigate how specific trait-trait relationships influence SNP-level predictions. We evaluate the approach on a multi-trait GWAS dataset covering five traits and show that C2BM improves predictions when ground-truth labels for related traits are available. Moreover, by analyzing variations in how trait-trait relationships influence predictions, we postulate that such differences may reflect the presence or absence of shared genetic mechanisms or indirect effects. Accepted at the CIBB 2026 conference (https://cibb2026.teralab.ai/)
ER -