Beyond Sequence-Only Models: Leveraging Structural Constraints for Antibiotic Resistance Prediction in Sparse Genomic Datasets

Summary: Presents a structure-aware hybrid model that injects contact-map priors and residue-level constraints into sequence-based predictors to maintain interpretability with limited labeled isolates. Across nine Mycobacterium tuberculosis resistance genes, the Fused Ridge model reaches a mean AUC of 0.766, versus 0.755 for plain ridge regression and 0.603 for zero-shot ESM-2 scoring.

Recommended citation: Tasmin, M., Green, A.G. Beyond Sequence-only Models: Leveraging Structural Constraints for Antibiotic Resistance Prediction in Sparse Genomic Datasets. ICLR 2025 Workshop on Machine Learning for Genomics Explorations.
Download Paper