Husam Abdulnabi

This paper introduces Mimic, a unified neural network architecture for genomic sequence modeling, showing it outperforms existing models in protein-DNA interactions and enhancer activity.

Oyster is a neural network that models genomic sequences by ignoring k-mer associations, providing human-understandable, exact position-specific k-mer contributions, and shows strong agreement with more complex models in case studies.

This paper introduces binning-based methods for improving imbalanced regression in genomics, showing that reciprocal density weighting outperforms other approaches.