Md-Nafiz Hamid

The paper develops a transfer learning model, TRAC, for antibiotic resistance class prediction and introduces a curated dataset to benchmark existing tools.

The paper reports results from the CAFA3 challenge, showing improved computational protein function prediction and new annotations for over 1000 genes through experimental screens in C. albicans, P. aureginosa, and Drosophila.

The paper introduces a self-attention model for antibiotic resistant gene classification that improves precision and recall and detects out-of-distribution data with reliable uncertainty estimates.

The paper predicts novel bacteriocins from protein sequences using word embeddings that preserve amino acid order, avoiding sequence similarity-based methods.

MetaRiPPquest identifies RiPPs by combining genome/metagenome mining with mass spectrometry analysis, discovering 5 novel natural products from 6 datasets.