Azat Tagirdzhanov

The paper presents 154 new Myxococcota genomes, expands taxonomy, and identifies novel natural products, highlighting their biosynthetic potential for drug discovery.

Nerpa 2 links biosynthetic gene clusters to nonribosomal peptides using probabilistic models, improving accuracy and scalability in pathway reconstruction.

GRIP predicts gradient retention times using physics-informed neural networks, showing zero-shot generalization and performance comparable to transfer learning baselines.

The paper introduces the BGC Atlas, a web resource that explores BGC diversity in metagenomes, identifying nearly 1.8 million BGCs and showing RiPPs as the most abundant compound class.

ABC-HuMi catalogs 19,218 biosynthetic gene clusters from the human microbiome, offering a comprehensive resource for exploring bioactive compound potential.

molDiscovery improves small molecule identification by learning fragmentation patterns from mass spectra, achieving higher efficiency and accuracy than existing methods.