Rohith Krishna

This paper develops a computational method to design glycoproteins with controlled N-linked glycan composition by encoding glycan location and structure into amino acid sequences.

This paper designs sequence-specific DNA binding proteins using deep learning, achieving a 100-fold improvement in success rates over previous methods.

RFdiffusion2 scaffolds unindexed atom-level catalytic active sites via flow matching without inverse rotamer enumeration, solving all 41 in silico benchmark cases and yielding active de novo enzymes across four reactions.

This paper designs highly active metallohydrolases using a new generative AI method, achieving kcat/KM values up to 53,000 M-1 s-1 without experimental optimization.

An atom-level graph neural network that denoises corrupted structures generates small-molecule and protein-ligand conformational ensembles, and its active-site pre-organization metric enriched for more active designed retroaldolases.

This paper introduces RFD2-MI, a deep learning framework for designing phosphotyrosine peptide binders, showing high specificity and affinity for phosphorylated targets.

An all-atom diffusion model using a 14-atom residue representation and sparse U-Net architecture accelerates biomolecular design 10-fold, enabling experimentally validated DNA-binding proteins and multi-turnover cysteine hydrolases.

This paper introduces ProDiT, a multimodal diffusion model for generating functional proteins with multiple states, demonstrating its ability to design proteins with specific molecular functions and allosteric regulation.

AtomWorks, a modular atom-level data framework, trains structure prediction and design models; the resulting RF3 improves chirality handling and performs between AF3 and Boltz.

This study designs novel serine hydrolases with high catalytic efficiency using computational methods, achieving structures close to design models and distinct from natural enzymes.