Diwakar Shukla

This study maps the sequence preferences of the generalist class II lanthipeptide synthetase ProcM using mRNA display and machine learning, revealing moderate predictive accuracy compared to specialized enzymes.

This study examines peptide-brush polymers mimicking protein structure, finding that polymer backbones disrupt secondary structures and alter free-energy landscapes.

This study shows how glucose binding reorganizes the conformational and energetic landscape of PfHT1, a malaria parasite transporter, using computational methods and experimental validation.

Pi-Ensemble generates protein conformational ensembles between two structural states using sequence-guided interpolation, producing physically plausible intermediates without additional training.

ESMDynamic predicts protein dynamic contact maps from sequences, outperforming existing methods with less computation and enabling large-scale analysis of conformational variability.

AdaptivePy provides a unified framework for adaptive sampling in MD simulations, implementing nine seed-selection policies and enabling meta adaptive sampling schemes.

This study uses a variational autoencoder to screen ~175,000 compounds for HIV latency modulators, identifying 16 LRAs and 2 LPAs with a 15.9% experimental hit rate.

This study investigates the biophysical mechanisms underlying anandamide selectivity for CB1 receptors, revealing enthalpic and entropic effects shaped by N-terminus movements and binding pocket volume differences.

This study uses molecular dynamics and deep learning to uncover the folding mechanisms of lasso peptides, revealing key thermodynamic and kinetic principles.

The paper uses molecular dynamics simulations to show how minor sequence changes in NarU enable symport instead of antiport compared to NarK.

This study identifies sequence constraints that predispose Class D GPCRs to an atypical activation mechanism involving TM7 displacement and TM6 inward movement.

This study uses MD simulations to show that Class B1 GPCRs share a common activation mechanism involving an intermediate state with outward movement of helix 6, but exhibit clade-specific residue-level differences.

The paper develops a machine learning-guided workflow to optimize cell-free biosensors for detecting lead in drinking water, achieving sensitivity at the EPA action level and improved selectivity.

This study develops LassoESM, a language model tailored for lasso peptide property prediction, showing improved performance in substrate compatibility and biological activity prediction.

This study shows SWEET family transporters in plants act as water-conducting carrier proteins through multiple mechanisms, validated by simulations and experiments.

This study uses molecular dynamics simulations to analyze the transport mechanism of Ala-Ala through PepTSo, revealing conformational changes and free energy barriers influenced by substrate binding.

The paper investigates cholesterol translocation mechanisms in the Smoothened receptor using simulations and experiments, showing that outer leaflet translocation has a lower energy barrier.

This study uses deep mutational scanning to analyze sequence-function relationships in the plant SWEET transporter AtSWEET13, identifying mutations that enhance transport function and revealing constraints in transmembrane helix 4.

This study investigates how phosphorylation and oligomerization regulate SWEET transporter function through molecular dynamics simulations and Markov state models, revealing their impact on conformational states and extracellular gating.

This study uses simulations to show cyclopamine acts as an agonist when bound to the CRD of Smoothened and as an antagonist when bound to the TMD, with mixed effects when bound to both sites.

TLmutation uses transfer learning to predict mutation effects by transferring knowledge between protein functions and homologous proteins, improving predictions from limited data.

FingerprintContacts predicts alternative protein conformations from residue-residue contacts by leveraging conformation-specific contact patterns in ligand-binding proteins.

The paper investigates the evolutionary emergence of cyclin dependency in CDKs by analyzing the regulatory mechanisms of CDK2 and its cyclin-independent ancestor.