Ruhong Zhou

MolJam assesses molecular dataset quality across five dimensions and shows that improving quality metrics does not always enhance machine learning performance due to trade-offs with data quantity.

The paper designs and validates high-affinity RNA aptamers for SARS-CoV-2 that match the binding affinity of neutralizing antibodies.

This paper reports the high-resolution structure of a viral:host hetero-amyloid complex between M45 and RIPK3, revealing its mechanism of inhibiting necroptosis.

PRISM provides a unified simulation platform for CADD agents, enabling automated workflows for drug screening and identifying potential allosteric inhibition sites.

NEOM improves neoantigen selection by integrating multiple strategies to enhance peptide binding affinity and immunogenic potential.

ANUBI optimizes protein and peptide drug candidates by simulating sequence space and binding affinity calculations, improving target binding efficiency and reducing costs.

This study compares computational methods for calculating antibody binding affinities and finds equilibrium MMPBSA outperforms other methods for a specific antibody-peptide system.

The paper designs high-specificity binders for pHLA complexes using a deep learning and simulation framework, achieving nanomolar potency and mutation selectivity.

BioLab uses a multi-agent system with foundation models to autonomously design and validate antibodies, achieving superior performance compared to existing methods.

This study designs non-covalent CDK7 inhibitors using computational methods to improve selectivity and safety compared to THZ1.

AlphaVacc optimizes neoantigen peptides using deep reinforcement learning, improving binding affinity and T cell response in experimental validation.

This study benchmarks RNA 3D structure prediction models using varying accuracy 2D structures, finding that 3D models modify input base-pairing interactions and are more sensitive to false positives in 2D structures.

RNAGenesis is a foundation model for RNA therapeutics that integrates sequence, structure, and function prediction, achieving state-of-the-art performance on multiple tasks and enabling functional RNA design.

MultiTAP improves tumor antigen immunogenicity prediction by integrating sequence and structure features with an attention mechanism, outperforming existing models across diverse HLA phenotypes.

IsRNAcirc predicts circular RNA 3D structures using coarse-grained molecular dynamics, outperforming template-based methods on a validation set.

OPUS-Fold3 is a gradient-based protein folding and docking framework that generates accurate 3D structures under specified constraints, outperforming pyRosetta in side-chain modeling.

This study uses Molecular Dynamics simulations to show nanoporous boron nitride has higher water permeability and salt rejection than existing materials and graphene.