Jinbo Xu

RedNet improves protein binder design by incorporating side-chain information and contrastive decoding to enhance binding affinity, folding stability, and selectivity.

PISCO improves codon optimization by integrating protein structure and host-specific codon usage, enhancing solubility and expression.

QuantaMind MD provides quantum-accurate molecular dynamics simulations for proteins, enabling accurate structure optimization and ligand interaction modeling.

This paper introduces PLAN, a machine learning model for antibody humanization, showing improved humanness scores and mutation overlap with experimental validation.

The paper uses primate genetic data to predict human variant pathogenicity with a deep learning classifier trained on 4.3 million common missense variants.

RaptorX-Single predicts protein structures from single sequences using language models and a structure generation module, outperforming MSA-based methods in specific cases.

This paper introduces DockGPT, a deep learning method for protein docking that improves accuracy and speed, especially for antibody-antigen complexes, and extends to co-designing antibody sequences and structures.

This paper integrates protein language models with geometric deep learning to improve protein representation learning, achieving a 20% performance boost on multiple benchmarks.

This paper introduces ESMPair, a method using protein language models to improve interolog identification, leading to better protein complex structure prediction than AlphaFold-Multimer.

This paper introduces a VAE-based generative model for protein design that generates high-quality 3D structures and outperforms existing methods in sequence design.

This paper introduces a deep SE(3)-equivariant model for inverse protein folding, achieving state-of-the-art results in sequence recovery and mutation effect prediction.

AttnPacker predicts protein side-chain conformations with lower RMSD than existing methods, achieving top performance in dihedral prediction on CASP13 and CASP14 data.

ProALIGN improves protein structure prediction by learning optimal sequence-template alignments using deep learning, outperforming existing methods on multiple datasets.

This paper introduces GAT-GO, a graph attention network that improves protein function prediction using predicted structure information, outperforming existing methods on benchmark datasets.

GLINTER improves inter-protein contact prediction for dimers using graph learning and MSA language models, achieving higher precision than existing methods.

This paper introduces a fast protein model refinement method using graph neural networks, achieving high quality results with limited conformation sampling.

This study shows that deep learning models like ResNet can predict protein structures accurately without co-evolution data, outperforming existing methods on CASP13 targets and human-designed proteins.

This paper introduces NDThreader, a deep learning method for template-based protein structure prediction that outperforms existing methods on CASP13 and CAMEO data.

This paper investigates real-valued distance prediction for protein structure prediction using deep learning, showing improved contact prediction and fold accuracy compared to discrete-valued methods.

The paper evaluates 43 methods for predicting intrinsically disordered regions and binding regions in proteins, finding that deep learning methods outperform older physicochemical approaches but binding prediction remains challenging.

The paper introduces MetaChrom, a deep transfer learning framework for predicting epigenomic functions of genetic variants in neurodevelopment, showing improved accuracy over existing methods.

The paper introduces ResNetQA, a deep learning method that improves protein model quality assessment by integrating sequential and pairwise features, outperforming existing methods on CASP12 and CASP13 datasets.

This paper evaluates RaptorX's performance in CASP13 using distance-based methods, showing strong contact prediction and fold prediction for some targets despite underperforming AlphaFold in 3D modeling.

This paper introduces a deep learning method to predict protein distance matrices, enabling accurate 3D structure prediction without folding simulation, even for proteins with few homologs.

PureseqTM predicts transmembrane topology from amino acid sequences, outperforming existing methods and correcting UniProt annotations in the human proteome.

This paper introduces a hybrid method combining clustering and deep learning to predict real-valued protein backbone dihedral angles and their confidence bounds, achieving better performance than existing methods.

The paper shows deep learning outperforms DCA in predicting inter-protein contacts using only intra-protein data and improves alignment for better predictions.

Deep learning rivals or beats baselines across imaging, health records, genomics and drug discovery but is not yet transformative; scarce labels, privacy and opacity remain hurdles.

This paper introduces a deep transfer learning method for predicting membrane protein structures, achieving improved contact prediction and accurate 3D models for many membrane proteins.

The paper evaluates a deep learning method for protein contact prediction in CASP12, achieving 47% and 44% accuracy for long- and medium-range contacts, respectively.