Jianhua Yao

FoldAbS: Repurposing the Protein Folding Model as a Foundation Encoder for Antibody Screening

FoldAbS repurposes protein folding models as foundation encoders to improve antibody screening by evaluating specificity, affinity, and developability in a unified framework.

Alignment-Aware Genomic Coordinate Encoding for Long-Range DNA Modeling

This paper introduces USM-AA, an alignment-aware genomic foundation model that improves long-range DNA modeling by incorporating reference genome coordinates and reverse-complement masked learning.

Spatial Transcriptomics Reveal Developmental Dynamics of the Human Cerebral Cortex and Striatum

This study uses spatial transcriptomics and snRNA-seq to identify 25 forebrain regions and characterize dynamic changes in the human fetal cortex and striatum during late first and early second trimesters.

An Artificial Intelligence Model for Longitudinal Assessment of TCR Repertoires in SARS-CoV-2 Vaccine Recipients

The paper develops a large language model to predict SARS-CoV-2-specific TCRs and shows their correlation with antibody levels post-vaccination.

Optimizing broadly neutralizing antibodies via all-atom interaction modeling and pre-trained language models

This paper introduces InterAb and InterAb-Opt, computational frameworks that predict and optimize broadly neutralizing antibodies using all-atom modeling and pre-trained language models, showing significant improvements in binding affinity and neutralization activity.

Genetic-to-chemical perturbation transfer learning through unified multimodal molecular representations

UniPert-G2CP transfers genetic perturbation insights to chemical perturbation modeling, enabling efficient in silico drug screening with reduced data costs.

IgGM2: An All-Atom Foundation Model for Adaptive Immune Receptor Design

IgGM2 is an all-atom foundation model for immune receptor design that jointly predicts CDR sequences and full-atom structures, outperforming existing methods in structure prediction and sequence design benchmarks.

Single-cell spatial transcriptomics and snRNA-seq decoding the organizational principles of functional modules in the mouse amygdala

This study combines spatial transcriptomics and snRNA-seq to map cell type organization and functional modules in the mouse amygdala, revealing developmental origins and spatial patterns.

Spatial-DC: a robust deep learning-based method for deconvolution of spatial proteomics

Spatial-DC improves spatial proteomics deconvolution by using deep learning to infer cell-type composition and reconstruct proteomic profiles from low-resolution data.

H2O: A Foundation Model Bridging Histopathology to Spatial Multi-Omics Profiling

H2O predicts spatial transcriptomics and proteomics from H&E images using a contrastive learning framework, outperforming existing models and recovering biologically relevant cell-cell communication.

Structural determinants of IGHV1-69 public antibodies conferring resilience to SARS-CoV-2 antigenic escape

This study identifies structural features of affinity-matured R1-32-like antibodies that enable tolerance to SARS-CoV-2 mutations and reveals an ultrapotent antibody with broad variant activity.

MolSpecFlow: Mass-Constrained Hybrid Flow Matching for Joint Molecular-Spectral Analysis

MolSpecFlow bridges the gap between molecules and mass spectra using a hybrid flow matching model, achieving state-of-the-art results in de novo generation and spectral simulation.

AI recognizes convergent somatic hypermutation signatures to allow the discovery of variant-resilient broadly neutralizing antibodies

The paper uses AI to identify convergent somatic hypermutation patterns in antibodies, enabling the discovery of variant-resilient broadly neutralizing antibodies from early-pandemic data.

A pre-trained large generative model for translating single-cell transcriptome to proteome

This paper introduces scTranslator, a pre-trained large generative model that translates single-cell transcriptomes to proteomes, showing accuracy and utility in multiple downstream tasks.

A synergistic generative-ranking framework for tailored design of therapeutic single-domain antibodies

This paper introduces TFDesign-sdAb, a deep learning framework for designing therapeutic single-domain antibodies with tailored functionalities, achieving high success rates in generating Protein A-binding sdAbs.

Disease associated human TCR characterization by deep-learning framework TCR-DeepInsight

The paper constructs a single-cell GEX-TCR reference atlas and introduces TCR-DeepInsight, a deep-learning framework to characterize disease-associated TCRs.

A Population-scale Single-cell Spatial Transcriptomic Atlas of the Human Cortex

This study creates a single-cell spatial transcriptomic atlas of the human cortex, revealing gene expression patterns, aging effects, and disease associations across layers and species.

A Generative Foundation Model for Antibody Design

IgGM is a generative model for antibody design that produces high-affinity antibodies through tasks like structure prediction and affinity maturation, validated on multiple antigens.

Genomic Touchstone: Benchmarking Genomic Language Models in the Context of the Central Dogma

Genomic Touchstone evaluates genomic language models across 36 tasks and 88 datasets, revealing insights on model performance, scaling, and pretraining strategies.

Beyond Static Brain Atlases: AI-Powered Open Databasing and Dynamic Mining of Brain-Wide Neuron Morphometry

NeuroXiv provides an AI-powered database of neuron morphologies from mouse brains, enabling dynamic analysis and comparison across a standardized atlas.

scTransMIL Bridges Patient-Level Phenotypes and Single-Cell Transcriptomics for Cancer Screening and Heterogeneity Inference

Fast and accurate modeling of TCR-peptide-MHC complexes using tFold-TCR

The paper introduces tFold-TCR, a model for predicting TCR-pMHC structures, achieving higher accuracy and speed than existing methods and creating a large database of these structures.

Evaluation of T Cell Receptor Construction Methods from scRNA-Seq Data

The paper benchmarks TCR reconstruction methods from scRNA-seq data, finding TRUST4 performs best, while sequencing depth limits accuracy.

An adaptive autoregressive diffusion approach to design active humanized antibody and nanobody

This paper introduces HuDiff, a diffusion model for humanizing antibodies and nanobodies, showing improved similarity to experimentally humanized sequences and enhanced binding affinity.

IgGM: A Generative Model for Functional Antibody and Nanobody Design

IgGM is a generative model that designs functional antibodies and nanobodies by predicting sequences and structures simultaneously for a given antigen.

CD-GPT As a Biological Foundation Model Bridging the Gap between Molecular Sequences Through Central Dogma

CD-GPT is a foundation model that captures sequence relationships between DNA, RNA, and proteins, performing well in predictive and generative tasks across molecular types.

Fast and accurate modeling and design of antibody-antigen complex using tFold

This paper introduces tFold-Ab and tFold-Ag for fast and accurate prediction of antibody and antibody-antigen complex structures, showing improved speed and performance over AlphaFold-Multimer.

Deep Domain Adversarial Neural Network for the Deconvolution of Cell Type Mixtures in Tissue Proteome Profiling

This paper introduces scpDeconv, a deep learning method for deconvolving cell type mixtures in proteomic data, showing improved performance across species and technologies.

De novo generation of T-cell receptors with desired epitope-binding property by leveraging a pre-trained large language model

The paper introduces ERTransformer, a large language model that generates T-cell receptors with desired epitope-binding properties, showing high functional similarity to natural TCRs.

De novo generation of antibody CDRH3 with a pre-trained generative large language model

This paper introduces PALM, a pre-trained generative large language model for de novo antibody CDRH3 design, and A2binder for predicting antigen-antibody binding, showing effectiveness against SARS-CoV-2 variants.