Bo Wang

A high-resolution protein-RNA binding atlas for structure-aware interaction prediction and post-transcriptional regulatory modeling

The paper introduces ecCLIP for high-resolution RBP binding maps and Pythia for structure-aware RNA-protein interaction modeling, improving RNA half-life prediction and variant effect assessment.

Complete genome-derived metabolic interactions reveal impact of gut ecology on human health

This study uses complete genomes to model gut microbiome metabolic interactions, revealing ecological group dynamics linked to inflammatory bowel disease and improving disease diagnosis.

A Practice on Antibody Hydrophobic Interaction Chromatography Retention Time Prediction using Pre-Trained Large Language Model Fine-Tuning

This study fine-tunes a pre-trained language model to predict antibody hydrophobicity using retention time data, achieving high accuracy with rigorous data quality control.

Phagocytic activity of perivascular cell promotes CNS injury pathology

The paper identifies perivascular cells as phagocytes that clear CNS debris and shows Axl inhibition reduces pathology and improves recovery after spinal cord injury.

Miniaturized subcutaneous cellular implants for sustained therapeutic protein delivery in resource-limited settings

A miniaturized cell encapsulation platform enables sustained therapeutic protein delivery in resource-limited settings through minimally invasive implantation and retrieval.

Decoding Immune Reconstitution Failure in People Living with HIV through Single-cell Genomics

This study uses single-cell multi-omics to analyze immune reconstitution failure in HIV patients, identifying genetic and epigenetic factors and developing a predictive model.

Complete Genomes of Cultivated Gut Bacteria Reveal Mobile Genetic Element-Driven Functional Diversity with Therapeutic Implications

The paper presents a comprehensive compendium of fully circularized human gut bacterial genomes and reveals how mobile genetic elements drive functional diversity with therapeutic implications.

Multiscale conformational sampling of multidomain fusion proteins by a physics informed diffusion model

This paper introduces a physics-informed diffusion model to efficiently sample conformational ensembles of multidomain fusion proteins, outperforming traditional methods in capturing large-scale dynamics.

Multimodal AI for Single cfDNA Profiling and Cancer Screening

The paper develops a Transformer-based model called cfAI to profile and detect cancer-derived cfDNA by integrating methylation, fragmentomics, and histone modifications, achieving high sensitivity and specificity in multi-cancer detection.

A Na+-selective receptor enables state-dependent plasticity in high-salt taste

The paper identifies a Na+-selective receptor mechanism in Drosophila that enables state-dependent plasticity in high-salt taste, allowing specific suppression of Na+ aversion during deficiency.

Evidence that humans underestimate body mass in microgravity: kinematic signatures in reaching movements during spaceflight

The paper shows astronauts' reaching movements slow in microgravity due to underestimated body mass, not strategic slowing, with kinematic changes linked to sensorimotor adaptation.

Remodeling of purinergic signaling in the paraventricular hypothalamus promotes hyperphagic obesity and insulin resistance

This study shows that high-fat diet induces purinergic signaling in the hypothalamus, leading to obesity and insulin resistance, and that targeting P2Y12 can reverse these effects.

STOmicsDB: a database of Spatial Transcriptomic data

STOmicsDB provides a database for spatial transcriptomics data with tools for dataset visualization, publication search, and data archiving.

Mechanistic Deep Learning Framework on Cell Traits Derived from Single-Cell Mass Cytometry Data

This paper develops a machine learning framework for analyzing mass cytometry data to uncover genetic perturbations and cell-type dynamics in hematopoietic systems.

The mutational landscape of single neurons and oligodendrocytes reveals evidence of inflammation-associated DNA damage in multiple sclerosis

The paper analyzes somatic mutations in neurons and oligodendrocytes from MS patients, finding increased DNA damage linked to inflammation.

CDCP: a visualization and analyzing platform for single-cell datasets

CDCP is a platform for sharing and analyzing single-cell datasets, offering visualization and analysis tools for researchers.

Structures of potent and convergent neutralizing antibodies bound to the SARS-CoV-2 spike unveil a unique epitope responsible for exceptional potency

The paper reports the cryo-EM structure of a potent SARS-CoV-2 NAb, BD-368-2, showing it blocks ACE2 binding and induces structural changes in the spike trimer, distinct from other NAbs.

Deep neural network affinity model for BACE inhibitors in D3R Grand Challenge 4

The paper develops a deep neural network model for predicting BACE ligand binding affinities, achieving a Spearman rank correlation of 0.43(7) in the D3R Grand Challenge 4.

Construction of the third generation Zea mays haplotype map

The paper constructs the third generation Zea mays haplotype map using whole genome sequencing data from 1,218 maize lines, identifying 83 million variant sites.