Yong Zhang

The paper identifies biological features that influence cross-species predictability of regulatory occupancy and provides a framework to estimate predictability probabilities.

The paper benchmarks phase-separating protein predictors using a taxonomy-aware, disorder-matched benchmark to reduce biases and improve evaluation.

ChromSkills provides a framework for reproducible and interpretable chromatin data analysis using domain-specific tools guided by LLMs.

ChromBERT-tools generates context-specific embeddings of transcription regulators for different cell types to enhance regulatory modeling and interpretation.

This study shows that SWI/SNF chromatin remodeling complexes regulate cilia stability and kidney function by modulating foxj1a and rfx2 expression in zebrafish.

ChromBERT, a foundation model pre-trained on ChIP-seq data, generates interpretable representations of context-specific transcription regulatory networks and improves imputation and modeling of regulatory effects in cell types.

This paper introduces HGGEP, a hypergraph neural network model that predicts gene expression from histology images by capturing cell morphology and higher-order feature associations.

ImSpiRE enhances spatial transcriptomic resolution using image features and optimal transport to improve subspot-level resolution and discover tissue domains and signaling patterns.

The paper introduces CondSigDetector, a computational framework to identify chromatin-associated biomolecular condensates, revealing their genomic landscapes and components in mESC and K562 cells.

The paper identifies maternal-specific chromatin regulators in zebrafish embryogenesis using a computational pipeline and F0 homozygous mutation technology.

The paper annotates and categorizes functional variants in farm animals using epigenomic data, showing improved genomic prediction accuracy and identifying trait-related tissues and cell types.

The paper investigates CTCF chromatin occupancy during mouse pre-implantation development and identifies ADNP's role in modulating SINE B2-derived CTCF-binding sites.

PSPire is a machine learning predictor that improves identification of phase-separating proteins without intrinsically disordered regions by incorporating residue and structure-level features.

The paper studies nucleosome dynamics in mouse zygotes after fertilization, identifying factors involved in zygotic genome activation.

This study shows that neuronal EZH2 regulates neuronal morphogenesis and cognitive behavior in mice by controlling gene expression and dendritic spine density.

NUCOME organizes and provides standardized nucleosome organization data from MNase-seq across human and mouse cell types for downstream analysis.

CAM provides a comprehensive quality control pipeline for MNase-seq data, including QC measurements and a reference atlas of 268 datasets from human and mouse.

Dr.seq2 is a QC and analysis pipeline for single cell transcriptome and epigenome data, providing reliable results on published datasets.

The paper validates the principle of co-adaptation between tRNA gene copy number and amino acid usage across three life domains, showing it improves translation efficiency in both organisms and individual proteins.

MACS calls ChIP-Seq peaks by estimating tag shift from Watson/Crick strand offsets and testing enrichment against a locally adaptive Poisson background, improving specificity and binding-site resolution.