Biology subjects

Huang, D.-S.

Publications and source records attributed to Huang, D.-S..

4 recordsLinked to original sources

bioRxiv2026

Hierarchical refinements of cis-regulatory inputs improve scalable gene expression prediction

Deciphering the relationships between cis-regulatory elements (CREs) and target gene expression has long been a challenging problem in molecular biology. However, predicting gene expression from hundreds of candidate cis-regulatory elements (cCREs) requires models that scale to long, noisy inputs while retaining interpretable regulatory structure. Existing Transformer-based approaches typically attend over all nucleotides and all surrounding cCREs, diluting causal signals when hundreds of elements compete for limited model capacity. Here we introduce a two-stage selective framework (TSSF) that performs hierarchical refinements: nucleotide-level masking within each cCRE, followed by cCRE-level selection around each gene, implemented with information-bottleneck priors and a fully Transformer-based architecture. Across 70 human cell types and tissues, TSSF and lightweight variants improve expression prediction and enhancer-gene prioritization relative to strong baselines, including on cross-cell-line and cell-type-specific benchmarks. Prediction-stratified analysis motivates a distance-decay prior that aligns attention with long-range regulatory geometry, and chromatin-contact augmentation improves recovery of distal links. Motif analyses of high-confidence predictions recover proximal and distal regulatory programs, supporting mechanistic interpretability. TSSF offers a general strategy for scalable, interpretable modeling of high-dimensional regulatory inputs in genomics.

bioinformatics↗

bioRxiv2025

Multi-task spatial omics analytics for high-precision modeling of tissue architecture with STAX

The rapid advancement of spatial omics technology has revolutionized biomedical research, unveiling unprecedented insights into the molecular and cellular architecture of biological systems. Despite this progress, a critical limitation arises from the widespread use of disparate analytical tools within a single workflow, leading to inconsistencies caused by heterogeneous preprocessing pipelines and extensive method-specific hyperparameter tuning. To this end, we aim to unify diverse analytical tasks within a multi-task learning platform, STAX, for diverse spatial omics types. STAX excels across numerous critical applications, including spatial domain identification, spatial slice integration, cohort-level spatial analysis, spatial spot completion, cell-gene co-embedding, expression profile denoising, and 3D spatial multi-slice simulation. Extensive evaluations demonstrate that STAX consistently delivers superior performance, robustness, and biologically meaningful interpretations, establishing it as an indispensable tool for spatial omics research. In short, STAX effectively addresses multiple analytical challenges in spatial omics, empowering researchers with a unified platform to accelerate biomedical discoveries and deepen understanding of complex biological systems.

bioinformatics↗

bioRxiv2025

Multi-species integration, alignment and annotation of single-cell RNA-seq data with CAMEX

Single-cell RNA-seq (scRNA-seq) data from multiple species present remarkable opportunities to explore cellular origins and evolution. However, integrating and annotating scRNA-seq data across different species remains challenging due to the variations in sequencing techniques, ambiguity of homologous relationships, and limited biological knowledge. To tackle the above challenges, we introduce CAMEX, a heterogeneous Graph Neural Network (GNN) tool that leverages many-to-many homologous relationships for multi-species integration, alignment, and annotation of scRNA-seq data from multiple species. Notably, CAMEX outperforms state-of-the-art methods integration on various cross-species benchmarking datasets (ranging from one to eleven species). Besides, CAMEX facilitates the alignment of diverse species across different developmental stages, significantly enhancing our understanding of organ and organism origins. Furthermore, CAMEX enables the detection of species-specific cell types and marker genes through cell and gene embedding. In short, CAMEX holds the potential to provide invaluable insights into how evolutionary forces operate across different species at single-cell resolution.

bioinformatics↗

bioRxiv2021

Base-resolution prediction of transcription factor binding signals by a deep learning framework

Transcription factors (TFs) play an important role in regulating gene expression, thus the identification of the sites bound by them has become a fundamental step for molecular and cellular biology. In this paper, we developed a deep learning framework leveraging existing fully convolutional neural networks (FCN) to predict TF-DNA binding signals at the base-resolution level, called FCNsignal. The proposed FCNsignal can simultaneously achieve the following tasks: (i) modeling the base-resolution signals of binding regions; (ii) discriminating binding or non-binding regions; (iii) locating TF-DNA binding regions; (iv) predicting binding motifs. The experimental results on 53 TF ChIP-seq datasets and 6 chromatin accessibility ATAC-seq datasets show that our proposed framework outperforms some existing state-of-the-art methods. In addition, we explored to use the trained FCNsignal to locate all potential TF-DNA binding regions on a whole chromosome and predict DNA sequences of arbitrary length, and the results show that our framework can find most of the known binding regions and accept sequences of arbitrary length. Furthermore, we demonstrated the potential ability of our framework in discovering causal disease-associated single-nucleotide polymorphisms (SNPs) through a series of experiments. Author summaryIdentification of transcription factor binding sites (TFBSs) is fundamental to study gene regulatory networks in biological systems, as TFs activate or suppress the transcription of genes by binding to specific TFBSs. With the development of high-throughput sequencing technologies and deep learning (DL), several DL-based approaches have been developed for systematically studying TFBSs, achieving impressive performance. Nevertheless, these methods either excessively focus on discriminating binding or non-binding sequences or individually accomplish multiple TFBSs-associated tasks. In this work, we provide an integrated framework, which utilizes the FCN architecture to predict TF-DNA binding signals at the base-resolution level, to simultaneously study multiple TFBSs-associated tasks. More importantly, we also demonstrate that our proposed framework has the ability to locate all potential TF-DNA binding regions from DNA sequences of arbitrary length. We hope that our framework can provide a new perspective on studying the mechanism of TF-DNA binding and its related tasks.

bioinformatics↗