Zhandong Liu

Transcriptomic data and biomedical literature synergize in finding pharmacologic gene regulators

The paper introduces SNACKKSS, a tool that integrates RNA-Seq data and biomedical literature to predict protein-inhibiting drugs, showing improved performance when combined with existing predictors.

A massively parallel reporter assay of MECP2 cis-regulatory elements reveals genetic candidates for male-biased autism

The paper identifies noncoding MECP2 variants that cause male-biased autism by disrupting CRE activity and reducing MECP2 expression.

Early dynamics of a neutrophil interferon program drive immunotherapy resistance and limit durable anti-tumor immunity

This study identifies an early neutrophil interferon program that predicts resistance to anti-PD1 therapy and limits durable anti-tumor immunity.

Integrated Clinical-Genomic Reanalysis Identifies Diagnostic Gaps and Candidate Genes in a Pediatric Rare Disease Cohort

Functional divergence of Capicua isoforms explains differential tissue vulnerability in neurological disease

The paper shows that different isoforms of CIC interact with paralogs ATXN1 and ATXN1L, leading to distinct phenotypes and explaining tissue-specific vulnerability in neurological diseases.

Vision-Based Genomic Model for Copy Number Variant Pathogenicity Prediction

This paper introduces a vision-based model for predicting CNV pathogenicity using track-based spatial representations, achieving improved performance on benchmarks and clinical datasets.

MARRVEL-MCP enables natural language variant interpretation through autonomous workflow construction

MARRVEL-MCP enables natural language variant interpretation by allowing LLMs to autonomously construct workflows using curated genomic tools, improving performance over models without tool access.

scDeepVariant: A population-informed deep learning framework for germline variant calling in scRNA-seq

scDeepVariant improves germline variant calling in scRNA-seq by integrating population allele frequency data, outperforming existing methods in precision, recall, and rare variant detection.

MECP2 Duplication Uncouples Mitochondrial and Purine Metabolism During neuronal maturation

The paper identifies a disrupted mitochondrial-purine metabolism link in MECP2 Duplication Syndrome across multiple models, linking it to neurodevelopmental issues.

Reinforcement learning enables single-cell foundation models to learn cellular differentiation

This paper introduces DiRL, a reinforcement learning framework that enables single-cell foundation models to model and control cellular differentiation by optimizing multi-step perturbation strategies.

Positional frequency chaos game representation for machine learning-based classification of crop lncRNAs

This paper introduces PFCGR, a new encoding method for classifying plant lncRNAs using machine learning, achieving high accuracy with significantly reduced computational time compared to DNABERT.

Revealing the nervous system requirements of Alzheimer disease risk genes in Drosophila

This study identifies nervous system requirements for Alzheimer's disease risk genes in Drosophila by analyzing gene function and neurodegeneration.

Early transcriptional signatures of MeCP2 positive and negative cells in Rett syndrome

The paper identifies early transcriptional differences between MeCP2 positive and negative cells in Rett syndrome models, revealing sex-specific molecular effects in excitatory and inhibitory circuits.

Multi-omics delineate growth factor network underlying exercise effects in an Alzheimer's mouse model

The paper investigates how exercise affects Alzheimer's disease in mice by analyzing gene expression and chromatin changes, finding that growth factor signaling pathways are key to exercise's benefits.

Comparative Analysis of AAV Serotypes for Transduction of Olfactory Sensory Neurons

This study compares 11 AAV serotypes for transduction efficiency and specificity in murine olfactory sensory neurons using nasal inoculation.

Lemur: A Single-Cell Foundation Model with Fine-Tuning-Free Hierarchical Cell-Type Generation for Drosophila melanogaster

Lemur is a single-cell foundation model for Drosophila melanogaster that enables fine-tuning-free cell-type annotation across diverse tissues and conditions.

A network regularized linear model to infer spatial expression pattern for single cell

The paper introduces glmSMA, a computational algorithm that predicts cell locations by integrating scRNA-seq data with spatial-omics reference atlases, demonstrating its ability to recapitulate spatial gene expression and anatomical structures.

Systems genetic dissection of Alzheimer's disease brain gene expression networks

This study uses a cross-species approach to identify gene expression networks linked to Alzheimer's disease pathology and neurodegeneration.

Differential effects of MATR3 variants on its cryptic splicing repression function

This study investigates how MATR3 variants affect cryptic splicing repression, showing that some variants reduce protein solubility and impair RNA binding and splicing regulation.

CoRegNet: Unraveling Gene Co-regulation Networks from Public RNA-Seq Repositories Using a Beta-Binomial Statistical Model

CoRegNet constructs gene co-regulation networks from public RNA-Seq data using a beta-binomial model, outperforming existing methods and identifying non-linear and Simpson's paradox gene pairs.

A cross-species proteomic map reveals neoteny of human synapse development

This study creates a cross-species proteomic map of synapse development in human, macaque, and mouse neocortex, revealing slower human PSD maturation and its potential link to neoteny.

Tau polarizes an aging transcriptional signature to excitatory neurons and glia

The paper uses single-cell RNA-sequencing in Drosophila to show that tau pathology and aging affect different cell types, with tau primarily impacting excitatory neurons and glia.

NMRQNet: a deep learning approach for automatic identification and quantification of metabolites using Nuclear Magnetic Resonance (NMR) in human plasma samples

NMRQNet automatically identifies and quantifies metabolites in human plasma NMR spectra, outperforming existing methods and identifying potential biomarkers for neurological disorders.

SPA-STOCSY: An Automated Tool for Identification of Annotated and Non-Annotated Metabolites in High-Throughput NMR Spectra

SPA-STOCSY is an automated tool for identifying annotated and non-annotated metabolites in NMR spectra, showing high accuracy and efficiency in both synthetic and real data.

Unraveling Spatial Gene Associations with SEAGAL: a Python Package for Spatial Transcriptomics Data Analysis and Visualization

SEAGAL is a Python package that detects and visualizes spatial gene correlations in spatial transcriptomics data using the L-index method.

MeCP2 regulates Gdf11, a dosage-sensitive gene critical for neurological function

This study identifies Gdf11 as a MeCP2-regulated gene critical for neurological function, showing that altering its dosage affects behavior and longevity in mouse models.

scGREAT: Graph-based regulatory element analysis tool for single-cell multi-omics data

scGREAT is a tool for analyzing regulatory elements in single-cell multi-omics data, enabling heterogeneity analysis and regulatory state inference.

PolyAMiner-Bulk: A Machine Learning Based Bioinformatics Algorithm to Infer and Decode Alternative Polyadenylation Dynamics from bulk RNA-seq data

PolyAMiner-Bulk identifies and decodes alternative polyadenylation dynamics from bulk RNA-seq data, revealing novel APA changes in disease contexts and Alzheimer's Disease.

Single-cell Multi-omics Integration for Unpaired Data by a Siamese Network with Graph-based Contrastive Loss

This paper introduces MinNet, a Siamese network with graph-based contrastive loss for integrating single-cell multi-omics data, showing its effectiveness in removing batch effects and improving downstream analysis.

Accurate cell type deconvolution in spatial transcriptomics using a batch effect-free strategy

This paper introduces ReSort, a method to improve cell type deconvolution in spatial transcriptomics by reducing batch effects, and shows it enhances accuracy in mouse breast cancer data.