This paper stratifies Parkinson's disease patients using T-cell receptor repertoires and develops classifiers that achieve high AUC for subtype diagnosis.

Genome Medicine · Sep 29, 2026Peer-reviewedNeuroscience

Blind Prediction of Complex Water and Ion Ensembles Around RNA in CASP16

Rachael C. Kretsch, Elisa Posani, Eugene F. Baulin, Janusz Marek Bujnicki, Giovanni Bussi, Thomas E. Cheatham, Shi‐Jie Chen, Arne Elofsson, Masoud Amiri Farsani, Olivia N. Fisher, M. Michael Gromiha, Ayush Gupta, Michiaki Hamada, Kannan Harini, Gang Hu, , Rhiju Das

This paper evaluates blind predictions of dynamic water and ion ensembles around RNA using cryo-EM densities from CASP16, finding that molecular dynamics approaches perform best.

Proteins Structure Function and Bioinformatics · Nov 8, 2025Peer-reviewedBiophysics

A Joint Deep Learning Model for Simultaneous Batch Effect Correction, Denoising and Clustering in Single-Cell Transcriptomics

Justin Lakkis, David Wang, Yuanchao Zhang, Gang Hu, Kui Wang, Huize Pan, Lyle Ungar, Muredach P. Reilly, Xiangjie Li, Mingyao Li

This paper introduces CarDEC, a deep learning model that simultaneously corrects batch effects, denoises, and clusters scRNA-seq data, outperforming existing methods in multiple evaluations.

Genome Research · Oct 1, 2021Peer-reviewedBioinformatics

Critical Assessment of Protein Intrinsic Disorder Prediction

Marco Necci, Damiano Piovesan, CAID Predictors, Md Tamjidul Hoque, Ian Walsh, Sumaiya Iqbal, Michele Vendruscolo, Pietro Sormanni, Chen Wang, Daniele Raimondi, Ronesh Sharma, Yaoqi Zhou, Thomas Litfin, Oxana V. Galzitskaya, Michail Yu. Lobanov, , Silvio C. E. Tosatto

The paper evaluates 43 methods for predicting intrinsically disordered regions and binding regions in proteins, finding that deep learning methods outperform older physicochemical approaches but binding prediction remains challenging.

Nature Methods · Apr 19, 2021Peer-reviewedBioinformatics

Deep learning enables accurate clustering and batch effect removal in single-cell RNA-seq analysis

Xiangjie Li, Kui Wang, Yafei Lyu, Huize Pan, Jingxiao Zhang, Dwight E. Stambolian, Katalin Suszták, Muredach P. Reilly, Gang Hu, Mingyao Li

This paper introduces DESC, a deep learning method for single-cell clustering that improves accuracy and removes batch effects.

Nature Communications · May 11, 2020Peer-reviewedGenomics

Data Denoising with transfer learning in single-cell transcriptomics

Jingshu Wang, Divyansh Agarwal, Mo Chao Huang, Gang Hu, Zilu Zhou, Chengzhong Ye, Nancy Ruonan Zhang

This paper improves scRNA-seq data quality using transfer learning by combining a deep autoencoder with a Bayesian model to extract gene-gene relationships across diverse datasets.

Nature Methods · Aug 30, 2019Peer-reviewedBioinformatics