This paper introduces deepGPS, a deep generative model that predicts protein subcellular localization using both sequence and image data, providing textual and image outputs.

Briefings in Bioinformatics · Mar 1, 2025Peer-reviewedBioinformatics

Large-scale benchmarking of circRNA detection tools reveals large differences in sensitivity but not in precision

Marieke Vromman, Jasper Anckaert, Stefania Bortoluzzi, Alessia Buratin, Chia-Ying Chen, Qinjie Chu, Trees‐Juen Chuang, Roozbeh Dehghannasiri, Christoph Dieterich, Xin Dong, Paul Flicek, Enrico Gaffo, Wanjun Gu, Chunjiang He, Steve Hoffmann, , Pieter‐Jan Volders

The paper benchmarks 16 circRNA detection tools across three human cell types, finding large differences in sensitivity but consistent precision, and recommends tool combinations for improved detection.

Nature Methods · Jul 13, 2023Peer-reviewedGenomics

RNAlight: a machine learning model to identify nucleotide features determining RNA subcellular localization

Guo-Hua Yuan, Ying Wang, Guang‐Zhong Wang, Li Chun Yang

RNAlight identifies nucleotide features determining RNA subcellular localization using LightGBM and Tree SHAP, revealing sequence basis for distinct RNA localization patterns.

Briefings in Bioinformatics · Oct 26, 2022Peer-reviewedBioinformatics

SCAPTURE: a deep learning-embedded pipeline that captures polyadenylation information from 3' tag-based RNA-seq of single cells

Guo‐Wei Li, Nan Fang, Guo-Hua Yuan, Chu‐Xiao Liu, Xindong Liu, Ling‐Ling Chen, Bin Tian, Li Chun Yang

SCAPTURE identifies and quantifies cleavage and polyadenylation sites from 3' tag-based scRNA-seq, improving cell identity refinement.

Genome biology · Aug 10, 2021Peer-reviewedBioinformatics