Publications & preprints

Publications by Bishal Shrestha

A coherent program, from chromatin to protein interfaces: journal papers, preprints, and work under review. Filter by first-author contributions or by the biological scale each project addresses.

7 entries

2026

First authorPROTEINS (Wiley), 2026, under review

ARC: Assessment of Interface Residue Conformation using an Ensemble of Graph Neural Networks

Shrestha B, Siciliano AJ, Huang G, Bao Y, Wang Z

An ensemble of graph neural networks that scores how accurate a predicted protein interface really is.

Graph Neural NetworksEnsembleCASP16Interface residues

Bioinformatics, 2026

Inferring the qualities of protein-RNA models with graph transformers

Siciliano AJ, Bao Y, Shrestha B, Wang Z

Extends structure-quality scoring beyond single proteins to protein-RNA complexes, the multi-biomolecule machines cells actually run on.

Graph TransformerProtein-RNAQuality assessment

EMBO Mol. Med., 2026

CITED2 is a druggable epigenetic switch coupling neuronal maturation to regenerative decline

Müller F, McLachlan E, Costa A, Qu J, Shrestha B, Wang Z, et al.

Identifies a druggable epigenetic switch that could restart nerve regeneration — a wet-lab-led collaboration with contributed computational analysis.

EpigeneticsComputational analysisNeuroscience

DOI

BMC Bioinformatics, 2026

SCW: building the whole-genome 3D structures based on extremely sparse single-cell Hi-C data

Zhu H, Liu T, Shrestha B, Wang Z

Reconstructs high-resolution whole-genome 3D structure from extremely sparse single-cell Hi-C data.

3D reconstructionsingle-cell Hi-CBenchmarking

DOI

2025

First authorBrief. Bioinform., 2025

HiC4D-SPOT: a spatiotemporal outlier detection tool for Hi-C data

Shrestha B, Wang Z

An unsupervised deep-learning tool that flags exactly where and when the 3D folding of the genome goes wrong across time.

ConvLSTMAutoencoderHi-CAnomaly detection

DOI PDF

First authorNAR Genom. Bioinform., 2025

scHiGex: predicting single-cell gene expression based on single-cell Hi-C data

Shrestha B, Siciliano AJ, Zhu H, Liu T, Wang Z

A graph transformer that predicts a single cell's gene expression directly from that same cell's 3D genome structure.

Graph Transformersingle-cell Hi-CPyTorch GeometricMulti-omics

DOI PDF Code

2023

First authorarXiv:2311.12857, 2023, preprint

Adversarial sample generation and training using geometric masks for accurate and resilient license plate character recognition

Shrestha B, Khakurel G, Simkhada K, Adhikari B

Makes license-plate recognition robust to deliberate tampering using geometric-mask adversarial training, lifting resilient accuracy from 25% to 99.7%.

Adversarial MLCNNComputer VisionRobustness

arXiv PDF Code

Earlier work

Prajapati S, Engelhardt M, Shrestha A, Khakurel G, Shrestha B, Simkhada K. Industry-Academia Collaboration in Nepal, A case study of Customer Churn Prediction for Worldlink. Research and Innovation Unit, 2021.