Author

Shirley W. I. Siu

Macao Polytechnic UniversityORCID 0000-0002-3695-7758Unclaimed ORCID profile · follow to get notified of new preprints

Biology Disciplines

Click to filter author papers

Bioinformatics· 6

Signature Assays, Organisms & Methods

Click to filter · or open tag

Approach:deep learning· 6 Assay:protein sequence· 5 Research Focus:benchmarking· 2 Research Focus:protein design· 2 Research Focus:sequence-to-function modeling· 2 Organism:bacteria (other)· 1 Research Focus:drug response / drug discovery· 1 Research Focus:gene regulatory network inference· 1

Frequent Co-Authors

Jianxiu CaiiD· 3 shared Jielu YaniD· 3 shared Mingliang ZhouiD· 3 shared François‐Xavier Campbell‐ValoisiD· 2 shared Shaolong Lin· 2 shared Silong ZhaiiD· 2 shared Tiantao Liu· 2 shared Xinke ZhaniD· 2 shared

Activity by Year

2021-2026 · peak 4/yr

Co-Author Collaboration Network

10 top collaborators · 20 mutual co-author links

Click any collaborator node to inspect or filter shared papers

Focal author (center)Selected co-authorORCID co-authorUnlinked name

Curved chords = mutual co-authorship

3 shared papersBioinformatics

Jianxiu CaiORCID

Mutual co-authors in cluster

Author profile →

6 papers

Recent·Most cited

MAERM: Predicting Enzyme-Reaction Matching Relationships with a Mixed-Attention Model

Tiantao Liu, Silong Zhai, Shaolong Lin, Xinke Zhan, Junwen Deng, Huanxiang Liu, Shirley W. I. Siu

MAERM predicts enzyme-reaction matching relationships using a mixed-attention model, outperforming baselines and enabling enzyme design.

bioRxiv · Jul 10, 2026 · PreprintBioinformatics

BERT-T6: Towards High-accuracy T6SS Bacterial Toxin Identification Using Protein Language Model

Xianwei Mo, Jianxiu Cai, Shirley W. I. Siu

The paper develops BERT-T6, a model using transfer learning on ProtBert embeddings to predict T6SEs with high accuracy and performance metrics.

Journal of Chemical Information and Modeling · May 7, 2026Peer-reviewedBioinformatics

Diffusion-ACP39: A Decoder-Adaptive Latent Diffusion Framework for Generative Anticancer Peptide Discovery

Jielu Yan, Qichun Wu, YiFan Li, Jianxiu Cai, Mingliang Zhou, François‐Xavier Campbell‐Valois, Shirley W. I. Siu

This paper introduces Diffusion-ACP39, a generative model for anticancer peptide discovery, achieving 94.5% accuracy in generating novel peptides.

bioRxiv · Mar 6, 2026 · PreprintBioinformatics

Protein-peptide Interaction Representation Learning with Pretrained Language Models

Xinke Zhan, Silong Zhai, Tiantao Liu, Shaolong Lin, Tao Bi, Bingwen Zhu, Shirley W. I. Siu

PepInter is a deep learning framework that uses pre-trained language models to predict protein-peptide interactions and bioactivity, outperforming existing methods on benchmark datasets.

bioRxiv · Jan 13, 2026 · PreprintBioinformatics

ClsDiff-AMP30: Generating Antimicrobial Peptides by a Classifier Guidance Noise Predictor

Jielu Yan, Jianxiu Cai, Yifan Li, Zhongyao Lin, Weizhi Xian, Xuekai Wei, Iun Fan Lei, Mingliang Zhou, François‐Xavier Campbell‐Valois, Shirley W. I. Siu

ClsDiff-AMP30 generates short antimicrobial peptides with high antimicrobial activity and low toxicity through a classifier-guided diffusion model.

bioRxiv · Nov 25, 2025 · PreprintBioinformatics

Multi-Branch-CNN: classification of ion channel interacting peptides using parallel convolutional neural networks

Jielu Yan, Bob Zhang, Mingliang Zhou, Hang Fai Kwok, Shirley W. I. Siu

The paper introduces Multi-Branch-CNN, a parallel CNN method for classifying ion channel interacting peptides, showing improved performance on novel sequences compared to traditional ML algorithms and other CNN variants.

bioRxiv · Nov 13, 2021 · PreprintBioinformatics