Faisal B. Ashraf

About · Publications · News · Experience

I'm a PhD Candidate in Computer Science at the University of California, Riverside, where I build multi-modal AI models for understanding antibody–antigen interactions and guiding antibody design, supervised by Prof. Stefano Lonardi.

My research integrates protein sequences, 3D structural context, and physicochemical properties to predict binding, capture mutation effects, and optimize therapeutic candidates. I am broadly interested in protein language modeling, structure-based learning, graph neural networks, and generative models for biomolecules and antibody design.

Email / Scholar / GitHub / LinkedIn / ResearchGate / CV

📌 On the job market (graduating by Spring 2027). Seeking Research Scientist roles in AI/ML for Protein & Antibody Design or Postdoc.

News

Nov '26	A paper on improved antibody design is published in PLoS Computational Biology
May '26	SPICE is published in Nucleic Acids Research
Mar '26	Reviewer at ACM BCB '26
Feb '26	SPICE webapp to analyse and compare protein complexes is live!
Dec '25	Sub-reviewer at RECOMB '26
Aug '25	Structure-aware LLM paper published at J. Chem. Inf. Model.
Jun '25	Bioinformatics R&D internship at Exact Sciences, San Diego

See all news →

Selected Publications

Full list on Google Scholar. See also all publications →

An antigen-specific protein language model guides CDR optimization for antibody design
Faisal Bin Ashraf, Karen Paco, Sanaz Zebardast, Zihao Zhang, Ryan Mooney, Christian J. Dávila Ojeda, Mariana P. Mendivil, Rashid M. Alam,Eva Chen,Iraneus Ogu, Jordan A. Lay, Tristan Y. Yang, Fernando L. Barroso da Silva, Malkiat Johal,Ilya Tolstorukov, Matthew H. Sazinsky, Animesh Ray, Stefano Lonardi
PLoS Computational Biology, 2026
paper / code

A finetuned PLM-driven antibody design framework integrating genetic algorithms and simulated annealing. Achieves >100× binding affinity improvements over parental antibody.

Comparative structural analysis of protein complexes with SPICE
Faisal Bin Ashraf, Stefano Lonardi
Nucleic Acids Research, Web Server Issue, 2026
paper / webapp

End-to-end web platform for comparative structural analysis of protein–protein complexes, supporting interface characterization, energetic analysis, and variant-level comparison.

Predicting Antibody–Antigen Interactions with Structure-Aware LLMs: Insights from SARS-CoV-2 Variants
Faisal Bin Ashraf, Vinz Angelo Madrigal, Stefano Lonardi
Journal of Chemical Information and Modeling, 2025
paper / code

Structure-aware ESM2 framework that jointly predicts antibody binding and neutralization for SARS-CoV-2, outperforming DeepAIR, AntiBERTa, AbMap, and A2Binder. Binding AUC improves from 0.84 → 0.93, neutralization AUC from 0.88 → 0.95.

All publications →

Education

	Ph.D. in Computer Science (expected 2027) University of California, Riverside Advisor: Prof. Stefano Lonardi.
	M.Sc. in Computer Science University of California, Riverside
	B.Sc. in Computer Science & Engineering Islamic University of Technology, Bangladesh

Design and source code from Jon Barron's website