|
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 |
|
|
|
Full list on Google Scholar. See also all publications → |
|
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. |
|
A Large Language Model Guides the Affinity Maturation of Antibodies Generated by Combinatorial Optimization Algorithms
Faisal Bin Ashraf, Karen Paco, Zihao Zhang, Christian J. Dávila Ojeda, Mariana P. Mendivil, Jordan A. Lay, Tristan Y. Yang, Fernando L. Barroso da Silva, Matthew H. Sazinsky, Animesh Ray, Stefano Lonardi Preprint (bioRxiv) · AAAI FMs4Bio Workshop, 2025 preprint / code Ab-Affinity: hybrid LLM-driven antibody design framework integrating genetic algorithms and simulated annealing. Achieves >160× binding affinity improvements over experimental candidates. |
| All publications → |
|
|
© Faisal B. Ashraf · faisal.b.ashraf@gmail.com · Riverside, CA |
|
Design and source code from Jon Barron's website |