Boston Protein Design and Modeling Club
Boston Protein Design and Modeling Club (BPDMC) is a community of computational protein engineers and modelers from both academia and industry. While we are based in Boston USA, BPDMC is also a global online community open to everyone.
BPDMC was founded by Chris Bahl in 2017, and is currently organized by Sergey Ovchinnikov, Nick Polizzi and Chris Bahl, with generous assistance from many folks.
Learning millisecond protein dynamics from what is missing in NMR spectra
Empowering Biomedical Discovery with “AI Scientists”
Model. Package. Deploy. Repeat: A DevOps Approach to Biomolecular Scalability
BindCraft: one-shot design of functional protein binders
Interpreting state-of-the-art structure predictors for protein-peptide complexes
RNA Function, Design, and Modeling
Designing new and improved functions in natural protein folds
From DNA Origami to Protein Design: Symmetry-Guided Principles Across Scales
Boltz-1 and the Future of Biomolecular Foundation Models
Physics-aware agentic artificial intelligence to model, design and discover proteins
De novo design of miniprotein-based natural killer cell engagers
Massively parallel discovery of peptides to inhibit cellular protein interactions
Small But Mighty: What an LSTM Network Reveals About Protein Design and About Machine Learning
Jointly Embedding Protein Structures and Sequences through Residue Level Alignment
Review and discussion of AlphaFold3
Recent methods for protein structure generation and design
Designer proteins for stem cell engineering
Shedding light on functional dark matter with genomic language modeling
Computational Design of non-porous, pH-responsive antibody nanoparticles
Unsupervised early warning of viral antibody escape to design & test variant-proof therapeutics
Bridging Biophysics and AI to Optimize Protein Design
Learning transferable protein backmapping from conformational ensembles
DiffDock: Diffusion Steps, Twists and Turns for Molecular Docking and Beyond!
Computational design of autoinhibitory domains for a protease-activated PD-L1 antagonist
Exploring structural heterogeneity through cryoEM, cryoET, and deep learning
Investigating the volume &diversity of data needed for generalizable antibody-antigen ∆∆G prediction
Exploration of novel functional sequence space using evolution-informed design