A Nextflow pipeline for protein binder design
-
Updated
Jul 24, 2026 - Python
A Nextflow pipeline for protein binder design
A modular, extensible peptide design pipeline with target preparation, backbone generation, sequence design, scoring, and ranking. Full local CPU pipeline, and backend hooks for RFpeptides, ProteinMPNN/LigandMPNN, and ColabFold.
In-silico protein design bench: takes a target + epitope to designed, structurally validated, developable binders and multivalent scaffolds. Composes the binder-design, developability-hardening, and multivalent-display skills with the structure-model
Unified Python library and CLI for protein structure prediction and inverse folding.
Protein binder design GUI
Open hotspot-guided de novo protein binder design pipeline integrating OpenMM, BindCraft, ProteinMPNN, and AlphaFold2.
Retraining of ProteinMPNN model specifically with acid-stable structures and sequences
Optimized ProteinMPNN for Apple Silicon: 15× speedup with 0% accuracy loss through architecture pruning, batching, and ANE acceleration. Comprehensive benchmarking study of speed-accuracy trade-offs.
RNA-seq counts to ranked de novo protein binder candidates, with full provenance back to the patient cohort.
LigandMPNN but with dynamic constraints. This allows the biases applied during inference to adjust to a desired goal during the generation process. Current implementations are for pI targeting and surface patch generation
Protein binder mutagenesis GUI
Manage protein design processes
Molecular dynamic simulation of RFdiffusion/ProteinMPNN designed HMERF mutated titin Ig152/Fn3-119 domain protein binder
Personalized lymphoma therapy design with Gemma 4, AlphaFold, RFdiffusion. Kaggle Gemma 4 Good Hackathon submission.
De novo protein binder design pipeline: motif-scaffolded RFdiffusion + ProteinMPNN + AlphaFold2 self-consistency validation. PD-L1 reference example.
🧬 Lectures for course ML-protein-design
Auditable SciForge × BioGym de novo protein-design run: RFdiffusion → ProteinMPNN → Boltz-2
Computational pipeline for measuring protein interior reprogrammability. Identifies chassis candidates where exterior fold is preserved while interior chemistry varies.
Python gRPC sidecar wrapping ProteinMPNN (inverse folding / sequence design) for FoldForge.
Design proteins in your terminal. A TUI agent for de novo protein design — free by default.
Add a description, image, and links to the proteinmpnn topic page so that developers can more easily learn about it.
To associate your repository with the proteinmpnn topic, visit your repo's landing page and select "manage topics."