boltz2

Stage-based evaluation pipeline for generative molecular design: filters, retrosynthesis checks, docking, pose validation, reports, CLI/TUI.

Boltz2 Notebook – A streamlined Colab-based pipeline for protein structure prediction and binding affinity analysis using the Boltz2 deep learning model.

Python drug discovery toolkit for Boltz2 structure and affinity prediction, BoltzGen binder and antibody design, and TxGemma ADMET integration in one API.

Uses DAP (Distributed Axial Parallelism) to prevent OOM when running Boltz-2 protein structure inference. Optional FlexAttention for triangle attention.

Converts Boltz output CIF to standardized PDB and then runs PLIP to analyze protein-ligand interactions and produce Pymol session file.

BoltzMaker: Boltz2 campaign-scale structure and affinity prediction, binding analysis, and run control, orchestrated end to end from a single spec file.

Auditable SciForge × BioGym de novo protein-design run: RFdiffusion → ProteinMPNN → Boltz-2

?? Ultron Workflow - Where Science Meets Sarcasm ??? | Visual workflows, protein & DNA labs, drug discovery, 3-D mech/circuit, all powered by Ultron - your brilliantly sarcastic superintelligence. He roasts, then results. ????

A minimal, production-ready shell wrapper for running Boltz-1/Boltz-2 structure predictions from the command line. Handles logging, runtime tracking, and input sanitisation automatically so every run is reproducible and auditable.

Sequence and structural-biology pipeline (BLAST/MSA, Boltz-2 co-folding, membrane MD) for Catanduba simoni Kv4 gating-modifier toxins

UC Berkeley MSSE Capstone Project: Evaluating & refining filtering strategies for de novo protein binders

GUI for generation of Boltz2 input YAML files and run commands

One-GPU Boltz-2 screening workflow for tiny labs

A post-run analysis script for Boltz-2 co-folding predictions.

A command-line utility for generating Boltz-2 / co-folding input YAML files from a batch of candidate SMILES stored in a JSON file.

Re-analysis of a Boltz-2 vs SEA off-target benchmark: both structural confidence metrics discriminate at chance, the affinity head does not.

A Claude Code Skill for de novo D-peptide inhibitor design using the Boltz2 IC₅₀ prediction pipeline