Boltz2-Notebook: An Interactive Google Colab Platform for Diffusion-Based Biomolecular Structure and Binding Affinity Prediction using the Boltz2 model.
- 1Gujarat Biotechnolgy University
Abstract
Recent advances in deep learning-based structure prediction, including AlphaFold3 and the open-source Boltz model family, have extended biomolecular modeling to joint prediction of protein-ligand, protein-nucleic acid, and multi-chain complexes with binding-affinity estimation. Boltz-2 is among the most feature-complete of these open models, but its practical use requires a local CUDA-capable GPU, command-line execution, and manually authored YAML configuration files, limiting accessibility for researchers without dedicated computational infrastructure. We developed Boltz2-Notebook, a Colab-native interface comprising four integrated stages - automated environment setup, interactive parameter-to-YAML generation, execution management, and automated confidence and affinity visualization - together with a manifest-driven batch mode for multi-target screening. All modelling capabilities are inherited unmodified from Boltz-2; Boltz2-Notebook's contributions are limited to accessibility, input construction, and workflow automation. Independent of the software, we curated a benchmark of 317 protein-ligand pairs (122 proteins, 277 ligands) from BindingDB and predicted binding affinity in triplicate using the Boltz-2 command-line engine on high-performance computing infrastructure. Predicted and experimental pIC50 values showed moderate correlation (Pearson r = 0.609 [95% CI 0.540-0.675]; Spearman {rho} = 0.625; R2 = 0.371; MAE = 0.968 pIC50 units), with high triplicate reproducibility (pairwise r = 0.97) but a systematic compression of the predicted affinity range and no measurable relationship between Boltz-2's self-reported confidence metrics and prediction accuracy. Boltz2-Notebook is freely available as open-source software and provides external, reproducible evidence - including a specific confidence-calibration limitation - relevant to interpreting Boltz-2 affinity predictions responsibly.
Related
- All-Atom Structure Tokenizer: AtomLM-9b for Biomolecular Structure Prediction
- RGI-Toolkit: Differentiable Restraints for Controllable Biomolecular Structure Prediction
- From Prediction Accuracy to Prediction Use: A Monitoring-Centered Framework for Interactive Sport Expertise
- labapi: a Python object model for the LabArchives electronic lab notebook
- Diffusion tensor imaging of whole human brains during long-term formaldehyde fixation: Temporal evolution of diffusion parameters, post-mortem conditions, and dependence on tissue structure
BibTeX
@misc{tilewale2026boltz2notebook,
title = {{Boltz2-Notebook: An Interactive Google Colab Platform for Diffusion-Based Biomolecular Structure and Binding Affinity Prediction using the Boltz2 model.}},
author = {A. Tilewale and D. Patel},
howpublished = {bioRxiv},
year = {2026},
month = sep,
doi = {10.64898/2026.09.18.752645},
url = {https://www.biorxiv.org/content/10.64898/2026.09.18.752645v1},
note = {CC BY},
}
RIS
TY - UNPB
TI - Boltz2-Notebook: An Interactive Google Colab Platform for Diffusion-Based Biomolecular Structure and Binding Affinity Prediction using the Boltz2 model.
AU - A. Tilewale
AU - D. Patel
PY - 2026
DA - 2026/09/18
PB - bioRxiv
DO - 10.64898/2026.09.18.752645
UR - https://www.biorxiv.org/content/10.64898/2026.09.18.752645v1
AB - Recent advances in deep learning-based structure prediction, including AlphaFold3 and the open-source Boltz model family, have extended biomolecular modeling to joint prediction of protein-ligand, protein-nucleic acid, and multi-chain complexes with binding-affinity estimation. Boltz-2 is among the most feature-complete of these open models, but its practical use requires a local CUDA-capable GPU, command-line execution, and manually authored YAML configuration files, limiting accessibility for researchers without dedicated computational infrastructure. We developed Boltz2-Notebook, a Colab-native interface comprising four integrated stages - automated environment setup, interactive parameter-to-YAML generation, execution management, and automated confidence and affinity visualization - together with a manifest-driven batch mode for multi-target screening. All modelling capabilities are inherited unmodified from Boltz-2; Boltz2-Notebook's contributions are limited to accessibility, input construction, and workflow automation. Independent of the software, we curated a benchmark of 317 protein-ligand pairs (122 proteins, 277 ligands) from BindingDB and predicted binding affinity in triplicate using the Boltz-2 command-line engine on high-performance computing infrastructure. Predicted and experimental pIC50 values showed moderate correlation (Pearson r = 0.609 [95% CI 0.540-0.675]; Spearman {rho} = 0.625; R2 = 0.371; MAE = 0.968 pIC50 units), with high triplicate reproducibility (pairwise r = 0.97) but a systematic compression of the predicted affinity range and no measurable relationship between Boltz-2's self-reported confidence metrics and prediction accuracy. Boltz2-Notebook is freely available as open-source software and provides external, reproducible evidence - including a specific confidence-calibration limitation - relevant to interpreting Boltz-2 affinity predictions responsibly.
ER -