How to use BindFilter Online

Use BindFilter online for binder screening, interface analysis, and developability-aware candidate ranking.

BindFilter is a binder evaluation workflow for screening many candidate proteins, antibodies, nanobodies, or peptides against a target. Rather than generating binders itself, it co-folds each target-binder pair and aggregates orthogonal evidence spanning interface quality, fold-backend ipTM, ipSAE-derived max ipTM, predicted affinity, structural energetics, solubility, stability, aggregation risk, toxicity, and optional mutation-scanning readouts.

On Neurosnap, researchers provide Target Sequences together with a library of Binder Sequences, choose a Chai-1 or Boltz-2 folding backend, and enable only the analysis modules relevant to the campaign. Binder and target sequences can include inline modified residues such as CCD-style PTM notation when the folding backend supports them, while sequence-only downstream tools are scored on the corresponding standard-residue representation. That makes BindFilter useful after de novo design, affinity maturation, or sequence-library generation when the main question is which candidates deserve experimental follow-up.

How BindFilter Works

BindFilter is best understood as a Neurosnap orchestration layer around complementary structure- and sequence-based models. Each candidate binder is folded against the target with either Chai-1 or Boltz-2, after which the pipeline can apply methods such as Prot2Prop for multitask developability prediction, Prodigy for affinity estimation, EvoEF2 for energetic scoring, NetSolP for solubility, TemStaPro for thermostability, Aggrescan3D for aggregation propensity, ToxinPred for peptide toxicity, and optional ProteinMPNN-ddG mutation scanning. The goal is not a single score, but a panel of partially independent signals that helps separate promising binders from candidates that only look good under one metric.

On Neurosnap, Fold Backend, MSA Mode, recycling, diffusion settings, and optional shared residue restraints control the structure-generation step, while the tool-selection toggles determine how broad the downstream screen will be. Results are organized around output.csv, with one row per successful binder candidate and human-readable columns for scalar interface, folding, developability, and energetics metrics. Detailed mutation-level tables from ProteinMPNN-ddG are provided separately as JSON files so the main binder-ranking table remains easy to compare.

What is Neurosnap?

Neurosnap is the leading platform for bioinformatics and computational science focused on expanding access to powerful modeling and simulation tools. Because many state-of-the-art machine learning systems remain complex to install, configure, and scale, Neurosnap offers a clean, browser-based workspace that removes the burden of infrastructure management, dependency conflicts, and command-line tooling.

Built for biologists, chemists, and cross-disciplinary scientists, the platform enables advanced computational workflows without requiring expertise in software engineering or cloud architecture. Researchers can launch analyses through an intuitive interface, connect programmatically through a comprehensive API, and rely on automated resource management to scale workloads efficiently. By taking care of the underlying compute and operational complexity, Neurosnap allows teams to devote their energy to scientific progress and faster iteration. Security and data protection remain foundational principles, with clear safeguards outlined in our Terms of Use and Privacy Policy to ensure your work stays protected.

Advancing Discovery with BindFilter on Neurosnap

Using BindFilter on Neurosnap could drastically accelerate binder-library screening and developability-aware target engagement triage from target and binder sequences.

Study-fit inputs: BindFilter starts from target sequences and a binder library, including multi-chain binders and supported modified residues, which matches the stage where many designed or selected candidates need to be compared against the same target.
Orthogonal evidence: The workflow combines co-folding, fold confidence, ipSAE-derived interface metrics, affinity proxies, energetics, Prot2Prop developability scores, solubility, stability, aggregation, toxicity, and optional mutation scanning so candidates are not ranked by a single fragile metric.
Configurable screening: Researchers can choose the folding backend, adjust sampling behavior, add shared restraints, and switch individual analysis modules on or off to match the campaign and binder modality.
Research workflow fit: A binder-level output.csv plus separate detailed JSON files reduces the manual work of reconciling separate tools before selecting candidates for experiments.

How to Use BindFilter on Neurosnap

To harness the capabilities of BindFilter, researchers can follow this streamlined workflow within Neurosnap:

Access Neurosnap: Start by logging in to the Neurosnap website.
Select Tool: From the list of available tools, choose BindFilter.
Provide Inputs: Provide all the inputs specified within the submission panel and optionally configure the tool as desired.
Run Tool: Submit the BindFilter job and Neurosnap will execute it in the cloud, automatically notifying you as soon as your results are ready.
Review Output: Explore your results through rich visualizations, including figures, plots, and interactive views designed to help you analyze findings with clarity and confidence.

Citations

Please cite the original work when using BindFilter in publications or research outputs.

Amani, Keaun, and Danial Gharaie Amirabadi. 2024. Neurosnap SDK Package. Software. https://github.com/NeurosnapInc/neurosnap.

Passaro, S., Corso, G., Wohlwend, J., Reveiz, M., Thaler, S., Somnath, V. R., Getz, N., Portnoi, T., Roy, J., Stark, H., Kwabi-Addo, D., Beaini, D., Jaakkola, T., & Barzilay, R. (2025). Boltz-2: Towards Accurate and Efficient Binding Affinity Prediction.

Mirdita, M., Schütze, K., Moriwaki, Y., Heo, L., Ovchinnikov, S., & Steinegger, M. (2022). ColabFold: making protein folding accessible to all. Nature Methods.

Chai Discovery, Jacques Boitreaud, Jack Dent, Matthew McPartlon, Joshua Meier, Vinicius Reis, Alex Rogozhnikov, Kevin Wu bioRxiv 2024.10.10.615955; doi: https://doi.org/10.1101/2024.10.10.615955

Vangone, A. and Bonvin, A. M. J. J. (2017). PRODIGY: A Contact-based Predictor of Binding Affinity in Protein-protein Complexes. Bio-protocol 7(3): e2124. DOI: 10.21769/BioProtoc.2124.

Vangone, A., and Bonvin, A. M. J. J. (2015). Contacts-based prediction of binding affinity in protein-protein complexes. eLife 4: 291.

Huang X, Pearce R, Zhang Y. EvoEF2: accurate and fast energy function for computational protein design. Bioinformatics. 2020 Feb 15;36(4):1135-42.

Amani, K. Prot2Prop: structure-aware fine-tuning of protein language models for joint prediction of multiple developability properties from protein inputs. bioRxiv (2026). https://www.biorxiv.org/content/10.64898/2026.06.28.735009v1

Thumuluri, V., Martiny, H.M., Almagro Armenteros, J., Salomon, J., Nielsen, H., & Johansen, A. (2021). NetSolP: predicting protein solubility in Escherichia coli using language models. Bioinformatics, 38(4), 941-946.

Aleksander Kuriata, Valentin Iglesias, Jordi Pujols, Mateusz Kurcinski, Sebastian Kmiecik, Salvador Ventura, Aggrescan3D (A3D) 2.0: prediction and engineering of protein solubility, Nucleic Acids Research, Volume 47, Issue W1, 02 July 2019, Pages W300–W307, https://doi.org/10.1093/nar/gkz321

Pudžiuvelytė, I. et al. "TemStaPro: protein thermostability prediction using sequence representations from protein language models", https://academic.oup.com/, 04 April 2024, https://academic.oup.com/bioinformatics/article/40/4/btae157/7632735.

Gajendra, P.S. R. et al., ToxinPred 3.0: An improved method for predicting the toxicity of peptides, https://www.biorxiv.org, 14 August 2023, https://www.biorxiv.org/content/10.1101/2023.08.11.552911v1.

Article Source: OpenMM 7: Rapid development of high performance algorithms for molecular dynamics Eastman P, Swails J, Chodera JD, McGibbon RT, Zhao Y, et al. (2017) OpenMM 7: Rapid development of high performance algorithms for molecular dynamics. PLOS Computational Biology 13(7): e1005659. https://doi.org/10.1371/journal.pcbi.1005659

ff14SB: Improving the Accuracy of Protein Side Chain and Backbone Parameters from ff99SB James A. Maier, Carmenza Martinez, Koushik Kasavajhala, Lauren Wickstrom, Kevin E. Hauser, and Carlos Simmerling Journal of Chemical Theory and Computation 2015 11 (8), 3696-3713 DOI: 10.1021/acs.jctc.5b00255

Jorgensen, W. L., Chandrasekhar, J., Madura, J. D., Impey, R. W., & Klein, M. L. (1983). Comparison of simple potential functions for simulating liquid water. The Journal of Chemical Physics, 79(2), 926–935. https://doi.org/10.1063/1.445869

McInnes, L, Healy, J, UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction, ArXiv e-prints 1802.03426, 2018.

Ester, M., Kriegel, H.-P., Sander, J., & Xu, X. (1996). A Density-Based Algorithm for Discovering Clusters in Large Spatial Databases with Noise. Proceedings of the Second International Conference on Knowledge Discovery and Data Mining, 226–231. Portland, Oregon: AAAI Press.

Neurosnap Inc. (2022). Neurosnap: An online platform for computational biology and chemistry. Available at: https://neurosnap.ai/

Similar Services

Explore related tools that support similar research workflows:

NeuroBind

ProteinMPNN-ddG

StaB-ddG

BioPhi

Proudly supporting 50,000+ scientists worldwide, including 7,000+ leading biotech and global biopharma organizations.