# Boltz-2 put binding-affinity prediction beside structure prediction The Boltz team introduced Boltz-2 on June 6, 2025, reporting an open model for joint biomolecular structure and binding-affinity prediction. Canonical: https://rangoon.ai/insights/archive-boltz2-binding-affinity-2025/ Author: Rangoon Editorial (https://rangoon.ai/insights/editorial/) Published: 2026-10-23 Updated: 2026-10-23 Event date: 2025-06-06 Tags: [protein science](https://rangoon.ai/insights/tags/protein-science/), [open models](https://rangoon.ai/insights/tags/open-models/), [research AI](https://rangoon.ai/insights/tags/research-ai/), [model evaluation](https://rangoon.ai/insights/tags/model-evaluation/) Source note: Historical reporting: the Boltz team announced Boltz-2 on June 6, 2025 and released its technical report. Predicted affinity and reported benchmark scores are not experimental binding confirmation or clinical guidance. Image: Binding prediction evidence ledger. Original Rangoon explanatory diagram: concepts for editorial review, not measured results, an official legal determination, vendor interface or event photograph. ## Key takeaways - Boltz-2 joined a structure prediction task with a binding-affinity prediction task. - Affinity evaluation needs target, ligand, assay and data-split context. - In-silico ranking cannot establish potency, selectivity, safety or therapeutic value. ## The June release expanded the target beyond structure [source 1](https://boltz.bio/boltz2) [source 2](https://github.com/jwohlwend/boltz) The Boltz team announced Boltz-2 on June 6, 2025, describing an open biomolecular foundation model intended to predict both complex structures and binding affinities. This matters because a plausible complex geometry and a useful affinity estimate are different scientific targets. The release and technical materials support inspection of the authors’ method and reported comparisons. They do not establish that a predicted interaction binds in an assay, that a ranked molecule is selective, or that a computational result has a medical implication. Those require their own experimental and regulatory evidence. ## Joint outputs should be judged against their separate observables [source 1](https://boltz.bio/boltz2) [source 2](https://github.com/jwohlwend/boltz) Structure and affinity labels arise from different measurements and sources of uncertainty. A model can produce a geometrically plausible pose yet mis-rank a series when solvation, flexibility, assay conditions or data bias matter. Conversely, an affinity score may be useful for ranking within a defined set without proving a detailed mechanism. Evaluation must name the target family, ligand representation, split strategy, assay type, metric and baseline. A headline comparison with a physics-based method belongs to the stated benchmark conditions, not to every protein-ligand pair a user may submit. ## Predicted binding is not a drug-development conclusion [source 1](https://boltz.bio/boltz2) [source 2](https://github.com/jwohlwend/boltz) Binding is only one part of a compound-development decision. Potency, selectivity, permeability, metabolism, toxicity, formulation and clinical benefit are distinct questions. A model output should be reported as a computational prioritization signal, with model revision and input provenance attached, rather than as proof of efficacy. This article offers no molecule-design instructions or medical advice. It distinguishes model prediction from laboratory evidence because a single affinity number can otherwise be misread as a broad statement about a candidate’s value or safety. ## Ranking studies need prospective and negative controls [source 1](https://boltz.bio/boltz2) [source 2](https://github.com/jwohlwend/boltz) To evaluate a model for a new target, hold out a prospective set before scoring and compare the model’s ranked list with a transparent baseline. Include known non-binders or decoys where appropriate, then record assay conditions, replicate variability and failures to obtain material. Test whether a score remains useful across chemical series rather than only within one familiar scaffold. If a score triggers synthesis, preserve the decision threshold and all tested candidates so later analysis can assess enrichment rather than only count an isolated successful hit. ## Analysis: co-folding claims should preserve the assay boundary [source 1](https://boltz.bio/boltz2) [source 2](https://github.com/jwohlwend/boltz) Boltz-2 is a good archival example of an AI research release that spans two related but non-interchangeable molecular outputs. The reporting discipline is to keep pose, affinity and downstream biological claims on separate ledgers. The release calls out protein-small-molecule affinity prediction; that named output must be evaluated with a target, ligand set and assay definition rather than borrowed from a structure-only benchmark. Prospective measurements remain the evidence that turns an in-silico ordering into a scientifically useful ranking for a defined target series. A binding-affinity model should earn confidence through prospective, measured rankings with explicit assay conditions, not through a structure image that makes a modeled complex appear experimentally observed. ## Sources 1. [Boltz: Introducing Boltz-2](https://boltz.bio/boltz2) 2. [Boltz project repository](https://github.com/jwohlwend/boltz) ## Related reading - [RFdiffusion2 made enzyme-backbone generation a testable design hypothesis](https://rangoon.ai/insights/archive-rfdiffusion2-enzyme-design-2025/) - [Chai-2 paired de novo antibody designs with a bounded wet-lab report](https://rangoon.ai/insights/archive-chai2-zero-shot-antibody-2025/) - [BioEmu-1 made protein-conformation emulation a sampling question](https://rangoon.ai/insights/archive-bioemu-protein-ensembles-2025/) ## More information - [Documentation index](https://rangoon.ai/llms.txt) - [AI access and policies](https://rangoon.ai/ai/) - [Source repository](https://github.com/hypler-dev/rangoon)