ArticleNature communications2025
Investigating whether deep learning models for co-folding learn the physics of protein-ligand interactions.
Article in Nature communications, 2025. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 66 papers.
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
The trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.
Who cites it
66 citing papers in PubMed.
- Tryptoline stereoprobe elaboration identifies inhibitors of the GRPEL1-HSPA9 complex.Nature chemical biology · 2026Article
- Article
- TechBio 3.0 closes the drug discovery loop with multimodal AI and generative chemistry.npj drug discovery · 2026Review
- Beyond Simple Mimicry: Next-Generation Geometric Architectures and Future Paradigms in Small-Molecule and Macrocyclic Peptidomimetics.Angewandte Chemie (International ed. in English) · 2026Review
- Docking-based virtual screening: Past, present, and future.Biophysical journal · 2026Review
- Data driven selection of consensus docking pipelines for structure based hit identification.npj drug discovery · 2026Article
- Structural T-Cell Receptor Analysis in the Age of Machine Learning.Immunological reviews · 2026Review
- Prioritizing Candidate YB‑1 Cold Shock Domain Ligands via 5D-ElectroShape and Boltz Generative Cofolding.ACS omega · 2026Article
- Explainable AI reveals the allosteric blind spot in protein-ligand binding predictions.Cell reports. Physical science · 2026Article
- Epidermal Growth Factor Receptor as a Model Drug Target for Scrutinizing the Status Quo in Drug Discovery and Chemical Biology.ACS bio & med chem Au · 2026Review
- On the generalization and usability of cofolding models for GPCR drug discovery.npj drug discovery · 2026Article
- Predicting Ligand Binding Modes by Scaffold-Guided Structure Refinement.Journal of medicinal chemistry · 2026Article
- Reliability of AI Methods in Drug Discovery: Evaluation of Boltz-2 for Structure and Binding Affinity Prediction.Journal of chemical theory and computation · 2026Article
- Strategic Template Filtering Accelerates Fragment-Based Peptide Docking.Journal of chemical information and modeling · 2026Article
- Artificial intelligence in drug discovery - what it is, where we stand and the path forward.Nature reviews. Drug discovery · 2026Review
- Synthetic sequence alignments as programmable probes of learned conformational landscapes in deep learning protein structure predictors.Bioinformatics (Oxford, England) · 2026Article
- Article
- AlphaFold reveals but sometimes distorts an organizational principle of protein folding.bioRxiv : the preprint server for biology · 2026Article
- CAFE: A Co-folding Approach for Fragment Exploration of Allosteric and Cryptic Binding Sites.bioRxiv : the preprint server for biology · 2026Article
- Ensembles ofbioRxiv : the preprint server for biology · 2026Article
6 more citing papers are in PubMed but not listed here.
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
3 authors.
Funding
Abstract
Co-folding models represent a major innovation in deep-learning-based protein-ligand structure prediction. The recent publications of RoseTTAFold All-Atom, AlphaFold3, and others have shown high-quality results on predicting the structures of proteins interacting with small-molecules, nucleic-acids, and other proteins. Despite these advanced capabilities and broad potential, the current study presents critical findings that question the adherence of these models to fundamental physical principles. Through adversarial examples based on established physical, chemical, and biological principles, we demonstrate notable discrepancies in protein-ligand structural predictions when subjected to biologically and chemically plausible perturbations. These discrepancies reveal a significant divergence from expected physical behaviors, indicating potential overfitting to particular data features within its training corpus. Our findings underscore the models' limitations in generalizing effectively across diverse protein-ligand structures and highlight the necessity of integrating robust physical and chemical priors in the development of such predictive tools. The results advocate a measured reliance on deep-learning-based models for critical applications in drug discovery and protein engineering, where a deep understanding of the underlying physical and chemical properties is crucial.
Indexed as
Identifiers
What OpenQuestion holds
Registered trials
Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.