Recep Adiyaman
bioinformatics

Issue #23: Benchmarking co-folding methods to predict the structures of covalent protein-ligand complexes.

January 15, 2026 Daily Intelligence
Protein Design Daily

Building something in Protein Design?

I love collaborating on new architectural challenges. Let's build together.

LinkedIn Connect Direct Message

🧬 Protein Design Digest

Curated protein signals by Recep Adiyaman

Join 1,000+ researchers. Unsubscribe anytime.

🚀 Today’s Top Signal

Benchmarking co-folding methods to predict the structures of covalent protein-ligand complexes.

🧬 Abstract

Targeted covalent inhibitors (TCIs) are emerging as a new modality in drug discovery because of their strong binding affinity and prolonged target engagement. However, the rational design of TCIs remains a significant challenge and is hindered by the lack of methods that accurately predict the structures of covalent protein-ligand complexes. Recent advances in co-folding approaches have made substantial strides in modeling complex biomolecular structures. Despite significant progress, their performance profiles for predicting the structures of covalent protein-ligand complexes remain largely unexplored because of the absence of rigorous benchmarks. Here, we introduce CoFD-Bench, a comprehensive benchmark dataset comprising 218 recently resolved covalent complexes designed to systematically evaluate both classical docking methods (AutoDock-GPU, CovDock, and GNINA) and deep learning co-folding models (AlphaFold3 (AF3), Chai-1, and Boltz-1x). Our results demonstrate that co-folding methods achieve superior ligand RMSD accuracy and protein-ligand interaction recovery. However, their performance markedly declines for novel pocket-ligand pairs. In contrast, classical docking methods exhibit stable but modest performance, which is primarily limited by target conformations. Furthermore, computational efficiency evaluations show that co-folding methods are slower than classical approaches, posing challenges for large-scale predictions. We also reveal that AF3 has the potential to identify native covalent residues through noncovalent co-folding, with a ligand RMSD comparable to that of covalent co-folding. These findings offer a possible route to explore covalent binding without prior specification of reactive residues, which are often unknown in real-world scenarios. Our study provides crucial insights and new opportunities for future co-folding-based TCI design, informing future model applications and improvements. CoFD-Bench offers rigorous evaluation criteria, diverse docking scenarios, and various methodological baselines, positioning it as an important benchmark for future model development and assessment.

Why it matters: Critical for improving fold accuracy and reducing structural uncertainty in de novo design.

⭐ Additional Signals

In Silico Discovery of RIOK3 Inhibitors Against Pancreatic Ductal Adenocarcinoma Using Homology Modelling, Molecular Docking, Molecular Dynamics Simulations, ADMET Prediction, and MTT assay

Abstract Pancreatic ductal adenocarcinoma (PDAC) is an aggressive cancer strongly linked to RIO Kinase 3 (RIOK3), which promotes progression by stabilizing and phosphorylating Focal Adhesion Kinase (FAK). Advances in protein structure prediction, particularly AlphaFold2, have significantly enhanced our understanding of protein dynamics, aiding in the identification of potential inhibitors for targeted therapies. This study used structure-based virtual screening, molecular dynamics simulations, ADMET/toxicity prediction, and in vitro validation to identify potential inhibitors of RIOK3 for PDAC treatment. The 3D structure of RIOK3 was predicted using AlphaFold2 and docked with FDA-approved drugs via AutoDock Vina. Pharmacokinetic and pharmacodynamic properties were assessed with SwissADME, and in vitro validation was performed using MTT assays to assess cell viability and growth inhibition. Four top-scoring compounds were identified, with binding energies between − 11.3 and − 10.4 kcal/mol. Venetoclax showed the most stable complex with RIOK3, followed by Conivaptan and Irinotecan. Drospirenone showed weaker binding. Molecular dynamics simulations and MM/GBSA analysis supported the stability of these complexes. SwissADME and ProTox-II confirmed that the compounds met drug-likeness criteria but exhibited distinct pharmacokinetic and toxicity profiles. In vitro MTT assays showed concentration-dependent growth inhibition in PANC-1 cells, with Conivaptan having the lowest IC₅₀ value. This study identifies RIOK3 as a promising therapeutic target for PDAC, with Venetoclax, Conivaptan, Drospirenone, and Irinotecan as repurposable candidates for further research. Further studies should include biochemical assays, expanded cytotoxicity profiling in multiple PDAC cell lines, and in vivo evaluations to validate RIOK3-targeted therapies for PDAC treatment.

Benchmarking all-atom biomolecular structure prediction with FoldBench.

Accurate prediction of biomolecular complex structures is fundamental for understanding biological processes and rational therapeutic design. Recent advances in deep learning methods, particularly all-atom structure prediction models, have significantly expanded their capabilities to include diverse biomolecular entities, such as proteins, nucleic acids, ligands, and ions. However, comprehensive benchmarks covering multiple interaction types and molecular diversity remain scarce, limiting fair and rigorous assessment of model performance and generalizability. To address this gap, we introduce FoldBench, an extensive benchmark dataset consisting of 1522 biological assemblies categorized into nine distinct prediction tasks. Our evaluations reveal critical performance dependencies, showing that ligand docking accuracy notably diminishes as ligand similarity to the training set decreases, a pattern similarly observed in protein-protein interaction modeling. Furthermore, antibody-antigen predictions remain particularly challenging, with current methods exhibiting failure rates exceeding 50%. Among evaluated models, AlphaFold 3 consistently demonstrates superior accuracy across the majority of tasks. In summary, our results highlight significant advancements yet reveal persistent limitations within the field, providing crucial insights and benchmarks to inform future model development and refinement.

Mechanistic study of plastic monomers in gestational diabetes mellitus: A network toxicology and molecular docking approach.

Plastics are widely used in various fields such as food packaging, textile fibers, building materials, and transportation. Although the relationship between plastic additives and diseases has been reported, there is limited research on the association between plastic monomers (PM) and gestational diabetes mellitus (GDM). This study aims to investigate the link between environmental PM and GDM. By employing advanced network toxicology and molecular docking techniques, we successfully elucidated the molecular mechanisms by which PM may induce GDM. Utilizing databases such as PubChem, SEA, Super-PRED, SwissTargetPrediction, PharmMapper, Gene Cards, and OMIM, we identified potential targets associated with the disease. Further analysis using STRING and Cytoscape software helped determine the core targets most significantly related to these metabolic disorders. Additionally, Gene Ontology and Kyoto Encyclopedia of Genes and Genomes pathway enrichment analyses were conducted using the David database to characterize these core targets. Finally, molecular docking with CB-Dock2 was used to validate the binding affinity of PM to these target proteins. Our findings suggest that PM may potentially induce GDM by modulating the insulin signaling pathway through STAT3, AKT1, and TP53. In summary, this work provides novel insights into the mechanisms by which environmental pollutants may trigger GDM, thereby laying a theoretical foundation for disease prevention and treatment. It offers valuable references for the safety evaluation of plastics, urging food safety regulatory agencies to strengthen oversight and encouraging the public to reduce plastic usage.

🧪 AI & Research News

🏢 Industry Insight & Applications

⚡ Quick Reads

Unexplored regions of the protein sequence-structure map revealed at scale by a library of foldtuned language models

Amino-acid sequence space is combinatorially vast, with well-folded proteins distributed sparsely and connected by vanishingly few permissible mutational paths. Novel-in-sequence versions of structures observed in nature promise to sample features such as new binding motifs and active site geometries but are rendered inaccessible to evolution or direct search by the extent of sequence perturbations required. Here we introduce a novel algorithm - termed “foldtuning” - that leverages principles of adversarial learning to drive protein language models (PLMs) to erase detectable homology to natural sequences while preserving a target structure, systematically traversing protein-space without being limited by evolutionary barriers. We build foldtuned PLMs for >700 targets including membrane-bound receptors, redox enzymes, and signaling domains. Foldtuned proteins are diverse and far-from-natural in sequence, filling out structurally-equivalent families defined by fundamental biophysical constraints invisible to traditional sequence-based bioinformatics methods. Experimental characterization demonstrates that foldtuned proteins express stably in vitro and function in vivo. By revealing sequence-structure information at scale beyond evolution, foldtuning promises to accelerate the reconstitution and realization of novel-to-nature systems for synthetic biology problems from therapeutics to catalysis.

Structure-based identification of triazole-based PARP1 inhibitors: insights from docking and molecular dynamics simulations.

Background Poly (ADP-ribose) polymerase 1 (PARP1) is a critical enzyme involved in DNA repair mechanisms, making it a promising target for anticancer drug development. Triazole derivatives have shown potential as PARP1 inhibitors, but systematic evaluation of a large library remains limited. Objective To perform comprehensive in silico screening and molecular dynamics simulations of 180 triazole derivatives to identify potent PARP1 inhibitors and evaluate their binding stability and interaction profiles. Methods A library of 180 triazole derivatives was subjected to molecular docking against the active site of PARP1 using [Schrodinger suite 2024-4]. Top-ranking compounds based on binding affinity were selected for further molecular dynamics (MD) simulations using to assess the stability of the ligand-protein complexes over a 100 ns simulation period. Binding free energies were calculated using MM-GBSA approaches. Key protein-ligand interactions were analyzed to elucidate binding mechanisms. Results Docking results identified 10 triazole derivatives with superior binding affinities -9.4 to -5.5 kcal/mol compared to reference inhibitors. MD simulations confirmed stable binding conformations with root mean square deviation (RMSD) fluctuations within acceptable limits. Interaction analysis highlighted crucial hydrogen bonds and hydrophobic contacts with catalytic residues of PARP1. Conclusion The integrated in silico screening and molecular dynamics simulation approach successfully identified promising triazole derivatives as potential PARP1 inhibitors. These findings provide valuable insights for the rational design and optimization of novel anticancer agents targeting PARP1.

Integrating machine learning and molecular docking to reveal the molecular network of aflatoxin B1-induced colorectal cancer

Abstract Aflatoxin B1 (AFB1) contributes to colorectal cancer development through multiple molecular pathways. This study aims to investigate the molecular mechanisms underlying Colorectal cancer (CRC) induced by AFB1. Using integrative transcriptomic differential expression data, we enumerated candidate genes for AFB1-related colorectal cancer based on the list of published AFB1 protein targets. The molecular relationship between AFB1 and its candidates were verified by machine learning, network-based toxicology and molecular docking algorithms. The study screened 55 AFB1-related CRC genes. Through machine learning algorithm, three key genes, ABCG2, PDE3A and CCND1, were selected. Down-regulation of ABCG2 and PDE3A but upregulation of CCND1 were observed under expression (P

Role of gut microbiota metabolites against vein graft restenosis: insights from network pharmacology, molecular docking and molecular dynamic simulation.

Background Gut microbiota metabolites are increasingly recognized for their role in modulating chronic disease progression. However, their potential impact on vein graft restenosis (VGR) remains unexplored. This study aimed to elucidate the mechanisms by which gut microbiota and its metabolites attenuate VGR using an integrated approach of network pharmacology, molecular docking, and molecular dynamics (MD) simulations. Methods Gut microbiota, metabolites, and human gut targets were obtained from the gutMGene database. Metabolite targets were predicted using SwissTargetPrediction and Similarity Ensemble Approach, while disease targets were collected from GeneCards, Online Mendelian Inheritance in Man (OMIM), and DrugBank. Overlapping targets were used to construct both a protein-protein interaction (PPI) network and a gut microbiota-metabolites-targets-VGR (GM-M-T-V) network to identify key microbiota, core metabolites, and hub targets. Enrichment analysis investigated associated biological processes, cellular components, molecular functions, and signaling pathways. Drug-likeness and toxicity were evaluated with SwissADME and ADMETlab 2.0. Molecular docking and MD simulations assessed the binding affinity and dynamic characteristics of target-metabolite complexes. Results Integrated data from relevant databases identified 260 gut microbiota, 251 metabolites, 404 metabolite targets, 238 human gut targets, and 741 VGR-related targets. Among these, 16 overlapping targets were identified for further analysis. Enrichment analysis highlighted significant involvement of the relaxin signaling pathway, while PPI topology analysis pinpointed AKT1, NFKB1, EGFR, PTGS2, and PPARG as hub targets. Quercetin was prioritized as the core metabolite based on its top network connectivity, favorable drug-likeness prediction, and manageable in silico-predicted hepatotoxicity/genotoxicity risks in light of its absent clinical toxicity. Molecular docking revealed that quercetin bound to four hub targets (AKT1, NFKB1, EGFR, PPARG) with affinities (ranging from-6.0 to-8.9 kcal/mol) comparable or superior to positive controls. MD simulations further suggested favorable structural stability and binding affinity of the EGFR-quercetin complex. Conclusion This integrative study elucidates the role of gut microbiota metabolites against VGR, identifying the microbial metabolite quercetin as a promising multi-target therapeutic agent primarily via the relaxin signaling pathway, which provides a mechanistic groundwork for a novel potential treatment strategy.

Comparative Molecular Docking Analysis, of Natural and Synthetic Ligands, Targeting BRCA1, BRCA2, ER, and PR in Breast Cancer Treatment.

Objective Breast cancer remains a leading cause of cancer-related mortality in women, necessitating the development of innovative therapeutic strategies. This study employs comparative molecular docking to evaluate the binding affinities of natural compounds, derived from a specifically formulated oil mixture, against key molecular targets in breast cancer BRCA1, BRCA2, estrogen receptor (ER), and progesterone receptor (PR). Methods Synthetic ligands commonly used in breast cancer therapy were included as reference compounds. Molecular docking was performed using 1-Click Docking software to determine binding energy values, expressed in kcal/mol, with more negative ΔG values indicating stronger and more spontaneous ligand-receptor interactions. Results Among the synthetic ligands, Epirubicin exhibited the highest binding affinity to BRCA2 (-9.0 kcal/mol), while Capecitabine demonstrated the strongest interaction with PR (-8.1 kcal/mol). Notably, the natural compound Narirutin outperformed these drugs, showing a superior binding affinity to BRCA2 (-9.2 kcal/mol) and PR (-8.9 kcal/mol). Additionally, Geraniol and Citronellol exhibited competitive binding affinities to ER and PR, respectively, underscoring their potential therapeutic relevance. These findings highlight the capability of natural compounds to act as effective inhibitors of critical breast cancer molecular targets. Narirutin, in particular, stands out as a promising candidate for further exploration in integrative cancer therapies. Conclusion This study demonstrates the utility of bioinformatics approaches, specifically molecular docking, in identifying natural compounds with high therapeutic potential and provides a computational framework for future experimental validation and drug development.

AI-Powered Structural and Co-Expression Analysis of Potato (<i>Solanum tuberosum</i>) <i>StABCG25</i> Transporters Under Drought: A Combined AlphaFold, WGCNA, and MD Approach.

Drought stress significantly impacts potato ( Solanum tuberosum ) yield and quality, necessitating the identification of molecular regulators involved in stress response. This study presents a systems-level, integrative in silico strategy to characterize StABCG25 transporter homologs, key players in abscisic acid (ABA) export in Arabidopsis, to evaluate their potential role in drought adaptation. We performed a genome-wide scan of the potato genome and identified four StABCG25 isoforms. A comprehensive computational framework was applied, including transcriptomic profiling, Weighted Gene Co-expression Network Analysis (WGCNA), AlphaFold2-based 3D modeling, docking, and long-timescale Molecular Dynamics (MD) simulations. Expression analyses revealed the coordinated upregulation of StABCG25-2 and -4 in the drought-tolerant FB clone, contrasted by suppression or instability in sensitive cultivars. WGCNA placed StABCG25-2 as a hub gene in ABA-enriched stress response modules, while StABCG25-4 was associated with plastid-related pathways, suggesting functional divergence. Structurally, StABCG25-2 and -6 exhibited high conformational stability in MD simulations, supported by consistent RMSD/RMSF profiles and MM/PBSA-based binding energy estimates. In contrast, StABCG25-5B , despite favorable docking scores, demonstrated poor dynamic stability and unreliable binding affinity. Overall, this study highlights the critical role of transcriptional coordination and structural robustness in the functional specialization of StABCG25 isoforms under drought stress. Our findings underscore the value of combining WGCNA and molecular dynamics simulations to identify structurally and functionally relevant ABA transporters for future crop improvement strategies.

Exploring structural diversity and dynamic stability of small-molecule PRMT5 inhibitors through machine learning-based QSAR and molecular modelling.

Protein arginine methyltransferase 5 (PRMT5) is a key epigenetic enzyme that catalyses symmetric arginine methylation on histone and non-histone proteins, influencing chromatin organisation, RNA splicing, and oncogenic signalling. Its overexpression and dependency in MTAP-deleted cancers such as glioblastoma, pancreatic adenocarcinoma, and non-small cell lung carcinoma highlight its therapeutic relevance. This study presents an integrative computational framework combining quantitative structure-activity relationship (QSAR) modelling, molecular docking, molecular dynamics (MD) simulations, and network pharmacology to identify potential PRMT5 inhibitors. The best QSAR models based on machine learning techniques used different fingerprint representations and algorithms to describe chemical structures; Random Forest models trained on PubChem and MACCS descriptor combinations provided the most accurate predictions. Analysis of consensus QSAR models identified two highly active PRMT5 inhibitor candidates (CHEMBL4539612 and CHEMBL4577464), with high affinity for binding (- 13.5 to - 13.7 kcal/mol) to the PRMT5 active site and interactions similar to those of the known clinical PRMT5 inhibitor ONAMETOSTAT. Molecular dynamics simulations showed that both candidate molecules-maintained stability throughout the PRMT5 catalytic cleft, due to consistent hydrogen bonding, compact conformations, and low negative binding free energy values determined by MM-GBSA calculations. Network pharmacology analysis indicated that PRMT5 and its interacting partners are mainly associated with histone arginine methylation and spliceosomal assembly, processes that are frequently dysregulated in MTAP-deficient cancers. These findings suggest CHEMBL4539612 and CHEMBL4577464 as promising scaffolds for the development of selective PRMT5 inhibitors in epigenetic cancer therapy.

Molecular docking and fluorescence spectroscopy analysis of the interaction of different polyphenols with salivary mucin and proline-rich protein toward the astringency mechanism.

Molecular docking, fluorescence spectroscopy, Fourier transform infrared (FTIR), and circular dichroism (CD) spectroscopy were used to systematically analyze the interactions between saliva mucin (MUC) or basic proline-rich proteins (bPRPs) and five typical polyphenols, including catechin (C), gallic acid (GA), epigallocatechin gallate (EGCG), proanthocyanidin (PC), and tannic acid (TA), aiming to explore the key roles of two saliva proteins in the generation of astringency. Molecular docking results revealed that the binding energies of the polyphenols with MUC were generally lower than those with bPRPs, following the order of binding affinity TA > PC > EGCG > C > GA. Higher content of phenolic hydroxyl groups and degree of gallate acylation of polyphenols resulted in stronger interaction and more binding sites with the salivary proteins. Fluorescence quenching and synchronous, FTIR, and CD spectra confirmed that the polyphenols bound more strongly to MUC than to bPRPs, and MUC demonstrated more unfolded conformation and ordered secondary structure change.

💡 Pipeline Tip

Use local MSA generation (colabfold_search) to bypass speed bottlenecks.

🛠️ Resources

Deep learning is not a magic wand, but a powerful lens for structural biology. — Recep Adiyaman

BS HF DK