More Like this

1. Predicting multiple conformations of ligand binding sites in proteins suggests that AlphaFold2 may remember too much

   https://doi.org/10.1073/pnas.2412719121  

   Lazou, Maria; Khan, Omeir; Nguyen, Thu; Padhorny, Dzmitry; Kozakov, Dima; Joseph-McCarthy, Diane; Vajda, Sandor (November 2024, Proceedings of the National Academy of Sciences)

   The goal of this paper is predicting the conformational distributions of ligand binding sites using the AlphaFold2 (AF2) protein structure prediction program with stochastic subsampling of the multiple sequence alignment (MSA). We explored the opening of cryptic ligand binding sites in 16 proteins, where the closed and open conformations define the expected extreme points of the conformational variation. Due to the many structures of these proteins in the Protein Data Bank (PDB), we were able to study whether the distribution of X-ray structures affects the distribution of AF2 models. We have found that AF2 generates both a cluster of open and a cluster of closed models for proteins that have comparable numbers of open and closed structures in the PDB and not too many other conformations. This was observed even with default MSA parameters, thus without further subsampling. In contrast, with the exception of a single protein, AF2 did not yield multiple clusters of conformations for proteins that had imbalanced numbers of open and closed structures in the PDB, or had substantial numbers of other structures. Subsampling improved the results only for a single protein, but very shallow MSA led to incorrect structures. The ability of generating both open and closed conformations for six out of the 16 proteins agrees with the success rates of similar studies reported in the literature. However, we showed that this partial success is due to AF2 “remembering” the conformational distributions in the PDB and that the approach fails to predict rarely seen conformations. 

   more » « less
2. Comparative assessment of binding residue predictions in intrinsically disordered regions

   https://doi.org/10.1002/pro.70298  

   Basu, Sushmita; Kurgan, Lukasz (October 2025, Protein Science)

   Abstract Dozens of impactful methods that predict intrinsically disordered regions (IDRs) in protein sequences that interact with proteins and/or nucleic acids were developed. Their training and assessment rely on the IDR‐level binding annotations, while the equivalent structure‐trained methods predict more granular annotations of binding amino acids (AA). We compiled a new benchmark dataset that annotates binding AA in IDRs and applied it to complete a first‐of‐its‐kind assessment of predictions of the disordered binding residues. We evaluated a representative collection of 14 methods, used several hundred low‐similarity test proteins, and focused on the challenging task of differentiating these binding residues from other disordered AA and considering ligand type‐specific predictions (protein–protein vs. protein–nucleic acid interactions). We found that current methods struggle to accurately predict binding IDRs among disordered residues; however, better‐than‐random tools predict disordered binding residues significantly better than binding IDRs. We identified at least one relatively accurate tool for predicting disordered protein‐binding and disordered nucleic acid‐binding AA. Analysis of cross‐predictions between interactions with protein and nucleic acids revealed that most methods are ligand‐type‐agnostic. Only two predictors of the nucleic acid‐binding IDRs and two predictors of the protein‐binding IDRs can be considered as ligand‐type‐specific. We also discussed several potential future directions that would move this field forward by producing more accurate methods that target the prediction of binding residues, reduce cross‐predictions, and cover a broader range of ligand types. 

   more » « less
3. ECOD: integrating classifications of protein domains from experimental and predicted structures

   https://doi.org/10.1093/nar/gkae1029  

   Schaeffer, R Dustin; Medvedev, Kirill E; Andreeva, Antonina; Chuguransky, Sara Rocio; Pinto, Beatriz Lazaro; Zhang, Jing; Cong, Qian; Bateman, Alex; Grishin, Nick V (January 2025, Nucleic Acids Research)

   Abstract The evolutionary classification of protein domains (ECOD) classifies protein domains using a combination of sequence and structural data (http://prodata.swmed.edu/ecod). Here we present the culmination of our previous efforts at classifying domains from predicted structures, principally from the AlphaFold Database (AFDB), by integrating these domains with our existing classification of PDB structures. This combined classification includes both domains from our previous, purely experimental, classification of domains as well as domains from our provisional classification of 48 proteomes in AFDB predicted from model organisms and organisms of concern to global health. ECOD classifies over 1.8 M domains from over 1000 000 proteins collectively deposited in the PDB and AFDB. Additionally, we have changed the F-group classification reference used for ECOD, deprecating our original ECODf library and instead relying on direct collaboration with the Pfam sequence family database to inform our classification. Pfam provides similar coverage of ECOD with family classification while being more accurate and less redundant. By eliminating duplication of effort, we can improve both classifications. Finally, we discuss the initial deployment of DrugDomain, a database of domain-ligand interactions, on ECOD and discuss future plans. 

   more » « less
4. Efficient generation of protein pockets with PocketGen

   https://doi.org/10.1038/s42256-024-00920-9  

   Zhang, Zaixi; Shen, Wan Xiang; Liu, Qi; Zitnik, Marinka (November 2024, Nature Machine Intelligence)

   Abstract Designing protein-binding proteins is critical for drug discovery. However, artificial-intelligence-based design of such proteins is challenging due to the complexity of protein–ligand interactions, the flexibility of ligand molecules and amino acid side chains, and sequence–structure dependencies. We introduce PocketGen, a deep generative model that produces residue sequence and atomic structure of the protein regions in which ligand interactions occur. PocketGen promotes consistency between protein sequence and structure by using a graph transformer for structural encoding and a sequence refinement module based on a protein language model. The graph transformer captures interactions at multiple scales, including atom, residue and ligand levels. For sequence refinement, PocketGen integrates a structural adapter into the protein language model, ensuring that structure-based predictions align with sequence-based predictions. PocketGen can generate high-fidelity protein pockets with enhanced binding affinity and structural validity. It operates ten times faster than physics-based methods and achieves a 97% success rate, defined as the percentage of generated pockets with higher binding affinity than reference pockets. Additionally, it attains an amino acid recovery rate exceeding 63%. 

   more » « less
5. RCSB Protein Data Bank: Delivering integrative structures alongside experimental structures and computed structure models

   https://doi.org/10.1093/nar/gkaf1187  

   Vallat, Brinda; Rose, Yana; Piehl, Dennis W; Duarte, Jose M; Bittrich, Sebastian; Bi, Chunxiao; Segura, Joan; Zalevsky, Arthur; Sekharan, Monica R; Webb, Benjamin M; et al (November 2025, Nucleic Acids Research)

   Abstract The Protein Data Bank (PDB) archives 3D structures of macromolecules determined experimentally using various methods. It is jointly managed by the Worldwide Protein Data Bank (wwPDB) consortium. Research Collaboratory for Structural Bioinformatics (RCSB) PDB, the US data center for the PDB, provides streamlined access to >240 000 structures through a variety of research-focused tools on RCSB.org. In addition, RCSB.org makes available over 1 million computed structure models (CSMs) predicted using deep learning methods and archived in the AlphaFold Database and ModelArchive. The PDB-IHM system was developed as a wwPDB project based on community recommendations to archive structures determined using integrative/hybrid methods (IHM). These structures are computed by combining information from multiple experimental and computational techniques to overcome the limitations of traditional single methods (e.g. macromolecular crystallography, 3D electron microscopy, nuclear magnetic resonance spectroscopy). In 2024, PDB-IHM was unified with the PDB to archive integrative structures alongside single-method experimental structures. These integrative structures have been made accessible via the RCSB.org website, facilitating efficient delivery of IHM data to a broad community of PDB users. Herein, we describe the expanded capabilities of RCSB.org that support discovery, analysis, and visualization of integrative structures together with single-method experimental structures and CSMs. 

   more » « less