Jared Sagendorf

Through the RCSB.org research-focused web portal, many millions of users access rigorously validated, expertly biocurated, 3D biostructure information stored in the Protein Data Bank (PDB) archive alongside predicted Computed Structure Models (CSMs) from AlphaFold DB and ModelArchive. Specialized tools and related resources, from 3D visualization to protein annotations, allow deep exploration of this rich trove of data. The recently updated RCSB.org Advanced Search interface provides a more intuitive experience with enhanced support for 3D structure exploration. The 3D Similarity Search option is powered by a new AI-based system that is more accurate and scalable to much larger collections of structures. Additional capabilities are provided through web-based APIs and a Python API wrapper package that enable researchers to easily interact with RCSB PDB programmatic services for individually tailored analyses. These resources, together with a statistics tool, training and documentation, and the upcoming wwPDB ID and archive transition, are described.

Integrative structure determination combines varied experimental information with computational modeling. We describe a programmatic workflow connecting the output of these calculations directly to deposition into the Protein Data Bank (PDB), a Worldwide Protein Data Bank Core Archive that now accommodates integrative or hybrid methods structures (PDB-IHM). The python-ihm package generates deposition-ready mmCIF files describing structure models, experimental restraints, modeling protocols, and their provenance. Subsequently, programmatic interfaces support pre-deposition validation, structure deposition, and processing status tracking. We illustrate the workflow using biostructure models derived from three-dimensional electron microscopy (3DEM) and crosslinking mass spectrometry (crosslinking-MS) information. We also demonstrate the workflow scalability through submission of a collection of crosslinking-MS structure models. Making structure validation and deposition machine-accessible in turn allows incorporation into high-throughput and AI-agent-driven structure-determination workflows. The workflow provides a reproducible and scalable pathway from integrative modeling to archival deposition.

DNAproDB (https://dnaprodb.usc.edu/) is a database, visualization tool, and processing pipeline for analyzing structural features of protein–DNA interactions. Here, we present a substantially updated version of the database through additional structural annotations, search, and user interface functionalities. The update expands the number of pre-analyzed protein–DNA structures, which are automatically updated weekly. The analysis pipeline identifies water-mediated hydrogen bonds that are incorporated into the visualizations of protein–DNA complexes. Tertiary structure-aware nucleotide layouts are now available. New file formats and external database annotations are supported. The website has been redesigned, and interacting with graphs and data is more intuitive. We also present a statistical analysis on the updated collection of structures revealing salient patterns in protein–DNA interactions.

The recognition and binding of nucleic acids (NAs) by proteins depends upon complementary chemical, electrostatic and geometric properties of the protein-NA binding interface. Structural models of protein-NA complexes provide insights into these properties but are scarce relative to models of unbound proteins. We present a deep learning approach for predicting protein-NA binding given the apo structure of a protein (PNAbind). Our method utilizes graph neural networks to encode spatial distributions of physicochemical and geometric properties of the protein molecular surface that are predictive of NA binding. Using global physicochemical encodings, our models predict the overall binding function of a protein and can discriminate between specificity for DNA or RNA binding. We show that such predictions made on protein structures modeled with AlphaFold2 can be used to gain mechanistic understanding of chemical and structural features that determine NA recognition. Using local encodings, our models predict the location of NA binding sites at the level of individual binding residues. Binding site predictions were validated against benchmark datasets, achieving AUROC scores in the range of 0.92-0.95. We applied our models to the HIV-1 restriction factor APOBEC3G and show that our predictions are consistent with experimental RNA binding data.

Predicting specificity in protein-DNA interactions is a challenging yet essential task for understanding gene regulation. Here, we present Deep Predictor of Binding Specificity (DeepPBS), a geometric deep-learning model designed to predict binding specificity across protein families based on protein-DNA structures. The DeepPBS architecture allows investigation of different family-specific recognition patterns. DeepPBS can be applied to predicted structures, and can aid in the modeling of protein-DNA complexes. DeepPBS is interpretable and can be used to calculate protein heavy atom-level importance scores, demonstrated as a case-study on p53-DNA interface. When aggregated at the protein residue level, these scores conform well with alanine scanning mutagenesis experimental data. The inference time for DeepPBS is sufficiently fast for analyzing simulation trajectories, as demonstrated on a molecular-dynamics simulation of a Drosophila Hox-DNA tertiary complex with its cofactor. DeepPBS and its corresponding data resources offer a foundation for machine-aided protein-DNA interaction studies, guiding experimental choices and complex design, as well as advancing our understanding of molecular interactions.