Critical Assessment of Structure Prediction 15 (CASP15) added a new category of ligand prediction to promote the development of protein/RNA-ligand modeling methods, which have become important tools in modern drug discovery. A total of 22 targets were released, including 18 protein-ligand targets and 4 RNA-ligand targets. We applied our recently developed template-guided method to the protein-ligand complex structure predictions. The method combined a physicochemical, molecular docking method, and a bioinformatics-based ligand similarity method. The Protein Data Bank was scanned for template structures containing the target protein, homologous proteins, or proteins sharing a similar fold with the target protein. The binding modes of the co-bound ligands in the template structures were used to guide the complex structure prediction for the target. The CASP assessment results show that the overall performance of our method was ranked second when the top predicted model was considered for each target. Here, we analyzed our predictions in detail, and discussed the challenges including protein conformational changes, large and flexible ligands, and multiple diverse ligands in a binding pocket.

As proposed here, β-turns play an essential role in protein self-assembly. This compact, four-residue motif affects protein conformation dramatically by reversing the overall chain direction. Turns are the "hinges" in globular proteins. This new proposal broadens a previous hypothesis that globular proteins solve the folding problem in part by filtering conformers with unsatisfied backbone hydrogen bonds, thereby preorganizing the folding population. Recapitulating that hypothesis: unsatisfied conformers would be dramatically destabilizing, shifting the U(nfolded) ⇌ N(ative) equilibrium far to the left. If even a single backbone polar group is satisfied by solvent when unfolded but buried and unsatisfied when folded, that energy penalty alone, approximately +5 kcal/mol, would rival almost the entire free energy of protein stabilization at room temperature. Consequently, globular proteins are built on scaffolds of hydrogen-bonded α-helices and/or strands of β-sheet, motifs that can be extended indefinitely, with intra-segment hydrogen bond partners for their backbone polar groups and without steric clash. Scaffolds foster a protein-wide hydrogen-bonded network, and, of thermodynamic necessity, they self-assemble cooperatively. Unlike elements of repetitive secondary structure, α-helices and β-sheet, a four-residue β-turn has only a single hydrogen bond (from i + 3 → i), not a cooperatively formed assembly of hydrogen bonds. As such, turns can form autonomously and are poised to initiate assembly of scaffold elements by bringing them together in an orientation and registration that promotes cooperative "zipping". The overall effect of this self-assembly mechanism is to induce substantial preorganization in the thermodynamically accessible folding population and, concomitantly, to reduce the folding entropy.

Protein engineers aim to discover and design novel sequences with targeted, desirable properties. Given the near limitless size of the protein sequence landscape, it is no surprise that these desirable sequences are often a relative rarity. This makes identifying such sequences a costly and time-consuming endeavor. In this work, we show how to use a deep transformer protein language model to identify sequences that have the most promise. Specifically, we use the model's self-attention map to calculate a Promise Score that weights the relative importance of a given sequence according to predicted interactions with a specified binding partner. This Promise Score can then be used to identify strong binders worthy of further study and experimentation. We use the Promise Score within two protein engineering contexts-Nanobody (Nb) discovery and protein optimization. With Nb discovery, we show how the Promise Score provides an effective way to select lead sequences from Nb repertoires. With protein optimization, we show how to use the Promise Score to select site-specific mutagenesis experiments that identify a high percentage of improved sequences. In both cases, we also show how the self-attention map used to calculate the Promise Score can indicate which regions of a protein are involved in intermolecular interactions that drive the targeted property. Finally, we describe how to fine-tune the transformer protein language model to learn a predictive model for the targeted property, and discuss the capabilities and limitations of fine-tuning with and without knowledge transfer within the context of protein engineering.

In CASP15, there was a greater emphasis on multimeric modeling than in previous experiments, with assembly structures nearly doubling in number (41 up from 22) since the previous round. CASP15 also included a new estimation of model accuracy (EMA) category in recognition of the importance of objective quality assessment (QA) for quaternary structure models. ModFOLDdock is a multimeric model QA server developed by the McGuffin group at the University of Reading, which brings together a range of single-model, clustering, and deep learning methods to form a consensus of approaches. For CASP15, three variants of ModFOLDdock were developed to optimize for the different facets of the quality estimation problem. The standard ModFOLDdock variant produced predicted scores optimized for positive linear correlations with the observed scores. The ModFOLDdockR variant produced predicted scores optimized for ranking, that is, the top-ranked models have the highest accuracy. In addition, the ModFOLDdockS variant used a quasi-single model approach to score each model on an individual basis. The scores from all three variants achieved strongly positive Pearson correlation coefficients with the CASP observed scores (oligo-lDDT) in excess of 0.70, which were maintained across both homomeric and heteromeric model populations. In addition, at least one of the ModFOLDdock variants was consistently ranked in the top two methods across all three EMA categories. Specifically, for overall global fold prediction accuracy, ModFOLDdock placed second and ModFOLDdockR placed third; for overall interface quality prediction accuracy, ModFOLDdockR, ModFOLDdock, and ModFOLDdockS were placed above all other predictor methods, and ModFOLDdockR and ModFOLDdockS were placed second and third respectively for individual residue confidence scores. The ModFOLDdock server is available at: https://www.reading.ac.uk/bioinf/ModFOLDdock/. ModFOLDdock is also available as part of the MultiFOLD docker package: https://hub.docker.com/r/mcguffin/multifold.

Prediction categories in the Critical Assessment of Structure Prediction (CASP) experiments change with the need to address specific problems in structure modeling. In CASP15, four new prediction categories were introduced: RNA structure, ligand-protein complexes, accuracy of oligomeric structures and their interfaces, and ensembles of alternative conformations. This paper lists technical specifications for these categories and describes their integration in the CASP data management system.