Impact of AlphaFold on structure prediction of protein complexes: The CASP15-CAPRI experiment

We present the results for CAPRI Round 54, the 5th joint CASP-CAPRI protein assembly prediction challenge. The Round offered 37 targets, including 14 homodimers, 3 homo-trimers, 13 heterodimers including 3 antibody-antigen complexes, and 7 large assemblies. On average ~70 CASP and CAPRI predictor groups, including more than 20 automatics servers, submitted models for each target. A total of 21 941 models submitted by these groups and by 15 CAPRI scorer groups were evaluated using the CAPRI model quality measures and the DockQ score consolidating these measures. The prediction performance was quantified by a weighted score based on the number of models of acceptable quality or higher submitted by each group among their five best models. Results show substantial progress achieved across a significant fraction of the 60+ participating groups. High-quality models were produced for about 40% of the targets compared to 8% two years earlier. This remarkable improvement is due to the wide use of the AlphaFold2 and AlphaFold2-Multimer software and the confidence metrics they provide. Notably, expanded sampling of candidate solutions by manipulating these deep learning inference engines, enriching multiple sequence alignments, or integration of advanced modeling tools, enabled top performing groups to exceed the performance of a standard AlphaFold2-Multimer version used as a yard stick. This notwithstanding, performance remained poor for complexes with antibodies and nanobodies, where evolutionary relationships between the binding partners are lacking, and for complexes featuring conformational flexibility, clearly indicating that the prediction of protein complexes remains a challenging problem.

Computational structure modeling for diverse categories of macromolecular interactions

Computational protein-protein docking is one of the most intensively studied topics in structural bioinformatics. The field has made substantial progress through over three decades of development. The development began with methods for rigid-body docking of two proteins, which have now been extended in different directions to cover the various macromolecular interactions observed in a cell. Here, we overview the recent developments of the variations of docking methods, including multiple protein docking, peptide-protein docking, and disordered protein docking methods.

Protein docking model evaluation by 3D deep convolutional neural networks

MOTIVATION

Many important cellular processes involve physical interactions of proteins. Therefore, determining protein quaternary structures provide critical insights for understanding molecular mechanisms of functions of the complexes. To complement experimental methods, many computational methods have been developed to predict structures of protein complexes. One of the challenges in computational protein complex structure prediction is to identify near-native models from a large pool of generated models.

RESULTS

We developed a convolutional deep neural network-based approach named DOcking decoy selection with Voxel-based deep neural nEtwork (DOVE) for evaluating protein docking models. To evaluate a protein docking model, DOVE scans the protein-protein interface of the model with a 3D voxel and considers atomic interaction types and their energetic contributions as input features applied to the neural network. The deep learning models were trained and validated on docking models available in the ZDock and DockGround databases. Among the different combinations of features tested, almost all outperformed existing scoring functions.

AVAILABILITY AND IMPLEMENTATION

Codes available at http://github.com/kiharalab/DOVE, http://kiharalab.org/dove/.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

In silico structure-based approaches to discover protein-protein interaction-targeting drugs

A core concept behind modern drug discovery is finding a small molecule that modulates a function of a target protein. This concept has been successfully applied since the mid-1970s. However, the efficiency of drug discovery is decreasing because the druggable target space in the human proteome is limited. Recently, protein-protein interaction (PPI) has been identified asan emerging target space for drug discovery. PPI plays a pivotal role in biological pathways including diseases. Current human interactome research suggests that the number of PPIs is between 130,000 and 650,000, and only a small number of them have been targeted as drug targets. For traditional drug targets, in silico structure-based methods have been successful in many cases. However, their performance suffers on PPI interfaces because PPI interfaces are different in five major aspects: From a geometric standpoint, they have relatively large interface regions, flat geometry, and the interface surface shape tends to fluctuate upon binding. Also, their interactions are dominated by hydrophobic atoms, which is different from traditional binding-pocket-targeted drugs. Finally, PPI targets usually lack natural molecules that bind to the target PPI interface. Here, we first summarize characteristics of PPI interfaces and their known binders. Then, we will review existing in silico structure-based approaches for discovering small molecules that bind to PPI interfaces.

PL-PatchSurfer2: Improved Local Surface Matching-Based Virtual Screening Method That Is Tolerant to Target and Ligand Structure Variation

Virtual screening has become an indispensable procedure in drug discovery. Virtual screening methods can be classified into two categories: ligand-based and structure-based. While the former have advantages, including being quick to compute, in general they are relatively weak at discovering novel active compounds because they use known actives as references. On the other hand, structure-based methods have higher potential to find novel compounds because they directly predict the binding affinity of a ligand in a target binding pocket, albeit with substantially lower speed than ligand-based methods. Here we report a novel structure-based virtual screening method, PL-PatchSurfer2. In PL-PatchSurfer2, protein and ligand surfaces are represented by a set of overlapping local patches, each of which is represented by three-dimensional Zernike descriptors (3DZDs). By means of 3DZDs, the shapes and physicochemical complementarities of local surface regions of a pocket surface and a ligand molecule can be concisely and effectively computed. Compared with the previous version of the program, the performance of PL-PatchSurfer2 is substantially improved by the addition of two more features, atom-based hydrophobicity and hydrogen-bond acceptors and donors. Benchmark studies showed that PL-PatchSurfer2 performed better than or comparable to popular existing methods. Particularly, PL-PatchSurfer2 significantly outperformed existing methods when apo-form or template-based protein models were used for queries. The computational time of PL-PatchSurfer2 is about 20 times shorter than those of conventional structure-based methods. The PL-PatchSurfer2 program is available at http://www.kiharalab.org/plps2/ .