MOTIVATION: It is important to assess the quality of modeled biomolecules to benchmark and assess the performance of different prediction methods. DockQ has emerged as the standard tool for assessing the quality of protein interfaces in model structures against given references. However, as predictions of large multimers with multiple chains become more common, DockQ needs to be updated with more functionality for robustness and speed. Moreover, as the field progresses and more methods are released to predict interactions between proteins and other types of molecules, such as nucleic acids and small molecules, it becomes necessary to have a tool that can assess all types of interactions. RESULTS: Here, we present a complete reimplementation of DockQ in pure Python. The updated version of DockQ is more portable, faster and introduces novel functionalities, such as automatic DockQ calculations for multiple interfaces and automatic chain mapping with multi-threading. These enhancements are designed to facilitate comparative analyses of protein complexes, particularly large multi-chain complexes. Furthermore, DockQ is now also able to score interfaces between proteins, nucleic acids, and small molecules. AVAILABILITY AND IMPLEMENTATION: DockQ v2 is available online at: https://wallnerlab.org/DockQ.

SUMMARY: The AlphaFold2 neural network model has revolutionized structural biology with unprecedented performance. We demonstrate that by stochastically perturbing the neural network by enabling dropout at inference combined with massive sampling, it is possible to improve the quality of the generated models. We generated ∼6000 models per target compared with 25 default for AlphaFold-Multimer, with v1 and v2 multimer network models, with and without templates, and increased the number of recycles within the network. The method was benchmarked in CASP15, and compared with AlphaFold-Multimer v2 it improved the average DockQ from 0.41 to 0.55 using identical input and was ranked at the very top in the protein assembly category when compared with all other groups participating in CASP15. The simplicity of the method should facilitate the adaptation by the field, and the method should be useful for anyone interested in modeling multimeric structures, alternate conformations, or flexible structures. AVAILABILITY AND IMPLEMENTATION: AFsample is available online at http://wallnerlab.org/AFsample.

MOTIVATION: Interactions between peptide fragments and protein receptors are vital to cell function yet difficult to experimentally determine in structural details of. As such, many computational methods have been developed to aid in peptide-protein docking or structure prediction. One such method is Rosetta FlexPepDock which consistently refines coarse peptide-protein models into sub-Ångström precision using Monte-Carlo simulations and statistical potentials. Deep learning has recently seen increased use in protein structure prediction, with graph neural networks used for protein model quality assessment. RESULTS: Here, we introduce a graph neural network, InterPepScore, as an additional scoring term to complement and improve the Rosetta FlexPepDock refinement protocol. InterPepScore is trained on simulation trajectories from FlexPepDock refinement starting from thousands of peptide-protein complexes generated by a wide variety of docking schemes. The addition of InterPepScore into the refinement protocol consistently improves the quality of models created, and on an independent benchmark on 109 peptide-protein complexes its inclusion results in an increase in the number of complexes for which the top-scoring model had a DockQ-score of 0.49 (Medium quality) or better from 14.8% to 26.1%. AVAILABILITY AND IMPLEMENTATION: InterPepScore is available online at http://wallnerlab.org/InterPepScore. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Interactions between proteins and peptides or peptide-like intrinsically disordered regions are involved in many important biological processes, such as gene expression and cell life-cycle regulation. Experimentally determining the structure of such interactions is time-consuming and difficult because of the inherent flexibility of the peptide ligand. Although several prediction-methods exist, most are limited in performance or availability. RESULTS: InterPep2 is a freely available method for predicting the structure of peptide-protein interactions. Improved performance is obtained by using templates from both peptide-protein and regular protein-protein interactions, and by a random forest trained to predict the DockQ-score for a given template using sequence and structural features. When tested on 252 bound peptide-protein complexes from structures deposited after the complexes used in the construction of the training and templates sets of InterPep2, InterPep2-Refined correctly positioned 67 peptides within 4.0 Å LRMSD among top10, similar to another state-of-the-art template-based method which positioned 54 peptides correctly. However, InterPep2 displays a superior ability to evaluate the quality of its own predictions. On a previously established set of 27 non-redundant unbound-to-bound peptide-protein complexes, InterPep2 performs on-par with leading methods. The extended InterPep2-Refined protocol managed to correctly model 15 of these complexes within 4.0 Å LRMSD among top10, without using templates from homologs. In addition, combining the template-based predictions from InterPep2 with ab initio predictions from PIPER-FlexPepDock resulted in 22% more near-native predictions compared to the best single method (22 versus 18). AVAILABILITY AND IMPLEMENTATION: The program is available from: http://wallnerlab.org/InterPep2. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: In the past few years, drug discovery processes have been relying more and more on computational methods to sift out the most promising molecules before time and resources are spent to test them in experimental settings. Whenever the protein target of a given disease is not known, it becomes fundamental to have accurate methods for ligand-based virtual screening, which compares known active molecules against vast libraries of candidate compounds. Recently, 3D-based similarity methods have been developed that are capable of scaffold hopping and to superimpose matching molecules. RESULTS: Here, we present InterLig, a new method for the comparison and superposition of small molecules using topologically independent alignments of atoms. We test InterLig on a standard benchmark and show that it compares favorably to the best currently available 3D methods. AVAILABILITY AND IMPLEMENTATION: The program is available from http://wallnerlab.org/InterLig. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Motivation: Protein-protein interactions (PPI) are essential for the function of the cellular machinery. The rapid growth of protein-protein complexes with known 3D structures offers a unique opportunity to study PPI to gain crucial insights into protein function and the causes of many diseases. In particular, it would be extremely useful to compare interaction surfaces of monomers, as this would enable the pinpointing of potential interaction surfaces based solely on the monomer structure, without the need to predict the complete complex structure. While there are many structural alignment algorithms for individual proteins, very few have been developed for protein interfaces, and none that can align only the interface residues to other interfaces or surfaces of interacting monomer subunits in a topology independent (non-sequential) manner. Results: We present InterComp, a method for topology and sequence-order independent structural comparisons. The method is general and can be applied to various structural comparison applications. By representing residues as independent points in space rather than as a sequence of residues, InterComp can be applied to a wide range of problems including interface-surface comparisons and interface-interface comparisons. We demonstrate a use-case by applying InterComp to find similar protein interfaces on the surface of proteins. We show that InterComp pinpoints the correct interface for almost half of the targets (283 of 586) when considering the top 10 hits, and for 24% of the top 1, even when no templates can be found with regular sequence-order dependent structural alignment methods. Availability and implementation: The source code and the datasets are available at: http://wallnerlab.org/InterComp. Supplementary information: Supplementary data are available at Bioinformatics online.

SUMMARY: Protein quality assessment is a long-standing problem in bioinformatics. For more than a decade we have developed state-of-art predictors by carefully selecting and optimising inputs to a machine learning method. The correlation has increased from 0.60 in ProQ to 0.81 in ProQ2 and 0.85 in ProQ3 mainly by adding a large set of carefully tuned descriptions of a protein. Here, we show that a substantial improvement can be obtained using exactly the same inputs as in ProQ2 or ProQ3 but replacing the support vector machine by a deep neural network. This improves the Pearson correlation to 0.90 (0.85 using ProQ2 input features). AVAILABILITY AND IMPLEMENTATION: ProQ3D is freely available both as a webserver and a stand-alone program at http://proq3.bioinfo.se/. CONTACT: [email protected]. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Protein-protein interactions are a key in virtually all biological processes. For a detailed understanding of the biological processes, the structure of the protein complex is essential. Given the current experimental techniques for structure determination, the vast majority of all protein complexes will never be solved by experimental techniques. In lack of experimental data, computational docking methods can be used to predict the structure of the protein complex. A common strategy is to generate many alternative docking solutions (atomic models) and then use a scoring function to select the best. The success of the computational docking technique is, to a large degree, dependent on the ability of the scoring function to accurately rank and score the many alternative docking models. RESULTS: Here, we present ProQDock, a scoring function that predicts the absolute quality of docking model measured by a novel protein docking quality score (DockQ). ProQDock uses support vector machines trained to predict the quality of protein docking models using features that can be calculated from the docking model itself. By combining different types of features describing both the protein-protein interface and the overall physical chemistry, it was possible to improve the correlation with DockQ from 0.25 for the best individual feature (electrostatic complementarity) to 0.49 for the final version of ProQDock. ProQDock performed better than the state-of-the-art methods ZRANK and ZRANK2 in terms of correlations, ranking and finding correct models on an independent test set. Finally, we also demonstrate that it is possible to combine ProQDock with ZRANK and ZRANK2 to improve performance even further. AVAILABILITY AND IMPLEMENTATION: http://bioinfo.ifm.liu.se/ProQDock CONTACT: [email protected] SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Model quality assessment programs are used to predict the quality of modeled protein structures. They can be divided into two groups depending on the information they are using: ensemble methods using consensus of many alternative models and methods only using a single model to do its prediction. The consensus methods excel in achieving high correlations between prediction and true quality measures. However, they frequently fail to pick out the best possible model, nor can they be used to generate and score new structures. Single-model methods on the other hand do not have these inherent shortcomings and can be used both to sample new structures and to improve existing consensus methods. RESULTS: Here, we present an implementation of the ProQ2 program to estimate both local and global model accuracy as part of the Rosetta modeling suite. The current implementation does not only make it possible to run large batch runs locally, but it also opens up a whole new arena for conformational sampling using machine learned scoring functions and to incorporate model accuracy estimation in to various existing modeling schemes. ProQ2 participated in CASP11 and results from CASP11 are used to benchmark the current implementation. Based on results from CASP11 and CAMEO-QE, a continuous benchmark of quality estimation methods, it is clear that ProQ2 is the single-model method that performs best in both local and global model accuracy. AVAILABILITY AND IMPLEMENTATION: https://github.com/bjornwallner/ProQ_scripts CONTACT: [email protected] SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

SUMMARY: Model Quality Assessment Programs (MQAPs) are used to predict the quality of modeled protein structures. These usually use two approaches: methods using consensus of many alternative models and methods requiring only a single model to do its prediction. The consensus methods are useful to improve overall accuracy; however, they frequently fail to pick out the best possible model and cannot be used to generate and score new structures. Single-model methods, on the other hand, do not have these inherent shortcomings and can be used to both sample new structures and improve existing consensus methods. Here, we present ProQM-resample, a membrane protein-specific single-model MQAP, that couples side-chain resampling with MQAP rescoring by ProQM to improve model selection. The side-chain resampling is able to improve side-chain packing for 96% of all models, and improve model selection by 24% as measured by the sum of the Z-score for the first-ranked model (from 25.0 to 31.1), even better than the state-of-the-art consensus method Pcons. The improved model selection can be attributed to the improved side-chain quality, which enables the MQAP to rescue good backbone models with poor side-chain packing. AVAILABILITY AND IMPLEMENTATION: http://proqm.wallnerlab.org/download/. CONTACT: [email protected] SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

BACKGROUND: Employing methods to assess the quality of modeled protein structures is now standard practice in bioinformatics. In a broad sense, the techniques can be divided into methods relying on consensus prediction on the one hand, and single-model methods on the other. Consensus methods frequently perform very well when there is a clear consensus, but this is not always the case. In particular, they frequently fail in selecting the best possible model in the hard cases (lacking consensus) or in the easy cases where models are very similar. In contrast, single-model methods do not suffer from these drawbacks and could potentially be applied on any protein of interest to assess quality or as a scoring function for sampling-based refinement. RESULTS: Here, we present a new single-model method, ProQ2, based on ideas from its predecessor, ProQ. ProQ2 is a model quality assessment algorithm that uses support vector machines to predict local as well as global quality of protein models. Improved performance is obtained by combining previously used features with updated structural and predicted features. The most important contribution can be attributed to the use of profile weighting of the residue specific features and the use features averaged over the whole model even though the prediction is still local. CONCLUSIONS: ProQ2 is significantly better than its predecessors at detecting high quality models, improving the sum of Z-scores for the selected first-ranked models by 20% and 32% compared to the second-best single-model method in CASP8 and CASP9, respectively. The absolute quality assessment of the models at both local and global level is also improved. The Pearson's correlation between the correct and local predicted score is improved from 0.59 to 0.70 on CASP8 and from 0.62 to 0.68 on CASP9; for global score to the correct GDT_TS from 0.75 to 0.80 and from 0.77 to 0.80 again compared to the second-best single methods in CASP8 and CASP9, respectively. ProQ2 is available at http://proq2.wallnerlab.org.

UNLABELLED: Multiple templates can often be used to build more accurate homology models than models built from a single template. Here we introduce PconsM, an automated protocol that uses multiple templates to build protein models. PconsM has been among the top-performing methods in the recent CASP experiments and consistently perform better than the single template models used in Pcons.net. In particular for the easier targets with many alternative templates with a high degree of sequence identity, quality is readily improved with a few percentages over the highest ranked model built on a single template. PconsM is available as an additional pipeline within the Pcons.net protein structure prediction server. AVAILABILITY AND IMPLEMENTATION: PconsM is freely available from http://pcons.net/.

MOTIVATION: Learning-based model quality assessment programs have been quite successful at discriminating between high- and low-quality protein structures. Here, we show that it is possible to improve this performance significantly by restricting the learning space to a specific context, in this case membrane proteins. Since these are among the most important structures from a pharmaceutical point-of-view, it is particularly interesting to resolve local model quality for regions corresponding, e.g. to binding sites. RESULTS: Our new ProQM method uses a support vector machine with a combination of general and membrane protein-specific features. For the transmembrane region, ProQM clearly outperforms all methods developed for generic proteins, and it does so while maintaining performance for extra-membrane domains; in this region it is only matched by ProQres. The predictor is shown to accurately predict quality both on the global and local level when applied to GPCR models, and clearly outperforms consensus-based scoring. Finally, the combination of ProQM and the Rosetta low-resolution energy function achieve a 7-fold enrichment in selection of near-native structural models, at very limited computational cost. AVAILABILITY: ProQM is available as a server at +proqm.cbr.su.se+.

MOTIVATION: The success of the consensus approach to the protein structure prediction problem has led to development of several different consensus methods. Most of them only rely on a structural comparison of a number of different models. However, there are other types of information that might be useful such as the score from the server and structural evaluation. RESULTS: Pcons5 is a new and improved version of the consensus predictor Pcons. Pcons5 integrates information from three different sources: the consensus analysis, structural evaluation and the score from the fold recognition servers. We show that Pcons5 is better than the previous version of Pcons and that it performs better than using only the consensus analysis. In addition, we also present a version of Pmodeller based on Pcons5, which performs significantly better than Pcons5. AVAILABILITY: Pcons5 is the first Pcons version available as a standalone program from http://www.sbc.su.se/~bjorn/Pcons5. It should be easy to implement in local meta-servers.