Discriminating physiological from non-physiological interfaces in structures of protein complexes: A community-wide study

Reliably scoring and ranking candidate models of protein complexes and assigning their oligomeric state from the structure of the crystal lattice represent outstanding challenges. A community-wide effort was launched to tackle these challenges. The latest resources on protein complexes and interfaces were exploited to derive a benchmark dataset consisting of 1677 homodimer protein crystal structures, including a balanced mix of physiological and non-physiological complexes. The non-physiological complexes in the benchmark were selected to bury a similar or larger interface area than their physiological counterparts, making it more difficult for scoring functions to differentiate between them. Next, 252 functions for scoring protein-protein interfaces previously developed by 13 groups were collected and evaluated for their ability to discriminate between physiological and non-physiological complexes. A simple consensus score generated using the best performing score of each of the 13 groups, and a cross-validated Random Forest (RF) classifier were created. Both approaches showed excellent performance, with an area under the Receiver Operating Characteristic (ROC) curve of 0.93 and 0.94, respectively, outperforming individual scores developed by different groups. Additionally, AlphaFold2 engines recalled the physiological dimers with significantly higher accuracy than the non-physiological set, lending support to the reliability of our benchmark dataset annotations. Optimizing the combined power of interface scoring functions and evaluating it on challenging benchmark datasets appears to be a promising strategy.

The LightDock Server: Artificial Intelligence-powered modeling of macromolecular interactions

Computational docking is an instrumental method of the structural biology toolbox. Specifically, integrative modeling software, such as LightDock, arise as complementary and synergetic methods to experimental structural biology techniques. Ubiquitousness and accessibility are fundamental features to promote ease of use and to improve user experience. With this goal in mind, we have developed the LightDock Server, a web server for the integrative modeling of macromolecular interactions, along with several dedicated usage modes. The server builds upon the LightDock macromolecular docking framework, which has proved useful for modeling medium-to-high flexible complexes, antibody-antigen interactions, or membrane-associated protein assemblies. We believe that this free-to-use resource will be a valuable addition to the structural biology community and can be accessed online at: https://server.lightdock.org/.

Improving classification of correct and incorrect protein-protein docking models by augmenting the training set

Motivation

Protein-protein interactions drive many relevant biological events, such as infection, replication and recognition. To control or engineer such events, we need to access the molecular details of the interaction provided by experimental 3D structures. However, such experiments take time and are expensive; moreover, the current technology cannot keep up with the high discovery rate of new interactions. Computational modeling, like protein-protein docking, can help to fill this gap by generating docking poses. Protein-protein docking generally consists of two parts, sampling and scoring. The sampling is an exhaustive search of the tridimensional space. The caveat of the sampling is that it generates a large number of incorrect poses, producing a highly unbalanced dataset. This limits the utility of the data to train machine learning classifiers.

Results

Using weak supervision, we developed a data augmentation method that we named hAIkal. Using hAIkal, we increased the labeled training data to train several algorithms. We trained and obtained different classifiers; the best classifier has 81% accuracy and 0.51 Matthews' correlation coefficient on the test set, surpassing the state-of-the-art scoring functions.

Availability and implementation

Docking models from Benchmark 5 are available at https://doi.org/10.5281/zenodo.4012018. Processed tabular data are available at https://repository.kaust.edu.sa/handle/10754/666961. Google colab is available at https://colab.research.google.com/drive/1vbVrJcQSf6\_C3jOAmZzgQbTpuJ5zC1RP?usp=sharing.

Supplementary information

Supplementary data are available at Bioinformatics Advances online.

A random forest classifier for protein-protein docking models

Herein, we present the results of a machine learning approach we developed to single out correct 3D docking models of protein-protein complexes obtained by popular docking software. To this aim, we generated 3 × 10 4 docking models for each of the 230 complexes in the protein-protein benchmark, version 5, using three different docking programs (HADDOCK, FTDock and ZDOCK), for a cumulative set of ≈ 7 × 10 6 docking models. Three different machine learning approaches (Random Forest, Supported Vector Machine and Perceptron) were used to train classifiers with 158 different scoring functions (features). The Random Forest algorithm outperformed the other two algorithms and was selected for further optimization. Using a features selection algorithm, and optimizing the random forest hyperparameters, allowed us to train and validate a random forest classifier, named COnservation Driven Expert System (CoDES). Testing of CoDES on independent datasets, as well as results of its comparative performance with machine learning methods recently developed in the field for the scoring of docking decoys, confirm its state-of-the-art ability to discriminate correct from incorrect decoys both in terms of global parameters and in terms of decoys ranked at the top positions.

Supplementary information

Supplementary data are available at Bioinformatics Advances online.

Software and data availability statement

The docking models are available at https://doi.org/10.5281/zenodo.4012018. The programs underlying this article will be shared on request to the corresponding authors.

Prediction of protein assemblies, the next frontier: The CASP14-CAPRI experiment

We present the results for CAPRI Round 50, the fourth joint CASP-CAPRI protein assembly prediction challenge. The Round comprised a total of twelve targets, including six dimers, three trimers, and three higher-order oligomers. Four of these were easy targets, for which good structural templates were available either for the full assembly, or for the main interfaces (of the higher-order oligomers). Eight were difficult targets for which only distantly related templates were found for the individual subunits. Twenty-five CAPRI groups including eight automatic servers submitted ~1250 models per target. Twenty groups including six servers participated in the CAPRI scoring challenge submitted ~190 models per target. The accuracy of the predicted models was evaluated using the classical CAPRI criteria. The prediction performance was measured by a weighted scoring scheme that takes into account the number of models of acceptable quality or higher submitted by each group as part of their five top-ranking models. Compared to the previous CASP-CAPRI challenge, top performing groups submitted such models for a larger fraction (70-75%) of the targets in this Round, but fewer of these models were of high accuracy. Scorer groups achieved stronger performance with more groups submitting correct models for 70-80% of the targets or achieving high accuracy predictions. Servers performed less well in general, except for the MDOCKPP and LZERD servers, who performed on par with human groups. In addition to these results, major advances in methodology are discussed, providing an informative overview of where the prediction of protein assemblies currently stands.

The CASP13-CAPRI targets as case studies to illustrate a novel scoring pipeline integrating CONSRANK with clustering and interface analyses

Background

Properly scoring protein-protein docking models to single out the correct ones is an open challenge, also object of assessment in CAPRI (Critical Assessment of PRedicted Interactions), a community-wide blind docking experiment. We introduced in the field CONSRANK (CONSensus RANKing), the first pure consensus method. Also available as a web server, CONSRANK ranks docking models in an ensemble based on their ability to match the most frequent inter-residue contacts in it. We have been blindly testing CONSRANK in all the latest CAPRI rounds, where we showed it to perform competitively with the state-of-the-art energy and knowledge-based scoring functions. More recently, we developed Clust-CONSRANK, an algorithm introducing a contact-based clustering of the models as a preliminary step of the CONSRANK scoring process.

In the latest CASP13-CAPRI joint experiment, we participated as scorers with a novel pipeline, combining both our scoring tools, CONSRANK and Clust-CONSRANK, with our interface analysis tool COCOMAPS. Selection of the 10 models for submission was guided by the strength of the emerging consensus, and their final ranking was assisted by results of the interface analysis.

Results

As a result of the above approach, we were by far the first scorer in the CASP13-CAPRI top-1 ranking, having high/medium quality models ranked at the top-1 position for the majority of targets (11 out of the total 19). We were also the first scorer in the top-10 ranking, on a par with another group, and the second scorer in the top-5 ranking. Further, we topped the ranking relative to the prediction of binding interfaces, among all the scorers and predictors. Using the CASP13-CAPRI targets as case studies, we illustrate here in detail the approach we adopted.

Conclusions

Introducing some flexibility in the final model selection and ranking, as well as differentiating the adopted scoring approach depending on the targets were the key assets for our highly successful performance, as compared to previous CAPRI rounds. The approach we propose is entirely based on methods made available to the community and could thus be reproduced by any user.

Blind prediction of homo- and hetero-protein complexes: The CASP13-CAPRI experiment

We present the results for CAPRI Round 46, the third joint CASP-CAPRI protein assembly prediction challenge. The Round comprised a total of 20 targets including 14 homo-oligomers and 6 heterocomplexes. Eight of the homo-oligomer targets and one heterodimer comprised proteins that could be readily modeled using templates from the Protein Data Bank, often available for the full assembly. The remaining 11 targets comprised 5 homodimers, 3 heterodimers, and two higher-order assemblies. These were more difficult to model, as their prediction mainly involved "ab-initio" docking of subunit models derived from distantly related templates. A total of ~30 CAPRI groups, including 9 automatic servers, submitted on average ~2000 models per target. About 17 groups participated in the CAPRI scoring rounds, offered for most targets, submitting ~170 models per target. The prediction performance, measured by the fraction of models of acceptable quality or higher submitted across all predictors groups, was very good to excellent for the nine easy targets. Poorer performance was achieved by predictors for the 11 difficult targets, with medium and high quality models submitted for only 3 of these targets. A similar performance "gap" was displayed by scorer groups, highlighting yet again the unmet challenge of modeling the conformational changes of the protein components that occur upon binding or that must be accounted for in template-based modeling. Our analysis also indicates that residues in binding interfaces were less well predicted in this set of targets than in previous Rounds, providing useful insights for directions of future improvements.

Cancer growth and metastasis as a metaphor of Go gaming: An Ising model approach

This work aims for modeling and simulating the metastasis of cancer, via the analogy between the cancer process and the board game Go. In the game of Go, black stones that play first could correspond to a metaphor of the birth, growth, and metastasis of cancer. Moreover, playing white stones on the second turn could correspond the inhibition of cancer invasion. Mathematical modeling and algorithmic simulation of Go may therefore benefit the efforts to deploy therapies to surpass cancer illness by providing insight into the cellular growth and expansion over a tissue area. We use the Ising Hamiltonian, that models the energy exchange in interacting particles, for modeling the cancer dynamics. Parameters in the energy function refer the biochemical elements that induce cancer birth, growth, and metastasis; as well as the biochemical immune system process of defense.

Docking-based modeling of protein-protein interfaces for extensive structural and functional characterization of missense mutations

Next-generation sequencing (NGS) technologies are providing genomic information for an increasing number of healthy individuals and patient populations. In the context of the large amount of generated genomic data that is being generated, understanding the effect of disease-related mutations at molecular level can contribute to close the gap between genotype and phenotype and thus improve prevention, diagnosis or treatment of a pathological condition. In order to fully characterize the effect of a pathological mutation and have useful information for prediction purposes, it is important first to identify whether the mutation is located at a protein-binding interface, and second to understand the effect on the binding affinity of the affected interaction/s. Computational methods, such as protein docking are currently used to complement experimental efforts and could help to build the human structural interactome. Here we have extended the original pyDockNIP method to predict the location of disease-associated nsSNPs at protein-protein interfaces, when there is no available structure for the protein-protein complex. We have applied this approach to the pathological interaction networks of six diseases with low structural data on PPIs. This approach can almost double the number of nsSNPs that can be characterized and identify edgetic effects in many nsSNPs that were previously unknown. This can help to annotate and interpret genomic data from large-scale population studies, and to achieve a better understanding of disease at molecular level.

IRaPPA: information retrieval based integration of biophysical models for protein assembly selection

MOTIVATION

In order to function, proteins frequently bind to one another and form 3D assemblies. Knowledge of the atomic details of these structures helps our understanding of how proteins work together, how mutations can lead to disease, and facilitates the designing of drugs which prevent or mimic the interaction.

RESULTS

Atomic modeling of protein-protein interactions requires the selection of near-native structures from a set of docked poses based on their calculable properties. By considering this as an information retrieval problem, we have adapted methods developed for Internet search ranking and electoral voting into IRaPPA, a pipeline integrating biophysical properties. The approach enhances the identification of near-native structures when applied to four docking methods, resulting in a near-native appearing in the top 10 solutions for up to 50% of complexes benchmarked, and up to 70% in the top 100.

AVAILABILITY AND IMPLEMENTATION

IRaPPA has been implemented in the SwarmDock server ( http://bmm.crick.ac.uk/∼SwarmDock/ ), pyDock server ( http://life.bsc.es/pid/pydockrescoring/ ) and ZDOCK server ( http://zdock.umassmed.edu/ ), with code available on request.

CONTACT

moal@ebi.ac.uk.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Diferential DNA synthesis in Anopheles albimanus tissues induced by immune challenge with different microorganisms

The induction of DNA synthesis in various tissues of Anopheles albimanus, in response to challenge with Saccharomyces cerevisiae, Micrococcus luteus, and Serratia marcescens, was analyzed by 5-bromo-2-deoxy-uridine (BrdU) incorporation. Microorganism-inoculated mosquitoes were fed with a sucrose solution containing BrdU and maintained alive for 5 days. Alternatively, abdominal carcasses of microorganisms-inoculated mosquitoes were cultivated in Roswell Park Memorial Institute (RPMI) medium supplemented with BrdU for 5 days. Control groups were inoculated with RPMI alone. In both experiments, DNA synthesis, evidenced by epifluorescence with an anti-BrdU fluorescein-labeled antibody, occurred in fat body, epithelial cells of pleural membranes, dorsal vessel, and the oviducts. Relative quantification of DNA synthesis, evaluated by ELISA using an anti-BrdU peroxidase-labeled antibody, was higher in abdomen tissues of microorganisms-inoculated mosquitoes than controls in in vitro and in vivo experiments. The intensity of DNA synthesis varied among the different microorganism challenges, but was higher in in vivo experiments, compared to cultured samples. These differences in DNA synthesis suggest a compartmentalization of the immune response, probably mediated by different signaling pathways.