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

Abstract

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.

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

“…Of the 157 descriptors from public sources, the one having by far the highest AUC value, 0.92, was the CONSRANK score. This is a consensus score, which reflects the conservation (or frequency) of the inter-residue contacts featured by a given model in the whole decoys ensemble it belongs to ( Chermak et al , 2015 ; Oliva et al , 2013 , 2015 ), widely tested on CAPRI targets ( Barradas-Bautista et al , 2020 ; Lensink et al , 2019 ; Vangone et al , 2013 ). The second highest AUC value, 0.78, was obtained for AP_GOAP_DF, an atomic distance-dependent potential, the DFIRE term in the GOAP energy ( Zhou and Skolnick, 2011 ), that we obtained from the CCharPPI server ( Moal et al , 2015a ).…”

“…This explains the need for developing novel and better scoring algorithms, potentially combining in a proper way the single scoring functions currently available (Barradas-Bautista et al, 2017), also by taking advantage of machine learning (ML) tools (Barradas-Bautista et al, 2022;Cao and Shen, 2020;Geng et al, 2020;Wang et al, 2020;Moal et al, 2017). One of the greatest challenges in developing novel scoring approaches consists in the limited number of correct decoys in the datasets used for training and testing.…”

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

“…Of the 157 descriptors from public sources, the one having by far the highest AUC value, 0.92, was the CONSRANK score. This is a consensus score, which reflects the conservation (or frequency) of the inter-residue contacts featured by a given model in the whole decoys ensemble it belongs to (Chermak et al ., 2015; Oliva et al ., 2015, 2013), widely tested on CAPRI targets (Barradas-Bautista et al ., 2020; Lensink et al ., 2019, 2016; Vangone et al ., 2013). The second highest AUC value, 0.78, was obtained for AP_GOAP_DF, an atomic distance-dependent potential, the DFIRE term in the GOAP energy (Zhou and Skolnick, 2011), that we obtained from the CCharPPI server (Moal et al ., 2015).…”

A random forest classifier for protein–protein docking models

“…One feature has an importance around 0.2 for both the approaches, being one order of magnitude larger than any other one. It is the CONSRANK score, a consensus score, which reflects the conservation (or frequency) of the inter-residue contacts featured by a given model in the whole decoys ensemble it belongs to Chermak et al (2015 ) and Oliva et al (2015 , 2013 ), widely tested on CAPRI targets ( Barradas-Bautista et al , 2020 ; Lensink et al , 2019 , 2016 ; Vangone et al , 2013 ). Among the top ten scoring functions, after CONSRANK, we find AP_GOAP_DF, CP_TD, CP_DI and CP_HLPL ( Garcia-Garcia et al , 2010 ; Pokarowski et al , 2005 ), which was interestingly also among the 10 most successful scoring functions when applied alone to DMs from three different docking software in Barradas-Bautista and Fernández-Recio (2017) , DDG_V, CP_MJ3h, pyDock_TOT, electrostatics, CP_SKOIP ( Lu et al , 2003 ), all obtained from the CCharPPI server ( Moal et al , 2015 ).…”