Abstract
The crucial role of protein interactions and the difficulty in characterising them experimentally strongly motivates the development of computational approaches for structural prediction. Even when protein-protein docking samples correct models, current scoring functions struggle to discriminate them from incorrect decoys. The previous incorporation of conservation and coevolution information has shown promise for improving protein-protein scoring. Here, we present a novel strategy to integrate atomic-level evolutionary information into different types of scoring functions to improve their docking discrimination.
We applied this general strategy to our residue-level statistical potential from InterEvScore and to two atomic-level scores, SOAP-PP and Rosetta interface score (ISC). Including evolutionary information from as few as ten homologous sequences improves the top 10 success rates of these individual scores by respectively 6.5, 6 and 13.5 percentage points, on a large benchmark of 752 docking cases. The best individual homology-enriched score reaches a top 10 success rate of 34.4%. A consensus approach based on the complementarity between different homology-enriched scores further increases the top 10 success rate to 40%.
All data used for benchmarking and scoring results, as well as pipelining scripts, are available at http://biodev.cea.fr/interevol/interevdata/
Competing Interest Statement
The authors have declared no competing interest.
Footnotes
Funding This work was supported by Agence Nationale de la Recherche [ANR‐15‐CE11‐0008 to R.G., ANR-18-CE45-0005 to J.A]; IDEX Paris-Saclay [IDI 2017 to C.Q.]; MINECO [BFU2016-76220-P to P.C.]; and AEI/FEDER, UE [PID2019-109041GB-C21 to P.C.].
