SAAMBE-3D: Predicting Effect of Mutations on Protein–Protein Interactions

Abstract

Maintaining wild type protein-protein interactions is essential for the normal function of cell and any mutation that alter their characteristics can cause disease. Therefore, the ability to correctly and quickly predict the effect of amino acid mutations is crucial for understanding disease effects and to be able to carry out genome-wide studies. Here, we report a new development of the SAAMBE method, SAAMBE-3D, which is a machine learning-based approach, resulting in accurate predictions and is extremely fast. It achieves the Pearson correlation coefficient ranging from 0.78 to 0.82 depending on the training protocol in benchmarking five-fold validation test against the SKEMPI v2.0 database and outperforms currently existing algorithms on various blind-tests. Furthermore, optimized and tested via five-fold cross-validation on the Cornell University dataset, the SAAMBE-3D achieves AUC of 1.0 and 0.96 on a homo and hereto-dimer test datasets. Another important feature of SAAMBE-3D is that it is very fast, it takes less than a fraction of a second to complete a prediction. SAAMBE-3D is available as a web server and as well as a stand-alone code, the last one being another important feature allowing other researchers to directly download the code and run it on their local computer. Combined all together, SAAMBE-3D is an accurate and fast software applicable for genome-wide studies to assess the effect of amino acid mutations on protein-protein interactions. The webserver and the stand-alone codes (SAAMBE-3D for predicting the change of binding free energy and SAAMBE-3D-DN for predicting if the mutation is disruptive or non-disruptive) are available.

The search of sequence variants using a constrained protein evolution simulation approach

“…In addition, most of former approaches, such as Backrub [38] , Rosetta-Design [15] or POP-Music [39] require the 3D coordinates of the protein while we consider here only the sequence. We discuss briefly our results in the light of the results obtained by the INPS server [40] – based on sequence and the very recent SAAMBE-3D server [41] – based on structure. Considering for instance the 1by0 target, both INPS and SAAMBE-3D predict that the subsitution E22D is slightly destabilizing, while it is not accepted by our protocol, nor observed in unriref90, which seems consistent.…”

Studying the Effects of ACE2 Mutations on the Stability, Dynamics, and Dissociation Process of SARS-CoV-2 S1/hACE2 Complexes

“…There are many bioinformatic methods to predict the stability of the protein complex and the affinity between subunits by using various approaches. We utilized PISA, 42 FoldX, 43 Prodigy, 44 SEPAS, 45 and SAAMBE-3D 46 for predicting the intersubunit affinity of the ACE2/S1 complexes using their 3D structures.…”

“…We predicted the affinity of the ACE2 mutants to the RBD of S1 by PISA, 42 FoldX, 43 Prodigy, 44 SEPAS, 45 and SAAMBE-3D. 46 We fed the noted tools with complexes whose ACE2 subunits are mutated.…”

“…We utilized the stand-alone version of the mentioned software. 46 The FoldX-constructed 3D structures of ACE2 mutants in complex with RBD of S1 are the inputs of SAAMBE-3D in the current study. On the basis of the software criteria, the positive binding energy of a mutant means that such a mutation weakens the binding free energy.…”

Two mutations P/L and Y/C in SARS-CoV-2 helicase domain exist together and influence helicase RNA binding

“…Protein structure stability and RNA binding mCSM NA was used to detect the effect of mutations on helicase-RNA binding. Structural stability was assessed using two different tools, SAAMBE 3D [3] and MUPro.…”