Evaluation of protein descriptors in computer-aided rational protein engineering tasks and its application in property prediction in SARS-CoV-2 spike glycoprotein.

The importance of protein engineering in the research and development of biopharmaceuticals and biomaterials has increased. Machine learning in computer-aided protein engineering can markedly reduce the experimental effort in identifying optimal sequences that satisfy the desired properties from a large number of possible protein sequences. To develop general protein descriptors for computer-aided protein engineering tasks, we devised new protein descriptors, one sequence-based descriptor (PCgrades), and three structure-based descriptors (PCspairs, 3D-SPIEs_5.4 Å, and 3D-SPIEs_8Å). While the PCgrades and PCspairs include general and statistical information in physicochemical properties in single and pairwise amino acids respectively, the 3D-SPIEs include specific and quantum-mechanical information with parameterized quantum mechanical calculations (FMO2-DFTB3/D/PCM). To evaluate the protein descriptors, we made prediction models with the new descriptors and previously developed descriptors for diverse protein datasets including protein expression and binding affinity change in SARS-CoV-2 spike glycoprotein. As a result, the newly devised descriptors showed a good performance in diverse datasets, in which the PCspairs showed the best performance ( R 2 = 0.783 for protein expression and R 2 = 0.711 for binding affinity). As a result, the newly devised descriptors showed a good performance in diverse datasets, in which the PCspairs showed the best performance. Similar approaches with those descriptors would be promising and useful if the prediction models are trained with sufficient quantitative experimental data from high-throughput assays for industrial enzymes or protein drugs.

Hot spot profiles of SARS-CoV-2 and human ACE2 receptor protein protein interaction obtained by density functional tight binding fragment molecular orbital method.

The prevalence of a novel ß-coronavirus (SARS-CoV-2) was declared as a public health emergency of international concern on 30 January 2020 and a global pandemic on 11 March 2020 by WHO. The spike glycoprotein of SARS-CoV-2 is regarded as a key target for the development of vaccines and therapeutic antibodies. In order to develop anti-viral therapeutics for SARS-CoV-2, it is crucial to find amino acid pairs that strongly attract each other at the interface of the spike glycoprotein and the human angiotensin-converting enzyme 2 (hACE2) complex. In order to find hot spot residues, the strongly attracting amino acid pairs at the protein-protein interaction (PPI) interface, we introduce a reliable inter-residue interaction energy calculation method, FMO-DFTB3/D/PCM/3D-SPIEs. In addition to the SARS-CoV-2 spike glycoprotein/hACE2 complex, the hot spot residues of SARS-CoV-1 spike glycoprotein/hACE2 complex, SARS-CoV-1 spike glycoprotein/antibody complex, and HCoV-NL63 spike glycoprotein/hACE2 complex were obtained using the same FMO method. Following this, a 3D-SPIEs-based interaction map was constructed with hot spot residues for the hACE2/SARS-CoV-1 spike glycoprotein, hACE2/HCoV-NL63 spike glycoprotein, and hACE2/SARS-CoV-2 spike glycoprotein complexes. Finally, the three 3D-SPIEs-based interaction maps were combined and analyzed to find the consensus hot spots among the three complexes. As a result of the analysis, two hot spots were identified between hACE2 and the three spike proteins. In particular, E37, K353, G354, and D355 of the hACE2 receptor strongly interact with the spike proteins of coronaviruses. The 3D-SPIEs-based map would provide valuable information to develop anti-viral therapeutics that inhibit PPIs between the spike protein of SARS-CoV-2 and hACE2.