Systematic Comparison and Comprehensive Evaluation of 80 Amino Acid Descriptors in Peptide QSAR Modeling

Abstract

The peptide quantitative structure−activity relationship (QSAR), also known as the quantitative sequence−activity model (QSAM), has attracted much attention in the bio-and chemoinformatics communities and is a well developed computational peptidology strategy to statistically correlate the sequence/structure and activity/property relationships of functional peptides. Amino acid descriptors (AADs) are one of the most widely used methods to characterize peptide structures by decomposing the peptide into its residue building blocks and sequentially parametrizing each building block with a vector of amino acid principal properties. Considering that various AADs have been proposed over the past decades and new AADs are still emerging today, we herein query the following: is it necessary to develop so many AADs and do we need to continuously develop more new AADs? In this study, we exhaustively collect 80 published AADs and comprehensively evaluate their modeling performance (including fitting ability, internal stability, and predictive power) on 8 QSAR-oriented peptide sample sets (QPSs) by employing 2 sophisticated machine learning methods (MLMs), totally building and systematically comparing 1280 (80 AADs × 8 QPSs × 2 MLMs) peptide QSAR models. The following is revealed: (i) None of the AADs can work best on all or most peptide sets; an AAD usually performs well for some peptides but badly for others. (ii) Modeling performance is primarily determined by the peptide samples and then the MLMs used, while AADs have only a moderate influence on the performance. (iii) There is no essential difference between the modeling performances of different AAD types (physiochemical, topological, 3D-structural, etc.). (iv) Two random descriptors, which are separately generated randomly in standard normal distribution N(0, 1) and uniform distribution U(−1, +1), do not perform significantly worse than these carefully developed AADs. (v) A secondary descriptor, which carries major information involved in the 80 (primary) AADs, does not perform significantly better than these AADs. Overall, we conclude that since there are various AADs available to date and they already cover numerous amino acid properties, further development of new AADs is not an essential choice to improve peptide QSAR modeling; the traditional AAD methodology is believed to have almost reached the theoretical limit nowadays. In addition, the AADs are more likely to be a vector symbol but not informative data; they are utilized to mark and distinguish the 20 amino acids but do not really bring much original property information to these amino acids.

Systematic Modeling, Prediction, and Comparison of Domain–Peptide Affinities: Does it Work Effectively With the Peptide QSAR Methodology?

“…Recently, we have systematically evaluated totally 80 AADs in pQSAR modeling and identified a number of AADs with good performance (Zhou et al, 2021), from which we herein selected four different types of AADs to characterize the 21,399 SLiMcontaining peptides listed in Table 2, including MolSurf (quantumchemical) (Norinder and Svensson 1998), ST_scale (topological) (Yang et al, 2010), VHSE (physicochemical) (Mei et al, 2005) and VSGETAWAY (3D-structural) (Tong and Zhang 2007). Their values are tabulated in Supplementary Tables S4-S7.…”

Noncognate HER2 sensitivity to cognate EGFR allosteric inhibitors at molecular level: New uses for old drugs in gynecological tumors

“…(b) Superposition between the binding modes of EAI045 to wild-type HER2 and HER2 T798M/C805S double-mutant calculated with MM-GB/SA analysis, where the residues in kinase's active sites were characterized using amino acid descriptors. [19] As can be seen in Table 1, these inhibitors exhibit a roughly consistent profile of energetic components over the two kinases, that is, they have very favorable interaction energy with the kinases (ΔE int = ~À95 kcal/mol), which, however, would be largely impaired by the considerably unfavorable solvent effect (ΔG sol = ~70 kcal/mol) and the modestly unfavorable strain energy (ΔU str = ~15 kcal/mol), consequently resulting in a moderate favorable binding energy (ΔG tot = ~À10 kcal/mol). The binding energies (ΔG tot ) of the 9 allosteric inhibitors to EGFR and HER2 as well as their difference (ΔΔG tot HER2-EGFR ) are compared in Figure 3a.…”

Systematic profiling and identification of the peptide‐mediated interactions between human Yes‐associated protein and its partners in esophageal cancer

“…45 The peptide is a 14-mer protein seg- ized by amino acid descriptors. 46 Subsequently, the native SMAD7 decapeptide (in complex with YAP WW1/2 domains) was computationally mutated to each of the target decapeptides to obtain the total of 212 modeled complex structures of two YAP WW1/2 domains with the 106 PRM-containing decapeptide candidates, 47 which were then subjected to molecular dynamics simulations for conformational relaxing and equilibrium.…”