Beyond Tripeptides Two-Step Active Machine Learning for Very Large Data sets.

Alexander Van Teijlingen,Tell Tuttle

doi:10.1021/acs.jctc.1c00159

Alexander Van Teijlingen, Tell Tuttle

Open Access

https://doi.org/10.1021/acs.jctc.1c00159

Copy DOI

Abstract

Self-assembling peptide nanostructures have been shown to be of great importance in nature and have presented many promising applications, for example, in medicine as drug-delivery vehicles, biosensors, and antivirals. Being very promising candidates for the growing field of bottom-up manufacture of functional nanomaterials, previous work (Frederix, et al. 2011 and 2015) has screened all possible amino acid combinations for di- and tripeptides in search of such materials. However, the enormous complexity and variety of linear combinations of the 20 amino acids make exhaustive simulation of all combinations of tetrapeptides and above infeasible. Therefore, we have developed an active machine-learning method (also known as “iterative learning” and “evolutionary search method”) which leverages a lower-resolution data set encompassing the whole search space and a just-in-time high-resolution data set which further analyzes those target peptides selected by the lower-resolution model. This model uses newly generated data upon each iteration to improve both lower- and higher-resolution models in the search for ideal candidates. Curation of the lower-resolution data set is explored as a method to control the selected candidates, based on criteria such as log P. A major aim of this method is to produce the best results in the least computationally demanding way. This model has been developed to be broadly applicable to other search spaces with minor changes to the algorithm, allowing its use in other areas of research.

Highlights

Many peptides exhibit the tendency to self-assemble in water into a vast array of different structures, including micelles, nanovesicles, nanotubes, and nanofibers.[1−7] The inherent biocompatibility of many of these unprotected peptide nanomaterials makes this an attractive class of materials
Despite the ease of synthesis, the discovery of short peptides that are able to self-assemble becomes an intractable problem to investigate experimentally due to the vast sequence space that exists for this set of compounds (4 × 102 dipeptides to 2.56 × 1010 octapeptides).[18]
In order to discern if the model was being biased heavily by this initial peptide, we run the model 20 times each time starting with a different sequence-uniform tripeptide; we found the maximum difference between any two mean AP values after 10 iterations to be 0.078, falling to 0.074 after 20 iterations; the plots have been visualized in the Supporting Information, Figure S4

Summary

Introduction

Many peptides exhibit the tendency to self-assemble in water into a vast array of different structures, including micelles, nanovesicles, nanotubes, and nanofibers.[1−7] The inherent biocompatibility of many of these unprotected peptide nanomaterials makes this an attractive class of materials. There has been a drive in large-scale efforts to identify peptides of interest (antimicrobial,[8−10] self-assembling,[3,4,11] antineoplastic,[12−15] etc.). This is partially due to the aforementioned biocompatibility, and to the ease of synthesis which has been automated for short sequences.[16,17]. Our aim is to survey peptides of chain length 4−6 with the intention that this method could be further scaled to peptides of chain length 7− 8 with modern computer equipment

Objectives

Methods

Results

Conclusion