Machine Learning Prediction of DNA Charge Transport

Abstract

First principle calculations of charge transfer in DNA molecules are computationally expensive given that charge carriers migrate in interaction with intra-and inter-molecular atomic motion. Screening sequences, e.g. to identify excellent electrical conductors is challenging even when adopting coarse-grained models and effective computational schemes that do not explicitly describe atomic dynamics. In this work, we present a machine learning (ML) model that allows the inexpensive prediction of the electrical conductance of millions of long double-stranded DNA (dsDNA) sequences, reducing computational costs by orders of magnitude. The algorithm is trained on short DNA nanojunctions with n = 3 − 7 base pairs. The electrical conductance of the training set is computed with a quantum scattering method, which captures charge-nuclei scattering processes. We demonstrate that the ML method accurately predicts the electrical conductance of varied dsDNA junctions tracing different transport mechanisms: coherent (short-range) quantum tunneling, onresonance (ballistic) transport, and incoherent site-to-site hopping. Furthermore, the ML approach supports physical observations that clusters of nucleotides regulate DNA transport behavior. The input features tested in this work could be used in other ML studies of charge transport in complex polymers, in the search for promising electronic and thermoelectric materials.

Degradation of Polyethylene and Biocomponent-Derived Polymer Materials: An Overview

“…Currently, starch is one of the most commonly used plant feedstocks for modifying the structure of polyethylene. This is confirmed by the relatively large number of scientific papers investigating the properties of starch and polyethylene mixtures [5,[29][30][31][32][33][34][35]. Starch is an easily available and cheap vegetable feedstock and, thanks to its properties, it is widely used in many branches of the economy, above all, in the industry of high-molecular-weight plastics as a biodegradable filler [1].…”

“…A good knowledge of starch properties, resulting from many years of research, finally led to the conclusion that native (unmodified) starch has a very limited application due to its poor solubility, strong hydrophobic properties, as well as unfavourable mechanical properties [33][34][35]. As stated by Żuchowska et al [1], the structure of primary starch, i.e.…”

“…As stated by Korol [35], reduced hydrophobicity of starch is possible through its chemical modification, but this process leads to the creation of products toxic to the environment and is expensive. For these reasons, another commonly used method of modifying native starch is its thermoplasticisation in the form of plasticisers during extrusion [35].…”

“…As stated by Korol [35], reduced hydrophobicity of starch is possible through its chemical modification, but this process leads to the creation of products toxic to the environment and is expensive. For these reasons, another commonly used method of modifying native starch is its thermoplasticisation in the form of plasticisers during extrusion [35]. This author stated that this process leads to the disruption of the crystalline structure of starch, resulting from breaking of hydrogen bonds and its transformation into an amorphous form of thermoplastic starch, which is fully biodegradable.…”

“…This author stated that this process leads to the disruption of the crystalline structure of starch, resulting from breaking of hydrogen bonds and its transformation into an amorphous form of thermoplastic starch, which is fully biodegradable. One of the few disadvantages of this material is sensitivity to moisture and brittleness, but in combination with synthetic polymers, it acts as a factor that increases their susceptibility to degradation [35]. Świerz-Motysia et al [34] highlighted that the homogeneity and effective compatibility are key parameters affecting the final properties of the polyethylenestarch composite.…”