Abstract
Topology Geometrics for the Generation of the Roccustyrnatm Molecule, A Ligand Targeted Covid-19-D614g Sites
Author(s): Grigoriadis IoannisSARS coronavirus 2 (SARS-CoV-2) encoding a D614G mutation in the viral spike (S) protein predominate over time in locales where it is found, implying that this change enhances viral transmission. It has also been observed that retroviruses pseudotyped with SG614 infected ACE2-expressing cells markedly more efficiently than those with SD614. The availability of newer modeling techniques, powerful computational resources, and good-quality data have made it possible to generate reliable predictions for new chemical entities, impurities, chemicals, natural products, and a lot of other substances fuelling further development and growth of the field to balance the trade-off between the molecular complexity and the quality of such predictions that cannot be obtained by any other method. In this article, we effectively use a decision tree to obtain an optimum number of small chemical active chemical features from a collection of thousands of them utilizing a shallow neural network and jointly free energy cumulative feature ranking method with decision tree taking both network parameters and input toxicity benchmark features into account. In this paper, we strongly combine the toxic models and ADMET methods that are simple in machine learning characteristics, efficient in computing resource usage, and powerful to achieve very high accuracy levels for the in-silico generation of the RoccustyrnaTM small molecule, a less toxic nano-ligand targeted the COVID-19-D614G mutation using Topology Euclidean Geometric and Artificial Intelligence-Driven Predictive Neural Networks. To demonstrate this, we also develop a Gravitational Topological (UFs) based Quantum-Parallel Particle Swarm Inspired framework using only 2D chemical features that are less compute- intensive.