Inductive inference of novel protein-molecule interactions using Heterogeneous Graph Transformer (HGT) AutoEncoder

Protein-molecule interactions are promoted by the physicochemical characteristics of the actors involved, but structural information alone does not capture expression patterns, localization and pharmacokinetics. In this work we propose an integrative strategy for protein-molecule interaction discovery that combines different layers of information through the use of convolutional operators on graph, and frame the problem as missing link prediction task on an heterogeneous graph constituted by three node types: 1) molecules 2) proteins 3) diseases. Physicochemical information of the actors are encoded using shallow embedding techniques (SeqVec, Mol2Vec, Doc2Vec respectively) and are supplied as feature vectors to a Graph AutoEncoer (GAE) that uses a Heterogeneous Graph Transformer (HGT) in the encoder module. We show in this work that HGT Autoencoder can be used to accurately recapitulate the protein-molecule interactions set and propose novel relationships in inductive settings that are grounded in biological and functional information extracted from the graph.

In silico Studies of Novel Synthetic Compounds as Potential Drugs to Inhibit Coronavirus (SARS-CoV-2): A Systematic Review

Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2), detected first in China, spread out fast to other parts of the world, and was soon recognized as a pandemic in March 2020. According to WHO, 179.686.071 confirmed cases and 3.899.172 deaths due to new coronavirus were reported worldwide on 26th June 2021. Despite countless efforts in searching for repositioned drugs to treat this disease, the results are still modest. Thus, the search for new molecular entities in the treatment of COVID-19 is an essential field in medicinal chemistry. Since the pandemic's beginning, several studies have reported the synthesis of novel organic compounds and their in silico interactions with the new coronavirus. Such computational studies are currently being applied to unveil the complexities of drug-target molecule interaction and also helping in developing new pharmacological treatments. This systematic review aims to provide an overview of studies describing the utilization of novel compounds as prospective drugs in the treatment of COVID-19.

DFT Simulation of the Water Molecule Interaction with the (00l) Surface of Montmorillonite

Montmorillonite is one of the principal mineralogical phases in clay minerals, where its interaction with water and other molecules represents one of the most important aspects and properties for basic science and specific applications. In fact, montmorillonite has many uses in various scientific and technological fields, ranging from environmental remediation to ceramics, food science, and construction/building materials. Several efforts have characterized its structure and physico-chemical properties, especially at the Tetrahedral-Octahedral-Tetrahedral TOT surface. For this purpose, in this work, the authors investigated the structural and electrostatic potential features of the (00l) surface of montmorillonite and the water adsorption process by first principle methods (density functional theory, DFT), considering both static and molecular dynamics approaches. The provided data further extend the knowledge of the modulation of the water molecule adsorption with this important clay mineral.