A conformational rearrangement of the SARS-CoV-2 host protein sigma-1 is required for antiviral activity: insights from a combined in-silico/in-vitro approach

Transformer Decoder Learns from a Pretrained Protein Language Model to Generate Ligands with High Affinity

The drug discovery process can be significantly accelerated by using deep learning methods to suggest molecules with druglike features and, more importantly, that are good candidates to bind specific proteins of interest. We present a novel deep learning generative model, Prot2Drug, that learns to generate ligands binding specific targets leveraging (i) the information carried by a pretrained protein language model and (ii) the ability of transformers to capitalize the knowledge gathered from thousands of protein-ligand interactions. The embedding unveils the receipt to follow for designing molecules binding a given protein, and Prot2Drug translates such instructions by using the syntax of the molecular language generating novel compounds which are predicted to have favorable physicochemical properties and high affinity toward specific targets. Moreover, Prot2Drug reproduced numerous known interactions between compounds and proteins used for generating them and suggested novel protein targets for known compounds, indicating potential drug repurposing strategies. Remarkably, Prot2Drug facilitates the design of promising ligands even for protein targets with limited or no information about their ligands or 3D structure.

AMALPHI: A Machine Learning Platform for Predicting Drug-Induced PhospholIpidosis

Drug-induced phospholipidosis (PLD) involves the accumulation of phospholipids in cells of multiple tissues, particularly within lysosomes, and it is associated with prolonged exposure to druglike compounds, predominantly cationic amphiphilic drugs (CADs). PLD affects a significant portion of drugs currently in development and has recently been proven to be responsible for confounding antiviral data during drug repurposing for SARS-CoV-2. In these scenarios, it has become crucial to identify potential safe drug candidates in advance and distinguish them from those that may lead to false in vitro antiviral activity. In this work, we developed a series of machine learning classifiers with the aim of predicting the PLD-inducing potential of drug candidates. The models were built on a high-quality chemical collection comprising 545 curated small molecules extracted from ChEMBL v30. The most effective model, obtained using the balanced random forest algorithm, achieved high performance, including an AUC value computed in validation as high as 0.90. The model was made freely available through a user-friendly web platform named AMALPHI (https://www.ba.ic.cnr.it/softwareic/amalphiportal/), which can represent a valuable tool for medicinal chemists interested in conducting an early evaluation of PLD inducer potential.

Benzomorphan and non-benzomorphan agonists differentially alter sigma-1 receptor quaternary structure, as does types of cellular stress

Sigma-1 receptor (S1R) is a calcium-sensitive, ligand-operated receptor chaperone present on the endoplasmic reticulum (ER) membrane. S1R plays an important role in ER-mitochondrial inter-organelle calcium signaling and cell survival. S1R and its agonists confer resilience against various neurodegenerative diseases; however, the molecular mechanism of S1R is not yet fully understood. At resting state, S1R is either in a monomeric or oligomeric state but the ratio of these concentrations seems to change upon activation of S1R. S1R is activated by either cellular stress, such as ER-calcium depletion, or ligands. While the effect of ligands on S1R quaternary structure remains unclear, the effect of cellular stress has not been studied. In this study we utilize cellular and an in-vivo model to study changes in quaternary structure of S1R upon activation. We incubated cells with cellular stressors (H2O2 and thapsigargin) or exogenous ligands, then quantified monomeric and oligomeric forms. We observed that benzomorphan-based S1R agonists induce monomerization of S1R and decrease oligomerization, which was confirmed in the liver tissue of mice injected with (+)-Pentazocine. Antagonists block this effect but do not induce any changes when used alone. Oxidative stress (H2O2) increases the monomeric/oligomeric S1R ratio whereas ER calcium depletion (thapsigargin) has no effect. We also analyzed the oligomerization ability of various truncated S1R fragments and identified the fragments favorizing oligomerization. In this publication we demonstrate that quaternary structural changes differ according to the mechanism of S1R activation. Therefore, we offer a novel perspective on S1R activation as a nuanced phenomenon dependent on the type of stimulus.