Advancing Drug Discovery via Artificial Intelligence

Anticancer peptides (ACPs) have emerged as a new class of therapeutic agent for cancer treatment due to their lower toxicity as well as greater efficacy, selectivity and specificity when compared to conventional small molecule drugs. However, the experimental identification of ACPs still remains a time-consuming and expensive endeavor. Therefore, it is desirable to develop and improve upon existing computational models for predicting and characterizing ACPs. In this study, we present a bioinformatics tool called the ACPred, which is an interpretable tool for the prediction and characterization of the anticancer activities of peptides. ACPred was developed by utilizing powerful machine learning models (support vector machine and random forest) and various classes of peptide features. It was observed by a jackknife cross-validation test that ACPred can achieve an overall accuracy of 95.61% in identifying ACPs. In addition, analysis revealed the following distinguishing characteristics that ACPs possess: (i) hydrophobic residue enhances the cationic properties of α-helical ACPs resulting in better cell penetration; (ii) the amphipathic nature of the α-helical structure plays a crucial role in its mechanism of cytotoxicity; and (iii) the formation of disulfide bridges on β-sheets is vital for structural maintenance which correlates with its ability to kill cancer cells. Finally, for the convenience of experimental scientists, the ACPred web server was established and made freely available online.

https://www.mdpi.com/1420-3049/24/10/1973/pdf

ACPred: A Computational Tool for the Prediction and Analysis of Anticancer Peptides

Drug discovery aims at finding new compounds with specific chemical properties for the treatment of diseases. In the last years, the approach used in this search presents an important component in computer science with the skyrocketing of machine learning techniques due to its democratization. With the objectives set by the Precision Medicine initiative and the new challenges generated, it is necessary to establish robust, standard and reproducible computational methodologies to achieve the objectives set. Currently, predictive models based on Machine Learning have gained great importance in the step prior to preclinical studies. This stage manages to drastically reduce costs and research times in the discovery of new drugs. This review article focuses on how these new methodologies are being used in recent years of research. Analyzing the state of the art in this field will give us an idea of where cheminformatics will be developed in the short term, the limitations it presents and the positive results it has achieved. This review will focus mainly on the methods used to model the molecular data, as well as the biological problems addressed and the Machine Learning algorithms used for drug discovery in recent years.

A review on machine learning approaches and trends in drug discovery.

Spike (S) protein cleavage is a crucial step in coronavirus infection. In this review, this process is discussed, with particular focus on the novel coronavirus, severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). Compared with influenza virus and paramyxovirus membrane fusion proteins, the cleavage activation mechanism of coronavirus S protein is much more complex. The S protein has two cleavage sites (S1/S2 and S2'), and the cleavage motif for furin protease at the S1/S2 site that results from a unique four-amino acid insertion is one of the distinguishing features of SARS-CoV-2. The viral particle incorporates the S protein, which has already undergone S1/S2 cleavage by furin, and then undergoes further cleavage at the S2' site, mediated by the type II transmembrane serine protease transmembrane protease serine 2 (TMPRSS2), after binding to the receptor angiotensin-converting enzyme 2 (ACE2) to facilitate membrane fusion at the plasma membrane. In addition, SARS-CoV-2 can enter the cell by endocytosis and be proteolytically activated by cathepsin L, although this is not a major mode of SARS-CoV-2 infection. SARS-CoV-2 variants with enhanced infectivity have been emerging throughout the ongoing pandemic, and there is a close relationship between enhanced infectivity and changes in S protein cleavability. All four variants of concern carry the D614G mutation, which indirectly enhances S1/S2 cleavability by furin. The P681R mutation of the delta variant directly increases S1/S2 cleavability, enhancing membrane fusion and SARS-CoV-2 virulence. Changes in S protein cleavability can significantly impact viral infectivity, tissue tropism, and virulence. Understanding these mechanisms is critical to counteracting the coronavirus pandemic.

https://onlinelibrary.wiley.com/doi/pdf/10.1111/1348-0421.12945

Proteolytic activation of SARS-CoV-2 spike protein.

COVID-19 has infected more than 22 million people worldwide causing over 750.000 deaths. The disease is caused by the severe acute respiratory syndrome coronavirus (CoV) 2 (SARS-CoV-2), which shares a high sequence similarity to SARS-CoV. Currently there are no vaccinations available to provide protection and the only antiviral therapy in active use in patients is remdesivir, which currently provides only limited benefit. Hence, there is an urgent need for antiviral therapies against SARS-CoV2. SARS-CoV requires Ca2+ ions for host cell entry and based on the similarity between SARS-CoV and SARS-CoV-2 it is highly likely that the same requirements exist for the two viruses. Here, we tested whether FDA-approved calcium channel blocker (CCB) drugs are efficacious to inhibit the spread of SARS-CoV-2 in cell culture. Our data shows that amlodipine, felodipine, and nifedipine limit the growth of SARS-CoV-2 in epithelial kidney (Vero E6) and epithelial lung (Calu-3) cells. We observed some differences in the inhibition efficacy of the drugs in the two different cell lines, but with felodipine and nifedipine having the greatest effect. Overall, our data suggest that CCBs have a high potential to treat SARS-CoV-2 infections and their current FDA approval would allow for a fast repurposing of these drugs.

/pdf/fda-approved-calcium-channel-blockers-inhibit-sars-cov-2-52mi1nu9o4.pdf

FDA approved calcium channel blockers inhibit SARS CoV 2 infectivity in epithelial lung cells

Ca2+-dependent mechanism of membrane insertion and destabilization by the SARS-CoV-2 fusion peptide.

G protein-coupled receptors (GPCRs) play a key role in many cellular signaling mechanisms, and must select among multiple coupling possibilities in a ligand-specific manner in order to carry out a myriad of functions in diverse cellular contexts. Much has been learned about the molecular mechanisms of ligand-GPCR complexes from Molecular Dynamics (MD) simulations. However, to explore ligand-specific differences in the response of a GPCR to diverse ligands, as is required to understand ligand bias and functional selectivity, necessitates creating very large amounts of data from the needed large-scale simulations. This becomes a Big Data problem for the high dimensionality analysis of the accumulated trajectories. Here we describe a new machine learning (ML) approach to the problem that is based on transforming the analysis of GPCR function-related, ligand-specific differences encoded in the MD simulation trajectories into a representation recognizable by state-of-the-art deep learning object recognition technology. We illustrate this method by applying it to recognize the pharmacological classification of ligands bound to the 5-HT2A and D2 subtypes of class-A GPCRs from the serotonin and dopamine families. The ML-based approach is shown to perform the classification task with high accuracy, and we identify the molecular determinants of the classifications in the context of GPCR structure and function. This study builds a framework for the efficient computational analysis of MD Big Data collected for the purpose of understanding ligand-specific GPCR activity.

A Machine Learning Approach for the Discovery of Ligand-Specific Functional Mechanisms of GPCRs.

Cell penetration after recognition of the SARS-CoV-2 virus by the ACE2 receptor, and the fusion of its viral envelope membrane with cellular membranes, are the early steps of infectivity. A region of the Spike protein (S) of the virus, identified as the fusion peptide (FP), is liberated at its N-terminal site by a specific cleavage occurring in concert with the interaction of the receptor binding domain of the Spike. Studies have shown that penetration is enhanced by the required binding of Ca2+ ions to the FPs of corona viruses, but the mechanisms of membrane insertion and destabilization remain unclear. We have identified the preferred positions of Ca2+ binding to the SARS-CoV-2-FP, the role of Ca2+ ions in mediating peptide-membrane interactions, the preferred mode of insertion of the Ca2+-bound SARS-CoV-2-FP and consequent effects on the lipid bilayer from extensive atomistic molecular dynamics (MD) simulations and trajectory analyses. In a systematic sampling of the interactions of the Ca2+-bound peptide models with lipid membranes SARS-CoV-2-FP penetrated the bilayer and disrupted its organization only in two modes involving different structural domains. In one, the hydrophobic residues F833/I834 from the middle region of the peptide are inserted. In the other, more prevalent mode, the penetration involves residues L822/F823 from the LLF motif which is conserved in CoV-2-like viruses, and is achieved by the binding of Ca2+ ions to the D830/D839 and E819/D820 residue pairs. FP penetration is shown to modify the molecular organization in specific areas of the bilayer, and the extent of membrane binding of the SARS-CoV-2 FP is significantly reduced in the absence of Ca2+ ions. These findings provide novel mechanistic insights regarding the role of Ca2+ in mediating SARS-CoV-2 fusion and provide a detailed structural platform to aid the ongoing efforts in rational design of compounds to inhibit SARS-CoV-2 cell entry.

https://biorxiv.org/content/10.1101/2020.12.03.410472v1.full.pdf

Ca 2+ -dependent mechanism of membrane insertion and destabilization by the SARS-CoV-2 fusion peptide.

Central among the tools and approaches used for ligand discovery and design are Molecular Dynamics (MD) simulations, which follow the dynamic changes in molecular structure in response to the environmental condition, interactions with other proteins, and the effects of ligand binding. The need for, and successes of, MD simulations in providing this type of essential information are well documented, but so are the challenges presented by the size of the resulting datasets encoding the desired information. The difficulty of extracting information on mechanistically important state-to-state transitions in response to ligand binding and other interactions is compounded by these being rare events in the MD trajectories of complex molecular machines, such as G-protein-coupled receptors (GPCRs). To address this problem, we have developed a protocol for the efficient detection of such events. We show that the novel Rare Event Detection (RED) protocol reveals functionally relevant and pharmacologically discriminating responses to the binding of different ligands to the 5-HT2AR orthosteric site in terms of clearly defined, structurally coherent, and temporally ordered conformational transitions. This information from the RED protocol offers new insights into specific ligand-determined functional mechanisms encoded in the MD trajectories, which opens a new and rigorously reproducible path to understanding drug activity with application in drug discovery.

https://www.mdpi.com/1420-3049/26/10/3059/pdf

Ligand-Dependent Conformational Transitions in Molecular Dynamics Trajectories of GPCRs Revealed by a New Machine Learning Rare Event Detection Protocol.

Ambrose Plante

Papers

Ca2+-dependent mechanism of membrane insertion and destabilization by the SARS-CoV-2 fusion peptide.

A Machine Learning Approach for the Discovery of Ligand-Specific Functional Mechanisms of GPCRs.

Ca 2+ -dependent mechanism of membrane insertion and destabilization by the SARS-CoV-2 fusion peptide.

Ligand-Dependent Conformational Transitions in Molecular Dynamics Trajectories of GPCRs Revealed by a New Machine Learning Rare Event Detection Protocol.

A Machine Learning Algorithm for the Detection of Function-Related Rare Events in MD Trajectories of Biomolecular Systems