Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userEvening the Score: Targeting SARS-CoV-2 Protease Inhibition in Graph Generative Models for Therapeutic Candidates
81
0
0.0
(
0
)
Ask ChatGPT about the research
No Arabic abstract
We examine a pair of graph generative models for the therapeutic design of novel drug candidates targeting SARS-CoV-2 viral proteins. Due to a sense of urgency, we chose well-validated models with unique strengths: an autoencoder that generates molecules with similar structures to a dataset of drugs with anti-SARS activity and a reinforcement learning algorithm that generates highly novel molecules. During generation, we explore optimization toward several design targets to balance druglikeness, synthetic accessability, and anti-SARS activity based on icfifty. This generative frameworkfootnote{https://github.com/exalearn/covid-drug-design} will accelerate drug discovery in future pandemics through the high-throughput generation of targeted therapeutic candidates.
rate research
Read More
Currently, there is no effective antiviral drugs nor vaccine for coronavirus disease 2019 (COVID-19) caused by acute respiratory syndrome coronavirus 2 (SARS-CoV-2). Due to its high conservativeness and low similarity with human genes, SARS-CoV-2 main protease (M$^{text{pro}}$) is one of the most favorable drug targets. However, the current understanding of the molecular mechanism of M$^{text{pro}}$ inhibition is limited by the lack of reliable binding affinity ranking and prediction of existing structures of M$^{text{pro}}$-inhibitor complexes. This work integrates mathematics and deep learning (MathDL) to provide a reliable ranking of the binding affinities of 92 SARS-CoV-2 M$^{text{pro}}$ inhibitor structures. We reveal that Gly143 residue in M$^{text{pro}}$ is the most attractive site to form hydrogen bonds, followed by Cys145, Glu166, and His163. We also identify 45 targeted covalent bonding inhibitors. Validation on the PDBbind v2016 core set benchmark shows the MathDL has achieved the top performance with Pearsons correlation coefficient ($R_p$) being 0.858. Most importantly, MathDL is validated on a carefully curated SARS-CoV-2 inhibitor dataset with the averaged $R_p$ as high as 0.751, which endows the reliability of the present binding affinity prediction. The present binding affinity ranking, interaction analysis, and fragment decomposition offer a foundation for future drug discovery efforts.
The primary cell surface receptor for SARS-CoV-2 is the angiotensin-converting enzyme 2 (ACE2). Recently it has been noticed that the viral Spike protein has an RGD motif, suggesting that cell surface integrins may be co-receptors. We examined the sequences of ACE2 and integrins with the Eukaryotic Linear Motif resource, ELM, and were presented with candidate short linear motifs (SLiMs) in their short, unstructured, cytosolic tails with potential roles in endocytosis, membrane dynamics, autophagy, cytoskeleton and cell signalling. These SLiM candidates are highly conserved in vertebrates. They suggest potential interactions with the AP2 mu2 subunit as well as I-BAR, LC3, PDZ, PTB and SH2 domains found in signalling and regulatory proteins present in epithelial lung cells. Several motifs overlap in the tail sequences, suggesting that they may act as molecular switches, often involving tyrosine phosphorylation status. Candidate LIR motifs are present in the tails of ACE2 and integrin beta3, suggesting that these proteins can directly recruit autophagy components. We also noticed that the extracellular part of ACE2 has a conserved MIDAS structural motif, which are commonly used by beta integrins for ligand binding, potentially supporting the proposal that integrins and ACE2 share common ligands. The findings presented here identify several molecular links and testable hypotheses that might help uncover the mechanisms of SARS-CoV-2 attachment, entry and replication, and strengthen the possibility that it might be possible to develop host-directed therapies to dampen the efficiency of viral entry and hamper disease progression. The strong sequence conservation means that these putative SLiMs are good candidates: Nevertheless, SLiMs must always be validated by experimentation before they can be stated to be functional.
The genomic ssRNA of coronaviruses is packaged within a helical nucleocapsid. Due to transitional symmetry of a helix, weakly specific cooperative interaction between ssRNA and nucleocapsid proteins leads to the natural selection of specific quasi-periodic assembly/packaging signals in the related genomic sequence. Such signals coordinated with the nucleocapsid helical structure were detected and reconstructed in the genomes of the coronaviruses SARS-CoV and SARS-CoV-2. The main period of the signals for both viruses was about 54 nt, that implies 6.75 nt per N protein. The complete coverage of ssRNA genome of length about 30,000 nt by the nucleocapsid would need 4,400 N proteins, that makes them the most abundant among the structural proteins. The repertoires of motifs for SARS-CoV and SARS-CoV-2 were divergent but nearly coincided for different isolates of SARS-CoV-2. We obtained the distributions of assembly/packaging signals over the genomes with non-overlapping windows of width 432 nt. Finally, using the spectral entropy, we compared the load from point mutations and indels during virus age for SARS-CoV and SARS-CoV-2. We found the higher mutational load on SARS-CoV. In this sense, SARS-CoV-2 can be treated as a newborn virus. These observations may be helpful in practical medical applications and are of basic interest.
Researchers across the globe are seeking to rapidly repurpose existing drugs or discover new drugs to counter the the novel coronavirus disease (COVID-19) caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). One promising approach is to train machine learning (ML) and artificial intelligence (AI) tools to screen large numbers of small molecules. As a contribution to that effort, we are aggregating numerous small molecules from a variety of sources, using high-performance computing (HPC) to computer diverse properties of those molecules, using the computed properties to train ML/AI models, and then using the resulting models for screening. In this first data release, we make available 23 datasets collected from community sources representing over 4.2 B molecules enriched with pre-computed: 1) molecular fingerprints to aid similarity searches, 2) 2D images of molecules to enable exploration and application of image-based deep learning methods, and 3) 2D and 3D molecular descriptors to speed development of machine learning models. This data release encompasses structural information on the 4.2 B molecules and 60 TB of pre-computed data. Future releases will expand the data to include more detailed molecular simulations, computed models, and other products.
We propose a benchmark to study surrogate model accuracy for protein-ligand docking. We share a dataset consisting of 200 million 3D complex structures and 2D structure scores across a consistent set of 13 million in-stock molecules over 15 receptors, or binding sites, across the SARS-CoV-2 proteome. Our work shows surrogate docking models have six orders of magnitude more throughput than standard docking protocols on the same supercomputer node types. We demonstrate the power of high-speed surrogate models by running each target against 1 billion molecules in under a day (50k predictions per GPU seconds). We showcase a workflow for docking utilizing surrogate ML models as a pre-filter. Our workflow is ten times faster at screening a library of compounds than the standard technique, with an error rate less than 0.01% of detecting the underlying best scoring 0.1% of compounds. Our analysis of the speedup explains that to screen more molecules under a docking paradigm, another order of magnitude speedup must come from model accuracy rather than computing speed (which, if increased, will not anymore alter our throughput to screen molecules). We believe this is strong evidence for the community to begin focusing on improving the accuracy of surrogate models to improve the ability to screen massive compound libraries 100x or even 1000x faster than current techniques.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
