Potential Neutralizing Antibodies Discovered for Novel Corona Virus Using Machine Learning

AbstractThe fast and untraceable virus mutations take lives of thousands of people before the immune system can produce the inhibitory antibody. The recent outbreak of COVID-19 infected and killed thousands of people in the world. Rapid methods in finding peptides or antibody sequences that can inhibit the viral epitopes of SARS-CoV-2 will save the life of thousands. To predict neutralizing antibodies for SARS-CoV-2 in a high-throughput manner, in this paper, we use different machine learning (ML) model to predict the possible inhibitory synthetic antibodies for SARS-CoV-2. We collected 1933 virus-antibody sequences and their clinical patient neutralization response and trained an ML model to predict the antibody response. Using graph featurization with variety of ML methods, like XGBoost, Random Forest, Multilayered Perceptron, Support Vector Machine and Logistic Regression, we screened thousands of hypothetical antibody sequences and found nine stable antibodies that potentially inhibit SARS-CoV-2. We combined bioinformatics, structural biology, and Molecular Dynamics (MD) simulations to verify the stability of the candidate antibodies that can inhibit SARS-CoV-2.

Download Full-text

Critical Sequence Hot-spots for Binding of nCOV-2019 to ACE2 as Evaluated by Molecular Simulations

10.1101/2020.06.27.175448 ◽

2020 ◽

Author(s):

Mahdi Ghorbani ◽

Bernard R. Brooks ◽

Jeffery B. Klauda

Keyword(s):

Md Simulations ◽

Host Cells ◽

Cell Surface Receptor ◽

Receptor Protein ◽

Structural Mechanism ◽

The World ◽

Surface Receptor ◽

Escape Mutants ◽

The Stability ◽

Novel Coronavirus

AbstractThe novel coronavirus (nCOV-2019) outbreak has put the world on edge, causing millions of cases and hundreds of thousands of deaths all around the world, as of June 2020, let alone the societal and economic impacts of the crisis. The spike protein of nCOV-2019 resides on the virion’s surface mediating coronavirus entry into host cells by binding its receptor binding domain (RBD) to the host cell surface receptor protein, angiotensin converter enzyme (ACE2). Our goal is to provide a detailed structural mechanism of how nCOV-2019 recognizes and establishes contacts with ACE2 and its difference with an earlier coronavirus SARS-COV in 2002 via extensive molecular dynamics (MD) simulations. Numerous mutations have been identified in the RBD of nCOV-2019 strains isolated from humans in different parts of the world. In this study, we investigated the effect of these mutations as well as other Ala-scanning mutations on the stability of RBD/ACE2 complex. It is found that most of the naturally-occurring mutations to the RBD either strengthen or have the same binding affinity to ACE2 as the wild-type nCOV-2019. This may have implications for high human-to-human transmission of coronavirus in regions where these mutations have been found as well as any vaccine design endeavors since these mutations could act as antibody escape mutants. Furthermore, in-silico Ala-scanning and long-timescale MD simulations, highlight the crucial role of the residues at the interface of RBD and ACE2 that may be used as potential pharmacophores for any drug development endeavors. From an evolutional perspective, this study also identifies how the virus has evolved from its predecessor SARS-COV and how it could further evolve to become more infectious.

Download Full-text

In Silico Exploration of Small-Molecule α-Helix Mimetics as Inhibitors of SARS-COV-2 Attachment to ACE2

10.26434/chemrxiv.12592286 ◽

2020 ◽

Author(s):

Mohammed Hakmi ◽

El Mehdi Bouricha ◽

Jihane Akachar ◽

Badreddine Lmimouni ◽

Jaouad EL Harti ◽

...

Keyword(s):

Small Molecule ◽

In Silico ◽

Md Simulations ◽

Host Cells ◽

Screening Experiments ◽

Infected Cells ◽

Helix Mimetics ◽

The Stability ◽

Α Helix ◽

Novel Coronavirus

The novel coronavirus, SARS-CoV-2, has infected more than 10 million people and caused more than 502,539 deaths worldwide as of June 2020. The explosive spread of the virus and the rapid increase in the number of cases require the immediate development of effective therapies and vaccines as well as accurate diagnosis tools. The pathogenesis of the disease is triggered by the entry of SARS-CoV-2 via its spike protein into ACE2-bearing host cells, particularly pneumocytes, resulting in overactivation of the immune system, which attacks the infected cells and damages the lung tissue. The interaction of the SARS-CoV-2 receptor binding domain (RBD) with host cells is primarily mediated by the N-terminal helix of the ACE2; thus, inhibition of the spike-ACE2 interaction may be a promising therapeutic strategy for blocking the entry of the virus into host cells. In this paper, we used an in-silico approach to explore small-molecule α-helix mimetics as inhibitors that may disrupt the attachment of SARS-CoV-2 to ACE2. First, the RBD-ACE2 interface in the 6M0J structure was studied by the MM-GBSA decomposition module of the HawkDock server, which led to the identification of two critical target regions in the RBD. Next, two virtual screening experiments of 7236 α-helix mimetics from ASINEX were conducted on the above regions using the iDock tool, which resulted in 10 candidates with favorable binding affinities. Finally, the stability of RBD complexes with the top-two ranked compounds was further validated by 40 ns MD simulations using Desmond package of Schrodinger.

Download Full-text

In Silico Exploration of Small-Molecule α-Helix Mimetics as Inhibitors of SARS-COV-2 Attachment to ACE2

10.26434/chemrxiv.12592286.v1 ◽

2020 ◽

Author(s):

Mohammed Hakmi ◽

El Mehdi Bouricha ◽

Jihane Akachar ◽

Badreddine Lmimouni ◽

Jaouad EL Harti ◽

...

Keyword(s):

Small Molecule ◽

In Silico ◽

Md Simulations ◽

Host Cells ◽

Screening Experiments ◽

Infected Cells ◽

Helix Mimetics ◽

The Stability ◽

Α Helix ◽

Novel Coronavirus

The novel coronavirus, SARS-CoV-2, has infected more than 10 million people and caused more than 502,539 deaths worldwide as of June 2020. The explosive spread of the virus and the rapid increase in the number of cases require the immediate development of effective therapies and vaccines as well as accurate diagnosis tools. The pathogenesis of the disease is triggered by the entry of SARS-CoV-2 via its spike protein into ACE2-bearing host cells, particularly pneumocytes, resulting in overactivation of the immune system, which attacks the infected cells and damages the lung tissue. The interaction of the SARS-CoV-2 receptor binding domain (RBD) with host cells is primarily mediated by the N-terminal helix of the ACE2; thus, inhibition of the spike-ACE2 interaction may be a promising therapeutic strategy for blocking the entry of the virus into host cells. In this paper, we used an in-silico approach to explore small-molecule α-helix mimetics as inhibitors that may disrupt the attachment of SARS-CoV-2 to ACE2. First, the RBD-ACE2 interface in the 6M0J structure was studied by the MM-GBSA decomposition module of the HawkDock server, which led to the identification of two critical target regions in the RBD. Next, two virtual screening experiments of 7236 α-helix mimetics from ASINEX were conducted on the above regions using the iDock tool, which resulted in 10 candidates with favorable binding affinities. Finally, the stability of RBD complexes with the top-two ranked compounds was further validated by 40 ns MD simulations using Desmond package of Schrodinger.

Download Full-text

Newly designed analogues from SARS-CoV inhibitors mimicking the druggable properties against SARS-CoV-2 and its novel variants

10.21203/rs.3.rs-515155/v1 ◽

2021 ◽

Author(s):

Nadim Ferdous ◽

Mahjerin Nasrin Reza ◽

Md. Shariful Islam ◽

Md. Tabassum Hossain Emon ◽

Mohamed A. Nassan ◽

...

Keyword(s):

Neutralizing Antibodies ◽

Md Simulations ◽

New Drugs ◽

Antiviral Compounds ◽

Main Protease ◽

Novel Variants ◽

Poisson Boltzmann ◽

The Stability

Abstract The emerging variants of SARS Coronavirus-2 (SARS-CoV-2) has been continuously spreading all over the world and raised global health concerns. The B.1.1.7 (United Kingdom), P.1 (Brazil), B.1.351 (South Africa) and B.1.617 (India) variants resulted due to multiple mutations in the spike glycoprotein (SGp), are resistant to neutralizing antibodies and enable increased transmission. Hence, new drugs might be of great importance against the novel variants of SARS-CoV-2. The SGp and main protease (Mpro) of SARS-CoV-2 are important targets to design and develop antiviral compounds for new drug discovery. In this study, we selected seventeen phytochemicals and later performed molecular docking to determine the binding interactions of the compounds with the two receptors and calculated several drug likeliness properties for each compound. Luteolin, myricetin and quercetin demonstrated higher affinity for both the proteins and interacted efficiently. To get better compounds, we designed three analogues from these compounds and showed the greater druggable properties than the parent compounds. Furthermore, we found that the analogues bind to the residues of both proteins including the recent novel variants of SARS-CoV-2. The binding study was further verified by molecular dynamics (MD) simulation and molecular mechanics/Poisson Boltzmann surface area (MM/PBSA) approaches by assessing the stability of the complexes. MD simulations revealed that Arg457 of SGp and Met49 of Mpro are the most important residues that interacted with the designed inhibitors. Our analysis may give some breakthroughs to develop new therapeutics to treat the proliferation of SARS-CoV-2 in vitro and in vivo.

Download Full-text

Scalable Approach to High Coverages on Oxides via Iterative Training of a Machine-Learning Algorithm

10.26434/chemrxiv.10288514.v1 ◽

2019 ◽

Author(s):

Andrew Medford ◽

Shengchun Yang ◽

Fuzhu Liu

Keyword(s):

Machine Learning ◽

Chemical Potential ◽

Learning Algorithm ◽

Absolute Error ◽

Low Energy ◽

Training Data ◽

High Coverage ◽

Metal Compounds ◽

Adsorption Energies ◽

The Stability

Understanding the interaction of multiple types of adsorbate molecules on solid surfaces is crucial to establishing the stability of catalysts under various chemical environments. Computational studies on the high coverage and mixed coverages of reaction intermediates are still challenging, especially for transition-metal compounds. In this work, we present a framework to predict differential adsorption energies and identify low-energy structures under high- and mixed-adsorbate coverages on oxide materials. The approach uses Gaussian process machine-learning models with quantified uncertainty in conjunction with an iterative training algorithm to actively identify the training set. The framework is demonstrated for the mixed adsorption of CHx, NHx and OHx species on the oxygen vacancy and pristine rutile TiO2(110) surface sites. The results indicate that the proposed algorithm is highly efficient at identifying the most valuable training data, and is able to predict differential adsorption energies with a mean absolute error of ~0.3 eV based on <25% of the total DFT data. The algorithm is also used to identify 76% of the low-energy structures based on <30% of the total DFT data, enabling construction of surface phase diagrams that account for high and mixed coverage as a function of the chemical potential of C, H, O, and N. Furthermore, the computational scaling indicates the algorithm scales nearly linearly (N1.12) as the number of adsorbates increases. This framework can be directly extended to metals, metal oxides, and other materials, providing a practical route toward the investigation of the behavior of catalysts under high-coverage conditions.

Download Full-text

Polysaccharide Structures in the Outer Mucilage of Arabidopsis Seeds Visualized by AFM

10.26686/wgtn.12585593.v1 ◽

2020 ◽

Author(s):

MAK Williams ◽

V Cornuault ◽

AH Irani ◽

VV Symonds ◽

J Malmström ◽

...

Keyword(s):

Average Length ◽

American Chemical Society ◽

Md Simulations ◽

Chemical Society ◽

Side Chains ◽

Rhamnogalacturonan I ◽

Afm Imaging ◽

Minor Population ◽

The Stability ◽

A Minor

© 2020 American Chemical Society. Evidence is presented that the polysaccharide rhamnogalacturonan I (RGI) can be biosynthesized in remarkably organized branched configurations and surprisingly long versions and can self-assemble into a plethora of structures. AFM imaging has been applied to study the outer mucilage obtained from wild-type (WT) and mutant (bxl1-3 and cesa5-1) Arabidopsis thaliana seeds. For WT mucilage, ordered, multichain structures of the polysaccharide RGI were observed, with a helical twist visible in favorable circumstances. Molecular dynamics (MD) simulations demonstrated the stability of several possible multichain complexes and the possibility of twisted fibril formation. For bxl1-3 seeds, the imaged polymers clearly showed the presence of side chains. These were surprisingly regular and well organized with an average length of ∼100 nm and a spacing of ∼50 nm. The heights of the side chains imaged were suggestive of single polysaccharide chains, while the backbone was on average 4 times this height and showed regular height variations along its length consistent with models of multichain fibrils examined in MD. Finally, in mucilage extracts from cesa5-1 seeds, a minor population of chains in excess of 30 μm long was observed.

Download Full-text

In Silico and in Vitro Evaluation of Deamidation Effects on the Stability of the Fusion Toxin DAB389IL-2

Current Proteomics ◽

10.2174/1570164616666190131150033 ◽

2019 ◽

Vol 16 (4) ◽

pp. 307-313 ◽

Cited By ~ 2

Author(s):

Nasrin Zarkar ◽

Mohammad Ali Nasiri Khalili ◽

Fathollah Ahmadpour ◽

Sirus Khodadadi ◽

Mehdi Zeinoddini

Keyword(s):

In Silico ◽

Catalytic Domain ◽

Md Simulations ◽

Special Importance ◽

Native Form ◽

Vitro Experiment ◽

In Vitro Experiment ◽

Pharmaceutical Protein ◽

The Stability

Background: DAB389IL-2 (Denileukin diftitox) as an immunotoxin is a targeted pharmaceutical protein and is the first immunotoxin approved by FDA. It is used for the treatment of various kinds of cancer such as CTCL lymphoma, melanoma, and Leukemia but among all of these, treatment of CTCL has special importance. DAB389IL-2 consists of two distinct parts; the catalytic domain of Diphtheria Toxin (DT) that genetically fused to the whole IL-2. Deamidation is the most important reaction for chemical instability of proteins occurs during manufacture and storage. Deamidation of asparagine residues occurs at a higher rate than glutamine residues. The structure of proteins, temperature and pH are the most important factors that influence the rate of deamidation. Methods: Since there is not any information about deamidation of DAB389IL-2, we studied in silico deamidation by Molecular Dynamic (MD) simulations using GROMACS software. The 3D model of fusion protein DAB389IL-2 was used as a template for deamidation. Then, the stability of deamidated and native form of the drug was calculated. Results: The results of MD simulations were showed that the deamidated form of DAB389IL-2 is more unstable than the normal form. Also, deamidation was carried by incubating DAB389IL-2, 0.3 mg/ml in ammonium hydrogen carbonate for 24 h at 37o C in order to in vitro experiment. Conclusion: The results of in vitro experiment were confirmed outcomes of in silico study. In silico and in vitro experiments were demonstrated that DAB389IL-2 is unstable in deamidated form.

Download Full-text

Role of key point Mutations in Receptor Binding Domain of SARS-CoV-2 Spike Glycoprotein

Infectious Disorders - Drug Targets ◽

10.2174/1871526520666200804161650 ◽

2020 ◽

Vol 20 ◽

Author(s):

Bipin Singh

Keyword(s):

Receptor Binding ◽

Point Mutations ◽

Binding Domain ◽

Receptor Binding Domain ◽

Spike Glycoprotein ◽

Angiotensin Converting Enzyme 2 ◽

Recent Outbreak ◽

Novel Coronavirus ◽

Genomic Similarity

: The recent outbreak of novel coronavirus (SARS-CoV-2 or 2019-nCoV) and its worldwide spread is posing one of the major threats to human health and the world economy. It has been suggested that SARS-CoV-2 is similar to SARSCoV based on the comparison of the genome sequence. Despite the genomic similarity between SARS-CoV-2 and SARSCoV, the spike glycoprotein and receptor binding domain in SARS-CoV-2 shows the considerable difference compared to SARS-CoV, due to the presence of several point mutations. The analysis of receptor binding domain (RBD) from recently published 3D structures of spike glycoprotein of SARS-CoV-2 (Yan, R., et al. (2020); Wrapp, D., et al. (2020); Walls, A. C., et al. (2020)) highlights the contribution of a few key point mutations in RBD of spike glycoprotein and molecular basis of its efficient binding with human angiotensin-converting enzyme 2 (ACE2).

Download Full-text

Machine Learning Approaches for Tackling Novel Coronavirus (COVID-19) Pandemic

SN Computer Science ◽

10.1007/s42979-021-00774-7 ◽

2021 ◽

Vol 2 (5) ◽

Author(s):

Mohammad Marufur Rahman ◽

Md. Milon Islam ◽

Md. Motaleb Hossen Manik ◽

Md. Rabiul Islam ◽

Mabrook S. Al-Rakhami

Keyword(s):

Machine Learning ◽

Learning Approaches ◽

Novel Coronavirus

Download Full-text