Browse
Submit Data
Databases
API
Help

Dataset Information

17 Views

0 Connections

0 Citations

0 Reanalyses

0 Downloads

Omics score: 0

Potential neutralizing antibodies discovered for novel corona virus using machine learning.

ABSTRACT: The 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.

SUBMITTER: Magar R

PROVIDER: S-EPMC7970853 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Json Xml

Similar Datasets

Prediction of protein corona on nanomaterials by machine learning using novel descriptors.

Project description:Effective in silico methods to predict protein corona compositions on engineered nanomaterials (ENMs) could help elucidate the biological outcomes of ENMs in biosystems without the need for conducting lengthy experiments for corona characterization. However, the physicochemical properties of ENMs, used as the descriptors in current modeling methods, are insufficient to represent the complex interactions between ENMs and proteins. Herein, we utilized the fluorescence change (FC) from fluorescamine labeling on a protein, with or without the presence of the ENM, as a novel descriptor of the ENM to build machine learning models for corona formation. FCs were significantly correlated with the abundance of the corresponding proteins in the corona on diverse classes of ENMs, including metal and metal oxides, nanocellulose, and 2D ENMs. Prediction models established by the random forest algorithm using FCs as the ENM descriptors showed better performance than the conventional descriptors, such as ENM size and surface charge, in the prediction of corona formation. Moreover, they were able to predict protein corona formation on ENMs with very heterogeneous properties. We believe this novel descriptor can improve in silico studies of corona formation, leading to a better understanding on the protein adsorption behaviors of diverse ENMs in different biological matrices. Such information is essential for gaining a comprehensive view of how ENMs interact with biological systems in ENM safety and sustainability assessments.

| S-EPMC7043407 | biostudies-literature

Prediction of Breast Cancer Estrogen Receptor Status using Machine Learning

Project description:Gene expression profiles were generated from 199 primary breast cancer patients. Samples 1-176 were used in another study, GEO Series GSE22820, and form the training data set in this study. Sample numbers 200-222 form a validation set. This data is used to model a machine learning classifier for Estrogen Receptor Status. RNA was isolated from 199 primary breast cancer patients. A machine learning classifier was built to predict ER status using only three gene features.

2013-01-01 | E-GEOD-29210 | biostudies-arrayexpress

New Anti-Flavivirus Fusion Loop Human Antibodies with Zika Virus-Neutralizing Potential.

Project description:Zika virus infections exhibit recurrent outbreaks and can be responsible for disease complications such as congenital Zika virus syndrome. Effective therapeutic interventions are still a challenge. Antibodies can provide significant protection, although the antibody response may fail due to antibody-dependent enhancement reactions. The choice of the target antigen is a crucial part of the process to generate effective neutralizing antibodies. Human anti-Zika virus antibodies were selected by phage display technology. The antibodies were selected against a mimetic peptide based on the fusion loop region in the protein E of Zika virus, which is highly conserved among different flaviviruses. Four rounds of selection were performed using the synthetic peptide in two strategies: the first was using the acidic elution of bound phages, and the second was by applying a competing procedure. After panning, the selected VH and VL domains were determined by combining NGS and bioinformatic approaches. Three different human monoclonal antibodies were expressed as scFvs and further characterized. All showed a binding capacity to Zika (ZIKV) and showed cross-recognition with yellow fever (YFV) and dengue (DENV) viruses. Two of these antibodies, AZ1p and AZ6m, could neutralize the ZIKV infection in vitro. Due to the conservation of the fusion loop region, these new antibodies can potentially be used in therapeutic intervention against Zika virus and other flavivirus illnesses.

| S-EPMC9321016 | biostudies-literature

Quantification of Lyssavirus-Neutralizing Antibodies Using Vesicular Stomatitis Virus Pseudotype Particles.

Project description:Rabies is a highly fatal zoonotic disease which is primarily caused by rabies virus (RABV) although other members of the genus Lyssavirus can cause rabies as well. As yet, 14 serologically and genetically diverse lyssaviruses have been identified, mostly in bats. To assess the quality of rabies vaccines and immunoglobulin preparations, virus neutralization tests with live RABV are performed in accordance with enhanced biosafety standards. In the present work, a novel neutralization test is presented which takes advantage of a modified vesicular stomatitis virus (VSV) from which the glycoprotein G gene has been deleted and replaced by reporter genes. This single-cycle virus was trans-complemented with RABV envelope glycoprotein. Neutralization of this pseudotype virus with RABV reference serum or immune sera from vaccinated mice showed a strong correlation with the rapid fluorescent focus inhibition test (RFFIT). Importantly, pseudotype viruses containing the envelope glycoproteins of other lyssaviruses were neutralized by reference serum to a significantly lesser extent or were not neutralized at all. Taken together, a pseudotype virus system has been successfully developed which allows the safe, fast, and sensitive detection of neutralizing antibodies directed against different lyssaviruses.

| S-EPMC5035968 | biostudies-literature

Recombinant Sheep Pox Virus Proteins Elicit Neutralizing Antibodies.

Project description:The aim of this work was to evaluate the immunogenicity and neutralizing activity of sheep pox virus (SPPV; genus Capripoxvirus, family Poxviridae) structural proteins as candidate subunit vaccines to control sheep pox disease. SPPV structural proteins were identified by sequence homology with proteins of vaccinia virus (VACV) strain Copenhagen. Four SPPV proteins (SPPV-ORF 060, SPPV-ORF 095, SPPV-ORF 117, and SPPV-ORF 122), orthologs of immunodominant L1, A4, A27, and A33 VACV proteins, respectively, were produced in Escherichia coli. Western blot analysis revealed the antigenic and immunogenic properties of SPPV-060, SPPV-095, SPPV-117 and SPPV-122 proteins when injected with adjuvant into experimental rabbits. Virus-neutralizing activity against SPPV in lamb kidney cell culture was detected for polyclonal antisera raised to SPPV-060, SPPV-117, and SPPV-122 proteins. To our knowledge, this is the first report demonstrating the virus-neutralizing activities of antisera raised to SPPV-060, SPPV-117, and SPPV-122 proteins.

| S-EPMC4926179 | biostudies-other

Identifying transcription factor-DNA interactions using machine learning

Project description:We focused on building models that incorporated transcription factor (TF)-DNA interaction data for 12 members of the Auxin Response Factor (ARF) family from soybean as assessed by DNA Affinity Purification and sequencing (DAP-seq).

2023-06-01 | GSE193400 | GEO

Antibodies Targeting Novel Neutralizing Epitopes of Hepatitis C Virus Glycoprotein Preclude Genotype 2 Virus Infection.

Project description:Currently, there is no effective vaccine to prevent hepatitis C virus (HCV) infection, partly due to our insufficient understanding of the virus glycoprotein immunology. Most neutralizing antibodies (nAbs) were identified using glycoprotein immunogens, such as recombinant E1E2, HCV pseudoparticles or cell culture derived HCV. However, the fact that in the HCV acute infection phase, only a small proportion of patients are self-resolved accompanied with the emergence of nAbs, indicates the limited immunogenicity of glycoprotein itself to induce effective antibodies against a highly evolved virus. Secondly, in previous reports, the immunogen sequence was mostly the genotype of the 1a H77 strain. Rarely, other genotypes/subtypes have been studied, although theoretically one genotype/subtype immunogen is able to induce cross-genotype neutralizing antibodies. To overcome these drawbacks and find potential novel neutralizing epitopes, 57 overlapping peptides encompassing the full-length glycoprotein E1E2 of subtype 1b were synthesized to immunize BALB/c mice, and the neutralizing reactive of the induced antisera against HCVpp genotypes 1-6 was determined. We defined a domain comprising amino acids (aa) 192-221, 232-251, 262-281 and 292-331 of E1, and 421-543, 564-583, 594-618 and 634-673 of E2, as the neutralizing regions of HCV glycoprotein. Peptides PUHI26 (aa 444-463) and PUHI45 (aa 604-618)-induced antisera displayed the most potent broad neutralizing reactive. Two monoclonal antibodies recognizing the PUHI26 and PUHI45 epitopes efficiently precluded genotype 2 viral (HCVcc JFH and J6 strains) infection, but they did not neutralize other genotypes. Our study mapped a neutralizing epitope region of HCV glycoprotein using a novel immunization strategy, and identified two monoclonal antibodies effective in preventing genotype 2 virus infection.

| S-EPMC4583415 | biostudies-literature

Discovery of Novel Conotoxin Candidates Using Machine Learning.

Project description:Cone snails (genus Conus) are venomous marine snails that inject prey with a lethal cocktail of conotoxins, small, secreted, and cysteine-rich peptides. Given the diversity and often high affinity for their molecular targets, consisting of ion channels, receptors or transporters, many conotoxins have become invaluable pharmacological probes, drug leads, and therapeutics. Transcriptome sequencing of Conus venom glands followed by de novo assembly and homology-based toxin identification and annotation is currently the state-of-the-art for discovery of new conotoxins. However, homology-based search techniques, by definition, can only detect novel toxins that are homologous to previously reported conotoxins. To overcome these obstacles for discovery, we have created ConusPipe, a machine learning tool that utilizes prominent chemical characters of conotoxins to predict whether a certain transcript in a Conus transcriptome, which has no otherwise detectable homologs in current reference databases, is a putative conotoxin. By using ConusPipe on RNASeq data of 10 species, we report 5148 new putative conotoxin transcripts that have no homologues in current reference databases. 896 of these were identified by at least three out of four models used. These data significantly expand current publicly available conotoxin datasets and our approach provides a new computational avenue for the discovery of novel toxin families.

| S-EPMC6315676 | biostudies-literature

Identification of Novel Antibacterials Using Machine Learning Techniques.

Project description:Many pharmaceutical companies are avoiding the development of novel antibacterials due to a range of rational reasons and the high risk of failure. However, there is an urgent need for novel antibiotics especially against resistant bacterial strains. Available in silico models suffer from many drawbacks and, therefore, are not applicable for scoring novel molecules with high structural diversity by their antibacterial potency. Considering this, the overall aim of this study was to develop an efficient in silico model able to find compounds that have plenty of chances to exhibit antibacterial activity. Based on a proprietary screening campaign, we have accumulated a representative dataset of more than 140,000 molecules with antibacterial activity against Escherichia coli assessed in the same assay and under the same conditions. This intriguing set has no analogue in the scientific literature. We applied six in silico techniques to mine these data. For external validation, we used 5,000 compounds with low similarity towards training samples. The antibacterial activity of the selected molecules against E. coli was assessed using a comprehensive biological study. Kohonen-based nonlinear mapping was used for the first time and provided the best predictive power (av. 75.5%). Several compounds showed an outstanding antibacterial potency and were identified as translation machinery inhibitors in vitro and in vivo. For the best compounds, MIC and CC50 values were determined to allow us to estimate a selectivity index (SI). Many active compounds have a robust IP position.

| S-EPMC6719509 | biostudies-literature

Hepatitis C virus resistance to broadly neutralizing antibodies measured using replication-competent virus and pseudoparticles.

Project description:A better understanding of natural variation in neutralization resistance and fitness of diverse hepatitis C virus (HCV) envelope (E1E2) variants will be critical to guide rational development of an HCV vaccine. This work has been hindered by inadequate genetic diversity in viral panels and by a lack of standardization of HCV entry assays. Neutralization assays generally use lentiviral pseudoparticles expressing HCV envelope proteins (HCVpp) or chimeric full-length viruses that are replication competent in cell culture (HCVcc). There have been few systematic comparisons of specific infectivities of E1E2-matched HCVcc and HCVpp, and to our knowledge, neutralization of E1E2-matched HCVpp and HCVcc has never been compared using a diverse panel of human broadly neutralizing monoclonal antibodies (bNAbs) targeting distinct epitopes. Here, we describe an efficient method for introduction of naturally occurring E1E2 genes into a full-length HCV genome, producing replication-competent chimeric HCVcc. We generated diverse panels of E1E2-matched HCVcc and HCVpp and measured the entry-mediating fitness of E1E2 variants using the two systems. We also compared neutralization of E1E2-matched HCVcc and HCVpp by a diverse panel of human bNAbs targeting epitopes across E1E2. We found no correlation between specific infectivities of E1E2-matched HCVcc versus HCVpp, but found a very strong positive correlation between relative neutralization resistance of these same E1E2-matched HCVcc and HCVpp variants. These results suggest that quantitative comparisons of neutralization resistance of E1E2 variants can be made with confidence using either HCVcc or HCVpp, allowing the use of either or both systems to maximize diversity of neutralization panels.

| S-EPMC5764126 | biostudies-literature

OmicsDI is part of the ELIXIR infrastructure

OmicsDI is an Elixir interoperability service. Learn more ›

Tweets

OmicsDI Databases

PRIDE
PeptideAtlas
MassIVE
JPOST Repository
Physiome Model Repository

EGA
EVA
ENA
LINCS
PAXDB
Cell Collective

MetaboLights
Metabolomics Workbench
MetabolomeExpress
GNPS
BioModels
FAIRDOMHub

ArrayExpress
dbGaP
ExpressionAtlas
GEO
NODE

Information

Databases
Help
API
Contact us
Code on GitHub
Terms of use
Submit Data