KC2021 - A machine learning platform to estimate anti-SARS-CoV-2 activities
Ontology highlight
ABSTRACT:
SUBMITTER: 
Zainab Ashimiyu-Abdusalam
PROVIDER: MODEL2405130004 | BioModels | 2024-05-13
REPOSITORIES: BioModels
Similar Datasets
Project description:ImageMol is a Representation Learning Framework that utilizes molecule images for encoding molecular inputs as machine readable vectors for downstream tasks such as bio-activity prediction, drug metabolism analysis, or drug toxicity prediction. The approach utilizes transfer learning, that is, pre-training the model on massive unlabeled datasets to help it in generalizing feature extraction and then fine tuning on specific tasks. This model is fine tuned on 13 assays concerned with a number of target categories ranging from viral entry to toxicity in humans. These interactions are formulated as binary classification tasks.
Model Type: Predictive machine learning model.
Model Relevance: SARS-CoV-2 Anti viral screening.
Model Encoded by: Dhanshree Arora (Ersilia)
Metadata Submitted in BioModels by: Zainab Ashimiyu-Abdusalam
Implementation of this model code by Ersilia is available here:
https://github.com/ersilia-os/eos4cxk
2024-05-08 | MODEL2405080005 | BioModels
Project description:The severe acute respiratory syndrome (SARS) epidemic was characterized by increased pathogenicity in the elderly due to an early exacerbated innate host response. SARS-CoV is a zoonotic pathogen that entered the human population through an intermediate host like the palm civet. To prevent future introductions of zoonotic SARS-CoV strains and subsequent transmission into the human population, heterologous disease models are needed to test the efficacy of vaccines and therapeutics against both late human and zoonotic isolates. Here we show that both human and zoonotic SARS-CoV strains can infect cynomolgus macaques and resulted in radiological as well as histopathological changes similar to those seen in mild human cases. Viral replication was higher in animals infected with a late human phase isolate compared to a zoonotic isolate. Host responses to the three SARS-CoV strains were similar and only apparent early during infection with the majority of genes associated with interferon signalling pathways.This study characterizes critical disease models in the evaluation and licensure of therapeutic strategies against SARS-CoV for human use 4 strains, time course, lungs
2011-08-31 | E-GEOD-23955 | biostudies-arrayexpress
Project description:ImageMol is a Representation Learning Framework that utilizes molecule images for encoding molecular inputs as machine readable vectors for downstream tasks such as bio-activity prediction, drug metabolism analysis, or drug toxicity prediction. The approach utilizes transfer learning, that is, pre-training the model on massive unlabeled datasets to help it in generalizing feature extraction and then fine tuning on specific tasks. This model is fine tuned on 13 assays concerned with a number of target categories ranging from viral entry to toxicity in humans. These interactions are formulated as binary classification tasks.
Model Type: Predictive machine learning model.
Model Relevance: Probability of HIV inhibition.
Model Encoded by: Dhanshree Arora (Ersilia)
Metadata Submitted in BioModels by: Zainab Ashimiyu-Abdusalam
Implementation of this model code by Ersilia is available here:
https://github.com/ersilia-os/eos6hy3
2024-05-13 | MODEL2405130001 | BioModels
Project description:Viral pandemics pose an imminent threat to humanity. The ongoing COVID-19 pandemic, caused by the SARS-CoV-2 virus, requires the urgent development of anti-viral therapies. Because of its recent emergence, there is a paucity of information regarding viral behavior and host response following SARS-CoV-2 infection. Here, we offer an in-depth analysis of the host response to SARS-CoV-2 as it compares to other respiratory infections. Cell and animal models of SARS-CoV-2 infections, in addition to transcriptional profiling of a COVID-19 lung biopsy consistently revealed a unique and inappropriate inflammatory response defined by elevated chemokine expression in the absence of Type I and III interferons. Our identification of a muted transcriptional response to SARS-CoV-2 supports a model in which initial failure to rapidly respond to infection results in prolonged viral replication and an influx of proinflammatory cells that induce alveolar damage and manifest in COVID-19 lung pathology.
2020-03-25 | GSE147507 | GEO
Project description:Severe acute respiratory syndrome-coronavirus 2 (SARS-CoV-2), which is the cause of a present global pandemic, infects human lung alveolar type 2 (hAT2) cells. Characterizing pathogenesis is crucial for developing vaccines and therapeutics. However, the lack of models mirroring the cellular physiology and pathology of hAT2 cells limits the study. Here, we develop a feeder-free, long-term three-dimensional (3D) culture technique for hAT2 cells, and investigate infection response to SARS-CoV-2. By imaging-based analysis and single-cell transcriptome profiling, we reveal rapid viral replication and the increased expression of interferon-associated genes and pro-inflammatory genes in infected hAT2 cells, indicating robust endogenous innate immune response. Further tracing of viral mutations acquired during transmission identifies full infection of individual cells effectively from a single viral entry. Our study provides deep insights into the pathogenesis of SARS-CoV-2, and the application of defined 3D hAT2 cultures as models for respiratory diseases.
2020-10-10 | GSE159316 | GEO
Project description:Several genome-wide CRISPR knockout screens have been conducted to identify host factors regulating SARS-CoV-2 replication, but the models used have often relied on overexpression of ACE2 receptor and didn’t express TMPRSS2 protease, known to be important for viral entry at the plasma membrane. Here, we conducted a meta-analysis of these screens and showed a high level of cell-type specificity of the identified hits, arguing for the necessity to pursue efforts to uncover the full landscape of SARS-CoV-2 regulators. We performed genome-wide, bidirectional CRISPR screens in Calu-3 lung epithelial cells, as well as knockout screens in Caco-2 intestinal cells. As well as identifying ACE2 and TMPRSS2 as top hits, our study reveals a series of so far unidentified and critical host-dependency factors, including the Adaptins AP1G1 and AP1B1 and the flippase ATP8B1. Additionally, new anti-SARS-CoV-2 proteins with potent activity, including several membrane-associated Mucins (MUC1, MUC4 and MUC21), IL6R and CD44 were identified . We further observed that these genes mostly acted at the critical step of viral entry, with the notable exception of ATP8B1, the knockout of which prevented late stages of viral replication. Exploring the pro- and anti-viral breadth of these genes using highly pathogenic MERS-CoV, seasonal HCoV-NL63 and -229E and influenza A virus, we reveal that some genes such as AP1G1 and ATP8B1 are general coronavirus cofactors. In contrast, Mucins recapitulated their known role as a general antiviral defense mechanism. These results demonstrate the value of considering multiple cell models and perturbational modalities for understanding SARS-CoV-2 replication and provide a list of potential new targets for therapeutic interventions.
2022-01-20 | GSE193834 | GEO
Project description:Several genome-wide CRISPR knockout screens have been conducted to identify host factors regulating SARS-CoV-2 replication, but the models used have often relied on overexpression of ACE2 receptor and didn’t express TMPRSS2 protease, known to be important for viral entry at the plasma membrane. Here, we conducted a meta-analysis of these screens and showed a high level of cell-type specificity of the identified hits, arguing for the necessity to pursue efforts to uncover the full landscape of SARS-CoV-2 regulators. We performed genome-wide, bidirectional CRISPR screens in Calu-3 lung epithelial cells, as well as knockout screens in Caco-2 intestinal cells. As well as identifying ACE2 and TMPRSS2 as top hits, our study reveals a series of so far unidentified and critical host-dependency factors, including the Adaptins AP1G1 and AP1B1 and the flippase ATP8B1. Additionally, new anti-SARS-CoV-2 proteins with potent activity, including several membrane-associated Mucins (MUC1, MUC4 and MUC21), IL6R and CD44 were identified . We further observed that these genes mostly acted at the critical step of viral entry, with the notable exception of ATP8B1, the knockout of which prevented late stages of viral replication. Exploring the pro- and anti-viral breadth of these genes using highly pathogenic MERS-CoV, seasonal HCoV-NL63 and -229E and influenza A virus, we reveal that some genes such as AP1G1 and ATP8B1 are general coronavirus cofactors. In contrast, Mucins recapitulated their known role as a general antiviral defense mechanism. These results demonstrate the value of considering multiple cell models and perturbational modalities for understanding SARS-CoV-2 replication and provide a list of potential new targets for therapeutic interventions.
2021-05-28 | GSE175666 | GEO
Project description: Not available
| S-BSST379 | biostudies-other
Project description:Interferons (IFNs) are critical for anti-viral host defence. Type-1 and type-3 IFNs are typically associated with early control of viral replication and promotion of inflammatory immune responses; however, less is known about the role of IFNγ in anti-viral immunity, particularly in the context of SARS-CoV-2. We have previously observed that lung infection with attenuated bacteria M. bovis BCG achieved though intravenous (iv) administration provides strong protection against SARS-CoV-2 (SCV2) infection and disease in two mouse models. Assessment of the pulmonary cytokine milieu revealed that iv BCG induces a robust IFNγ response and low levels of IFNβ. Here we examined the role of ongoing IFNγ responses due to concurrent bacterial infection on SCV2 disease outcomes in two murine models. We report that IFNγ is required for iv BCG induced reduction in pulmonary viral loads and that this outcome is dependent on IFNγ receptor expression by non-hematopoietic cells. Further analysis revealed that BCG infection promotes the upregulation of ISGs with reported anti-viral activity by pneumocytes and bronchial epithelial cells in an IFNγ dependent manner, suggesting a possible mechanism for the observed protection. Finally, we confirmed the importance of IFNγ in these anti-viral effects by demonstrating that the recombinant cytokine itself provides strong protection against SCV2 challenge when administered intranasally. Together, our data show that a pre-established IFNγ response within the lung is protective against SCV2 infection, suggesting that concurrent or recent infections that drive IFNγ may limit the pathogenesis of this virus and supporting possible prophylactic uses of this cytokine in COVID-19 management.
2023-11-01 | GSE236601 | GEO
Project description:Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) causes severe health crisis and huge socioeconomic upheaval internationally. This study proposes an ab initio design strategy to obtain antiviral peptides to against SARS-CoV-2 infection. The study employed database filtering technology to generate 7 amphipathic-symmetric peptides named DFTavPs with low cytotoxicity and random coil structure. Three DFTavPs promoted SARS-CoV-2 pseudoviruses infection and three DFTavPs inhibited virus infection, which are accompanied by up-regulation or down-regulation of SARS-CoV receptor angiotensin-converting enzyme 2 mRNA levels. Particularly, microRNA profiling showed that some differentially expressed microRNAs had potential to target key factors for cell entry of SARS-CoV-2. Furthermore, we explored the relationship of parameters and antiviral efficacy index (AEI). The results suggested that higher AEI of coronavirus was most likely to occur at mean amphipathic moment between 0.3 and 0.4. Automated machine learning was used to construct parameters-AEI regression models for various viruses. The Extra-Trees and CatBoost had a good predicting performance for AEI of coronavirus (R2=0.794 and Rpearson=0.897) and human immunodeficiency virus (R2=0.735 and Rpearson=0.859), respectively. Overall, this strategy is expected to efficiently obtain huge amounts of potential peptide drugs with anti-SARS-CoV-2 activity, and machine learning models could contribute to discovery of high antivirus-activity peptides.
2021-08-26 | GSE182562 | GEO