Dataset Information

A machine learning method for the identification and characterization of novel COVID-19 drug targets.

ABSTRACT: In addition to vaccines, the World Health Organization sees novel medications as an urgent matter to fight the ongoing COVID-19 pandemic. One possible strategy is to identify target proteins, for which a perturbation by an existing compound is likely to benefit COVID-19 patients. In order to contribute to this effort, we present GuiltyTargets-COVID-19 ( https://guiltytargets-covid.eu/ ), a machine learning supported web tool to identify novel candidate drug targets. Using six bulk and three single cell RNA-Seq datasets, together with a lung tissue specific protein-protein interaction network, we demonstrate that GuiltyTargets-COVID-19 is capable of (i) prioritizing meaningful target candidates and assessing their druggability, (ii) unraveling their linkage to known disease mechanisms, (iii) mapping ligands from the ChEMBL database to the identified targets, and (iv) pointing out potential side effects in the case that the mapped ligands correspond to approved drugs. Our example analyses identified 4 potential drug targets from the datasets: AKT3 from both the bulk and single cell RNA-Seq data as well as AKT2, MLKL, and MAPK11 in the single cell experiments. Altogether, we believe that our web tool will facilitate future target identification and drug development for COVID-19, notably in a cell type and tissue specific manner.

SUBMITTER: Schultz B

PROVIDER: S-EPMC10156718 | biostudies-literature | 2023 May

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

A machine learning method for the identification and characterization of novel COVID-19 drug targets.

Schultz Bruce B DeLong Lauren Nicole LN Masny Aliaksandr A Lentzen Manuel M Raschka Tamara T van Dijk David D Zaliani Andrea A Fröhlich Holger H

Scientific reports 20230503 1

In addition to vaccines, the World Health Organization sees novel medications as an urgent matter to fight the ongoing COVID-19 pandemic. One possible strategy is to identify target proteins, for which a perturbation by an existing compound is likely to benefit COVID-19 patients. In order to contribute to this effort, we present GuiltyTargets-COVID-19 ( https://guiltytargets-covid.eu/ ), a machine learning supported web tool to identify novel candidate drug targets. Using six bulk and three sing ...[more]

PMID: 37137934

Similar Datasets

Project description:BackgroundSince the epidemic continues, there is a pressing need to improve our understanding of coronavirus disease 2019 (COVID-19). Mendelian randomization (MR) studies provide us with a method to explore the causality between circulating proteins and COVID-19 susceptibility and severity. We aim to find new perspectives on the pathological mechanism of the disease and possible drug targets for treatment based on this study.MethodsWe conducted a phenome-wide MR study to prioritize circulating proteins causally associated with COVID-19 susceptibility, which was defined as "patients tested positive for COVID-19 vs. population controls", and severity, which was defined as "patients hospitalized with COVID-19 vs. population controls". And we repeated the analysis for different definition of COVID-19 susceptibility, severity and control groups.ResultsAssociation of three circulating proteins with COVID-19 susceptibility and severity were demonstrated via our study. C-C motif chemokine 4 (OR =1.887, 95% CI: 1.608-2.165, P=8.04×10-6) and 2'-5'-oligoadenylate synthase 1 (OR =0.511, 95% CI: 0.266-0.757, P=8.51×10-8) were found respectively positively and negatively correlated with increased COVID-19 severity. Tissue factor, contrary to previous studies, was found associated with decreased COVID-19 susceptibility (OR =0.667, 95% CI: 0.484-0.850, P=1.47×10-5) and decreased COVID-19 severity (OR =0.459, 95% CI: 0.132-0.786, P=3.01×10-6).ConclusionsGenetic evidence supports C-C motif chemokine 4 as a risk factor for COVID-19 severity, and 2'-5'-oligoadenylate synthase 1 as a protective factor for COVID-19 severity. The causal association between tissue factor and COVID-19 is contrary to the previous studies, needing further analyses. Further research is warranted to assess the viability of C-C motif chemokine 4 and 2'-5'-oligoadenylate synthase 1 as well as their downstream pathways as drug targets for anti-inflammatory and anti-virus treatment in severe cases.

Project description:The 2019 newfound Coronavirus (COVID-19) still remains as a threatening disease of which new cases are being reported daily from all over the world. The present study aimed at estimating the related rates of morbidity, growth, and mortality for COVID-19 over a three-month period starting from Feb, 19, 2020 to May 18, 2020 in Iran. In addition, it revealed the effect of the mean age, changes in weather temperature and country's executive policies including social distancing, restrictions on travel, closing public places, shops and educational centers. We have developed a combined neural network to estimate basic reproduction number, growth, and mortality rates of COVID-19. Required data was obtained from daily reports of World Health Organization (WHO), Iran Meteorological Organization (IRIMO) and the Statistics Center of Iran. The technique used in the study encompassed the use of Artificial Neural Network (ANN) combined with Swarm Optimization (PSO) and Bus Transportation Algorithms (BTA). The results of the present study showed that the related mortality rate of COVID-19 is in the range of [0.1], and the point 0.275 as the mortality rate provided the best results in terms of the total training and test squared errors of the network. Furthermore, the value of basic reproduction number for ANN-BTA and ANN-PSO was 1.045 and 1.065, respectively. In the present study, regarding the closest number to the regression line (0.275), the number of patients was equal to 2566200 cases (with and without clinical symptoms) and the growth rate based on arithmetic means was estimated to be 1.0411 and 1.06911, respectively. Reviewing the growth and mortality rates over the course of 90 days, after 45 days of first case detection, the highest increase in mortality rate was reported 158 cases. Also, the highest growth rate was related to the eighth and the eighteenth days after the first case report (2.33). In the present study, the weather variant in relationship to the basic reproduction number and mortality rate was estimated ineffective. In addition, the role of quarantine policies implemented by the Iranian government was estimated to be insignificant concerning the mortality rate. However, the age range was an ifluential factor in mortality rate. Finally, the method proposed in the present study cofirmed the role of the mean age of the country in the mortality rate related to COVID-19 patients at the time of research conduction. The results indicated that if sever quarantine restrictions are not applied and Iranian government does not impose effective interventions, about 60% to 70% of the population (it means around 49 to 58 million people) would be afflicted by COVID-19 during June to September 2021.

Project description:ImportanceDuring the COVID-19 pandemic, the effective distribution of limited treatments became a crucial policy goal. Yet, limited research exists using electronic health record data and machine learning techniques, such as policy learning trees (PLTs), to optimize the distribution of scarce therapeutics.ObjectiveTo evaluate whether a machine learning PLT-based method of scarce resource allocation optimizes the treatment benefit of COVID-19 neutralizing monoclonal antibodies (mAbs) during periods of resource constraint.Design, setting, and participantsThis retrospective cohort study used electronic health record data from October 1, 2021, to December 11, 2021, for the training cohort and data from June 1, 2021, to October 1, 2021, for the testing cohort. The cohorts included patients who had positive test results for SARS-CoV-2 and qualified for COVID-19 mAb therapy based on the US Food and Drug Administration's emergency use authorization criteria, ascertained from the patient electronic health record. Only some of the qualifying candidates received treatment with mAbs. Data were analyzed between from January 2023 to May 2024.Main outcomes and measuresThe primary outcome was overall expected hospitalization, assessed as the potential reduction in overall expected hospitalization if the PLT-based allocation system was used. This was compared to observed allocation using risk differences.ResultsAmong 9542 eligible patients in the training cohort (5418 female [56.8%]; age distribution: 18-44 years, 4151 [43.5%]; 45-64 years, 3146 [33.0%]; and ≥65 years, 2245 [23.5%]), a total of 3862 (40.5%) received mAbs. Among 6248 eligible patients in the testing cohort (3416 female [54.7%]; age distribution: 18-44 years, 2827 [45.2%]; 45-64 years, 1927 [30.8%]; and ≥65 years, 1494 [23.9%]), a total of 1329 (21.3%) received mAbs. Treatment allocation using the trained PLT model led to an estimated 1.6% reduction (95% CI, -2.0% to -1.2%) in overall expected hospitalization compared to observed treatment allocation in the testing cohort. The visual assessment showed that the PLT-based point system had a larger reduction in 28-day hospitalization compared with the Monoclonal Antibody Screening Score (maximum overall hospitalization difference, -1.0% [95% CI, -1.3% to -0.7%]) in the testing cohort.Conclusions and relevanceThis retrospective cohort study proposes and tests a PLT method, which can be linked to a electronic health record data platform to improve real-time allocation of scarce treatments. Use of this PLT-based allocation method would have likely resulted in fewer hospitalizations across a population than were observed in usual care, with greater expected reductions than a commonly used point system.

Dataset Information

A machine learning method for the identification and characterization of novel COVID-19 drug targets.

Publications

A machine learning method for the identification and characterization of novel COVID-19 drug targets.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets