Repurposing of drugs for combined treatment of COVID-19 cytokine storm using machine learning
© 2022 The Author(s)..
Severe acute respiratory syndrome coronavirus 2 (SARS‑CoV‑2) induced cytokine storm is the major cause of COVID-19 related deaths. Patients have been treated with drugs that work by inhibiting a specific protein partly responsible for the cytokines production. This approach provided very limited success, since there are multiple proteins involved in the complex cell signaling disease mechanisms. We targeted five proteins: Angiotensin II receptor type 1 (AT1R), A disintegrin and metalloprotease 17 (ADAM17), Nuclear Factor‑Kappa B (NF‑κB), Janus kinase 1 (JAK1) and Signal Transducer and Activator of Transcription 3 (STAT3), which are involved in the SARS‑CoV‑2 induced cytokine storm pathway. We developed machine-learning (ML) models for these five proteins, using known active inhibitors. After developing the model for each of these proteins, FDA-approved drugs were screened to find novel therapeutics for COVID‑19. We identified twenty drugs that are active for four proteins with predicted scores greater than 0.8 and eight drugs active for all five proteins with predicted scores over 0.85. Mitomycin C is the most active drug across all five proteins with an average prediction score of 0.886. For further validation of these results, we used the PyRx software to conduct protein-ligand docking experiments and calculated the binding affinity. The docking results support findings by the ML model. This research study predicted that several drugs can target multiple proteins simultaneously in cytokine storm-related pathway. These may be useful drugs to treat patients because these therapies can fight cytokine storm caused by the virus at multiple points of inhibition, leading to synergistically effective treatments.
| Medienart: |
E-Artikel |
|---|
| Erscheinungsjahr: |
2023 |
|---|---|
| Erschienen: |
2023 |
| Enthalten in: |
Zur Gesamtaufnahme - volume:17 |
|---|---|
| Enthalten in: |
Medicine in drug discovery - 17(2023) vom: 25. Feb., Seite 100148 |
| Sprache: |
Englisch |
|---|
| Beteiligte Personen: |
Gantla, Maanaskumar R [VerfasserIn] |
|---|
| Links: |
|---|
| Anmerkungen: |
Date Revised 28.02.2023 published: Print-Electronic Citation Status PubMed-not-MEDLINE |
|---|
| doi: |
10.1016/j.medidd.2022.100148 |
|---|
| funding: |
|
|---|---|
| Förderinstitution / Projekttitel: |
|
| PPN (Katalog-ID): |
NLM349788731 |
|---|
| LEADER | 01000naa a22002652 4500 | ||
|---|---|---|---|
| 001 | NLM349788731 | ||
| 003 | DE-627 | ||
| 005 | 20231226043447.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 231226s2023 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1016/j.medidd.2022.100148 |2 doi | |
| 028 | 5 | 2 | |a pubmed24n1165.xml |
| 035 | |a (DE-627)NLM349788731 | ||
| 035 | |a (NLM)36466363 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 100 | 1 | |a Gantla, Maanaskumar R |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a Repurposing of drugs for combined treatment of COVID-19 cytokine storm using machine learning |
| 264 | 1 | |c 2023 | |
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a ƒaComputermedien |b c |2 rdamedia | ||
| 338 | |a ƒa Online-Ressource |b cr |2 rdacarrier | ||
| 500 | |a Date Revised 28.02.2023 | ||
| 500 | |a published: Print-Electronic | ||
| 500 | |a Citation Status PubMed-not-MEDLINE | ||
| 520 | |a © 2022 The Author(s). | ||
| 520 | |a Severe acute respiratory syndrome coronavirus 2 (SARS‑CoV‑2) induced cytokine storm is the major cause of COVID-19 related deaths. Patients have been treated with drugs that work by inhibiting a specific protein partly responsible for the cytokines production. This approach provided very limited success, since there are multiple proteins involved in the complex cell signaling disease mechanisms. We targeted five proteins: Angiotensin II receptor type 1 (AT1R), A disintegrin and metalloprotease 17 (ADAM17), Nuclear Factor‑Kappa B (NF‑κB), Janus kinase 1 (JAK1) and Signal Transducer and Activator of Transcription 3 (STAT3), which are involved in the SARS‑CoV‑2 induced cytokine storm pathway. We developed machine-learning (ML) models for these five proteins, using known active inhibitors. After developing the model for each of these proteins, FDA-approved drugs were screened to find novel therapeutics for COVID‑19. We identified twenty drugs that are active for four proteins with predicted scores greater than 0.8 and eight drugs active for all five proteins with predicted scores over 0.85. Mitomycin C is the most active drug across all five proteins with an average prediction score of 0.886. For further validation of these results, we used the PyRx software to conduct protein-ligand docking experiments and calculated the binding affinity. The docking results support findings by the ML model. This research study predicted that several drugs can target multiple proteins simultaneously in cytokine storm-related pathway. These may be useful drugs to treat patients because these therapies can fight cytokine storm caused by the virus at multiple points of inhibition, leading to synergistically effective treatments | ||
| 650 | 4 | |a Journal Article | |
| 650 | 4 | |a 1D 2D 3D, one- two- three-dimensional | |
| 650 | 4 | |a ADAM17, A disintegrin and metalloprotease 17 | |
| 650 | 4 | |a ARDS, acute respiratory distress syndrome | |
| 650 | 4 | |a AT1R, Angiotensin II receptor type 1 | |
| 650 | 4 | |a AUROC, Area under receiver operator characteristic curve | |
| 650 | 4 | |a COVID-19 | |
| 650 | 4 | |a COVID-19, coronavirus disease 2019 | |
| 650 | 4 | |a CRS, cytokine release syndrome | |
| 650 | 4 | |a CXCL10, CXC-chemokine ligand 10 | |
| 650 | 4 | |a Docking | |
| 650 | 4 | |a FDA, Food and Drug Administration | |
| 650 | 4 | |a G-CSF, granulocyte colony stimulating factor | |
| 650 | 4 | |a IC50, half maximal inhibitory concentration | |
| 650 | 4 | |a ICU, intensive care unit | |
| 650 | 4 | |a IL, interleukin | |
| 650 | 4 | |a JAK1, Janus kinase 1 | |
| 650 | 4 | |a MCP1, monocyte chemoattractant protein-1 | |
| 650 | 4 | |a MIP1α, macrophage inflammatory protein 1 | |
| 650 | 4 | |a ML, machine learning | |
| 650 | 4 | |a Machine learning | |
| 650 | 4 | |a Multi-targeted drug discovery | |
| 650 | 4 | |a NF-κB, Nuclear Factor-Kappa B | |
| 650 | 4 | |a PDB, Protein Data Bank | |
| 650 | 4 | |a PaDEL, Pharmaeutical data exploration laboratory | |
| 650 | 4 | |a ROC, receiver operator characteristic curve | |
| 650 | 4 | |a SARS-CoV-2 | |
| 650 | 4 | |a SMILES, Simplified Molecular-Input Line-Entry System | |
| 650 | 4 | |a STAT3, signal transducer and activator of transcription 3 | |
| 650 | 4 | |a Screening of FDA-approved drugs | |
| 650 | 4 | |a TNFα, tumor necrosis factor α | |
| 650 | 4 | |a WEKA, Waikato Environment for Knowledge Analysis | |
| 700 | 1 | |a Tsigelny, Igor F |e verfasserin |4 aut | |
| 700 | 1 | |a Kouznetsova, Valentina L |e verfasserin |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t Medicine in drug discovery |d 2020 |g 17(2023) vom: 25. Feb., Seite 100148 |w (DE-627)NLM308741242 |x 2590-0986 |7 nnns |
| 773 | 1 | 8 | |g volume:17 |g year:2023 |g day:25 |g month:02 |g pages:100148 |
| 856 | 4 | 0 | |u http://dx.doi.org/10.1016/j.medidd.2022.100148 |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a GBV_NLM | ||
| 951 | |a AR | ||
| 952 | |d 17 |j 2023 |b 25 |c 02 |h 100148 | ||