PubMed:32654489 JSONTXT

{"project":"LitCovid-PD-FMA-UBERON","denotations":[{"id":"T1","span":{"begin":810,"end":818},"obj":"Body_part"},{"id":"T2","span":{"begin":1234,"end":1239},"obj":"Body_part"}],"attributes":[{"id":"A1","pred":"fma_id","subj":"T1","obj":"http://purl.org/sig/ont/fma/fma67257"},{"id":"A2","pred":"fma_id","subj":"T2","obj":"http://purl.org/sig/ont/fma/fma68646"}],"text":"Repurpose Open Data to Discover Therapeutics for COVID-19 Using Deep Learning.\nThere have been more than 2.2 million confirmed cases and over 120 000 deaths from the human coronavirus disease 2019 (COVID-19) pandemic, caused by the novel severe acute respiratory syndrome coronavirus (SARS-CoV-2), in the United States alone. However, there is currently a lack of proven effective medications against COVID-19. Drug repurposing offers a promising route for the development of prevention and treatment strategies for COVID-19. This study reports an integrative, network-based deep-learning methodology to identify repurposable drugs for COVID-19 (termed CoV-KGE). Specifically, we built a comprehensive knowledge graph that includes 15 million edges across 39 types of relationships connecting drugs, diseases, proteins/genes, pathways, and expression from a large scientific corpus of 24 million PubMed publications. Using Amazon's AWS computing resources and a network-based, deep-learning framework, we identified 41 repurposable drugs (including dexamethasone, indomethacin, niclosamide, and toremifene) whose therapeutic associations with COVID-19 were validated by transcriptomic and proteomics data in SARS-CoV-2-infected human cells and data from ongoing clinical trials. Whereas this study by no means recommends specific drugs, it demonstrates a powerful deep-learning methodology to prioritize existing drugs for further investigation, which holds the potential to accelerate therapeutic development for COVID-19."}

{"project":"LitCovid-PD-UBERON","denotations":[{"id":"T1","span":{"begin":875,"end":881},"obj":"Body_part"}],"attributes":[{"id":"A1","pred":"uberon_id","subj":"T1","obj":"http://purl.obolibrary.org/obo/UBERON_3000645"}],"text":"Repurpose Open Data to Discover Therapeutics for COVID-19 Using Deep Learning.\nThere have been more than 2.2 million confirmed cases and over 120 000 deaths from the human coronavirus disease 2019 (COVID-19) pandemic, caused by the novel severe acute respiratory syndrome coronavirus (SARS-CoV-2), in the United States alone. However, there is currently a lack of proven effective medications against COVID-19. Drug repurposing offers a promising route for the development of prevention and treatment strategies for COVID-19. This study reports an integrative, network-based deep-learning methodology to identify repurposable drugs for COVID-19 (termed CoV-KGE). Specifically, we built a comprehensive knowledge graph that includes 15 million edges across 39 types of relationships connecting drugs, diseases, proteins/genes, pathways, and expression from a large scientific corpus of 24 million PubMed publications. Using Amazon's AWS computing resources and a network-based, deep-learning framework, we identified 41 repurposable drugs (including dexamethasone, indomethacin, niclosamide, and toremifene) whose therapeutic associations with COVID-19 were validated by transcriptomic and proteomics data in SARS-CoV-2-infected human cells and data from ongoing clinical trials. Whereas this study by no means recommends specific drugs, it demonstrates a powerful deep-learning methodology to prioritize existing drugs for further investigation, which holds the potential to accelerate therapeutic development for COVID-19."}

{"project":"LitCovid-PD-MONDO","denotations":[{"id":"T1","span":{"begin":49,"end":57},"obj":"Disease"},{"id":"T2","span":{"begin":172,"end":196},"obj":"Disease"},{"id":"T3","span":{"begin":198,"end":206},"obj":"Disease"},{"id":"T4","span":{"begin":238,"end":271},"obj":"Disease"},{"id":"T5","span":{"begin":285,"end":293},"obj":"Disease"},{"id":"T6","span":{"begin":401,"end":409},"obj":"Disease"},{"id":"T7","span":{"begin":516,"end":524},"obj":"Disease"},{"id":"T8","span":{"begin":636,"end":644},"obj":"Disease"},{"id":"T9","span":{"begin":1143,"end":1151},"obj":"Disease"},{"id":"T10","span":{"begin":1208,"end":1216},"obj":"Disease"},{"id":"T11","span":{"begin":1514,"end":1522},"obj":"Disease"}],"attributes":[{"id":"A1","pred":"mondo_id","subj":"T1","obj":"http://purl.obolibrary.org/obo/MONDO_0100096"},{"id":"A2","pred":"mondo_id","subj":"T2","obj":"http://purl.obolibrary.org/obo/MONDO_0100096"},{"id":"A3","pred":"mondo_id","subj":"T3","obj":"http://purl.obolibrary.org/obo/MONDO_0100096"},{"id":"A4","pred":"mondo_id","subj":"T4","obj":"http://purl.obolibrary.org/obo/MONDO_0005091"},{"id":"A5","pred":"mondo_id","subj":"T5","obj":"http://purl.obolibrary.org/obo/MONDO_0005091"},{"id":"A6","pred":"mondo_id","subj":"T6","obj":"http://purl.obolibrary.org/obo/MONDO_0100096"},{"id":"A7","pred":"mondo_id","subj":"T7","obj":"http://purl.obolibrary.org/obo/MONDO_0100096"},{"id":"A8","pred":"mondo_id","subj":"T8","obj":"http://purl.obolibrary.org/obo/MONDO_0100096"},{"id":"A9","pred":"mondo_id","subj":"T9","obj":"http://purl.obolibrary.org/obo/MONDO_0100096"},{"id":"A10","pred":"mondo_id","subj":"T10","obj":"http://purl.obolibrary.org/obo/MONDO_0005091"},{"id":"A11","pred":"mondo_id","subj":"T11","obj":"http://purl.obolibrary.org/obo/MONDO_0100096"}],"text":"Repurpose Open Data to Discover Therapeutics for COVID-19 Using Deep Learning.\nThere have been more than 2.2 million confirmed cases and over 120 000 deaths from the human coronavirus disease 2019 (COVID-19) pandemic, caused by the novel severe acute respiratory syndrome coronavirus (SARS-CoV-2), in the United States alone. However, there is currently a lack of proven effective medications against COVID-19. Drug repurposing offers a promising route for the development of prevention and treatment strategies for COVID-19. This study reports an integrative, network-based deep-learning methodology to identify repurposable drugs for COVID-19 (termed CoV-KGE). Specifically, we built a comprehensive knowledge graph that includes 15 million edges across 39 types of relationships connecting drugs, diseases, proteins/genes, pathways, and expression from a large scientific corpus of 24 million PubMed publications. Using Amazon's AWS computing resources and a network-based, deep-learning framework, we identified 41 repurposable drugs (including dexamethasone, indomethacin, niclosamide, and toremifene) whose therapeutic associations with COVID-19 were validated by transcriptomic and proteomics data in SARS-CoV-2-infected human cells and data from ongoing clinical trials. Whereas this study by no means recommends specific drugs, it demonstrates a powerful deep-learning methodology to prioritize existing drugs for further investigation, which holds the potential to accelerate therapeutic development for COVID-19."}

{"project":"LitCovid-PD-CLO","denotations":[{"id":"T1","span":{"begin":166,"end":171},"obj":"http://purl.obolibrary.org/obo/NCBITaxon_9606"},{"id":"T2","span":{"begin":354,"end":355},"obj":"http://purl.obolibrary.org/obo/CLO_0001020"},{"id":"T3","span":{"begin":435,"end":436},"obj":"http://purl.obolibrary.org/obo/CLO_0001020"},{"id":"T4","span":{"begin":686,"end":687},"obj":"http://purl.obolibrary.org/obo/CLO_0001020"},{"id":"T5","span":{"begin":819,"end":824},"obj":"http://purl.obolibrary.org/obo/OGG_0000000002"},{"id":"T6","span":{"begin":856,"end":857},"obj":"http://purl.obolibrary.org/obo/CLO_0001020"},{"id":"T7","span":{"begin":960,"end":961},"obj":"http://purl.obolibrary.org/obo/CLO_0001020"},{"id":"T8","span":{"begin":1016,"end":1018},"obj":"http://purl.obolibrary.org/obo/CLO_0053794"},{"id":"T9","span":{"begin":1228,"end":1239},"obj":"http://purl.obolibrary.org/obo/CLO_0053065"},{"id":"T10","span":{"begin":1353,"end":1354},"obj":"http://purl.obolibrary.org/obo/CLO_0001020"}],"text":"Repurpose Open Data to Discover Therapeutics for COVID-19 Using Deep Learning.\nThere have been more than 2.2 million confirmed cases and over 120 000 deaths from the human coronavirus disease 2019 (COVID-19) pandemic, caused by the novel severe acute respiratory syndrome coronavirus (SARS-CoV-2), in the United States alone. However, there is currently a lack of proven effective medications against COVID-19. Drug repurposing offers a promising route for the development of prevention and treatment strategies for COVID-19. This study reports an integrative, network-based deep-learning methodology to identify repurposable drugs for COVID-19 (termed CoV-KGE). Specifically, we built a comprehensive knowledge graph that includes 15 million edges across 39 types of relationships connecting drugs, diseases, proteins/genes, pathways, and expression from a large scientific corpus of 24 million PubMed publications. Using Amazon's AWS computing resources and a network-based, deep-learning framework, we identified 41 repurposable drugs (including dexamethasone, indomethacin, niclosamide, and toremifene) whose therapeutic associations with COVID-19 were validated by transcriptomic and proteomics data in SARS-CoV-2-infected human cells and data from ongoing clinical trials. Whereas this study by no means recommends specific drugs, it demonstrates a powerful deep-learning methodology to prioritize existing drugs for further investigation, which holds the potential to accelerate therapeutic development for COVID-19."}

{"project":"LitCovid-PD-CHEBI","denotations":[{"id":"T1","span":{"begin":626,"end":631},"obj":"Chemical"},{"id":"T2","span":{"begin":793,"end":798},"obj":"Chemical"},{"id":"T3","span":{"begin":810,"end":818},"obj":"Chemical"},{"id":"T4","span":{"begin":1032,"end":1037},"obj":"Chemical"},{"id":"T5","span":{"begin":1049,"end":1062},"obj":"Chemical"},{"id":"T6","span":{"begin":1095,"end":1105},"obj":"Chemical"},{"id":"T7","span":{"begin":1330,"end":1335},"obj":"Chemical"},{"id":"T8","span":{"begin":1413,"end":1418},"obj":"Chemical"}],"attributes":[{"id":"A1","pred":"chebi_id","subj":"T1","obj":"http://purl.obolibrary.org/obo/CHEBI_23888"},{"id":"A2","pred":"chebi_id","subj":"T2","obj":"http://purl.obolibrary.org/obo/CHEBI_23888"},{"id":"A3","pred":"chebi_id","subj":"T3","obj":"http://purl.obolibrary.org/obo/CHEBI_36080"},{"id":"A4","pred":"chebi_id","subj":"T4","obj":"http://purl.obolibrary.org/obo/CHEBI_23888"},{"id":"A5","pred":"chebi_id","subj":"T5","obj":"http://purl.obolibrary.org/obo/CHEBI_41879"},{"id":"A6","pred":"chebi_id","subj":"T6","obj":"http://purl.obolibrary.org/obo/CHEBI_9635"},{"id":"A7","pred":"chebi_id","subj":"T7","obj":"http://purl.obolibrary.org/obo/CHEBI_23888"},{"id":"A8","pred":"chebi_id","subj":"T8","obj":"http://purl.obolibrary.org/obo/CHEBI_23888"}],"text":"Repurpose Open Data to Discover Therapeutics for COVID-19 Using Deep Learning.\nThere have been more than 2.2 million confirmed cases and over 120 000 deaths from the human coronavirus disease 2019 (COVID-19) pandemic, caused by the novel severe acute respiratory syndrome coronavirus (SARS-CoV-2), in the United States alone. However, there is currently a lack of proven effective medications against COVID-19. Drug repurposing offers a promising route for the development of prevention and treatment strategies for COVID-19. This study reports an integrative, network-based deep-learning methodology to identify repurposable drugs for COVID-19 (termed CoV-KGE). Specifically, we built a comprehensive knowledge graph that includes 15 million edges across 39 types of relationships connecting drugs, diseases, proteins/genes, pathways, and expression from a large scientific corpus of 24 million PubMed publications. Using Amazon's AWS computing resources and a network-based, deep-learning framework, we identified 41 repurposable drugs (including dexamethasone, indomethacin, niclosamide, and toremifene) whose therapeutic associations with COVID-19 were validated by transcriptomic and proteomics data in SARS-CoV-2-infected human cells and data from ongoing clinical trials. Whereas this study by no means recommends specific drugs, it demonstrates a powerful deep-learning methodology to prioritize existing drugs for further investigation, which holds the potential to accelerate therapeutic development for COVID-19."}

{"project":"LitCovid-PD-GO-BP","denotations":[{"id":"T1","span":{"begin":69,"end":77},"obj":"http://purl.obolibrary.org/obo/GO_0007612"},{"id":"T2","span":{"begin":580,"end":588},"obj":"http://purl.obolibrary.org/obo/GO_0007612"},{"id":"T3","span":{"begin":982,"end":990},"obj":"http://purl.obolibrary.org/obo/GO_0007612"},{"id":"T4","span":{"begin":1369,"end":1377},"obj":"http://purl.obolibrary.org/obo/GO_0007612"}],"text":"Repurpose Open Data to Discover Therapeutics for COVID-19 Using Deep Learning.\nThere have been more than 2.2 million confirmed cases and over 120 000 deaths from the human coronavirus disease 2019 (COVID-19) pandemic, caused by the novel severe acute respiratory syndrome coronavirus (SARS-CoV-2), in the United States alone. However, there is currently a lack of proven effective medications against COVID-19. Drug repurposing offers a promising route for the development of prevention and treatment strategies for COVID-19. This study reports an integrative, network-based deep-learning methodology to identify repurposable drugs for COVID-19 (termed CoV-KGE). Specifically, we built a comprehensive knowledge graph that includes 15 million edges across 39 types of relationships connecting drugs, diseases, proteins/genes, pathways, and expression from a large scientific corpus of 24 million PubMed publications. Using Amazon's AWS computing resources and a network-based, deep-learning framework, we identified 41 repurposable drugs (including dexamethasone, indomethacin, niclosamide, and toremifene) whose therapeutic associations with COVID-19 were validated by transcriptomic and proteomics data in SARS-CoV-2-infected human cells and data from ongoing clinical trials. Whereas this study by no means recommends specific drugs, it demonstrates a powerful deep-learning methodology to prioritize existing drugs for further investigation, which holds the potential to accelerate therapeutic development for COVID-19."}

{"project":"LitCovid-PubTator","denotations":[{"id":"1","span":{"begin":49,"end":57},"obj":"Disease"},{"id":"19","span":{"begin":150,"end":156},"obj":"Disease"},{"id":"20","span":{"begin":172,"end":196},"obj":"Disease"},{"id":"21","span":{"begin":198,"end":206},"obj":"Disease"},{"id":"22","span":{"begin":238,"end":283},"obj":"Species"},{"id":"23","span":{"begin":285,"end":295},"obj":"Species"},{"id":"24","span":{"begin":401,"end":409},"obj":"Disease"},{"id":"25","span":{"begin":516,"end":524},"obj":"Disease"},{"id":"26","span":{"begin":636,"end":644},"obj":"Disease"},{"id":"27","span":{"begin":653,"end":656},"obj":"Species"},{"id":"28","span":{"begin":1049,"end":1062},"obj":"Chemical"},{"id":"29","span":{"begin":1064,"end":1076},"obj":"Chemical"},{"id":"30","span":{"begin":1078,"end":1089},"obj":"Chemical"},{"id":"31","span":{"begin":1095,"end":1105},"obj":"Chemical"},{"id":"32","span":{"begin":1143,"end":1151},"obj":"Disease"},{"id":"33","span":{"begin":1208,"end":1227},"obj":"Disease"},{"id":"34","span":{"begin":1228,"end":1233},"obj":"Species"},{"id":"35","span":{"begin":1514,"end":1522},"obj":"Disease"}],"attributes":[{"id":"A1","pred":"tao:has_database_id","subj":"1","obj":"MESH:C000657245"},{"id":"A19","pred":"tao:has_database_id","subj":"19","obj":"MESH:D003643"},{"id":"A20","pred":"tao:has_database_id","subj":"20","obj":"MESH:C000657245"},{"id":"A21","pred":"tao:has_database_id","subj":"21","obj":"MESH:C000657245"},{"id":"A22","pred":"tao:has_database_id","subj":"22","obj":"Tax:694009"},{"id":"A23","pred":"tao:has_database_id","subj":"23","obj":"Tax:2697049"},{"id":"A24","pred":"tao:has_database_id","subj":"24","obj":"MESH:C000657245"},{"id":"A25","pred":"tao:has_database_id","subj":"25","obj":"MESH:C000657245"},{"id":"A26","pred":"tao:has_database_id","subj":"26","obj":"MESH:C000657245"},{"id":"A27","pred":"tao:has_database_id","subj":"27","obj":"Tax:11118"},{"id":"A28","pred":"tao:has_database_id","subj":"28","obj":"MESH:D003907"},{"id":"A29","pred":"tao:has_database_id","subj":"29","obj":"MESH:D007213"},{"id":"A30","pred":"tao:has_database_id","subj":"30","obj":"MESH:D009534"},{"id":"A31","pred":"tao:has_database_id","subj":"31","obj":"MESH:D017312"},{"id":"A32","pred":"tao:has_database_id","subj":"32","obj":"MESH:C000657245"},{"id":"A33","pred":"tao:has_database_id","subj":"33","obj":"MESH:C000657245"},{"id":"A34","pred":"tao:has_database_id","subj":"34","obj":"Tax:9606"},{"id":"A35","pred":"tao:has_database_id","subj":"35","obj":"MESH:C000657245"}],"namespaces":[{"prefix":"Tax","uri":"https://www.ncbi.nlm.nih.gov/taxonomy/"},{"prefix":"MESH","uri":"https://id.nlm.nih.gov/mesh/"},{"prefix":"Gene","uri":"https://www.ncbi.nlm.nih.gov/gene/"},{"prefix":"CVCL","uri":"https://web.expasy.org/cellosaurus/CVCL_"}],"text":"Repurpose Open Data to Discover Therapeutics for COVID-19 Using Deep Learning.\nThere have been more than 2.2 million confirmed cases and over 120 000 deaths from the human coronavirus disease 2019 (COVID-19) pandemic, caused by the novel severe acute respiratory syndrome coronavirus (SARS-CoV-2), in the United States alone. However, there is currently a lack of proven effective medications against COVID-19. Drug repurposing offers a promising route for the development of prevention and treatment strategies for COVID-19. This study reports an integrative, network-based deep-learning methodology to identify repurposable drugs for COVID-19 (termed CoV-KGE). Specifically, we built a comprehensive knowledge graph that includes 15 million edges across 39 types of relationships connecting drugs, diseases, proteins/genes, pathways, and expression from a large scientific corpus of 24 million PubMed publications. Using Amazon's AWS computing resources and a network-based, deep-learning framework, we identified 41 repurposable drugs (including dexamethasone, indomethacin, niclosamide, and toremifene) whose therapeutic associations with COVID-19 were validated by transcriptomic and proteomics data in SARS-CoV-2-infected human cells and data from ongoing clinical trials. Whereas this study by no means recommends specific drugs, it demonstrates a powerful deep-learning methodology to prioritize existing drugs for further investigation, which holds the potential to accelerate therapeutic development for COVID-19."}

{"project":"LitCovid_AGAC_only","denotations":[{"id":"p53299s29","span":{"begin":216,"end":220},"obj":"Reg"}],"text":"Repurpose Open Data to Discover Therapeutics for COVID-19 Using Deep Learning.\nThere have been more than 2.2 million confirmed cases and over 120 000 deaths from the human coronavirus disease 2019 (COVID-19) pandemic, caused by the novel severe acute respiratory syndrome coronavirus (SARS-CoV-2), in the United States alone. However, there is currently a lack of proven effective medications against COVID-19. Drug repurposing offers a promising route for the development of prevention and treatment strategies for COVID-19. This study reports an integrative, network-based deep-learning methodology to identify repurposable drugs for COVID-19 (termed CoV-KGE). Specifically, we built a comprehensive knowledge graph that includes 15 million edges across 39 types of relationships connecting drugs, diseases, proteins/genes, pathways, and expression from a large scientific corpus of 24 million PubMed publications. Using Amazon's AWS computing resources and a network-based, deep-learning framework, we identified 41 repurposable drugs (including dexamethasone, indomethacin, niclosamide, and toremifene) whose therapeutic associations with COVID-19 were validated by transcriptomic and proteomics data in SARS-CoV-2-infected human cells and data from ongoing clinical trials. Whereas this study by no means recommends specific drugs, it demonstrates a powerful deep-learning methodology to prioritize existing drugs for further investigation, which holds the potential to accelerate therapeutic development for COVID-19."}

{"project":"LitCovid-sentences","denotations":[{"id":"T1","span":{"begin":0,"end":78},"obj":"Sentence"},{"id":"T2","span":{"begin":79,"end":325},"obj":"Sentence"},{"id":"T3","span":{"begin":326,"end":410},"obj":"Sentence"},{"id":"T4","span":{"begin":411,"end":525},"obj":"Sentence"},{"id":"T5","span":{"begin":526,"end":662},"obj":"Sentence"},{"id":"T6","span":{"begin":663,"end":916},"obj":"Sentence"},{"id":"T7","span":{"begin":917,"end":1278},"obj":"Sentence"},{"id":"T8","span":{"begin":1279,"end":1523},"obj":"Sentence"}],"namespaces":[{"prefix":"_base","uri":"http://pubannotation.org/ontology/tao.owl#"}],"text":"Repurpose Open Data to Discover Therapeutics for COVID-19 Using Deep Learning.\nThere have been more than 2.2 million confirmed cases and over 120 000 deaths from the human coronavirus disease 2019 (COVID-19) pandemic, caused by the novel severe acute respiratory syndrome coronavirus (SARS-CoV-2), in the United States alone. However, there is currently a lack of proven effective medications against COVID-19. Drug repurposing offers a promising route for the development of prevention and treatment strategies for COVID-19. This study reports an integrative, network-based deep-learning methodology to identify repurposable drugs for COVID-19 (termed CoV-KGE). Specifically, we built a comprehensive knowledge graph that includes 15 million edges across 39 types of relationships connecting drugs, diseases, proteins/genes, pathways, and expression from a large scientific corpus of 24 million PubMed publications. Using Amazon's AWS computing resources and a network-based, deep-learning framework, we identified 41 repurposable drugs (including dexamethasone, indomethacin, niclosamide, and toremifene) whose therapeutic associations with COVID-19 were validated by transcriptomic and proteomics data in SARS-CoV-2-infected human cells and data from ongoing clinical trials. Whereas this study by no means recommends specific drugs, it demonstrates a powerful deep-learning methodology to prioritize existing drugs for further investigation, which holds the potential to accelerate therapeutic development for COVID-19."}

{"project":"sentences","denotations":[{"id":"T1","span":{"begin":0,"end":78},"obj":"Sentence"},{"id":"T2","span":{"begin":79,"end":325},"obj":"Sentence"},{"id":"T3","span":{"begin":326,"end":410},"obj":"Sentence"},{"id":"T4","span":{"begin":411,"end":525},"obj":"Sentence"},{"id":"T5","span":{"begin":526,"end":662},"obj":"Sentence"},{"id":"T6","span":{"begin":663,"end":916},"obj":"Sentence"},{"id":"T7","span":{"begin":917,"end":1278},"obj":"Sentence"},{"id":"T8","span":{"begin":1279,"end":1523},"obj":"Sentence"},{"id":"T1","span":{"begin":0,"end":78},"obj":"Sentence"},{"id":"T2","span":{"begin":79,"end":325},"obj":"Sentence"},{"id":"T3","span":{"begin":326,"end":410},"obj":"Sentence"},{"id":"T4","span":{"begin":411,"end":525},"obj":"Sentence"},{"id":"T5","span":{"begin":526,"end":662},"obj":"Sentence"},{"id":"T6","span":{"begin":663,"end":916},"obj":"Sentence"},{"id":"T7","span":{"begin":917,"end":1278},"obj":"Sentence"},{"id":"T8","span":{"begin":1279,"end":1523},"obj":"Sentence"}],"namespaces":[{"prefix":"_base","uri":"http://pubannotation.org/ontology/tao.owl#"}],"text":"Repurpose Open Data to Discover Therapeutics for COVID-19 Using Deep Learning.\nThere have been more than 2.2 million confirmed cases and over 120 000 deaths from the human coronavirus disease 2019 (COVID-19) pandemic, caused by the novel severe acute respiratory syndrome coronavirus (SARS-CoV-2), in the United States alone. However, there is currently a lack of proven effective medications against COVID-19. Drug repurposing offers a promising route for the development of prevention and treatment strategies for COVID-19. This study reports an integrative, network-based deep-learning methodology to identify repurposable drugs for COVID-19 (termed CoV-KGE). Specifically, we built a comprehensive knowledge graph that includes 15 million edges across 39 types of relationships connecting drugs, diseases, proteins/genes, pathways, and expression from a large scientific corpus of 24 million PubMed publications. Using Amazon's AWS computing resources and a network-based, deep-learning framework, we identified 41 repurposable drugs (including dexamethasone, indomethacin, niclosamide, and toremifene) whose therapeutic associations with COVID-19 were validated by transcriptomic and proteomics data in SARS-CoV-2-infected human cells and data from ongoing clinical trials. Whereas this study by no means recommends specific drugs, it demonstrates a powerful deep-learning methodology to prioritize existing drugs for further investigation, which holds the potential to accelerate therapeutic development for COVID-19."}

{"project":"mondo_disease","denotations":[{"id":"T1","span":{"begin":49,"end":57},"obj":"Disease"},{"id":"T2","span":{"begin":172,"end":196},"obj":"Disease"},{"id":"T3","span":{"begin":198,"end":206},"obj":"Disease"},{"id":"T4","span":{"begin":238,"end":271},"obj":"Disease"},{"id":"T5","span":{"begin":285,"end":295},"obj":"Disease"},{"id":"T6","span":{"begin":401,"end":409},"obj":"Disease"},{"id":"T7","span":{"begin":516,"end":524},"obj":"Disease"},{"id":"T8","span":{"begin":636,"end":644},"obj":"Disease"},{"id":"T9","span":{"begin":1143,"end":1151},"obj":"Disease"},{"id":"T10","span":{"begin":1208,"end":1218},"obj":"Disease"},{"id":"T11","span":{"begin":1514,"end":1522},"obj":"Disease"}],"attributes":[{"id":"A1","pred":"mondo_id","subj":"T1","obj":"http://purl.obolibrary.org/obo/MONDO_0100096"},{"id":"A2","pred":"mondo_id","subj":"T2","obj":"http://purl.obolibrary.org/obo/MONDO_0100096"},{"id":"A3","pred":"mondo_id","subj":"T3","obj":"http://purl.obolibrary.org/obo/MONDO_0100096"},{"id":"A4","pred":"mondo_id","subj":"T4","obj":"http://purl.obolibrary.org/obo/MONDO_0005091"},{"id":"A5","pred":"mondo_id","subj":"T5","obj":"http://purl.obolibrary.org/obo/MONDO_0100096"},{"id":"A6","pred":"mondo_id","subj":"T6","obj":"http://purl.obolibrary.org/obo/MONDO_0100096"},{"id":"A7","pred":"mondo_id","subj":"T7","obj":"http://purl.obolibrary.org/obo/MONDO_0100096"},{"id":"A8","pred":"mondo_id","subj":"T8","obj":"http://purl.obolibrary.org/obo/MONDO_0100096"},{"id":"A9","pred":"mondo_id","subj":"T9","obj":"http://purl.obolibrary.org/obo/MONDO_0100096"},{"id":"A10","pred":"mondo_id","subj":"T10","obj":"http://purl.obolibrary.org/obo/MONDO_0100096"},{"id":"A11","pred":"mondo_id","subj":"T11","obj":"http://purl.obolibrary.org/obo/MONDO_0100096"}],"text":"Repurpose Open Data to Discover Therapeutics for COVID-19 Using Deep Learning.\nThere have been more than 2.2 million confirmed cases and over 120 000 deaths from the human coronavirus disease 2019 (COVID-19) pandemic, caused by the novel severe acute respiratory syndrome coronavirus (SARS-CoV-2), in the United States alone. However, there is currently a lack of proven effective medications against COVID-19. Drug repurposing offers a promising route for the development of prevention and treatment strategies for COVID-19. This study reports an integrative, network-based deep-learning methodology to identify repurposable drugs for COVID-19 (termed CoV-KGE). Specifically, we built a comprehensive knowledge graph that includes 15 million edges across 39 types of relationships connecting drugs, diseases, proteins/genes, pathways, and expression from a large scientific corpus of 24 million PubMed publications. Using Amazon's AWS computing resources and a network-based, deep-learning framework, we identified 41 repurposable drugs (including dexamethasone, indomethacin, niclosamide, and toremifene) whose therapeutic associations with COVID-19 were validated by transcriptomic and proteomics data in SARS-CoV-2-infected human cells and data from ongoing clinical trials. Whereas this study by no means recommends specific drugs, it demonstrates a powerful deep-learning methodology to prioritize existing drugs for further investigation, which holds the potential to accelerate therapeutic development for COVID-19."}

{"project":"NCBITAXON","denotations":[{"id":"T1","span":{"begin":166,"end":171},"obj":"OrganismTaxon"},{"id":"T2","span":{"begin":172,"end":196},"obj":"OrganismTaxon"},{"id":"T3","span":{"begin":238,"end":271},"obj":"OrganismTaxon"},{"id":"T4","span":{"begin":285,"end":293},"obj":"OrganismTaxon"},{"id":"T5","span":{"begin":1208,"end":1216},"obj":"OrganismTaxon"},{"id":"T6","span":{"begin":1228,"end":1233},"obj":"OrganismTaxon"}],"attributes":[{"id":"A1","pred":"db_id","subj":"T1","obj":"9606"},{"id":"A2","pred":"db_id","subj":"T2","obj":"2697049"},{"id":"A3","pred":"db_id","subj":"T3","obj":"694009"},{"id":"A4","pred":"db_id","subj":"T4","obj":"694009"},{"id":"A5","pred":"db_id","subj":"T5","obj":"694009"},{"id":"A6","pred":"db_id","subj":"T6","obj":"9606"}],"text":"Repurpose Open Data to Discover Therapeutics for COVID-19 Using Deep Learning.\nThere have been more than 2.2 million confirmed cases and over 120 000 deaths from the human coronavirus disease 2019 (COVID-19) pandemic, caused by the novel severe acute respiratory syndrome coronavirus (SARS-CoV-2), in the United States alone. However, there is currently a lack of proven effective medications against COVID-19. Drug repurposing offers a promising route for the development of prevention and treatment strategies for COVID-19. This study reports an integrative, network-based deep-learning methodology to identify repurposable drugs for COVID-19 (termed CoV-KGE). Specifically, we built a comprehensive knowledge graph that includes 15 million edges across 39 types of relationships connecting drugs, diseases, proteins/genes, pathways, and expression from a large scientific corpus of 24 million PubMed publications. Using Amazon's AWS computing resources and a network-based, deep-learning framework, we identified 41 repurposable drugs (including dexamethasone, indomethacin, niclosamide, and toremifene) whose therapeutic associations with COVID-19 were validated by transcriptomic and proteomics data in SARS-CoV-2-infected human cells and data from ongoing clinical trials. Whereas this study by no means recommends specific drugs, it demonstrates a powerful deep-learning methodology to prioritize existing drugs for further investigation, which holds the potential to accelerate therapeutic development for COVID-19."}

{"project":"Anatomy-UBERON","denotations":[{"id":"T1","span":{"begin":875,"end":881},"obj":"Body_part"}],"attributes":[{"id":"A1","pred":"uberon_id","subj":"T1","obj":"http://purl.obolibrary.org/obo/UBERON_0004360"},{"id":"A2","pred":"uberon_id","subj":"T1","obj":"http://purl.obolibrary.org/obo/UBERON_3000645"}],"text":"Repurpose Open Data to Discover Therapeutics for COVID-19 Using Deep Learning.\nThere have been more than 2.2 million confirmed cases and over 120 000 deaths from the human coronavirus disease 2019 (COVID-19) pandemic, caused by the novel severe acute respiratory syndrome coronavirus (SARS-CoV-2), in the United States alone. However, there is currently a lack of proven effective medications against COVID-19. Drug repurposing offers a promising route for the development of prevention and treatment strategies for COVID-19. This study reports an integrative, network-based deep-learning methodology to identify repurposable drugs for COVID-19 (termed CoV-KGE). Specifically, we built a comprehensive knowledge graph that includes 15 million edges across 39 types of relationships connecting drugs, diseases, proteins/genes, pathways, and expression from a large scientific corpus of 24 million PubMed publications. Using Amazon's AWS computing resources and a network-based, deep-learning framework, we identified 41 repurposable drugs (including dexamethasone, indomethacin, niclosamide, and toremifene) whose therapeutic associations with COVID-19 were validated by transcriptomic and proteomics data in SARS-CoV-2-infected human cells and data from ongoing clinical trials. Whereas this study by no means recommends specific drugs, it demonstrates a powerful deep-learning methodology to prioritize existing drugs for further investigation, which holds the potential to accelerate therapeutic development for COVID-19."}