SperoPredictor: An Integrated Machine Learning and Molecular Docking-Based Drug Repurposing Framework With Use Case of COVID-19

被引:38
作者
Ahmed, Faheem [1 ]
Lee, Jae Wook [1 ,2 ]
Samantasinghar, Anupama [1 ]
Kim, Young Su [2 ]
Kim, Kyung Hwan [1 ]
Kang, In Suk [1 ]
Memon, Fida Hussain [1 ]
Lim, Jong Hwan [1 ]
Choi, Kyung Hyun [1 ,2 ]
机构
[1] Jeju Natl Univ, Dept Mechatron Engn, Jeju, South Korea
[2] BioSpero Inc, Jeju, South Korea
关键词
drug repurposing; COVID-19; machine learning; databases; data analytics; host proteomes; molecular docking; TARGET INTERACTION PREDICTION; STITCH; CORONAVIRUSES; INFORMATION; SARS-COV-2; DISCOVERY; NETWORKS; DISGENET; DATABASE;
D O I
10.3389/fpubh.2022.902123
中图分类号
R1 [预防医学、卫生学];
学科分类号
1004 ; 120402 ;
摘要
The global spread of the SARS coronavirus 2 (SARS-CoV-2), its manifestation in human hosts as a contagious disease, and its variants have induced a pandemic resulting in the deaths of over 6,000,000 people. Extensive efforts have been devoted to drug research to cure and refrain the spread of COVID-19, but only one drug has received FDA approval yet. Traditional drug discovery is inefficient, costly, and unable to react to pandemic threats. Drug repurposing represents an effective strategy for drug discovery and reduces the time and cost compared to de novo drug discovery. In this study, a generic drug repurposing framework (SperoPredictor) has been developed which systematically integrates the various types of drugs and disease data and takes the advantage of machine learning (Random Forest, Tree Ensemble, and Gradient Boosted Trees) to repurpose potential drug candidates against any disease of interest. Drug and disease data for FDA-approved drugs (n = 2,865), containing four drug features and three disease features, were collected from chemical and biological databases and integrated with the form of drug-disease association tables. The resulting dataset was split into 70% for training, 15% for testing, and the remaining 15% for validation. The testing and validation accuracies of the models were 99.3% for Random Forest and 99.03% for Tree Ensemble. In practice, SperoPredictor identified 25 potential drug candidates against 6 human host-target proteomes identified from a systematic review of journals. Literature-based validation indicated 12 of 25 predicted drugs (48%) have been already used for COVID-19 followed by molecular docking and re-docking which indicated 4 of 13 drugs (30%) as potential candidates against COVID-19 to be pre-clinically and clinically validated. Finally, SperoPredictor results illustrated the ability of the platform to be rapidly deployed to repurpose the drugs as a rapid response to emergent situations (like COVID-19 and other pandemics).
引用
收藏
页数:17
相关论文
共 101 条
[1]   Mental depression: Relation to different disease status, newer treatments and its association with COVID-19 pandemic [J].
Abdel-Bakky, Mohamed S. ;
Amin, Elham ;
Faris, Tarek M. ;
Abdellatif, Ahmed A. H. .
MOLECULAR MEDICINE REPORTS, 2021, 24 (06)
[2]  
Abramo JM., 2012, Assessment Evaluation in Higher Education, V37, P435, DOI [DOI 10.1007/82, 10.3389/fpsyg.2014.00661]
[3]   Azithromycin and ambroxol as potential pharmacotherapy for SARS-CoV-2 [J].
Alkotaji, Myasar .
INTERNATIONAL JOURNAL OF ANTIMICROBIAL AGENTS, 2020, 56 (06)
[4]  
[Anonymous], 2020, COVID 19 RESOURCE CT
[5]  
[Anonymous], VALIDATION PREDICTIN
[6]   The $2.6 Billion Pill - Methodologic and Policy Considerations [J].
Avorn, Jerry .
NEW ENGLAND JOURNAL OF MEDICINE, 2015, 372 (20) :1877-1879
[7]   UniProt: the universal protein knowledgebase in 2021 [J].
Bateman, Alex ;
Martin, Maria-Jesus ;
Orchard, Sandra ;
Magrane, Michele ;
Agivetova, Rahat ;
Ahmad, Shadab ;
Alpi, Emanuele ;
Bowler-Barnett, Emily H. ;
Britto, Ramona ;
Bursteinas, Borisas ;
Bye-A-Jee, Hema ;
Coetzee, Ray ;
Cukura, Austra ;
Da Silva, Alan ;
Denny, Paul ;
Dogan, Tunca ;
Ebenezer, ThankGod ;
Fan, Jun ;
Castro, Leyla Garcia ;
Garmiri, Penelope ;
Georghiou, George ;
Gonzales, Leonardo ;
Hatton-Ellis, Emma ;
Hussein, Abdulrahman ;
Ignatchenko, Alexandr ;
Insana, Giuseppe ;
Ishtiaq, Rizwan ;
Jokinen, Petteri ;
Joshi, Vishal ;
Jyothi, Dushyanth ;
Lock, Antonia ;
Lopez, Rodrigo ;
Luciani, Aurelien ;
Luo, Jie ;
Lussi, Yvonne ;
Mac-Dougall, Alistair ;
Madeira, Fabio ;
Mahmoudy, Mahdi ;
Menchi, Manuela ;
Mishra, Alok ;
Moulang, Katie ;
Nightingale, Andrew ;
Oliveira, Carla Susana ;
Pundir, Sangya ;
Qi, Guoying ;
Raj, Shriya ;
Rice, Daniel ;
Lopez, Milagros Rodriguez ;
Saidi, Rabie ;
Sampson, Joseph .
NUCLEIC ACIDS RESEARCH, 2021, 49 (D1) :D480-D489
[8]   Predicting commercially available antiviral drugs that may act on the novel coronavirus (SARS-CoV-2) through a drug-target interaction deep learning model [J].
Beck, Bo Ram ;
Shin, Bonggun ;
Choi, Yoonjung ;
Park, Sungsoo ;
Kang, Keunsoo .
COMPUTATIONAL AND STRUCTURAL BIOTECHNOLOGY JOURNAL, 2020, 18 :784-790
[9]   The history of the drug utilization research group in Europe [J].
Bergman, U .
PHARMACOEPIDEMIOLOGY AND DRUG SAFETY, 2006, 15 (02) :95-98
[10]  
Bjerrum E.J., 2017, arXiv