Beta Fulltext view is in preview — article structure may vary. Browse all articles
Contents
Nanomedicine & Nanotechnology Open Access Research Article 17 min read

Artificial Intelligence and Machine Learning Approach towards COVID-19

Silpi Sarkar and Murthy Chavali*
* Corresponding author
ISSN: 2574-187X  10.23880/nnoa-16000201  Received: September 15, 2020  Published: October 13, 2020
 — views
 46 references
 4 figures
 4 tables
PDF
Keywords
Search Engines Contact tracing Drug Discovery Drug Repurposing Artificial Intelligence Machine Learning COVID-19
Abstract

COVID-19 pandemic is abruptly changing the normality and is taking a colossal toll which leads to human death. The scientific advancement requires the support and delivery of upcoming technologies like Artificial Intelligence (AI), Internet of Things, Big Data and Machine Learning Language which can look beyond the conventional strategies of healthcare delivery system. In this review we have discussed several search engines tools and AI-based applications viz., early detection and diagnosis during the infection, tracing the contact of the individuals, monitoring the treatment, development of drugs and vaccines which can be approached by the usage of these technologies. Discovery of drugs requires these technologies to accelerate deep learning technologies to create a model and predict the diagnosis process to treat COVID-19. AI can be used to understand the existing patterns of the drugs and extract new insight by AI algorithms which would discover in developing a vaccine and can be therapeutic potential.

Introduction

The pandemic disease novel Corona (COVID-19), had its origin from the Wuhan District of China (Hubei Province). SARS CoV-2 belongs to a class of enveloped viruses β-corona virus group with an RNA genome. It is observed SARS CoV and the Middle East Respiratory Syndrome Coronavirus (MERS-CoV) have a phylogenetic similarity with previous severe acute Respiratory syndrome [1]. During the Corona virus pandemic, COVID-19 virus got evolved evolutionarily. Thus the range of COVID -19 spread was severe than the previous COVID-19 and MERS-CoV. Severe Acute Respiratory Coronavirus 2 (SARS-CoV-2 which widely spreads through contact, droplets, and air. The patients can be divided into mild, moderate and acute based on the aetiology of the symptoms [2]. The tracking of the spread of the virus can be identified by using technology such as AI, Machine learning which can identify high – risk patients and can treat patients in real-time. AI can predict by population screening samples data the prediction for the risk of mortality of the patients [2]. It was observed in the prior literature survey of [3a,3b], 1273 online publications were checked related to SARS CoV-2, COVID-19 from databases of Nature, Elsevier, arXiv, bioRxiv, Google Scholar, medRxiv out of which filtered 267 papers used AI methods explicitly. Nevertheless, it can also predict notification and suggestions to control the infection and help us to fight the virus through screening of the population. As it is an evidenced-based tool which can be used medically to improve planning in treatment procedure and can have reported the outcome of the COVID-19. A schematic representation of the general procedure which can be helpful to general physicians during the Covid-19 is shown in figure 1.

Figure 1: A schematic representation of the general procedure which can be helpful to general physicians during the Covid-19.
Click to enlarge
Figure 1: A schematic representation of the general procedure which can be helpful to general physicians during the Covid-19.

The above figure 1 represents a flow diagram of Artificial based treatment and non- AI-based treatment which represents high accuracy and reduces complexity and the time taken for diagnosis. The AI application will allow the physician to not only control the disease but also help to focus on the treatment process. There is now an enormous amount of datasets related to coronavirus which can be leveraged with Artificial Intelligence (AI) to fight against the pandemic by establishing innovative approaches to contacting tracing of individuals, monitoring the patients, drug discovery, drug repurposing, vaccine development and reducing the burden on healthcare [2]. There is now a growing amount of coronavirus related datasets as well as published papers that must be leveraged along with artificial intelligence (AI) to fight this pandemic by driving news approaches to drug discovery, vaccine development, and public awareness. In the review, we will discuss the key areas about the application of AI and Machine learning (ML) which can address the challenges in clinical research, clinical trials in repurposing drugs to treat COVID-19, and the clinical trials for new drugs discovery.

The Significance of Artificial Intelligence

FDA approved drugs are on a declining spree due to adverse efficiency and reduced potential of potential compounds. The release of drugs with new molecular entities (NMEs) is declining to create a complex situation? Artificial Intelligence with computational drug designing provides a new way into a system-centric idea for R and D leading to future precise discovery [4]. AI has the potential to act in case of inefficiencies which occurs during the time of drug development thus minimising bias and human intervention in the process [5]. The scientists and the healthcare system have increasingly shown inclination on computer simulations to understand the pandemic situations in real-time. Further, computational scientists can construct a physical system in which virtually computerised model can take real-world data as input and prediction of assessment can be done based on the future evolution and severity of the Covid-19. These model predictions can be closely matched with model predictions and can thus empower the administrations to take local-specific decisions. AI aims to track the literature which has grown exponentially as the new updates in Corona Virus surfaces. It is observed in the website of NIH that tracks papers related to SARS-Cov-2 lists contain 28,000 articles [6]. To extract specific relevant literature which is driven by a combination of factors which includes the availability of a large collection of relevant papers, advancement in natural language processing (NLP) technology the AI and Machine learning tools can be utilised. The AI usually comprises of two methods A. Specific keywords in paper and analyse the text accordingly B. Deep neural networks a type of machine – learning method trained in collecting and recognizing information based on large data sets. The details of AI-based search engines which can track the latest on COVID-19 are listed in Table 4.

Applications of Artificial Intelligence

AI strategy can be implemented in several ways to quickly access the pandemic on a real-time basis which can be more accurately involved in treating patients. The applications of Artificial Intelligence in different arenas are listed in figure 2 and the schematic with the applications of Machine Learning is shown in figure 3.

Figure 2: Representation of applications of artificial intelligence in different arenas.
Click to enlarge
Figure 2: Representation of applications of artificial intelligence in different arenas.
AI can be used in quick detection of potential drug a. Tracing the contact of the individuals
discovery, planning, treatment on a clinical methodology and b. Monitoring the treatment
can be an evidence-based tool against COVID-19 [1]. c. Development of drugs and vaccines
d. Drug Repurposing
The early detection and diagnosis during the infection		a. Tracing the contact of the individuals
b. Monitoring the treatment
c. Development of drugs and vaccines
d. Drug Repurposing
The early detection and diagnosis during the infection
Figure 3: The schematic showing the applications of machine learning.
Click to enlarge
Figure 3: The schematic showing the applications of machine learning.

The Early Detection and Diagnosis During the Infection

AI can quickly analyse the symptoms based on irregular situations and thus can monitor the patients with the other healthcare authorities. AI can provide faster decision thus can be cost-effective. It gives a new diagnosis which can be managed effectively through proper algorithms. AI uses technologies viz., Computed tomography (CT), Magnetic Resonance Imaging (MRI) and scanning of the human body [2].

Tracing the Contact of the Individuals

AI can construct a platform by using a neural network for the proper treatment of categorised affected individuals. This can be done by automatic monitoring and prediction by AI to limit the spread of the virus by tracing the contact of the individuals [2]. This can increase the updates as AI can process effectively heterogeneous data and its sources within a limited duration of time and can provide solutions in COVID-19. In AI machine learning (ML) and deep learning (DL) are two important approaches. AI-powered temperature screening has been deployed in public locations during the pandemic in China. Further, AI-powered smartphones application is developed to track the geographical scale of COVID-19 these kinds of apps can be targeted to understand the population and communities which are susceptible and thus will envisage us with real-time dissemination of information about the potential hotspots in real-time. This is significant to identify and isolate rapid transmission which can flatten the transmission curve [7]. AI and big data can be leveraged upon to develop robust and predictive models eg. Deep convolution network model was adopted to classify X-ray images into normal, pneumonia and COVID-19 [8]. Apps developed for contact tracing in various countries is given in Table 1.

S. No.Apps used for contact tracingLocation TrackingLaunch OnCountry
1COVIDSafeBlueTrace protocol: Bluetooth14-Apr-20Australia
2Stopp CoronaBluetooth, Google/AppleMar-20Austria
3ViruSafeGSMMay-20Bulgaria
4BeAware BahrainBluetooth, GSM31-Mar-20Bahrain
5CovTracerGPS, GSMMay-20Cyprus
6CoronAppGPS12-Apr-20Colombia
7eRouška (eFacemask)BlueTrace protocol: Bluetooth15-Apr-20Czech Republic
8Estonia’s AppGoogle/Apple, DP-3T, BluetoothApr-20Estonia
9KetjuDP-3T, BluetoothMay, 2020Finland
10StopCovidBluetoothMay-20France
11CoronaAppBluetooth, Google/AppleMay-20Germany
12GH Covid-19 Tracker AppGPS12-Apr-20Ghana
13VirusRadarBluetooth13-May-20Hungary
14Ranking C-19GPSApr-20Iceland
15Aarogya SetuBluetooth & location-generated social
graph		2-Apr-20India
16Mask.irGSMMay-20Iran
17HSE Covid-19 AppBluetooth, Google/AppleMay-20Ireland
18HaMagenStandard location APIsMar-20Israel
19ImmuniBluetooth, Google/AppleMay-20Italy
20AMAN AppGPSMay-20Jordan
21Apturi COVIDBluetooth29-May-20Latvia
22MyTraceBluetooth, Google/Apple3-May-20Malaysia
23CovidRadarBluetoothMay-20Mexico
24NZ COVID TracerContact details and physical address20-May-20New Zealand
25StopKoronaBluetooth13-Apr-20North Macedonia
26SmittestoppBluetooth and GSM16-Apr-20Norway
27ProteGOBluetoothMay-20Poland
28EhterazBluetooth and GSMMay-20Qatar
29Corona MapBluetooth3-Apr-20Saudi Arabia
30TraceTogetherBlueTrace protocol, Bluetooth20-Mar-20Singapore
31Non-app-basedMobile device tracking data and card
transaction data		May-20South Korea
32SwissCovidDP-3T protocol, Bluetooth, Google/Apple20-May-20Switzerland
33Hayat Eve SigarBluetooth, GSMApril, 2020Turkey
34TraceCovidBluetoothMay-20UAE
35NHS Covid-19 AppBluetooth,May-20UK

Table 2: Apps for Contact Tracing Used in Various Countries.

Monitoring the Treatment

Diagnosis in the quick process helps to screen pandemic diseases like COVID-19. Thus, monitoring is a significant part of the transmission of disease in a cost-effective manner. AI and ML can augment the diagnosis and screen the process for identification of a patient with radio imaging technology akin to Computed Tomography (CT), X-ray, and clinical samples of blood. Prior literature studies of ML with the use of the convolutional neural network (Resnet-101) as an adjuvant tool on 1020 CT images of 108 Covid-19 infected patients along with viral pneumonia of 86 patients, which resulted in 86.27%, 83.33% of accuracy and specificity respectively [9]. The potentiality of AI and ML tools can be explored thus suggesting new models which can rapidly validate a method for SARS-CoV-2 by using a deep convolutional network. These models can process large heterogeneous data to create inter and intra layers of operability in systems to handle predictable tasks [10]. In prior literature, researchers have employed support vector machines to determine clinical, laboratory features and demographic information of patients to build classification model [11].

Development of Drugs and Vaccines

In the US for treating Ebola antiviral drug was developed. This discovery was actively done in 2014 by AI, ML-based pharmacophore computational analysing on a limited size of invitro infected carriers of the Ebola virus. Nevertheless, this led to the uncovering of drug development based on AI and ML technology fusion which utilised computational screening with docking application [12]. As the coronavirus has become pandemic AI and ML technology constitutes to be enthralling. It is seen from prior literature in Taiwan a new model has been developed to augment the development of a novel drug. Using AI and ML technology utilised deep neural network eight drugs viz., Gemcitabine, Clofazimine, Vismodegib, Celecoxib, Brequinar, Conivaptan, Tolcapone, Bedaquiline that were found to be effective in infectious feline peritonitis coronavirus [12]. Further, there are drugs viz., Homoharringtonine, Salinomycin Tilorone, Chloroquine and Boceprevir which are found to be operational during various AI experiments [13]. Prior literature studies revealed that in the US and South Korea a molecule transformer-drug target interaction model was proposed which can treat the Covid-19. This study was organized by virtual screening and molecular docking by AutoDock Vina which employed a deep learning algorithm with the proposed model on 3C like proteinase. And also, further FDA approved 3,410 existing drugs which are available in the market of Covid-19. These findings resulted in antiretroviral drug which can be used to treat HIV led Antazanavir followed by Remidisivir [12]. According to prior literature, in 2019 clinical trial on AI- based flu vaccine was sponsored by the National Institute of Allergy and Infectious Diseases. The vaccine was developed by scientists at Flinders University first using AI programme which generated trillions of synthetic compounds. Further, they used the AI program known as Search Algorithm for Ligands (SAM) which screen trillions of compounds to determine good candidates as vaccine adjuvants. This whole process of AI and ML technology can vividly shorten the process of vaccine development. Using CORD-19 dataset AI algorithms can be trained to build a model to screen existing drugs which can have potential efficacy towards the treatment of COVID-19 [14]. The process of drug discovery to market is represented in figure 4.

Figure 4: Representation from the process of drug discovery to market.
Click to enlarge
Figure 4: Representation from the process of drug discovery to market.

Drug Repurposing

A new drug discovery and development process take a sustainable amount of time before it is released in the market. The below table shows the process of drug development (Table 2).

Cost (%)Time in YearsThe population used for testingRate of Success
Discovery of the target42.5Studies in Laboratory and AnimalsCompounds of 5000 evaluated
Generation of Lead Compounds and Optimization153
Development at Preclinical stages101--
Clinical Trials at I, II and III Phases687-5 enters trial out of which 1 will be approved
Phase I-1.520-100 healthy volunteers
Phase II-2100-500 patient volunteers
Phase III-3.51000-5000 patient volunteers
Review and FDA Approval31.5--
Marketing of the drugs$88015--

Table 3: Various Stages of Development of a Drug before Marketing in the Countries.

According to prior literature reports, it is observed that the discovery of drug is a lengthy and expensive process, and prone to several trials which takes time to come to the market [15, 16]. A new molecular drug entity takes 10-15 years to develop thus the success rate is 2.01% [1]. As, the development of a drug is lengthy, high-priced during clinical trials and it has to undergo regulatory authorizations to get released in the market as potential drugs, it is quick to repurpose already approved drugs for active treatments of COVID-19 patients. Drug repurposing is a technique where old drugs are modified and the therapeutics entity of the repurposed drugs are utilised for the treatment [17]. With AI, the new drug can directly enter into phase II trials without passing phase I clinical trials which becomes economic leveraging with time and toxicity testing repeatedly. A deep learning-based drug target interaction model was developed known as Molecular Transformer -Drug Target Interaction (MT-DTI) by Natural Language Processing based on an algorithm. Thus, in COVID-19 it was used to recognize those drugs which can act on viral proteins [18]. Prior studies drug-target interaction datasets suggested good performance and robust results. In studies of Li et al. proposed [19] a novel network for the repurposing of a drug to treat COVID-19. The genomic sequence of COVID-19 was first analysed and through the pipeline of AutoSeed 34 genes related to COVID-19 was identified. These obtained genes are then used as seeds to build the network [19]. Repositioning of the drug is significant as the repurposed drugs can be directly used in clinical trials which minimize the initial steps of manufacturing thus lowering the costs. Thus, based on the time factor and potential treatments repurposing of the approved drugs for the treatment during COVID-19 can show directions in the faster treatment process [1]. In prior studies, a machine learning model was developed to discover antibodies through high throughput screening of antibodies that inhibits COVID-19. 18 antibodies are found to be very effective with this model. Molecular Dynamics simulation was used to predict 8 stable antibodies [20]. Prior literature of Rapaport and Rapaport in 2004 suggested the stability of predicted antibody was checked by molecular dynamics simulation and found 8 stable antibodies which could neutralize COVID-19. So, here in this context for viral infection, we can use Chloroquine (CQ) and Hydroxyl analogue Hydroxychloroquine (HCQ) which have already shown it effective treatment as an antimalarial drug [21]. Likewise, antiviral drug Remdesivir which is mainly used in the Ebola virus treatment has already been exposed to market against the new treatment of COVID -19 [22]. Drugs viz., Lopinavir and Ritonavir can be administered for COVID-19 treating patients. These drugs mainly affect proteolysis in the replication cycle of corona [23]. An analogue of ribonucleic and inhibitor of RNA polymerization Ribavirin drug in the preclinical study has shown in-vitro activity against SARS-COV 2 [24]. Moreover, an immunosuppressive drug Tocilizumab, mainly deployed for rheumatoid arthritis which decreases the clinical symptoms of virus infection was used in the treatment of patients in vivo during COVID-19 pandemic in China [25]. Nevertheless, antiviral drugs mixed with Ascorbic acid (Vitamin C) additionally can be supportive in the treatment of patients of COVID-19 patients. In future studies associated with repurposing a drug in this line against COVID-19 can be suggested [26]. List of companies which use AI for Drug discovery and repurposing is given in Table 3.

S. No.Name of the CompanyAI in drug repurposingRef.
1InnoplexusThe Indo-German company utilized patients’ information to treatments
during Covid-19 viz., Remdesivir Hydroxychloroquine		[27,28]
2DeargenThe Korean company with Dankook University at AI stage has
recommended Atazanavir (A medication for HIV treatment) to increase
the power of activity in treatment.		[29]
3GeroThe Singaporean organization anticipated having adequacy of 9
medications using AI which includes - niclosamide and nitazoxanide being
hostile to viral and parasitic medications		[30]
4CyclicaThe organization based in Canada screened 6,700 atoms in preliminary
Human Phase I on their AI-based medication repurposing stage Match
Maker. They are also working with China’s Institute of Materia Medica for
evaluating in vitro and in vivo samples		[28]
5HealxThis organization based in the UK is using the information to find out the
rate of mortality which found higher with comorbidities of respiratory
and heart frameworks. Also, this organization is working on uncommon
infections and is trying to reveal bi and tri mixes of affirmed drugs against
infection		[31]
6VantAIThis organization based in New York recognizes drugs which can obstruct
the infection’s movement in Golgi contraption and is presently screening
around 300 leads with a CRO to prevent viral contamination further		[32]
7Benevolent AIThe UK based organization is employing AI techniques to repurpose the
drugs against coronavirus		[33,34]
8ExscientiaSpin-out from the University of Dundee (U.K) and it collaborates with
many companies to successfully apply AI in small molecule for drug
discovery. Further, it is heading to study mechanism and functioning of
SARS-CoV-2 by data modelling through AI		[35]
9BergIn clinical-stage, an artificial intelligence-powered biotech company which
leverages its platform to map disease and revolutionize treatments across
oncology, neurology and rare diseases		[36]
10In silico MedicineA Hong-Kong based company which came up with seven molecules out of
which two molecules are synthesized for testing against COVID-19		[4]
11Iktos and SRI
international		France-based AI firm Iktos teamed up with SRI Biosciences (US) and work
with new potent molecules to synthesize and test the molecules in their
synthetic chemistry laboratory		[4]
S. No.Search EngineFunctionDeveloped byRef.
1COVID ScholarLiterature Search for COVID-19 which uses AI to tag
papers with keywords and topic labels and filters		Lawrence Berkeley
National Lab		[37]
2SPIKE-CORDAI is used to retrieve the papers on extract information
by a simple query language		Allen Institute for AI and
Bar-Ilan University		[38]
3COVID-19 Open
Research Dataset
(CORD-19)		AI is used to data mining for the COVID-19 literatureWhite House Office of
Science and Technology
Policy		[39]
4COVID-19
KnetMiner		AI visualises linked human biological data related to
SARS-CoV-2 and GWAS data		Rothamsted Research,
Harpenden, UK		[40]
5COVID-19 PortfolioAI tools use this a website that tracks papers related to
the SARS-CoV-2 coronavirus		National Institutes of
Health (NIH)		[41]
6COVID-19 Research
Explorer		A semantic search interface with AI-powered tool
which helps researcher and scientists to efficiently
search articles to answer COVID-19 related questions		Google[42]
7COVID-19 PRIMERUses the most advanced NLP algorithms, which trends
the latest research in COVID-19, conversations around
them and updates within 24 hours		PRIMER[43]
8VilokanaBased on artificial intelligence it’s a deep semantic
search which enables researchers to get deeper
insights into scientific studies on Covid-19		Indian Institute of
Information Technology
and Management –
Kerala		[44]
9SciSightSearch tool based on AI to visualize the emerging
literature network around COVID-19		Allen Institute of AI[45]

Table 4: List of Companies Which Use AI for Drug Discovery and Repurposing.

Conclusion

With the existence of pandemic SARS-COVID-19, there is a hike in coronavirus related datasets which drives new approaches to fight against the virus. AI, ML, can leverage this situation through its applications in various public awareness, early detection and diagnosis during the infection, contact tracing, monitoring the treatment, drug discovery and vaccine development. AI can be powered to screen trillions of compounds and establish models to predict for rapid diagnosis and treatment. For this, pharmaceutical companies and science laboratories can cooperate to work with industry leaders such as Google and IBM to create powerful AI tools to search good published papers and to predict drugs which can be clinically tested further. Further, during this panic situation chatbots can be created through AI tools to disseminate the information related to COVID-19 thus minimizing the spread of false information and interpretation related to COVID-19. In the paper we have discussed how patients can be diagnosed, contact traced, monitored and drugs and vaccines can be developed with AI- based approaches. The usage of emerging technologies with integrative medicines with AI could accelerate the revival of the pandemic situation in a manageable way.

References

  1. Harun Al Rashid, Mridul Mayank, Mohanty Chandana, Swayamsiddha Swati (2020) Application of Artificial Intelligence in COVID-19 drug repurposing. Diabetes & Metabolic Syndrome: Clinical Research & Reviews 14(5): 1027-1031.
  2. Vaishya R, Javaid M, Khan IH, Haleem A (2020) Artificial Intelligence (AI) applications for COVID-19 pandemic.  Diabetes & Metabolic Syndrome: Clinical Research & Reviews 14(4): 337-339.
  3. Chen J, Li K, Zhang Z, Li K, Yu PS (2020) A Survey on Applications of Artificial Intelligence in Fighting Against COVID-19. arXiv preprint arXiv, 2007.02202.
  4. (2020) How AI is fighting COVID-19: the companies using intelligent tech to find new drugs. Pharmaphorum.
  5. Kaushik AC, Raj U (2020) AI-driven drug discovery: A boon against COVID-19? AI Open 1: 1-4.
  6. Seddon G, Lounnas V, McGuire R, van den Bergh T, Bywater RP, et al. (2012) Drug design forever, from hype to hope  Journal of computer-aided molecular design 26(1): 137-150.
  7. Growth of the COVID-19 Literature.
  8. Hellewell J, Abbott S, Gimma A, Bosse NI, Jarvis CI, et al. (2020) Feasibility of controlling COVID-19 outbreaks by isolation of cases and contacts. The Lancet Global Health 8(4): 488-496.
  9. Agbehadji IE, Awuzie BO, Ngowi AB, Millham RC (2020) Review of Big Data Analytics, Artificial Intelligence and Nature-Inspired Computing Models towards Accurate Detection of COVID-19 Pandemic Cases and Contact Tracing. International journal of environmental research and public health 17(15): 5330.
  10. Ardakani AA, Kanafi AR, Acharya UR, Khadem N, Mohammadi A (2020) Application of deep learning technique to manage COVID-19 in routine clinical practice using CT images: Results of 10 convolutional neural networks.  Computers in Biology and Medicine 121: 103795.
  11. Salah K, Rehman MHU, Nizamuddin N, Al-Fuqaha A (2019) Blockchain for AI: Review and open research challenges. IEEE Access 7: 10127-10149.
  12. Sun L, Liu G, Song F, Shi N, Liu F, et al. (2020) Combination of four clinical indicators predicts the severe/critical symptom of patients infected COVID-19.  Journal of Clinical Virology 128: 104431.
  13. Ekins S, Mottin M, Ramos PR, Sousa BK, Neves BJ, et al. (2020) Déjà vu: Stimulating open drug discovery for SARS-CoV-2. Drug Discovery Today 25(5): 928-941.
  14. Lalmuanawma S, Hussain J, Chhakchhuak L (2020) Applications of machine learning and artificial intelligence for Covid-19 (SARS-CoV-2) pandemic: A review. Chaos, Solitons & Fractals 139: 110059.
  15. Ahuja AS, Reddy VP, Marques O (2020) Artificial Intelligence and COVID-19: A Multidisciplinary Approach. Integrative Medicine Research 9(3): 100434.
  16. DiMasi JA, Faden LB (2011) Competitiveness in follow- on drug R&D: a race or imitation? Nature Reviews Drug Discovery 10(1): 23-27.
  17. Carter PH, Berndt ER, DiMasi JA, Trusheim M (2016) Investigating investment in biopharmaceutical R&D. Nature Reviews Drug Discovery 15: 673-674.
  18. Xue H, Li J, Xie H, Wang Y (2018) Review of drug repositioning approaches and resources.  International Journal of Biological Sciences 14(10): 1232-1244.
  19. Beck BR, Shin B, Choi Y, Park S, Kang K (2020) Predicting commercially available antiviral drugs that may act on the novel coronavirus (SARS-CoV-2) through a drug- target interaction deep learning model. Computational and structural biotechnology journal 18: 784-790.
  20. Li X, Yu J, Zhang Z, Ren J, Peluffo AE, et al. (2020) Network bioinformatics analysis provides insight into drug repurposing for COVID-2019. Preprints.
  21. Magar R, Yadav P, Farimani AB (2020) Potential neutralizing antibodies discovered for novel coronavirus using machine learning. arXiv preprint arXiv:2003.08447.
  22. Rolain JM, Colson P, Raoult D (2007) Recycling of chloroquine and its hydroxyl analogue to face bacterial, fungal and viral infections in the 21st century. International journal of antimicrobial agents 30(4): 297-308.
  23. Gautret P, Lagier JC, Parola P, Meddeb L, Mailhe M, et al. (2020) Hydroxychloroquine and azithromycin as a treatment of COVID-19: results of an open-label non-randomized clinical trial.  International journal of antimicrobial agents 56(1): 105949.
  24. Elavarasi A, Prasad M, Seth T, et al. (2020) Chloroquine and Hydroxychloroquine for the Treatment of COVID-19: a Systematic Review and Meta-analysis. J Gen Intern Med.
  25. Wang LS, Wang YR, Ye DW, Liu QQ (2020) A review of the 2019 Novel Coronavirus (COVID-19) based on current evidence. International Journal of Antimicrobial Agents 55(6): 105948.
  26. Onder G, Rezza G, Brusaferro S (2020) Case-fatality rate and characteristics of patients dying in relation to COVID-19 in Italy. Jama 323(18): 1775-1776.
  27. Chan JFW, Yao Y, Yeung ML, Deng W, Bao L, et al. (2015) Treatment with lopinavir/ritonavir or interferon- β1b improves the outcome of MERS-CoV infection in a nonhuman primate model of the common marmoset. The Journal of infectious diseases 212(12): 1904-1913.
  28. Gordon DE, Jang GM, Bouhaddou M, Xu J, Obernier K, et al. (2020) A SARS-CoV-2 protein interaction map reveals targets for drug repurposing. Nature 583: 459-468.
  29. Siddiqui A (2020) China’s Institute of Materia Medica Partners with Cyclica on Innovative drug repurposing for COVID-19. China’s Institute of Materia Medica Partners with Cyclica for COVID-19.
  30. Scudellari M (2020) Five companies using AI to fight coronavirus. IEEE Spectrum.
  31. Kurji N (2020) China’s Institute of Materia Medica Partners with Cyclica on Innovative drug repurposing for COVID-19. Cyclica News.
  32. Guilliams T (2019) Healx joins forces with Boehringer Ingelheim to discover new treatment approaches for rare neurological diseases. Healx News.
  33. Vant AI (2020) DE NOVO AI-powered drug design.
  34. Mak KK, Pichika MR (2019) Artificial intelligence in drug development: present status and future prospects. Drug discovery today 24(3):773-780.
  35. Richardson PJ, Corbellino M, Stebbing J (2020) Baricitinib for COVID-19: a suitable treatment? – Authors’ reply. The Lancet, Infectious Diseases 20(9): 1013-1014.
  36. https://www.exscientia.ai
  37. https://www.berghealth.com
  38. https://www.nature.com/articles/d41586-020-01733- 7
  39. https://spike.covid-19.apps.allenai.org/search/covid19
  40. https://www.kaggle.com/allen-institute-for-ai/CORD- 19
  41. https://www.bio.tools/covid-19_knetminer
  42. https://www.icite.od.nih.gov/covid19/search/
  43. https://www.covid19-research-explorer.appspot.com/
  44. https://www.covid19primer.com/
  45. https://www.vilokana.in/
  46. https://www.scisight.apps.allenai.org/
More from this journal

Cite this article

BibTeX
APA
RIS
@article{silpi2020,
  title   = {Artificial Intelligence and Machine Learning Approach towards
COVID-19},
  author  = {Silpi Sarkar and Murthy Chavali},
  journal = {Nanomedicine & Nanotechnology Open Access},
  year    = {2020},
  volume  = {5},
  number  = {3},
  doi     = {10.23880/nnoa-16000201}
}
Silpi Sarkar and Murthy Chavali (2020). Artificial Intelligence and Machine Learning Approach towards
COVID-19. Nanomedicine & Nanotechnology Open Access, 5(3). https://doi.org/10.23880/nnoa-16000201
TY  - JOUR
TI  - Artificial Intelligence and Machine Learning Approach towards
COVID-19
AU  - Silpi Sarkar and Murthy Chavali
JO  - Nanomedicine & Nanotechnology Open Access
PY  - 2020
VL  - 5
IS  - 3
DO  - 10.23880/nnoa-16000201
ER  -