A Ruxolitinib: A restorative of
COVID-19
Surabhi Gangani 1, Robin Sinha 1 , Preeti P. 1 , Trapti Sharma 1 , Kamal Rawal #1
1. Amity Institute of Biotechnology, Amity University Uttar Pradesh, India.
#Corresponding Author
Email ID: kamal.rawal@gmail.com
Centre for Computational Biology and Bioinformatics,
AIB Amity University, Noida
CoV-DRUGX Software Pipeline: http://drugx.kamalrawal.in/drugx/
Abstract
Despite mass level vaccinations and the launch of several repurposed drugs, the recently
emerged SARS CoV-2 Omicron (B.1.1.529) is a variant of concern. New drugs must be
discovered with artificial intelligence (AI) assistance. Artificial intelligence (AI) enabled
drug repurposing reduces the time and costs of drug discovery. Ruxolitinib (formerly known
as INCB018424; Jakavi; Jakafi) is an oral inhibitor of JAK 1 & 2. Ruxolitinib has been
approved to treat primary myelofibrosis, polycythemia vera, and hemophagocytic
lymphohistiocytosis by the Food and Drug Administration and European Medicines
Agency. The analysis of ruxolitinib is done via the CoV-DrugX pipeline. We find that the
Ruxolitinib has a 75% probability of being considered a COVID-19 repurposed drug with
the help of the CoV-DrugX pipeline. In addition, there is a clinical trial assessing the safety
and efficacy of ruxolitinib. Therefore, we believe that Ruxolitinib could be a potent drug
against the treatment of COVID-19.
Keywords: Artificial intelligence, drug repurposing, DrugX pipeline, COVID-19, Ruxcovid1. Introduction
In late 2019, severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infections
spread worldwide. Its associated coronavirus disease COVID-19 pandemic has infected a
large proportion of the world’s population [Caocci et al., 2021]. There is a worldwide effort
to develop vaccines for this disease as a consequence [Carneiro et al., 2021]. Furthermore,
2020 brought drug repurposing (also known as drug repositioning), which is nothing but
recycling old drugs trying to treat new diseases, an attractive form of drug discovery
[Dotolo et al., 2021].
Ruxolitinib, a small molecule (formerly known as INCB018424; Jakavi; Jakafi), is a potent
JAK1 and JAK2 inhibitor developed by Incyte Corporation (Wilmington, DE, USA) that
blocks JAK Kinase activity and prevents STAT activation and nuclear translocation [Ostojic
et al., 2011; Bagca et al., 2020]. It also inhibits IL6/JAK/STAT3 pathway, thus reducing
circulating IL6 levels [Caocci et al., 2020]. The chemical structure of ruxolitinib determines
its physical and chemical properties (see Supplementary figure 1). Ruxolitinib was approved
as a treatment for primary myelofibrosis, polycythemia vera, and hemophagocytic
lymphohistiocytosis in November 2011 by the Food and Drug Administration and European
Medicines Agency because it manifests cytokine dysregulations similar to SARS-CoV-2
[Cao et al., 2020; D’Alessio et al., 2021]. Several clinical trials will check ruxolitinib’s
efficacy and safety in COVID-19 related symptoms, shown in Supplementary Table 1.
The JAK/STAT pathway controls cytokines’ activation, which regulates different cellular
and immune functions [Bagca et al., 2020]. The main regulatory cell signalling pathways
are JAK (Janus Kinases) and STAT (signal transducers and activators of transcription) (see
Supplementary figure 2) [Villarino et al., 2015]. The JAK family comprises JAK1, JAK2,
JAK3, protein tyrosine kinases, and TYK2, a non-receptor tyrosine kinase 2 [Ostojic et al.,
2011]. At the carboxy-terminal (C-terminal), two kinases domains, JH1 and JH2, out of
seven JAK homology domains are present. The JH1 domain is a catalytic component,
whereas JH2 is a pseudo-kinase with an autoregulatory suppressor function. At the
amino-terminal (N-terminal) end is a receptor-interacting FERM domain comprising JH4-7
and Src homology (SH2) domain-containing JH3. This activated SH2 generates a binding
site for STAT transcription factors [Garrido et al., 2020]. The STAT protein family (STAT1,
STAT2, STAT3, STAT4, STAT5a, STATb, and STAT6) are present on the N-terminal,
followed by coiled-coil domain involved in protein-protein interaction, DNA bindingdomain for sequence-specific DNA binding and nuclear localisation, a linker region, an SH2
domain involved in dimerisation and protein association, and a transactivation domain
(TAD) carries conserved tyrosine residues that are phosphorylation sites for host kinases
[Seif et al., 2017]. The JAK/STAT pathway regulates hyperactivated immune responses,
cytokine storm, differentiation, proliferation, migration, and apoptosis depending on the
physiological signal [Lee et al., 2017].
Previously, we have developed several machine learning and bioinformatics platforms.
These include text mining and network biology-based systems [Jagannadham et al., 2016],
vaccine discovery systems [Rawal et al., 2021], next-generation sequencing analysis
systems for cancer and other genomes [Preeti et al., 2021, Rawal et al., 2011, Mandal et
al., 2006].
2. Implementation
CoV-DrugX pipeline is a multimodal pipeline relying on artificial intelligence,
network-based systems, and clinical information [Sinha et al., 2021]. The pipeline consists
of over 50 databases, including network data, therapeutic data, side effects data, drug
targets, gene expression, clinical features, pathway data, and structure data. Using this
eight-network medicine drug repurposing module, the ruxolitinib drug will be shortlisted
against COVID-19 based on the overall score it gains in each target molecule [Sinha et al.,
2021]. This section describes all modules based on these modules [Singh et al., 2021]:
2.1 Module 1 & 2: Deep learning-based modules:
Modules 1 and 2 are deep learning (DL) based modules that compute 11 biological
properties such as mutagenicity and drug-likeness and 200 cheminformatic properties such
as logP value and molecular weight of drug candidates. Furthermore, each module uses the
drug candidate in SMILES format as input and predicts whether the candidate might be
repurposed against COVID-19.
2.2 Module 3: Drug Dock
It is important to understand how small molecules and proteins interact, which is why
DrugDock uses AutoDock Vina to perform molecular docking of proteins with specific
ligands (drug candidates).2.3 Module 4: Drug Target
This module scores a drug candidate based on the similarity of their target molecules to the
target molecules of drugs associated with COVID-19. The module predicts a score of 1
when the target molecules of the query drug match COVID-19, otherwise a score of 0.
2.4 Module 5: Drug Side-Effect
The Drug Side-effect module assigns a score to drug candidates based on the similarity of
their side effects to the side effect of the drugs associated with COVID-19.
2.5 Module 6: Gene expression
It is essential to gain insights about gene expression patterns through gene expression
profiling and bioinformatics analysis; this will help to develop drugs that will accomplish
desired characteristics, such as disease-free survival, eradication of disease, elimination or
minimisation of toxic side effects, reduction of undesirable biotransformations,
enhancement of distribution (bioavailability), overcoming drug resistance, and improvement
of immune responses. In this regard, rational drug design would be integral to drug
discovery and development.
2.6 Module 7: Drug Phenotype
This module functions so that if the input drug is associated with COVID-19, it provides
the phenotype of the input drug and the number of matching phenotypes for the input drug.
2.7 Module 8: Drug-Gene Network
This module will assemble the interactions of genes, proteins, and drugs associated with
COVID-19 from the literature using text mining and deep curation approaches.
3. Usage
Ruxolitinib drug having drug bank ID or accession number “DB08877” is a potent and
selective inhibitor of JAK 1 and JAK 2, which are tyrosine kinases involved in cytokine
signalling and hematopoiesis. Its
SMILES are taken from the drug bank database
“N#CC[C@H](C1CCCC1)N1C=C(C=N1)C1=C2C=CNC2=NC=N1”.Users can choose any COVID-19 (viral) or Human targets to conduct a drug repurposing
process (Sinha et al., 2021). Using Drugbank data, the chemical identifiers: SMILES
structure of the ruxolitinib drug are reserved in the text file. It is the only form used as input
in the DrugX pipeline. This SMILES structure is run against eight-network medicine drug
repurposing modules to analyse the drug. The scores range between 0 and 1; 0 refers to not
considering the drug for repositioning for COVID-19. 1 indicates consideration of using the
drug for repurposing for COVID-19. To analyze the drug, the steps in Supplementary figure
3 must be followed.
4. Results and Discussion
The first module predicting the drug is COVID-19 repurposing, based on 11 biological
properties; the results are in Supplementary Table 2. This particular module gives the
properties of the ruxolitinib drug such as smiles (chemical identifier), synthetic accessibility
score, cycle, quantitative estimation of drug-likeness, rule of five, molecular weight,
mutagenicity, donors, acceptors. In addition, the module predicts the biological properties,
including ADME (absorption, distribution, metabolism, excretion), that help companies
discard compounds that are not drug-like in the discovery phase. The second module
predicting the drug is COVID-19 repurposable drug based on 200 properties results are
listed in Supplementary Table 3. In addition, this module lists the descriptors based on the
different types of cheminformatics descriptors such as surface, charge, fragment, simple,
graph, e-state, drug-likeness, logP, refractivity, and general values for the ruxolitinib drug.
Another module analysing the ruxolitinib drug based on the conditions related to COVID-19
results is listed in Supplementary Table 4. In this module, the total number of COVID-19
conditions shown is 34, and the number of conditions is 2, whereas the number of common
conditions is 0. This means there is no common condition for ruxolitinib to be used as a
COVID-19 repurpose drug.
This module provides the COVID-19 phenotype for ruxolitinib drug results in
Supplementary Table 5 and also suggests whether the ruxolitinib drug in use is affecting
COVID-19 susceptibility or not. The total number of COVID-19 phenotypes is 1952, and
the number of the phenotypes is 5, whereas the number of common phenotypes is also 5.
Common phenotypes are pancreatic neuroendocrine tumour, renal cyst, pheochromocytoma,
hemangioma, and renal cell carcinoma.Another module provides the side-effect of the ruxolitinib drug because using more than one
drug may cause serious side effects on patients (see Supplementary Table 6). The total
number of COVID-19 side effects is 6123, and the number of side effects is 1344, whereas
the number of common side effects is 240. The common side effects include alveolitis,
transplant, haemorrhage, back pain, bursitis, dialysis, and many more.
Recognising the COVID-19 target (see Supplementary Table 7) is necessary because a
particular drug like ruxolitinib will exert biological activity through physical binding to the
target proteins and understanding the action mechanism. The total number of COVID-19
targets is 377, and the number of targets is 3, whereas the number of common targets is 3.
This module predicts the abnormal human gene expression level involved in the interaction
with ruxolitinib drug results listed in Supplementary Table 8.
A docking module follows SARS-CoV-2 targets, and the results are in Supplementary Table
9. A molecular docking approach to understanding the interactions between proteins and
small molecules is presented in this module using AutoDock Vina. The module also
calculates the binding affinity between proteins which are SARS CoV-2 targets and specific
drug ruxolitinib. A docking study of ruxolitinib against 23 proteins results in a binding
affinity assessment. The average binding affinity came out to be -6.56 KCal/mol. Amongst
the 5 highest interacting viral proteins with ruxolitinib are Nsp14, Npro, ORF3A, Nsp4, and
Nsp2 with -8.2, -7.9, -7.8, -7.7, and -7.5 Kcal/mol as their respective binding energies.
While on the other hand, Nsp1 and ORF6 had minimal binding energies of -3.4 and -4.7
KCal/mol, respectively. The histogram lists the distribution of binding affinities for viral
proteins in Supplementary Figure 4.
Similarly, when ruxolitinib is docked against human proteins (ACE2, TMPRSS2) and their
associated protein kinases (AAK1, JAK1/2, and GAK), we find the average binding energy
to be -6.55 kcal/mol. The output binding affinity values of the human proteins and their
associated protein kinases are listed in Supplementary Table 10. To better analyze the
binding affinity values obtained, Supplementary Figure 5 illustrates a histogram..
Another docking with protein kinases associated with human protein results is listed in
Supplementary Table 11. This particular module carries out molecular docking with 3
essential protein kinases, AAK1 GAK and JAK 1 and 2, and the binding affinities are -7.9,-7.9, and -8, respectively.
To better analyze the results of the binding affinity values,
Supplementary Figure 6 shows a histogram plot..
This module searches for the gene related to the ruxolitinib drug and gives the pathway in
which that particular gene is involved. The results for this module don't show any pathway
involved, which means the results are not satisfactory and are shown in Supplementary
Table 12. The Euclidean distance between the Ruxolitinib drug and SARS-CoV-2 disease
results are shown in Supplementary Table 13.
In this module, ruxolitinib drugs showing similar symptoms to COVID-19 symptoms results
are mentioned in Supplementary Table 14. The total number of COVID-19 symptoms is
105, and the number of symptoms is 8, whereas the number of common symptoms is 0.
Compilation of scores for all 13 modules is shown in Supplementary Table 15. We get the
final score in the range of 0 and 1 for almost all modules, except docking modules, which
give a score between 0 and 1, considering the cumulative score for the docked proteins
considered in the docking modules. Among the 13 modules, the ruxolitinib drug reported a
score of 1 in COVID-19 drug phenotype, ide-effect, target, gene expression, and
interaction with the AAK1, GAK, JAK2, and ACE2 modules which means that this drug
has little potential to be used as COVID-19 repurposed drug. Based on the calculated
average score, we find a 75% probability for the Ruxolitinib to be considered a COVID-19
repurposed drug, and its calculation is tabulated in Supplementary Table 16.
Supplementary Materials:
Ruxolitinib Supplementary Figures
Ruxolitinib Supplementary Tables
4. Conclusion
Ruxolitinib is an oral inhibitor of Jak 1 and 2 as well as a potential treatment for COVID-19
infection as a repurposed drug with all the results assembled and analysed by the
CoV-DrugX pipeline. However, it has a lot of side effects that clinical trials can examine.
Therefore, several clinical trials are going on o assess the efficacy and safety of ruxolitinib
in COVID-19 related symptoms. The scientific community is currently conductingextensive research in search of direct anti-viral drugs and supportive therapies to reduce the
fatal complications associated with COVID-19 infections.
Acknowledgement
Dr Kamal Rawal acknowledges the support provided by SERB, Department of Science and
Technology (Grant ID: CVD/2020/000842). The project involved the usage of
computational infrastructure (server etc.) provided by the Department of Biotechnology
(DBT), Ministry of Science and Technology Government of India (Grant ID:
BT/PRI7252/BID/7/708/2016) and Robert J. Kleberg Jr. and Helen C. Kleberg Foundation
and Baylor College of Medicine, Houston, Texas, USA. We are also thankful to Amity
University for the support provided during the conduct of the study.References
1.
Caocci G, Mulas O, Mantovani D, Costa A, Galizia A, Barabino L, Greco M, Murru
R, La Nasa G. Ruxolitinib does not impair humoral immune response to COVID-19
vaccination with BNT162b2 mRNA COVID-19 vaccine in patients with
myelofibrosis.
Annals
of
Hematology.
2021
Jul
24:1-3.
https://doi.org/10.1007/s00277-021-04613-w
2.
Carneiro DC, Sousa JD, Monteiro-Cunha JP. The COVID-19 Vaccine Development:
A
Pandemic
Paradigm.
Virus
Research.
2021
May
17:198454.
https://doi.org/10.1016/j.virusres.2021.198454
3.
Dotolo S, Marabotti A, Facchiano A, Tagliaferri R. A review on drug repurposing
applicable to COVID-19. Briefings in bioinformatics. 2021 Mar;22(2):726-41.
https://doi.org/10.1093/bib/bbaa288
4.
Ostojic A, Vrhovac R, Verstovsek S. Ruxolitinib: a new JAK1/2 inhibitor that offers
promising options for treatment of myelofibrosis. Future oncology. 2011
Sep;7(9):1035-43. https://doi.org/10.2217/fon.11.81
5.
Bagca BG, Avci CB. The potential of JAK/STAT pathway inhibition by ruxolitinib
in the treatment of COVID-19. Cytokine & growth factor reviews. 2020 Aug
1;54:51-61. https://doi.org/10.1016/j.cytogfr.2020.06.013
6.
Caocci G, La Nasa G. Could ruxolitinib be effective in patients with COVID-19
infection
at
risk
of
acute
respiratory
distress
syndrome
(ARDS)?.
https://doi.org/10.1007/s00277-020-04067-6
7.
Cao Y, Wei J, Zou L, Jiang T, Wang G, Chen L, Huang L, Meng F, Huang L, Wang
N, Zhou X. Ruxolitinib in treatment of severe coronavirus disease 2019
(COVID-19): A multicenter, single-blind, randomized controlled trial. Journal of
Allergy
and
Clinical
Immunology.
2020
Jul
1;146(1):137-46.
https://doi.org/10.1016/j.jaci.2020.05.019
8.
D’Alessio A, Del Poggio P, Bracchi F, Cesana G, Sertori N, Di Mauro D, Fargnoli
A, Motta M, Giussani C, Moro P, Vitale G. Low-dose ruxolitinib plus steroid in
severe
SARS-CoV-2
pneumonia.
Leukemia.
2021
Feb;35(2):635-8.
https://doi.org/10.1038/s41375-020-01087-z
9.
Villarino AV, Kanno Y, Ferdinand JR, O’Shea JJ. Mechanisms of Jak/STAT signaling
in immunity and disease. The Journal of Immunology. 2015 Jan 1;194(1):21-7.
https://doi.org/10.4049/jimmunol.140186710.
Garrido-Trigo A, Salas A. Molecular structure and function of Janus kinases:
implications for the development of inhibitors. Journal of Crohn's and Colitis. 2020
Jul;14(Supplement_2): S713-24. https://doi.org/10.1093/ecco-jcc/jjz206
11.
Seif F, Khoshmirsafa M, Aazami H, Mohsenzadegan M, Sedighi G, Bahar M. The
role of JAK-STAT signaling pathway and its regulators in the fate of T helper cells.
Cell
communication
and
signaling.
2017
Dec;15(1):1-3.
https://doi.org/10.1186/s12964-017-0177-y
12.
Lee M, Rhee I. Cytokine signaling in tumor progression. Immune network. 2017
Aug;17(4):214. https://doi.org/10.4110/in.2017.17.4.214
13.
Sinha R, Preeti P. Cov-drugx Pipeline for Covid-19 Drug Repurposing.
https://doi.org/10.31219/osf.io/whka3
14.
Singh P, Sinha R, Nath SK, Preeti P, Kumari P. COV-DOCK server: A web server
for COVID-19 ligand-target docking. https://doi.org/10.31219/osf.io/x2ky5
15.
Vannucchi AM, Sordi B, Morettini A, Nozzoli C, Poggesi L, Pieralli F, Bartoloni A,
Atanasio A, Miselli F, Paoli C, Loscocco GG. Compassionate use of JAK1/2
inhibitor ruxolitinib for severe COVID-19: a prospective observational study.
Leukemia. 2021 Apr;35(4):1121-33. https://doi.org/10.1038/s41375-020-01018-y
16.
Kaplanski G, Bontemps D, Esnault P, Blasco V, Carvelli J, Delarbre D, Cauchois R,
Forel JM, Papazian L. Combined Anakinra and Ruxolitinib treatment to rescue
extremely ill COVID-19 patients: A pilot study. Autoimmunity Reviews. 2021
Feb;20(2):102726. https://dx.doi.org/10.1016%2Fj.autrev.2020.102726
17.
Barbui T, Vannucchi AM, Alvarez-Larran A, Iurlo A, Masciulli A, Carobbio A,
Ghirardi A, Ferrari A, Rossi G, Elli E, Andrade-Campos MM. High mortality rate in
COVID-19 patients with myeloproliferative neoplasms after abrupt withdrawal of
ruxolitinib.
Leukaemia
a
based
on.
2021
Feb;35(2):485-93.
https://doi.org/10.1038/s41375-020-01107-y
Built a first integrated pipeline & machine learning based resource for analysis of
mobile genetic elements and mutations in cancers and other diseases
18.
Rawal K, Ramaswamy R. Genome-wide analysis of mobile genetic element
insertion
sites.
Nucleic
acids
https://doi.org/10.1093/nar/gkr337
research.
2011
Sep
1;39(16):6864-78.19.
Mandal PK, Rawal K, Ramaswamy R, Bhattacharya A, Bhattacharya S.
Identification of insertion hot spots for non-LTR retrotransposons: computational
and biochemical application to Entamoeba histolytica. Nucleic acids research. 2006
Nov 1;34(20):5752-63. https://doi.org/10.1093/nar/gkl710
20.
Dev BB, Malik A, Rawal K. Detecting motifs and patterns at mobile genetic element
insertion site. Bioinformation. 2012;8(16):777. doi: 10.6026/97320630008777
21.
Rawal K, Dorji S, Kumar A, Ganguly A, Grewal AS. Identification and
characterization of MGEs and their insertion sites in the gorilla genome. Mobile
genetic elements. 2013 Jul 8;3(4):e25675. https://doi.org/10.4161/mge.25675
22.
Rawal K, Priya A, Malik A, Bahl R, Ramaswamy R. Distribution of MGEs and their
insertion sites in the Macaca mulatta genome. Mobile genetic elements. 2012 May
1;2(3):133-41. https://doi.org/10.4161/mge.21074
23.
Bakre AA, Rawal K, Ramaswamy R, Bhattacharya A, Bhattacharya S. The LINEs
and SINEs of Entamoeba histolytica: comparative analysis and genomic distribution.
Experimental
parasitology.
2005
Jul
1;110(3):207-13.
https://doi.org/10.1016/j.exppara.2005.02.009
Developed the first molecular network on human obesity through screening >25
million PubMed records, gene expression databases, clinical studies, drug side
effects and other information resources. Built a new text mining system and machine
learning model for semi-automated screening of literature records with a high F
score.
24.
Jagannadham J, Jaiswal HK, Agrawal S, Rawal K. Comprehensive map of
molecules implicated in obesity. PLoS One. 2016 Feb 17;11(2):e0146759.
https://doi.org/10.1371/journal.pone.0146759
25.
Jagannadham J, Jaiswal HK, Rawal K. Deciphering relationships in disease
networks using computational approaches: Fatty Liver, PCOD, Osteoarthritis,
cholelithiasis & hyperlipidemia. CODEN (USA): IJPRIF, ISSN.:0974-4304.
26.
Jagannadham, J., Jaiswal, H.K., Agarwal, S., Rawal, K., Biomedical Text Mining of
Obesity, Diabetes and hypertension genes. International Journal of Pharmaceutical
Sciences Review and Research. vol 33(2), 182-186, 2015.27.
Agrawal, S., Rawal, K., Sahu, A., Mahajan, S., Garg, P. and Bahl, R., "To find gene
distributions in PubMed abstracts using Perl software", Journal of Pharmacy
Research 2013.
28.
Jaiswal, H.K., Rawal, K., Jaganadham, J., Agrawal, S., “Evaluation of inhibition
activity of Tetrahydrolipstatin analogues on Diacylglycerol lipase alpha using
In-silico techniques”. Journal of Pharmacy Research, vol.5, no.6, pp. 3473-3477,
2012.
Built a new system for finding the role of microRNAs in heart development and
heart diseases by integrating large-scale experimental data with computational and
comparative approaches. We detected 353 known and 703 novel miRNAs involved
in heart development. The target mRNAs were appeared to be enriched with genes
related to cell cycle, apoptosis, signalling pathways, extracellular remodelling,
metabolism, chromatin remodelling and transcriptional regulators.
29.
Rustagi Y, Jaiswal HK, Rawal, K., Kundu GC, Rani V (2015). Comparative
Characterization of Cardiac Development Specific microRNAs: Fetal Regulators for
Future. PLoS ONE.10(10): e0139359. https://doi.org/10.1371/journal.pone.0139359
30.
Gupta, R., Soni, Patnaik, Sood, I., Singh, R., Rawal, K., Rani, V. High AU content:
A Signature of Upregulated miRNA in Cardiac Diseases, Bioinformation, vol. 3,
pp.132-135, 2010
Vaccine Development
31.
Abbasi, B. A., Saraf, D., Sharma, T., Sinha, R., Singh, S., Gupta, P. Rawal, K. (2020,
April 8). Identification of vaccine targets & design of vaccine against SARS-CoV-2
coronavirus
using
computational
and
deep
learning-based
approaches.
https://doi.org/10.31219/osf.io/f8zyw
32.
Kamal Rawal, v, Abbasi, B. A., et al. (2020). Design a multi-epitope Chagas disease
vaccine by computational analysis of the Trypanosoma cruzi CL Brenner proteome.
(Communicated)
33.
Rawal k, Sinha R et al. (2020) Vaxi – DL: A web-based Deep Learning (DL) server
to identify Potential Vaccine Candidates, (Bioinformatics- communicated)
34.
COVID-1935.
Jethani B., Rawal, K. et al. (2020). Clinical Characteristics and Remedy Profile of
Patients with COVID-19: Retrospective Cohort Study, Accepted (In Press)
36.
Rawal, K., Sinha R et al. (2020) To Study the Effect of Unconventional Treatment
Protocol on COVID-19 patients in Delhi using AI-based techniques (Lancet-
communicated)
37. Machine Learning
38. Rawal, K., Khurana T, Sharma H, . 2019. An extensive survey of molecular docking
tools and their applications using text mining and deep curation strategies. PeerJ
Preprints7:e27538v1. https://doi.org/10.7287/peerj.preprints.27538v1
Established the new framework/portal of "obesity treatment" and other diseases such
as type 2 diabetes and hypertension among the people living sedentary lifestyles by
engaging relevant community sections using social networks, data science systems,
machine learning, sensors and mobile apps. The system is being used by general
public as a social service initiative.
39.
Development of a Web Based Weight Loss Programme. K. Rawal, P. Gaur and K.
Kashive, LAP LAMBERT Academic Publishing GmbH & Co. KG, Saarbrücken
Germany, October, 2014
40.
Developing Networks in Obesity using Text Mining. K. Rawal, S. Agarwal and J.
Jagannadham, LAP LAMBERT Academic Publishing GmbH & Co. KG,
Saarbrücken Germany, September, 2014.