ChemRxiv
These are preliminary reports that have not been peer-reviewed. They should not be regarded as conclusive, guide clinical practice/health-related behavior, or be reported in news media as established information. For more information, please see our FAQs.
target2drug.pdf (364.98 kB)

Target2drug : A Novel Programmatic Workflow to Automate in Silico Drug Discovery

preprint
submitted on 19.11.2020, 19:37 and posted on 23.11.2020, 09:13 by Ben Geoffrey A S, Rafal Madaj, Akhil Sanker, Pavan Preetham Valluri, Judith Gracia, Harshmeet Singh
As the Big Data and Artificial Intelligence (AI) revolution continues to affect every area of our lives, it’s influence is also exerted in the areas of bioinformatics, computational biology and drug discovery. Machine/Deep Learning tools have been developed to predict compounds-drug target interactions and the vice-versa process of predicting target interactions for an compound. In our presented work, we report a programmatic tool, which incorporates many features of the bioinformatics, computational biology and AI-driven drug discovery revolutions into a single workflow assembly. When a user is required to identify drugs against a new drug target, the user provides target signatures in the form of amino acid sequence of the target or it’s corresponding nucleotide sequence as input to the tool and the tool carries out a BLAST protocol to identify known protein drug targets that are similar to the new target submitted by the user and collects data linked to the target involving, active compounds against the target, the activity value and molecular descriptors of active compounds to perform QSAR modelling and to generate drug leads with predictions from the validated QSAR model. The tool performs an In-Silico modelling to generate In-Silico interaction profiles of compounds generated as drug leads and the target and stores the results in the working folder of the user. To demonstrate the use of the tool, we have carried out a demonstration with the target signatures of the current pandemic causing virus, SARS-CoV 2. However the tool can be used against any target and is expected to help in growing our knowledge graph of targets and interacting compounds.

History

Email Address of Submitting Author

bengeof@gmail.com

Institution

University of Madras

Country

India

ORCID For Submitting Author

0000-0001-6545-6314

Declaration of Conflict of Interest

No conflict of interest to disclose

Exports