Abstract:
Healthcare drug discovery is known to be a time-consuming and expensive process, which traditionally requires manual effort to filter through available data and validate ...Show MoreMetadata
Abstract:
Healthcare drug discovery is known to be a time-consuming and expensive process, which traditionally requires manual effort to filter through available data and validate the findings in a laboratory, after which there is a long road to clinical trials and final approval. The expenditure, time, and effort put into coming up with a healthcare drug is of such a huge magnitude, that it raises the cost, which makes it harder to acquire for public. Computational methods aided by robust software engineering practices can significantly help speed up and ease drug discovery. A lot of work has been done on applying such methods, like AI in target-based drug discovery. But when it comes to drugs without a clear target, not much has been done in that regard. The currently available tools and techniques that can aid target-less drug discovery are generally they lack versatility and customizability. Hence, this work aims to propose a target-less drug discovery pipeline, based on computational methods backed by current software engineering practices, which can fulfill this need and help empower pharmacists with a tool to pick suitable drug-like compounds having the ideal expected properties. This feature-rich pipeline has been developed keeping in mind the principles of the Feature Driven Development (FDD) model, to be able to systematically develop the several modules of this pipeline. It has also shown promising results in filtering candidates based on their pharmacological characteristics and physicochemical properties.
Date of Conference: 09-12 December 2021
Date Added to IEEE Xplore: 14 January 2022
ISBN Information: