Development and Extension of Cheminformatics Techniques for Integration of Diverse Data to Enhance Drug Discovery

Public Deposited
Analytics

Downloadable Content

Download PDF
Request Version for Screen Reader
Last Modified
  • March 20, 2019
Creator
  • Grulke, Christopher M.
    • Affiliation: Eshelman School of Pharmacy, Division of Chemical Biology and Medicinal Chemistry
Abstract
  • The scientific community has fallen headlong into the age of data. With the available crop of information available to scientists growing at an exponential pace, tools to harvest this data and process it into knowledge are needed. This blanket statement is nowhere more true than in drug discovery today. The increasing quantities of bioactivity and protein crystallographic data provide key information capable of improving the state of virtual screening. The CoLiBRI methodology attempts to learn from the large knowledge base of protein-ligand interactions to discover a comprehensive model capable of filtering large libraries very quickly using only a protein structure. This modeling procedure has been greatly expanded to encompass a wide range of descriptor techniques and to use advanced statistical methods of multidimensional mapping. The growth of virtual screening methods (including CoLiBRI) has provided a plethora of options to cheminformaticians with little guidance on their strengths and weaknesses. This oversight in methodology benchmarking should be addressed to reduce the time and effort wasted applying subpar screening protocols. To attend to this issue, we developed a benchmark dataset that will enable a flood of methodology experimentation and validation. The recent generation of gene expression data and cancer cell growth inhibition data enable identification of signatures of cellular resistance. These signatures can be used as validated prognostic markers to guide patient management thereby fueling the personalization of cancer treatment. From the available data, we have derived hypothetical biomarkers of multidrug resistance and a flood of links between gene expression and chemical specific resistance that require experimental validation. The increasing capabilities of cheminformatics techniques require dissemination to the public to produce the greatest impact. We have therefore developed a web portal providing cheminformatics software and models to fuel public drug discovery efforts.
Date of publication
DOI
Resource type
Rights statement
  • In Copyright
Note
  • " ... in partial fulfillment of the requirements for the degree of Doctor of Philosophy in the School of Pharmacy (Division of Medicinal Chemistry and Natural Products)."
Advisor
  • Tropsha, Alexander
Language
Publisher
Place of publication
  • Chapel Hill, NC
Access right
  • Open access
Date uploaded
  • March 18, 2013

Relations

Parents:

This work has no parents.

Items

Thumbnail Title Date Uploaded Visibility Actions
file details 2019-04-10 Public Download