We are witnessing the growing menace of both increasing cases of drug-sensitive and drug-resistant Mycobacterium tuberculosis (Mtb) strains and the challenge to produce the first new tuberculosis (TB) drug in well over 40 years. The TB community, having invested in extensive high-throughput screening efforts, is faced with the question of how to optimally leverage this data in order to move from a hit to a lead to a clinical candidate and potentially a new drug. Complementing this approach, yet conducted on a much smaller scale, cheminformatic techniques have been leveraged. We suggest these computational approaches should be more optimally integrated in a workflow with experimental approaches to accelerate TB drug discovery. This Small Business Technology Transfer Phase II project entitled """"""""Identification of novel therapeutics for tuberculosis combining cheminformatics, diverse databases and logic-based pathway analysis"""""""" describes the development of software that will facilitate new drug discovery efforts for Mycobacterium tuberculosis (TB) and the progression of molecules discovered with it as mimics for substrates of enzymes and their in vivo essential genes. In phase 1 we illustrated the concept of loosely marrying the cheminformatic and pathways database that resulted in two compounds as proposed mimics of 2 D-fructose 1,6 bisphosphate with activity against Mtb (MIC 20 and 40mg/ml). In phase II via an API we will link the knowledge in CDD, SRI and other databases and tools seamlessly. A researcher will be able to investigate molecules, targets, pathways and then select metabolites or other molecules for pharmacophore analysis, scoring with TB machine learning models and ADME and drug-likeness assessment from within one interface. This tool will be used to aid the identification of novel therapeutics for tuberculosis and be useful for hypotheses testing, knowledge sharing, data archiving, data mining and drug discovery. We will make CDD into a mobile application such that the generalized workflow in this project can be performed anywhere. We present promising preliminary work which resulted in two active compounds, that suggests phase II support of the mimic strategy to identify compounds of interest for TB would be a viable strategy. This proposal balances software development, database development and drug discovery activities in order to achieve our goals. We expect this product could be quickly applied to other infectious diseases which have a great societal impact and as a stretch goal we will endeavor to demonstrate this.

Public Health Relevance

We propose to develop an integrated system to facilitate new drug discovery efforts for TB using novel logical inference techniques developed by scientists at SRI International, linked with knowledge which has been assembled by the curation of diverse biological data types and computational prediction by Collaborative Drug Discovery (CDD). This tool will be used to aid the identification of novel therapeutics for tuberculosis by combining cheminformatics, diverse databases and logic-based pathway analysis. We will demonstrate the utility of the tool (available also as a mobile application) and overall workflow ourselves by discovering and developing compounds for TB and other infectious diseases.

National Institute of Health (NIH)
National Institute of Allergy and Infectious Diseases (NIAID)
Small Business Technology Transfer (STTR) Grants - Phase II (R42)
Project #
Application #
Study Section
Special Emphasis Panel (ZRG1-IMST-K (14))
Program Officer
Lacourciere, Karen A
Project Start
Project End
Budget Start
Budget End
Support Year
Fiscal Year
Total Cost
Indirect Cost
Collaborative Drug Discovery, Inc.
United States
Zip Code
Lane, Thomas; Russo, Daniel P; Zorn, Kimberley M et al. (2018) Comparing and Validating Machine Learning Models for Mycobacterium tuberculosis Drug Discovery. Mol Pharm 15:4346-4360
Ekins, Sean; Spektor, Anna Coulon; Clark, Alex M et al. (2017) Collaborative drug discovery for More Medicines for Tuberculosis (MM4TB). Drug Discov Today 22:555-565
Ekins, Sean; Perryman, Alexander L; Clark, Alex M et al. (2016) Machine Learning Model Analysis and Data Visualization with Small Molecules Tested in a Mouse Model of Mycobacterium tuberculosis Infection (2014-2015). J Chem Inf Model 56:1332-43
Djaout, Kamel; Singh, Vinayak; Boum, Yap et al. (2016) Predictive modeling targets thymidylate synthase ThyX in Mycobacterium tuberculosis. Sci Rep 6:27792
Litterman, Nadia K; Ekins, Sean (2015) Databases and collaboration require standards for human stem cell research. Drug Discov Today 20:247-54
Perryman, Alexander L; Yu, Weixuan; Wang, Xin et al. (2015) A virtual screen discovers novel, fragment-sized inhibitors of Mycobacterium tuberculosis InhA. J Chem Inf Model 55:645-59
Ekins, Sean; Madrid, Peter B; Sarker, Malabika et al. (2015) Combining Metabolite-Based Pharmacophores with Bayesian Machine Learning Models for Mycobacterium tuberculosis Drug Discovery. PLoS One 10:e0141076
Ekins, Sean; Casey, Allen C; Roberts, David et al. (2014) Bayesian models for screening and TB Mobile for target inference with Mycobacterium tuberculosis. Tuberculosis (Edinb) 94:162-9
Ekins, Sean; Clark, Alex M; Swamidass, S Joshua et al. (2014) Bigger data, collaborative tools and the future of predictive drug discovery. J Comput Aided Mol Des 28:997-1008
Ekins, Sean; Pottorf, Richard; Reynolds, Robert C et al. (2014) Looking back to the future: predicting in vivo efficacy of small molecules versus Mycobacterium tuberculosis. J Chem Inf Model 54:1070-82

Showing the most recent 10 out of 11 publications