Collaborative drug discovery for More Medicines for Tuberculosis (MM4TB)

Abstract

Neglected disease drug discovery is generally poorly funded compared with major diseases and hence there is an increasing focus on collaboration and precompetitive efforts such as public–private partnerships (PPPs). The More Medicines for Tuberculosis (MM4TB) project is one such collaboration funded by the EU with the goal of discovering new drugs for tuberculosis. Collaborative Drug Discovery has provided a commercial web-based platform called CDD Vault which is a hosted collaborative solution for securely sharing diverse chemistry and biology data. Using CDD Vault alongside other commercial and free cheminformatics tools has enabled support of this and other large collaborative projects, aiding drug discovery efforts and fostering collaboration. We will describe CDD's efforts in assisting with the MM4TB project.

Comparing and Validating Machine Learning Models for Mycobacterium tuberculosis Drug Discovery

“…The discovery of new TB drug candidates with novel mechanisms of action and a shortened length of treatment is of fundamental importance. Much of the effort has resorted to large high-throughput screens in academia, industry and efforts funded by the NIH and the Bill and Melinda Gates Foundation 3–5 . However, the translation of in vitro active compounds coming from these screens and moving them in vivo is fraught with difficulty in terms of finding molecules that balance activity versus good physicochemical and pharmacokinetic properties.…”

Big data and machine learning for materials science

“…A highly relevant issue that can strongly benefit from novel procedures standing on big data and classical ML methods is drug discovery for neglected diseases. Cheminformatics tools have been assembled into a web-based platform in the project More Medicines for Tuberculosis (MM4TB), funded by the European Union [ 104 ]. The project relies on classical ML methods ( Bayesian modelling , SVMs, random forest , and bootstrapping ), collaboratively working on data acquired from the screening of natural products and synthetic compounds against the microorganism Mycobacterium tuberculosis .…”

The Benefits of In Silico Modeling to Identify Possible Small-Molecule Drugs and Their Off-Target Interactions

“…This technique is already proving beneficial to investigations into drug repurposing, a relatively low-risk strategy where small molecules that are known to have therapeutic benefits and acceptable safety profiles are investigated to see if they can be applied to other conditions by exploiting drug repurposing databases such as the NCGC Pharmaceutical Collection [30]. A number of drug repurposing studies have already been published to demonstrate the potential of machine learning for exploiting information to identify novel molecular disease targets [31] and repurpose existing medications for the treatment of a range of conditions including lupus [32], neurodegenerative disorders [33] and tuberculosis [34]. As it becomes easier to collate and analyse more data it is expected that this technology can also make significant in-roads into combatting orphan diseases, which although rare still affect up to 350 million people worldwide [35].…”

“…[73], utilising not only standard methods and ideas, but also innovative concepts, approaches and algorithms, there are intrinsic problems that are related to how the research in this area is funded and how these efforts are rewarded. Whilst the pharmaceutical industry is engaged in data sharing and there are excellent examples of developing collaborative platforms for opensource drug discovery [34], their need to protect their intellectual property and not share all the data and software applications is understandable. However, due to the lack of appropriate funding, the efforts of the academic community often result in projects that are short-lived delivering sometimes ingenious software solutions that are frequently not finished and/or difficult to integrate into other relevant software platforms as the file formats and data storage are not standardized.…”