Combining Machine Learning, Molecular Dynamics and Membrane Biophysics to identify new therapeutics for the treatment of Tuberculosis

Lead Research Organisation: Imperial College London
Department Name: Chemistry

Abstract

Tuberculosis (TB) is currently one of the world's leading causes of mortality with 10 million new
cases reported in 2017 alone and 1.3 million deaths (Global Tuberculosis Report 2018 WHO), a
further complicating factor is the evolution of multi-drug and totally drug resistant strains. There is
an urgent need to develop effective new therapeutic agents to target TB and critical in this process
is the identification of a suitable protein to target. MmpL3 is a transmembrane protein which is
essential for the replication and viability of bacterial cells and therefore represents a suitable target.
The recent determination of the structure of MmpL3 from M. smegmatis (Cell 2019; 176: 636-648)
provides the starting point for developing new therapeutic strategies. Molecular Dynamics (MD)
simulations will be utilised to construct a model of MmpL3 for M. tuberculosis (Mtb) facilitating
investigation of drug-protein interactions, known inhibitors will be modelled at physiological
conditions with the protein embedded in a realistic representation of the cell membrane. Validation
of the computational model will be achieved through the investigation of the structure and
mechanics of model membranes, in which Mtb MmpL3 is embedded, via X-ray diffraction and light
microscopy. Identification of the binding modes of know inhibitors to Mtb MmpL3 and known drug
resistant mutants will be used as input into Machine Learning (ML) to generate rules to search large
compound libraries, in particular the Zinc database, to identify suitable compounds to screen. This project will provide the student with a broad range of skills, computational modelling, machine
learning, protein expression and purification and experimental membrane biophysics.

Planned Impact

Addressing UK skills demand: The most important impact of the CDT will be to train a new generation of Chemical Biology PhD graduates (~80) to be future leaders of enterprise, molecular technology innovation and translation for academia and industry. They will be able to embrace the life science's industrialisation thereby filling a vital skills gap in UK industry. These students will be able to bridge the divide between academia/industry and development/application across the physical/mathematical sciences and life sciences, as well as the human-machine interfaces. The technology programme of the CDT will empower our students as serial inventors, not reliant on commercial solutions.
CDT Network-Communication & Engagement: The CDT will shape the landscape by bringing together >160 research groups with leading players from industry, government, tech accelerators, SMEs and CDT affiliates. The CDT is pioneering new collaboration models, from co-located prototyping warehouses through to hackathons-these will redefine industry-academic collaborations and drive technology transfer.
UK plc: The technologies generated by the CDT will produce IP with potential for direct commercial exploitation and will also provide valuable information for healthcare and industry. They will redefine the state of the art with respect to the ability to make, measure, model and manipulate molecular interactions in biological systems across multiple length scales. Coupled with industry 4.0 approaches this will reduce the massive, spiralling cost of product development pipelines. These advances will help establish the molecular engineering rules underlying challenging scientific problems in the life sciences that are currently intractable. The technology advances and the corresponding insight in biology generated will be exploitable in industrial and medical applications, resulting in enhanced capabilities for end-users in biological research, biomarker discovery, diagnostics and drug discovery.
These advances will make a significant contribution to innovation in UK industry, with a 5-10 year timeframe for commercial realisation. e.g. These tools will facilitate the identification of illness in its early stages, minimising permanent damage (10 yrs) and reducing associated healthcare costs. In the context of drug discovery, the ability to fuse the power of AI with molecular technologies that provide insight into the molecular mechanisms of disease, target and biomarker validation and testing for side effects of candidates will radically transform productivity (5-10 yrs). Developments in automation and rapid prototyping will reduce the barrier to entry for new start-ups and turn biology into an information technology driven by data, computation and high-throughput robotics. Technologies such as integrated single cell analysis and label free molecular tracking will be exploitable for clinical diagnostics and drug discovery on shorter time scales (ca.3-5 yrs).
Entrepreneurship & Exploitation: Embedded within the CDT, the DISRUPT tech-accelerator programme will drive and support the creation of a new wave of student-led spin-out vehicles based on student-owned IP.
Wider Community: The outreach, responsible research and communication skill-set of our graduates will strengthen end-user engagement outside their PhD research fields and with the general public. Many technologies developed in the CDT will address societal challenges, and thus will generate significant public interest. Through new initiatives such as the Makerspace the CDT will spearhead new citizen science approaches where the public engage directly in CDT led research by taking part in e.g hackathons. Students will also engage with a wide spectrum of stakeholders, including policy makers, regulatory bodies and end-users. e.g. the Molecular Quarter will ensure the CDT can promote new regulatory frameworks that will promote quick customer and patient access to CDT led breakthroughs.

Publications

10 25 50

Studentship Projects

Project Reference Relationship Related To Start End Student Name
EP/S023518/1 30/09/2019 30/03/2028
2277910 Studentship EP/S023518/1 30/09/2019 31/12/2023 Sara Cioccolo