Learning to learn how to design drugs

A key step in developing a new drug is to learn quantitative structure activity relationships (QSARs). These are mathematical functions that predict how well chemical compounds will act as drugs. QSARs are used to guide the synthesis of new drugs.

The current situation is:
1) There is a vast range of approaches to learning QSARs.
2) It is clear from theory and practice that the best QSAR approach depends on the type of problem.
3) Currently the QSAR scientist has little to guide her/him on which QSAR approach to choose for a specific problem.

We therefore propose to make a step-change in QSAR research. We will utilise newly available public domain chemoinformatic databases, and in-house datasets, to systematically run extensive comparative QSAR experiments. We will then generalise these results to learn which target-type/ compound-type/ compound-representation /learning-method combinations work best together.

We do not propose to develop any new QSAR method. Rather, we will learn how to better apply existing QSAR methods. This approach is called "meta-learning", using machine learning to learn about QSAR leaning.

We will make the knowledge we learn publically available to guide and improve future QSAR learning.

Knowledge Production for Better Drug Design

The proposal is an ambitious one: its goal to change the way drug-design research is done, and to make it more efficient and cost-effective.

The most important deliverable of the proposal is to produce knowledge (QSAR-KB) about how to better apply quantitative structure activity (QSAR) methods for drug design. The beneficiaries of this knowledge will drug design practitioners both in industry and the increasing number in the public sector.

We will communicate this knowledge to these beneficiaries by:
1) Publishing in high-impact journals.
2) Talking at drug-design conferences.
3) Project Website

The other project deliverables will also be of direct utility to drug design beneficiaries as they will be made openly available. These will enable drug-designers to:
1) Better develop and evaluate new QSAR methods.
2) Develop their own meta-QSAR systems for application to their own commercially sensitive or proprietary chemoinformatic databases.
To achieve these applications of the project deliverable we will actively seek to transfer our knowledge and knowhow about meta-learning to the drug-design community.

We have excellent contacts with the pharmaceutical industry, which we will use to ensure that our research is exploited commercially. ALH is leading the UK partners in the IMI Lead Factory consortium (Dundee, Oxford and Biocity Scotland), which expects to be finalized by the end of 2012. The IMI Lead Factory project is a 160 Million euro public-private consortium consisting of seven major Pharmaceutical companies that proposed to offer 120 industrial scale HTS projects to European academic over the next 5 years with the creation of a screening file of 500,000 novel compounds.

In addition 2012 ALH founded, Ex Scientia Ltd., a new spin out company focusing on developing novel machine learning methods to automate drug design (Besnard et al., Nature, In Press; PCT/GB2010/05194,0).


Broader economic benefits

The problem of how best to learn QSARs is of great industrial and medical importance. Drug development is arguably the most important applications of science in the UK. The average cost to bring a new drug to market is ~£500 million. A successful drug can earn £billions a year, and as patent protection is time-limited, even an extra week of protection can be of great financial significance. The UK (both academia and industry) is a leader in QSAR research and chemoinformatics in general as can be seen by its publication record. This project aims to help to maintain this lead.


Health and health sector benefits

The deliverables of the proposal will, over the medium term, lead to the faster development of better, and cheaper pharmaceuticals. This will increase the effectiveness of health services. Cost reduction in the delivery of existing services thus freeing up resources to use elsewhere in the health system;


Research capacity building

The project will train three PDRAs in areas of crucial importance to the future science and industry: drug-design, machine-learning, and the semantic web.