Learning to learn how to design drugs
Lead Research Organisation:
University of Manchester
Department Name: Computer Science
Abstract
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.
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.
Planned Impact
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.
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.
Organisations
People |
ORCID iD |
Ross King (Principal Investigator) | |
Andrew Hopkins (Co-Investigator) |
Publications
Williams K
(2015)
Cheaper faster drug development validated by the repositioning of drugs against neglected tropical diseases.
in Journal of the Royal Society, Interface
Wang K
(2021)
NERO: a biomedical named-entity (recognition) ontology with a large, annotated corpus reveals meaningful associations through text embedding.
in NPJ systems biology and applications
Sadawi N
(2019)
Multi-task learning with a natural metric for quantitative structure activity relationship learning.
in Journal of cheminformatics
Panov P
(2016)
Generic ontology of datatypes
in Information Sciences
Orhobor O
(2020)
Predicting rice phenotypes with meta and multi-target learning
Orhobor O
(2020)
Predicting rice phenotypes with meta and multi-target learning
in Machine Learning
Olier I
(2021)
Transformational machine learning: Learning how to learn from many related scientific problems.
in Proceedings of the National Academy of Sciences of the United States of America
Description | I reported this in previous years! |
Exploitation Route | The partner company ExScientia is now worth £800M based on its AI and drug design experrtise. |
Sectors | Chemicals Pharmaceuticals and Medical Biotechnology |
Description | The results of all the base learning QSAR systems have been put online. It is one of the largest collections of machine learning results in the world. The SMEs ex scientia and Kinetic Discovery are working with the University of Manchester and Brunel University to develop machine learning for QSARs. Ex Scientia and KInetic now employ ~50 people and have deals with the Pharmaceutical industry worth >£800 million - £600M more than last year! |
First Year Of Impact | 2020 |
Sector | Chemicals,Pharmaceuticals and Medical Biotechnology |
Impact Types | Economic |
Title | ExScientia |
Description | ExScientia were a partner in this grant. They are now worth £800M based on their drug development partnerships. |
Type | Therapeutic Intervention - Drug |
Current Stage Of Development | Refinement. Clinical |
Year Development Stage Completed | 2021 |
Development Status | Under active development/distribution |
Impact | ExScientia were a partner in this grant. They are now worth £800M based on their drug development partnerships. |
Company Name | Zeroth Analytics Ltd |
Description | |
Year Established | 2021 |
Impact | SME |
Description | Horizons article |
Form Of Engagement Activity | A magazine, newsletter or online publication |
Part Of Official Scheme? | No |
Geographic Reach | International |
Primary Audience | Professional Practitioners |
Results and Impact | Ross King was interviewed for an article in Cartlidge, E. "Let the Robots do the tedious work", Horizons (Swiss magazine for Scientific Research); Vol 113; pg 10-11 |
Year(s) Of Engagement Activity | 2017 |
URL | http://www.snf.ch/SiteCollectionDocuments/horizonte/Horizonte_gesamt/SNSF_horizons_113_en.pdf |