Thesis
The application of active learning to the lead optimisation of a novel series of antimalarials
- Creator
- Rights statement
- Awarding institution
- University of Strathclyde
- Date of award
- 2022
- Thesis identifier
- T17029
- Person Identifier (Local)
- 201773522
- Qualification Level
- Qualification Name
- Department, School or Faculty
- Abstract
- Malaria remains a significant global health problem, affecting the lives of hundreds of millions of people each year. Plasmodium falciparum (the parasitic species responsible for almost all malaria-related deaths) has developed resistance to front-line treatment, threatening to reverse decades of progress made towards eradication of the disease. To overcome this, novel medicines that are effective against resistant strains are required urgently. During previous work at GSK Tres Cantos, a series of aminoquinazolines were discovered that showed potential of meeting this medical need. The research reported in this thesis focussed on lead optimisation of the series by applying active learning – an iterative form of machine learning whereby the model identifies data points from which it would learn most, in order to maximise improvement in prediction accuracy. To evaluate the current effectiveness of this technology when applied prospectively to a live drug discovery programme, this project was conducted independently and in parallel to conventional lead optimisation efforts by the Team in Tres Cantos. Both the conventional medicinal chemistry strategy and the active learning strategy identified significantly improved compounds with respect to the initial lead. The best compounds from both efforts were similar both in terms of their structure and properties. However, the active learning method reached this comparable end-point with the synthesis and testing of one-third the number of compounds and with one-third the number of chemists over the same time period. Hence, this thesis demonstrates that active learning can increase the efficiency of lead optimisation and, as such, could help to tackle declining R&D productivity, a problem the pharmaceutical industry has been faced with over the last two decades.
- Advisor / supervisor
- Tape, Daniel
- Hirst, David
- Murphy, John
- Resource Type
- Note
- Previously held under moratorium in Chemistry Department (GSK) from 6/6/2022 until 1/8/2024
- DOI
- Funder
- Embargo Note
关系
项目
| 缩略图 | 标题 | 上传日期 | 公开度 | 行动 |
|---|---|---|---|---|
|
|
File | 2024-08-07 | 限制运用 |