The high-throughput technologies of combinatorial chemistry and high-throughput screening have caused an explosion in the amount of data that pharmaceutical companies have available to them in the early stages of drug discovery. These large datasets are frequently analysed with machine learning tools and techniques. In this work, kernel-based machine learning algorithms are assessed and developed for virtual screening purposes using a wide range of molecular representations, and recommendations for improving the accuracy or the activity models are made.
| Identifer | oai:union.ndltd.org:bl.uk/oai:ethos.bl.uk:498104 |
| Date | January 2007 |
| Creators | Fischer, Andrew Martin |
| Publisher | London School of Economics and Political Science (University of London) |
| Source Sets | Ethos UK |
| Detected Language | English |
| Type | Electronic Thesis or Dissertation |
Page generated in 0.002 seconds