uu.seUppsala University Publications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Active machine learning for quantitative kinetic analyses of ligand cell-surface interactions.
Uppsala University, Disciplinary Domain of Science and Technology, Biology, Biology Education Centre.
2017 (English)Independent thesis Advanced level (professional degree), 20 credits / 30 HE creditsStudent thesis
Abstract [en]

In the analysis of a ligand-target interaction the kinetic constants are of high interest. Making a good estimation on the kinetic constants is governed by using the best model that describes the data the best. It also of great importance to choose experiments such that certainty on the kinetic constants increases to the highest degree possible. This project is part of a collaboration between UU (Cancer Pharmacology and Computational Medicine, Dept Medical Sciences) and Ridgeview Instruments AB in Uppsala with the aim to implement model selection procedure followed by a plotting of probability density maps, this is referred to as probability distribution of unknown kinetic interaction constants (PDUKC). The project also aims to implement an active learning algorithm to propose optimal experiments so that the parameter certainty increases. It is all implemented in the framework of Bayesian statistics. The implemented active learning algorithm shows promising results in terms of precision evaluation, but does not show any improved accuracy compared to random experimental sampling. The model selection in PDUKC performs well in low noise examples but struggles when noise is increased. It shows PDUKC got some promising potential in good visualization of the unknown kinetic constants.

Place, publisher, year, edition, pages
2017.
Series
UPTEC X, 17 027
National Category
Bioinformatics (Computational Biology)
Identifiers
URN: urn:nbn:se:uu:diva-331767OAI: oai:DiVA.org:uu-331767DiVA: diva2:1150084
Educational program
Molecular Biotechnology Engineering Programme
Supervisors
Examiners
Available from: 2017-10-23 Created: 2017-10-17 Last updated: 2017-10-23Bibliographically approved

Open Access in DiVA

No full text

By organisation
Biology Education Centre
Bioinformatics (Computational Biology)

Search outside of DiVA

GoogleGoogle Scholar

Total: 14 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf