Corresponding projections for orphan screening

Sven Giesselbach, Katrin Ullrich, Michael Kamp, Daniel Paurat, Thomas Gärtner

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

Abstract

We propose a novel transfer learning approach for orphan screening called corresponding projections. In orphan screening the learning task is to predict the binding affinities of compounds to an orphan protein, i.e., one for which no training data is available. The identification of compounds with high affinity is a central concern in medicine since it can be used for drug discovery and design. Given a set of prediction models for proteins with labelled training data and a similarity between the proteins, corresponding projections constructs a model for the orphan protein from them such that the similarity between models resembles the one between proteins. Under the assumption that the similarity resemblance holds, we derive an efficient algorithm for kernel methods We empirically show that the approach outperforms the state-of-the-art in orphan screening.
Original languageEnglish
Title of host publicationML4H: Machine Learning for Health, Workshop at NeurIPs 2018
EditorsSam Finlayson, Brett K Beaulieu-Jones
Place of PublicationSan Diego CA USA
PublisherNeural Information Processing Systems (NIPS)
Number of pages10
Publication statusPublished - 2018
Externally publishedYes
EventWorkshop on Machine Learning for Health at NeurIPs 2018 - Montreal, Canada
Duration: 8 Dec 20188 Dec 2018
https://ml4health.github.io/2018/

Conference

ConferenceWorkshop on Machine Learning for Health at NeurIPs 2018
Abbreviated titleML4H
Country/TerritoryCanada
CityMontreal
Period8/12/188/12/18
Internet address

Cite this