Learning Type Extension Trees for Metal Bonding State Prediction

Paolo Frasconi, Manfred Jaeger, Andrea Passerini

Research output: Contribution to book/anthology/report/conference proceedingArticle in proceedingResearch

Abstract

Type Extension Trees (TET) have been recently introduced as an expressive

representation language allowing to encode complex combinatorial features

of relational entities. They can be efficiently learned with a greedy search

strategy driven by a generalized relational information gain and a discriminant

function. In predicting the metal bonding state of proteins, TET achieve significant

improvements over manually curated motifs, and the expressiveness of combinatorial

features significantly contributes to such performance. Preliminary collective

classification results seem to indicate it as a promising direction for further

research.

Original languageEnglish
Title of host publicationStReBio Workshop online proceedings
Number of pages4
Publication date2008
Publication statusPublished - 2008
EventWorkshop on Statistical and Relational Learning in Bioinformatics - Antwerp, Belgium
Duration: 19 Sep 200819 Sep 2008

Conference

ConferenceWorkshop on Statistical and Relational Learning in Bioinformatics
CountryBelgium
CityAntwerp
Period19/09/200819/09/2008

    Fingerprint

Cite this

Frasconi, P., Jaeger, M., & Passerini, A. (2008). Learning Type Extension Trees for Metal Bonding State Prediction. In StReBio Workshop online proceedings