|
The increasing availability of biological data from sources as diverse
as gene expression analysis, mass spectrometry, DNA sequencing and
protein structure determination provides an unprecedented opportunity
for machine learning approaches to computational molecular biology.
Efficient algorithms are demanded in order to deal with such data, as
well as techniques capable of learning from heterogeneous information,
and jointly addressing related tasks. Transparency is a major concern
to be traded-off and explanatory solutions are especially appealing
for the domain experts. Intelligent optimization schemes like reactive
search can be applied to deal with some of the most challenging
problems, like ab initio protein structure prediction. This special
session aims at bringing together researches from different fields of
machine learning and intelligent optimization working on computational
molecular biology, in order to discuss novel approaches to challenging
bioinformatics problems and interesting formalizations of new tasks.
To ensure extensive interaction among participants as well as
scientific quality and novelty of results, contributions to the
special session will be by invitation only, and no formal proceedings
will be published in order to allow for the most recent and
interesting results to be presented and discussed. Contributions will
be limited to a title and abstract, concerning either novel
unpublished work, interesting results recently published elsewhere, or
work in progress.
Session Chairs:
- Andrea Passerini, Università degli Studi di Firenze, Italy
- Roberto Battiti, Università degli Studi di Trento, Italy
- Mauro Brunato, Università degli Studi di Trento, Italy
|