Sumários
Lab #6 Unsupervised/Supervised Learning
23 novembro 2015, 14:00 • Ana Teresa Correia de Freitas
This laboratory will use the data from the article “Distinct types of diffuse large B-cell
lymphoma identified by gene expression profiling”, by Alizade et. Al., NATURE, VOL 403,
n. 3, 503-511, 2000, available at http://eps.upo.es/bigs/datasets.html.
From the diverse datasets available, select the reduced database, with 45 instances of
4026 genes each, in format ARFF (Reduced database (45 instances x 4026 genes) in
ARFF format, with two labelled classes (Germinal Centre, GCL, and Activated, ACL)
[1Mb]).
Program the K-Means algorithm
Use the Weka package to run: K-Mean; J48; Naive Bayes, NN
This work will take 2 weeks.
Biclustering
23 novembro 2015, 12:30 • Ana Teresa Correia de Freitas
Formalism
Lab 5 - Molecular phylogenetics
17 novembro 2015, 17:00 • Ana Teresa Correia de Freitas
Hierarchical clustering: UPGMA, single linkage, complete linkage. Neighbour joining method. Maximum parsimony method.
Molecular Phylogenetics
17 novembro 2015, 12:30 • Ana Teresa Correia de Freitas
Hierarchical clustering: UPGMA, single linkage, complete linkage. Neighbour joining method. Maximum parsimony method.
Lab 5 - Molecular phylogenetics
17 novembro 2015, 09:30 • Ana Teresa Correia de Freitas
Hierarchical clustering: UPGMA, single linkage, complete linkage. Neighbour joining method. Maximum parsimony method.