Discovering functional gene pathways associated with cancer heterogeneity via sparse supervised learning.
Shuichi KawanoTeppei ShimamuraAtsushi NiidaSeiya ImotoRui YamaguchiMasao NagasakiRyo YoshidaCristin G. PrintSatoru MiyanoPublished in: BIBM (2010)
Keyphrases
- supervised learning
- gene products
- gene ontology terms
- gene expression profiles
- gene expression
- differential expression
- gene ontology
- expression profiles
- gene selection
- related genes
- microarray
- functional analysis
- dna microarray
- gene function
- gene expression data
- genome wide
- biological pathways
- cancer classification
- gene sets
- microarray data
- gene interactions
- signaling pathways
- breast cancer
- training data
- high dimensional
- cancer diagnosis
- gene regulatory networks
- unsupervised learning
- gene expression analysis
- colon cancer
- biological entities
- high throughput
- training set
- genome scale
- active learning
- semi supervised
- gene expression data sets
- microarray datasets
- biological processes
- statistical significance
- regulatory networks
- gene expression datasets
- gene expression patterns
- cell lines
- protein protein interaction networks
- genomic data
- learning algorithm
- multiple instance learning
- gene clusters
- interaction networks
- saccharomyces cerevisiae
- reinforcement learning
- biomedical literature
- candidate genes
- cancer datasets
- machine learning
- biological networks
- systems biology
- prostate cancer
- lung cancer
- escherichia coli
- transcription factors
- data sets
- metabolic pathways