[[DW: very large-scale models (vs. VLSI): markov logic network on customer networks, Innovation Award Talk by Pedro Domingos, KDD 2014 ]]
http://homes.cs.washington.edu/~pedrod/803
also, it has biological applications like:
Markov Logic Networks in the Analysis of Genetic Data
https://www.systemsbiology.org/markov-logic-networks-analysis-genetic-data
– apply to metabric consortium
– 17K clin feat. + ~50K gene exp. + ~30K CNVs ==to-predict==> 10yr survival – uses CI instead of AUC for real valued predictions
– combine collaboration & competition to beat the baseline (cox regression on only clinical features)
– mol. feat. on their own don’t work well due to the curse of dimensionality – features more important than the learning method
http://www.ploscompbiol.org/article/info%3Adoi%2F10.1371%2Fjournal.pcbi.1003047
Pandey mentions: Cancer Survival Analysis through
Competition-Based…Modeling, using Human #Ensembles
http://www.ploscompbiol.org/article/info%3Adoi%2F10.1371%2Fjournal.pcbi.1003047 #kdd2014
contains proteomics on some of the TCGA samples
http://proteomics.cancer.gov/programs/cptacnetwork
http://www.fenyolab.org/tools/tools.html
QT:{{”
QUILTS is a tools for creating sample specific protein sequence databased. It uses genomic and transcriptomic information to create comprehensive sample specific protein database that supports the identification of novel proteins, resulting from single nucleotide variants, splice variants and fusion genes.
“}}
Similar to the alleleseq personal genome for proteomics
Fenyo: Nice discussion of Quilts Tools for making up sample specific protein databases to identify novel proteins in cancer. Similar to personal genome construction #kdd2014 #biokdd
Fenyo: Quilts Tools for sample-specific DBs to identify novel proteins in cancer. Similar to personal genome construction #kdd2014 #biokdd
metabric consortium
gene expression & copy number data available and survival data (on request) for the 4 main breast cancer types (basal, her2 , luma, lumb)
similar to TCGA but from the UK
Allows construction of discovery & validation sets to compare segregation of survival with mRNA level
compare segreg. of survival with inferred protein activity v mRNA level
Related to BIP KDD talk, dealing with overlapping biclusters http://www.biomedcentral.com/1471-2105/15/130