CS 229: Machine Learning, taught by Andrew Ng.
Automatically Detecting Banner Ads in Web Pages [PDF].
This paper describes AdZap, a Firefox browser plugin for
detecting and blocking advertisements on web pages. AdZap uses
a set of labeled training data collected from the user as
input to a supervised learning algorithm. The trained
algorithm then examines images embedded in HTML documents
shown to the user and hides images classified as
advertisements.
BMI 217: Translational Bioinformatics, taught by Atul Butte.
A Genome-Wide Association Study of Inbred Rat Strains [PDF].
Python
source code available.
This paper describes a genome-wide association study conducted
on various inbred strains of Brown Norway rat. The study used
preexisting, publicly available data. Phenotype data
collected by NBRP-Rat, Kyoto, was merged with genotype data
collected by the European STAR consortium. Applying a
stringent Bonferroni correction, no statistically significant
results were found. Applying a more lenient criterion based
on false discovery rate led to several hundred possibly
significant correlations between SNPs and phenotypes. These
findings were combined with Gene Ontology annotations from the
Rat Genome Database to associate particular phenotypes with
particular Gene Ontology terms. The associations suggest
biological pathways and mechanisms that may give rise to the
phenotypic variations observed between various strains of
rats.