MOTIVATION: Methods to improve tiling array expression signals are needed to accurately detect genome features. Royce et al. provide statistical normalizations of tile signal based on probe sequence content that promises improved accuracy, and should be independently verified. RESULTS: Assessment of the sequence content normalization methods identified a problem: confounding of probe sequence content with gene structure (intron/exon) sequence content. Normalization obscured tile signal changes at gene structure boundaries. This and other evidence suggests that simple sequence normalization does not improve detection of genes from tile expression data.

We describe a network approach to building recommendation systems for a Web service. We employ two different types of weighted graphs in our analysis and development: proximity graphs, a type of fuzzy graphs based on a co-occurrence probability, and semi-metric distance graphs, which do not observe the triangle inequality of Euclidean distances. Both types of graphs are used to develop intelligent recommendation and collaboration systems for the MyLibrary@LANL Web service, a user-centered front-end to the Los Alamos National Laboratory's digital library collections and Web resources.

BACKGROUND: We participated in the BioCreAtIvE Task 2, which addressed the annotation of proteins into the Gene Ontology (GO) based on the text of a given document and the selection of evidence text from the document justifying that annotation. We approached the task utilizing several combinations of two distinct methods: an unsupervised algorithm for expanding words associated with GO nodes, and an annotation methodology which treats annotation as categorization of terms from a protein's document neighborhood into the GO. RESULTS: The evaluation results indicate that the method for expanding words associated with GO nodes is quite powerful; we were able to successfully select appropriate evidence text for a given annotation in 38% of Task 2.1 queries by building on this method. The term categorization methodology achieved a precision of 16% for annotation within the correct extended family in Task 2.2, though we show through subsequent analysis that this can be improved with a different parameter setting. Our architecture proved not to be very successful on the evidence text component of the task, in the configuration used to generate the submitted results. CONCLUSION: The initial results show promise for both of the methods we explored, and we are planning to integrate the methods more closely to achieve better results overall.