LitInspector: literature and signal transduction pathway mining in PubMed abstracts.

LitInspector is a literature search tool providing gene and signal transduction pathway mining within NCBI's PubMed database. The automatic gene recognition and color coding increases the readability of abstracts and significantly speeds up literature research. A main challenge in gene recognition is the resolution of homonyms and rejection of identical abbreviations used in a 'non-gene' context. LitInspector uses automatically generated and manually refined filtering lists for this purpose. The quality of the LitInspector results was assessed with a published dataset of 181 PubMed sentences. LitInspector achieved a precision of 96.8%, a recall of 86.6% and an F-measure of 91.4%. To further demonstrate the homonym resolution qualities, LitInspector was compared to three other literature search tools using some challenging examples. The homonym MIZ-1 (gene IDs 7709 and 9063) was correctly resolved in 87% of the abstracts by LitInspector, whereas the other tools achieved recognition rates between 35% and 67%. The LitInspector signal transduction pathway mining is based on a manually curated database of pathway names (e.g. wingless type), pathway components (e.g. WNT1, FZD1), and general pathway keywords (e.g. signaling cascade). The performance was checked for 10 randomly selected genes. Eighty-two per cent of the 38 predicted pathway associations were correct. LitInspector is freely available at http://www.litinspector.org/.

In silico prediction of scaffold/matrix attachment regions in large genomic sequences.

Scaffold/matrix attachment regions (S/MARs) are essential regulatory DNA elements of eukaryotic cells. They are major determinants of locus control of gene expression and can shield gene expression from position effects. Experimental detection of S/MARs requires substantial effort and is not suitable for large-scale screening of genomic sequences. In silico prediction of S/MARs can provide a crucial first selection step to reduce the number of candidates. We used experimentally defined S/MAR sequences as the training set and generated a library of new S/MAR-associated, AT-rich patterns described as weight matrices. A new tool called SMARTest was developed that identifies potential S/MARs by performing a density analysis based on the S/MAR matrix library (http://www.genomatix.de/cgi-bin/smartest_pd/smartest.pl). S/MAR predictions were evaluated by using six genomic sequences from animal and plant for which S/MARs and non-S/MARs were experimentally mapped. SMARTest reached a sensitivity of 38% and a specificity of 68%. In contrast to previous algorithms, the SMARTest approach does not depend on the sequence context and is suitable to analyze long genomic sequences up to the size of whole chromosomes. To demonstrate the feasibility of large-scale S/MAR prediction, we analyzed the recently published chromosome 22 sequence and found 1198 S/MAR candidates.