|
"Improved prediction of signal
peptides: SignalP 3.0," by
Jannick Dyrlov Bendtsen, Henrik Nielsen, Gunnar von Heijne, and Soren Brunak, Journal
of Molecular Biology, 340(4): 783-95, 16 July 2004.
[Authors' affiliations: Technical University
of Denmark, Lyngby; Stockholm University, Sweden]
Abstract:
"We describe improvements of the currently most popular method for
prediction of classically secreted proteins, SignalP. SignalP consists of two
different predictors based on neural network and hidden Markov model
algorithms, where both components have been updated. Motivated by the idea
that the cleavage site position and the amino acid composition of the signal
peptide are correlated, new features have been included as input to the neural
network. This addition, combined with a thorough error-correction of a new
data set, have improved the performance of the predictor significantly over
SignalP version 2. In version 3, correctness of the cleavage site predictions
has increased notably for all three organism groups, eukaryotes, Gram-negative
and Gram-positive bacteria. The accuracy of cleavage site prediction has
increased in the range 6-17% over the previous version, whereas the signal
peptide discrimination improvement is mainly due to the elimination of
false-positive predictions, as well as the introduction of a new
discrimination score for the neural network. The new method has been
benchmarked against other available methods. Predictions can be made at the
publicly available web server http://www.cbs.dtu.dk/services/SignaIP/."
This 2004 report from the Journal of
Molecular Biology was cited 56 times in current journal
articles indexed by
Thomson Scientific during July-August 2005. No other biology paper published
in the last two years, aside from
reviews, garnered a greater number of citations during that two-month period.
Prior to the most recent bimonthly
count, citations to the paper have accrued as follows:
May-June 2005: 36 citations
March-April 2005: 24
January-February 2005: 22
November-December 2004: 6
September-October 2004: 2
Total citations to date: 146
SOURCE: Hot
Papers Database (Included with a subscription to the ISI print newsletter Science
Watch®, available from the ISI
Research Services Group. Packaged on a CD-ROM that is mailed with each Science
Watch issue, the Hot
Papers Database contains data on hundreds of highly cited papers published
during the last two years. User interface permits searching by author,
organization, journal, field, and more. Total citations, as well as citations
accrued during successive bimonthly periods, can be assessed and graphed. An
updated CD containing the most recent bimonthly data is mailed with every new
issue of Science
Watch,
six times a year. The CD also includes an electronic version of the Science
Watch
issue in HTML format, for personal desktop access.)
|
cites
:
View the past and present 
