The importance of functional genomics data for the prediction of essential genes in S. cerevisiae
By Michael Seringhaus, Alberto Paccanaro, and Mark Gerstein*

* To whom correspondence should be addressed: mark.gerstein@yale.edu

Supplementary Data Website "ESSfeatures"
Main URL: http://www.gersteinlab.org/proj/ESSfeatures/
Gerstein Group Homepage: http://www.gersteinlab.org/

Contents of this Website:

1. Supplementary Figures
2. Complete feature sets (S.cerevisiae)
3. Full output of C4.5 decision tree (threshold 0.5) on above feature sets (S.mikatae)

1. Supplementary Figures

• No suppementary figures at this time. This is where they will go if deemed necessary by reviewers; otherwise, this section will be removed.

2. Complete feature sets (S.cerevisiae)

S.cerevisiae

• COMPILED FEATURES in MS Excel (.xls) format
  
  • MASTER SET 1 (including rows containing one or more empty values, labeled with 'NaN')
  • MASTER SET 2 (not including rows containing one or more empty values, labeled with 'NaN')
  • SET A (12 features x 3089 ORFs)
  • SET B (8 sequence-derived predicted features x 3089 ORFs)
  • SET C (8 experimental-data features x 3089 ORFs)
  • SET AB (20 features x 3089 ORFs)
  • SET AC (20 features x 3089 ORFs)
  • SET BC (16 features x 3089 ORFs)
  • SET ABC (28 features x 3089 ORFs)
  • SET A_LARGE (12 sequence-based features x 5548 ORFs)

   

• COMPILED FEATURES in WEKA (.arff) format
  • Feature sets as above in directory ESSfeatures/FEATURE_SETS/WEKA

3. Full output of C4.5 decision tree (threshold 0.5 all sets except 0.275 for SET LARGE_A) on above feature sets (S.cerevisiae)

Output

• Decision tree output in .txt format.

This Website © 2007 Gerstein Lab. HTML by Michael Seringhaus.