Date: 28 Oct 1996 


This directory contains 3 sets of GSDB GenBank flat-file format entries
to be used to test and train gene-finding algorithms for human DNA.

UCSC and LBNL provide these data sets "as is" in an effort to create
a common data set to be used by all gene-finding algorithms.  We
encourage others to compare their results using these data sets.

Accompanying each data set is a ".sets" file listing 9 test/train
subsets.  These subsets can be used for cross-validation.

Data sets PART0 - PART6 are consistent to the old cross-validation
from 1995 (See ../data_1995!).
Data sets PART7 and PART8 contain only new intron genes that 
were added to GenBank between June '95 and July '96. 

The 3 data sets are:

Only single exon genes:

	single_exon_GB.dat.gz
	single_exon_GB.sets


Multiple exon genes:
	multi_exon_GB.dat.gz
	multi_exon_GB.sets


Combined -- single and multiple exon genes:
	combined_GB.dat.gz
	combined_GB.sets


We also provide our data set split into intron and exon sequences:
	2107exons.gz
	1754introns.gz

=====
David Kulp (USCS)
Martin Reese (LBNL) mgreese@lbl.gov