TREC 2004 Genomics Track Data

This page lists the files that are in the distribution for the TREC Genomics Track 2004. More detail about these files can be found in the 2004 track protocol. There is also a description of how the files were updated. To use the data, read the instructions below.

Ad Hoc Retrieval Task

Documents

MEDLINE ASCII format

2004_TREC_ASCII_MEDLINE_1.gz (1.29 GB)
2004_TREC_ASCII_MEDLINE_1.gz (1.31 GB)

MEDLINE XML format

2004_TREC_XML_MEDLINE_A.gz (553 MB)
2004_TREC_XML_MEDLINE_B.gz (595 MB)
2004_TREC_XML_MEDLINE_C.gz (566 MB)
2004_TREC_XML_MEDLINE_D.gz (572 MB)
2004_TREC_XML_MEDLINE_E.gz (605 MB)

PMID list

2004_TREC_PMID_list.gz (10.6 MB)

Topics

Official topics

Official.xml (17 KB)

Relevance judgments

Readme file about judgments

04.readme.txt (3 KB)

Qrels for input to trec_eval (contains all judgments so bpref measurement is accurate)

04.qrels-full.txt (639 KB)

Categorization Task

Documents

Training documents - Highwire full text SGML 2002

train.tar.Z (150 MB)

Test documents - Highwire full text SGML 2003

test.tar.Z (140 MB)

PMID-full text crosswalk

Training data - 2002

train.crosswalk.txt (206 KB)

Test data - 2003

test.crosswalk.txt (199 KB)

Triage subtask

Training positive examples, updated - 2002

triage+train2.txt (4 KB)

Test positive examples, updated - 2003

triage+test2.txt (5 KB)

There are also the original training and test files from TREC 2004

triage+train.txt (4 KB)
triage+test.txt (5 KB)

Categorization subtask

File contents	Training data file name	Test data file name
Documents - PMIDs	ptrain.txt (5 KB)	ptest.txt (4 KB)
Genes - Gene symbol, MGI identifier, and gene name for all used	gtrain.txt (68 KB)	gtest.txt (41 KB)
Document gene pairs - PMID-gene pairs	pgtrain.txt (24 KB)	pgtest.txt (24 KB)
Positive examples - PMIDs	p+train.txt (2 KB)	p+test.txt (2 KB)
Positive examples - PMID-gene pairs	pg+train.txt (6 KB)	pg+test.txt (5 KB)
Positive examples - PMID-gene-domain tuples	pgd+train.txt (12 KB)	pgd+test.txt (10 KB)
Positive examples - PMID-gene-domain-evidence tuples	pgde+train.txt (15 KB)	pgde+test.txt (12 KB)
Positive examples - all PMID-gene-GO-evidence tuples	all+train.txt (92 KB)	all+test.txt (48 KB)
Negative examples - PMIDs	p-train.txt (4 KB)	p-test.txt (3 KB)
Negative examples - PMID-gene pairs	pg-train.txt (19 KB)	pg-test.txt (10 KB)

Also available are the original files that were used for the results reported in the official track runs. The derivation of these files is described on the data update page. The original files have been renamed and include:

ptrain04.txt
ptest04.txt
pgtrain04.txt
pgtest04.txt
p-train04.txt
p-test04.txt
pg-train04.txt
pg-test04.txt

Evaluation program cat_eval

Python source code version

cat_eval_1.2.tar.gz (24 KB)

Windows executable version

cat_eval_win32_1.2.zip (540 KB)

Accessing the files

Excluding the MEDLINE XML files (which are identical to the ASCII MEDLINE files except for their format), there are 45 files totaling 2.9 GB in size. The data files are available on this site.

The document files are:

2004_TREC_ASCII_MEDLINE_1.gz (1.29 GB)
2004_TREC_ASCII_MEDLINE_1.gz (1.31 GB)
2004_TREC_XML_MEDLINE_A.gz (553 MB)
2004_TREC_XML_MEDLINE_B.gz (595 MB)
2004_TREC_XML_MEDLINE_C.gz (566 MB)
2004_TREC_XML_MEDLINE_D.gz (572 MB)
2004_TREC_XML_MEDLINE_E.gz (605 MB)
test.tar.Z (140 MB)
train.tar.Z (150 MB)

The other archived/compressed files that do not require signing the data usage agreement include:

2004_TREC_PMID_list.gz (10.6 MB)
cat_eval_1.2.tar.gz (24 KB)
cat_eval_win32_1.2.zip (540 KB)

The rest of the files also do not require signing the data usage agreement. They are archived/compressed into a single file, rest.zip, which contains the following files:

all+test.txt (48 KB)
all+train.txt (92 KB)
gtest.txt (41 KB)
gtrain.txt (68 KB)
Official.xml (17 KB)
p+test.txt (2 KB)
p+train.txt (2 KB)
pg+test.txt (5 KB)
pg+train.txt (6 KB)
pgd+test.txt (10 KB)
pgd+train.txt (12 KB)
pgde+test.txt (12 KB)
pgde+train.txt (15 KB)
pg-test.txt (10 KB)
pgtest.txt (24 KB)
pg-test2.txt (10 KB)
pgtest2.txt (24 KB)
pg-train.txt (19 KB)
pgtrain.txt (24 KB)
pg-train2.txt (19 KB)
pgtrain2.txt (24 KB)
p-test.txt (3 KB)
ptest.txt (4 KB)
p-test2.txt (3 KB)
ptest2.txt (4 KB)
p-train.txt (4 KB)
ptrain.txt (5 KB)
p-train2.txt (4 KB)
ptrain2.txt (5 KB)
test.crosswalk.txt (199 KB)
train.crosswalk.txt (206 KB)
triage+test.txt (5 KB)
triage+test2.txt (5 KB)
triage+train.txt (4 KB)
triage+train2.txt (4 KB)

Last update - April 6, 2015