CRAIG Predictions

Test Set 1: Genes with short introns and short intergenic regions

shortIntrons.fa.gz <- Sequences in Fasta format
shortIntrons.gtf <- Annotation in gtf format
shortIntrons.predict.gtf <- CRAIG's Prediction in gtf format

Test Set 2: Genes with long introns and short intergenic regions

tigr.fa.gz <- Sequences in Fasta format
tigr.gtf <- Annotation in gtf format
tigr.predict.gtf <- CRAIG's prediction in gtf format

Test Set 3: The ENCODE regions (31 test regions)

encode_test.masked.fa.gz <- Masked Sequences in Fasta format
encode_test.gtf <- Annotation in gtf format
encode_test.predict.masked.gtf <- CRAIG's prediction in gtf format (masked input)
encode_test.predict.gtf <- CRAIG's prediction in gtf format

Test Set 4: The Split and trimmed ENCODE regions, alternatively spliced genes only

encode_test_alt.masked.fa.gz <- Masked Sequences in Fasta format
encode_test_alt.gtf <- Annotation in gtf format
encode_test_alt.predict.gtf <- CRAIG's prediction in gtf format

Test Set 5: The Split and trimmed ENCODE regions, non-alternatively spliced genes only

encode_test_alt.masked.fa.gz <- Masked Sequences in Fasta format
encode_test_alt.gtf <- Annotation in gtf format
encode_test_alt.predict.gtf <- CRAIG's prediction in gtf format