summaryrefslogtreecommitdiffstats
Side-by-side diff
-rw-r--r--configure.ac20
-rw-r--r--src/Makefile.am6
-rw-r--r--src/aggregator.c14
-rw-r--r--src/assign_protein_type.c72
-rw-r--r--src/assign_protein_type.h6
-rw-r--r--src/check_error.c14
-rw-r--r--src/check_error.h11
-rw-r--r--src/check_h5_error.c12
-rw-r--r--src/check_h5_error.h12
-rw-r--r--src/check_ncbi_error.c13
-rw-r--r--src/check_ncbi_error.h13
-rw-r--r--src/load_influenza_aa_dat.c31
12 files changed, 211 insertions, 13 deletions
diff --git a/src/assign_protein_type.h b/src/assign_protein_type.h
index 312b774..1dfb8e6 100644
--- a/src/assign_protein_type.h
+++ b/src/assign_protein_type.h
@@ -4,7 +4,11 @@
#include <hdf5.h>
/*
- * Determine the protein type for each protein sequence record.
+ * Determine the protein type for each protein sequence record. The
+ * technique used by NCBI is used here. A BLAST database of
+ * prototypical protein sequences serves as the reference. Each input
+ * sequence is BLASTed against this database. The first hit is used
+ * to assign a protein type to sequence.
*/
void
assign_protein_type (hid_t file_id);

Valid XHTML 1.0 Strict

Copyright © 2009 Don Pellegrino All Rights Reserved.