Patch building of the Single copy reference DB to make a single blast

database for Large and Small Single copy


Former-commit-id: 9bad3443085b2b6b066c7f33f3eaf2e49b5e8992
Former-commit-id: 15ce54a189d9def4b824c149f0ba5ba036794567
This commit is contained in:
2015-10-07 12:29:48 -03:00
parent cbc32a6326
commit b75035064c
10 changed files with 75 additions and 71 deletions

Binary file not shown.

Binary file not shown.

BIN
data/ir/SC_RefDB.nhr Normal file

Binary file not shown.

BIN
data/ir/SC_RefDB.nin Normal file

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

View File

@ -1,63 +1,65 @@
2015-10-07 11:25:33 [OA INFO ] 89006 -- Selecting Viridiplantae genebank entries...
2015-10-07 11:25:42 [OA INFO ] 89006 -- --> 695 entries selected
2015-10-07 11:25:42 [OA INFO ] 89006 -- Done
2015-10-07 11:25:42 [OA INFO ] 89006 -- Extracting Long Single Copies (LSC)...
2015-10-07 11:26:36 [OA INFO ] 89006 -- --> 64 retreived sequences
2015-10-07 11:26:36 [OA INFO ] 89006 -- Done
2015-10-07 11:26:36 [OA INFO ] 89006 -- Building LSC coorientation graph...
2015-10-07 11:26:36 [OA INFO ] 89127 -- Build temporary blast DB...
2015-10-07 11:26:36 [OA INFO ] 89127 -- Done
2015-10-07 11:26:36 [OA INFO ] 89127 -- Running Blast...
2015-10-07 11:27:47 [OA INFO ] 89127 -- Done
2015-10-07 11:27:47 [OA INFO ] 89006 -- --> 6 connected componants
2015-10-07 11:27:47 [OA INFO ] 89006 -- Done
2015-10-07 11:27:47 [OA INFO ] 89006 -- Indexing LCS...
2015-10-07 11:27:47 [OA INFO ] 89006 -- Done
2015-10-07 11:27:47 [OA INFO ] 89006 -- Extracting main connected components for LCS...
2015-10-07 11:27:48 [OA INFO ] 89006 -- --> 40 sequences
2015-10-07 11:27:48 [OA INFO ] 89006 -- Done
2015-10-07 11:27:48 [OA INFO ] 89006 -- Extracting second connected components for LCS...
2015-10-07 11:27:48 [OA INFO ] 89006 -- --> 5 sequences
2015-10-07 11:27:48 [OA INFO ] 89006 -- Done
2015-10-07 11:27:48 [OA INFO ] 89006 -- merging both connected components for LCS...
2015-10-07 11:27:48 [OA INFO ] 89006 -- --> 45 sequences in total
2015-10-07 11:27:48 [OA INFO ] 89006 -- Done
2015-10-07 11:27:48 [OA INFO ] 89006 -- Checking LCS homogeneity...
2015-10-07 11:27:48 [OA INFO ] 89258 -- Build temporary blast DB...
2015-10-07 11:27:48 [OA INFO ] 89258 -- Done
2015-10-07 11:27:48 [OA INFO ] 89258 -- Running Blast...
2015-10-07 11:28:50 [OA INFO ] 89258 -- Done
2015-10-07 11:28:50 [OA INFO ] 89006 -- --> 1 connected componants
2015-10-07 11:28:50 [OA INFO ] 89006 -- Done
2015-10-07 11:28:50 [OA INFO ] 89006 -- Installing LCS reference databases...
2015-10-07 11:28:50 [OA INFO ] 89006 -- Done
2015-10-07 11:28:50 [OA INFO ] 89006 -- Extracting Short Single Copies (SSC)...
2015-10-07 11:29:42 [OA INFO ] 89006 -- --> 76 retreived sequences
2015-10-07 11:29:42 [OA INFO ] 89006 -- Done
2015-10-07 11:29:42 [OA INFO ] 89006 -- Building SSC coorientation graph...
2015-10-07 11:29:42 [OA INFO ] 89336 -- Build temporary blast DB...
2015-10-07 11:29:42 [OA INFO ] 89336 -- Done
2015-10-07 11:29:42 [OA INFO ] 89336 -- Running Blast...
2015-10-07 11:30:03 [OA INFO ] 89336 -- Done
2015-10-07 11:30:03 [OA INFO ] 89006 -- --> 1 connected componants
2015-10-07 11:30:03 [OA INFO ] 89006 -- Done
2015-10-07 11:30:03 [OA INFO ] 89006 -- Indexing SSC...
2015-10-07 11:30:03 [OA INFO ] 89006 -- Done
2015-10-07 11:30:03 [OA INFO ] 89006 -- Extracting main connected components for SSC...
2015-10-07 11:30:03 [OA INFO ] 89006 -- --> 72 sequences
2015-10-07 11:30:03 [OA INFO ] 89006 -- Done
2015-10-07 11:30:03 [OA INFO ] 89006 -- Extracting second connected components for SSC...
2015-10-07 11:30:03 [OA INFO ] 89006 -- --> 0 sequences
2015-10-07 11:30:03 [OA INFO ] 89006 -- Done
2015-10-07 11:30:03 [OA INFO ] 89006 -- merging both connected components for SSC...
2015-10-07 11:30:03 [OA INFO ] 89006 -- --> 72 sequences in total
2015-10-07 11:30:03 [OA INFO ] 89006 -- Done
2015-10-07 11:30:03 [OA INFO ] 89006 -- Checking SSC homogeneity...
2015-10-07 11:30:03 [OA INFO ] 89497 -- Build temporary blast DB...
2015-10-07 11:30:03 [OA INFO ] 89497 -- Done
2015-10-07 11:30:03 [OA INFO ] 89497 -- Running Blast...
2015-10-07 11:30:23 [OA INFO ] 89497 -- Done
2015-10-07 11:30:23 [OA INFO ] 89006 -- --> 1 connected componants
2015-10-07 11:30:23 [OA INFO ] 89006 -- Done
2015-10-07 11:30:23 [OA INFO ] 89006 -- Installing SSC reference databases...
2015-10-07 11:30:23 [OA INFO ] 89006 -- Done
2015-10-07 12:22:15 [OA INFO ] 90184 -- Selecting Viridiplantae genebank entries...
2015-10-07 12:22:24 [OA INFO ] 90184 -- --> 695 entries selected
2015-10-07 12:22:24 [OA INFO ] 90184 -- Done
2015-10-07 12:22:24 [OA INFO ] 90184 -- Extracting Long Single Copies (LSC)...
2015-10-07 12:23:17 [OA INFO ] 90184 -- --> 64 retreived sequences
2015-10-07 12:23:17 [OA INFO ] 90184 -- Done
2015-10-07 12:23:17 [OA INFO ] 90184 -- Building LSC coorientation graph...
2015-10-07 12:23:17 [OA INFO ] 90306 -- Build temporary blast DB...
2015-10-07 12:23:18 [OA INFO ] 90306 -- Done
2015-10-07 12:23:18 [OA INFO ] 90306 -- Running Blast...
2015-10-07 12:24:29 [OA INFO ] 90306 -- Done
2015-10-07 12:24:29 [OA INFO ] 90184 -- --> 6 connected componants
2015-10-07 12:24:29 [OA INFO ] 90184 -- Done
2015-10-07 12:24:29 [OA INFO ] 90184 -- Indexing LCS...
2015-10-07 12:24:30 [OA INFO ] 90184 -- Done
2015-10-07 12:24:30 [OA INFO ] 90184 -- Extracting main connected components for LCS...
2015-10-07 12:24:30 [OA INFO ] 90184 -- --> 40 sequences
2015-10-07 12:24:30 [OA INFO ] 90184 -- Done
2015-10-07 12:24:30 [OA INFO ] 90184 -- Extracting second connected components for LCS...
2015-10-07 12:24:30 [OA INFO ] 90184 -- --> 5 sequences
2015-10-07 12:24:30 [OA INFO ] 90184 -- Done
2015-10-07 12:24:30 [OA INFO ] 90184 -- merging both connected components for LCS...
2015-10-07 12:24:30 [OA INFO ] 90184 -- --> 45 sequences in total
2015-10-07 12:24:30 [OA INFO ] 90184 -- Done
2015-10-07 12:24:30 [OA INFO ] 90184 -- Checking LCS homogeneity...
2015-10-07 12:24:30 [OA INFO ] 90439 -- Build temporary blast DB...
2015-10-07 12:24:30 [OA INFO ] 90439 -- Done
2015-10-07 12:24:30 [OA INFO ] 90439 -- Running Blast...
2015-10-07 12:25:35 [OA INFO ] 90439 -- Done
2015-10-07 12:25:35 [OA INFO ] 90184 -- --> 1 connected componants
2015-10-07 12:25:35 [OA INFO ] 90184 -- Done
2015-10-07 12:25:35 [OA INFO ] 90184 -- Installing LCS reference databases...
2015-10-07 12:25:35 [OA INFO ] 90184 -- Done
2015-10-07 12:25:35 [OA INFO ] 90184 -- Extracting Short Single Copies (SSC)...
2015-10-07 12:26:28 [OA INFO ] 90184 -- --> 76 retreived sequences
2015-10-07 12:26:28 [OA INFO ] 90184 -- Done
2015-10-07 12:26:28 [OA INFO ] 90184 -- Building SSC coorientation graph...
2015-10-07 12:26:28 [OA INFO ] 90517 -- Build temporary blast DB...
2015-10-07 12:26:28 [OA INFO ] 90517 -- Done
2015-10-07 12:26:28 [OA INFO ] 90517 -- Running Blast...
2015-10-07 12:26:49 [OA INFO ] 90517 -- Done
2015-10-07 12:26:49 [OA INFO ] 90184 -- --> 1 connected componants
2015-10-07 12:26:49 [OA INFO ] 90184 -- Done
2015-10-07 12:26:49 [OA INFO ] 90184 -- Indexing SSC...
2015-10-07 12:26:49 [OA INFO ] 90184 -- Done
2015-10-07 12:26:49 [OA INFO ] 90184 -- Extracting main connected components for SSC...
2015-10-07 12:26:49 [OA INFO ] 90184 -- --> 72 sequences
2015-10-07 12:26:49 [OA INFO ] 90184 -- Done
2015-10-07 12:26:49 [OA INFO ] 90184 -- Extracting second connected components for SSC...
2015-10-07 12:26:49 [OA INFO ] 90184 -- --> 0 sequences
2015-10-07 12:26:49 [OA INFO ] 90184 -- Done
2015-10-07 12:26:49 [OA INFO ] 90184 -- merging both connected components for SSC...
2015-10-07 12:26:49 [OA INFO ] 90184 -- --> 72 sequences in total
2015-10-07 12:26:49 [OA INFO ] 90184 -- Done
2015-10-07 12:26:49 [OA INFO ] 90184 -- Checking SSC homogeneity...
2015-10-07 12:26:49 [OA INFO ] 90675 -- Build temporary blast DB...
2015-10-07 12:26:49 [OA INFO ] 90675 -- Done
2015-10-07 12:26:49 [OA INFO ] 90675 -- Running Blast...
2015-10-07 12:27:10 [OA INFO ] 90675 -- Done
2015-10-07 12:27:10 [OA INFO ] 90184 -- --> 1 connected componants
2015-10-07 12:27:10 [OA INFO ] 90184 -- Done
2015-10-07 12:27:10 [OA INFO ] 90184 -- Installing SSC reference databases...
2015-10-07 12:27:10 [OA INFO ] 90184 -- Done
2015-10-07 12:27:10 [OA INFO ] 90184 -- Installing blast version of the SC_RefDB reference databases...
2015-10-07 12:27:10 [OA INFO ] 90184 -- Done

View File

@ -89,9 +89,6 @@ pushTmpDir ORG.buildSCDB
cp LSC.direct.fasta "${IR_DATA_DIR}/LSC_RefDB.fasta"
cp LSC_RefDB.tgf "${IR_DATA_DIR}/LSC_RefDB.tgf"
makeblastdb -in "${IR_DATA_DIR}/LSC_RefDB.fasta" \
-dbtype nucl \
-out "${IR_DATA_DIR}/LSC_RefDB" >& /dev/null
loginfo "Done"
#
@ -163,12 +160,17 @@ pushTmpDir ORG.buildSCDB
loginfo "Installing SSC reference databases..."
cp SSC.direct.fasta "${IR_DATA_DIR}/SSC_RefDB.fasta"
cp SSC_RefDB.tgf "${IR_DATA_DIR}/SSC_RefDB.tgf"
makeblastdb -in "${IR_DATA_DIR}/SSC_RefDB.fasta" \
-dbtype nucl \
-out "${IR_DATA_DIR}/SSC_RefDB" >& /dev/null
cp SSC_RefDB.tgf "${IR_DATA_DIR}/SSC_RefDB.tgf"
loginfo "Done"
loginfo "Installing blast version of the SC_RefDB reference databases..."
cat "${IR_DATA_DIR}/LSC_RefDB.fasta" \
"${IR_DATA_DIR}/SSC_RefDB.fasta" > SC_RefDB.fasta
makeblastdb -in SC_RefDB.fasta \
-dbtype nucl \
-out "${IR_DATA_DIR}/SC_RefDB" >& /dev/null
loginfo "Done"
popTmpDir