Update README.md

1. Update database from V11 to V12
2. Update PUL version
3. change cgc.out into cgc_standard.out

README.md

@@ -60,17 +60,17 @@ If you are old user, just update the conda virtual environment `run_dbcan` via r
 test -d db || mkdir db
 cd db \
     && wget http://bcb.unl.edu/dbCAN2/download/Databases/fam-substrate-mapping-08252022.tsv \
-	&& wget http://bcb.unl.edu/dbCAN2/download/Databases/PUL.faa && makeblastdb -in PUL.faa -dbtype prot \
-	&& wget http://bcb.unl.edu/dbCAN2/download/Databases/dbCAN-PUL_07-01-2022.xlsx \
-    && wget http://bcb.unl.edu/dbCAN2/download/Databases/dbCAN-PUL_07-01-2022.txt \
+	&& wget http://bcb.unl.edu/dbCAN2/download/Databases/PUL_12112023.faa && mv PUL_12112023.faa PUL.faa && makeblastdb -in PUL.faa -dbtype prot \
+	&& wget http://bcb.unl.edu/dbCAN2/download/Databases/dbCAN-PUL_12-12-2023.xlsx \
+    && wget http://bcb.unl.edu/dbCAN2/download/Databases/dbCAN-PUL_12-12-2023.txt \
 	&& wget http://bcb.unl.edu/dbCAN2/download/Databases/dbCAN-PUL.tar.gz && tar xvf dbCAN-PUL.tar.gz \
-    && wget http://bcb.unl.edu/dbCAN2/download/Databases/dbCAN_sub.hmm && hmmpress dbCAN_sub.hmm \
-    && wget http://bcb.unl.edu/dbCAN2/download/Databases/V11/CAZyDB.08062022.fa && diamond makedb --in CAZyDB.08062022.fa -d CAZy \
-    && wget https://bcb.unl.edu/dbCAN2/download/Databases/V11/dbCAN-HMMdb-V11.txt && mv dbCAN-HMMdb-V11.txt dbCAN.txt && hmmpress dbCAN.txt \
-    && wget https://bcb.unl.edu/dbCAN2/download/Databases/V11/tcdb.fa && diamond makedb --in tcdb.fa -d tcdb \
-    && wget http://bcb.unl.edu/dbCAN2/download/Databases/V11/tf-1.hmm && hmmpress tf-1.hmm \
-    && wget http://bcb.unl.edu/dbCAN2/download/Databases/V11/tf-2.hmm && hmmpress tf-2.hmm \
-    && wget https://bcb.unl.edu/dbCAN2/download/Databases/V11/stp.hmm && hmmpress stp.hmm \
+    && wget https://bcb.unl.edu/dbCAN2/download/Databases/dbCAN_sub.hmm && hmmpress dbCAN_sub.hmm \
+    && wget https://bcb.unl.edu/dbCAN2/download/Databases/V12/CAZyDB.07262023.fa && diamond makedb --in CAZyDB.07262023.fa -d CAZy \
+    && wget https://bcb.unl.edu/dbCAN2/download/Databases/V12/dbCAN-HMMdb-V12.txt && mv dbCAN-HMMdb-V12.txt dbCAN.txt && hmmpress dbCAN.txt \
+    && wget https://bcb.unl.edu/dbCAN2/download/Databases/V12/tcdb.fa && diamond makedb --in tcdb.fa -d tcdb \
+    && wget http://bcb.unl.edu/dbCAN2/download/Databases/V12/tf-1.hmm && hmmpress tf-1.hmm \
+    && wget http://bcb.unl.edu/dbCAN2/download/Databases/V12/tf-2.hmm && hmmpress tf-2.hmm \
+    && wget https://bcb.unl.edu/dbCAN2/download/Databases/V12/stp.hmm && hmmpress stp.hmm \
     && cd ../ && wget http://bcb.unl.edu/dbCAN2/download/Samples/EscheriaColiK12MG1655.fna \
     && wget http://bcb.unl.edu/dbCAN2/download/Samples/EscheriaColiK12MG1655.faa \
     && wget http://bcb.unl.edu/dbCAN2/download/Samples/EscheriaColiK12MG1655.gff
@@ -314,6 +314,8 @@ Several files will be produced via `run_dbcan`. They are as follows:
 
 	cgc.out - ouput from the CGCFinder run
 
+  	cgc_standard.out - standardized output of cgc.out,  which contains column names.
+
 	overview.txt - Details the CAZyme predictions across the three tools with signalp results
 
  see https://github.com/linnabrown/run_dbcan/issues/127 for some explanation of different output files for substrate predictions