add download database script and meta.yalm info, pre release 1.5

BU-ISCIII · Mar 16, 2020 · 715ff1c · 715ff1c
1 parent e31c341
commit 715ff1c
Show file tree

Hide file tree

Showing 3 changed files with 30 additions and 14 deletions.
diff --git a/bin/download_plasmid_database.py b/bin/download_plasmid_database.py
@@ -113,7 +113,7 @@ def get_arguments():
     #remove duplicates
     plasmid_reference = set(plasmid_reference)
     #Set terms to exclude
-    terms_to_exclude = ['gene', 'protein', 'partial', 'putative', 'hypothetical']
+    terms_to_exclude = ['gene ', 'protein', 'partial', 'putative', 'hypothetical']
     #Dictionary with erroneous accession numbers to determine the reason
     erroneous = {}
 
@@ -132,12 +132,12 @@ def get_arguments():
                 if sum(terms_present) > 0:
                     terms_true = [terms_to_exclude[i] for i, x in enumerate(terms_present) if x == True]
                     erroneous[record.id] = "Include terms: " + ', '.join(terms_true) + " => " + record.description
-                    logger.info(" %s/%s Invalid terms in record %s" % (current_record,total_sequences, record.id))
+                    logger.debug(" %s/%s Invalid terms in record %s" % (current_record,total_sequences, record.id))
                 else:
-                    logger.info(" %s/%s Downloading record %s" % (current_record,total_sequences, record.id))
+                    logger.debug(" %s/%s Downloading record %s" % (current_record,total_sequences, record.id))
                     SeqIO.write(record, output_handle, "fasta")
             except:
-                logger.info(" %s/%s Failed to download %s" % (current_record,total_sequences, record.id))
+                logger.debug(" %s/%s Failed to download %s" % (current_record,total_sequences, record.id))
                 erroneous[record.id] = "failed to download"
             current_record = current_record + 1
 

diff --git a/plasmidID.sh → plasmidID b/plasmidID.sh → plasmidID
@@ -1013,19 +1013,18 @@ done
 #obtain list of contigs per plasmid in a separate file
 for i in $(cat $reconstruct_fasta | grep ">" | awk 'gsub(">","",$1) {print $1}')
 do
-	cat $output_dir/$group/$sample/data/$sample".plasmids.complete" \
-	| awk '/'$i'/ && !x[$4]++ {print "_"$4}' > $output_dir/$group/$sample/fasta_files/$i.ac &>> $log_file || error ${LINENO} $(basename $0) "See $output_dir/logs/plasmidID.log for more information.\ncommand:\n cat $output_dir/$group/$sample/data/$sample\".plasmids.complete\" | awk \'/\'$i\'/ && !x[$4]++ {print \"_\"$4}\' > $output_dir/$group/$sample/fasta_files/$i.ac"
+	cat $output_dir/$group/$sample/data/$sample".plasmids.complete" | awk '/'"${i}"'/ && !x[$4]++ {print "_"$4}' > $output_dir/$group/$sample/fasta_files/$i.ac
 done
 
-#Extract fasta from contig file, oe per plasmid
+#Extract fasta from contig file, one per plasmid
 for i in $(ls $output_dir/$group/$sample/fasta_files/*.ac)
 do
 	if [ -s $i ]; then
 		filter_fasta.sh -i $output_dir/$group/$sample/data/$sample".fna" -f $i -n $(basename $i .ac) -o $output_dir/$group/$sample/fasta_files &>> $log_file || error ${LINENO} $(basename $0) "See $output_dir/logs/plasmidID.log for more information.\ncommand:\nfilter_fasta.sh -i $output_dir/$group/$sample/data/$sample\".fna\" -f $i -n $(basename $i .ac) -o $output_dir/$group/$sample/fasta_files"
 	fi
 done
 
-#Remove previous
+#Remove temp files in fasta_files
 for i in $(ls $output_dir/$group/$sample/fasta_files/*.ac)
 do
 	if [ -e $i ]; then

diff --git a/plasmidID_191122.yml → plasmidID_200316.ylm b/plasmidID_191122.yml → plasmidID_200316.ylm
@@ -1,5 +1,7 @@
 name: plasmidID
 channels:
+  - conda-forge
+  - anaconda
   - bioconda
   - defaults
 dependencies:
@@ -10,37 +12,42 @@ dependencies:
   - blast=2.9.0=pl526h3066fca_4
   - bowtie2=2.3.5=py36he860b03_0
   - bzip2=1.0.8=h7b6447c_0
-  - ca-certificates=2019.10.16=0
+  - ca-certificates=2019.11.27=0
   - cairo=1.14.12=h8948797_3
   - cd-hit=4.8.1=hdbcaa40_0
-  - certifi=2019.9.11=py36_0
+  - certifi=2019.11.28=py36_0
   - circos=0.69.8=0
   - curl=7.67.0=hbc83047_0
   - entrez-direct=11.0=pl526_1
   - expat=2.2.6=he6710b0_0
   - fontconfig=2.13.0=h9420a91_0
   - freetype=2.9.1=h8a8886c_1
   - fribidi=1.0.5=h7b6447c_0
+  - gawk=5.0.1=h7b6447c_0
   - giflib=5.1.4=h14c3975_1
   - glib=2.63.1=h5a9c865_0
   - graphite2=1.3.13=h23475e2_0
   - graphviz=2.40.1=h21bd128_2
+  - gsl=2.5=h294904e_1
   - harfbuzz=1.8.8=hffaf4a1_0
   - hmmer=3.2.1=he1b5a44_2
   - htslib=1.9=h4da6232_3
   - icu=58.2=h9c2bf20_1
   - infernal=1.1.2=h14c3975_2
   - jpeg=9b=h024ee3a_2
-  - krb5=1.16.1=h173b8e3_7
+  - krb5=1.16.4=h173b8e3_0
+  - libblas=3.8.0=14_openblas
+  - libcblas=3.8.0=14_openblas
   - libcurl=7.67.0=h20c2e04_0
-  - libdb=6.1.26=0
+  - libdb=6.1.26=he6710b0_0
   - libdeflate=1.2=h516909a_1
   - libedit=3.1.20181209=hc058e9b_0
   - libffi=3.2.1=hd88cf55_4
-  - libgcc=7.2.0=h69d50b8_2
   - libgcc-ng=9.1.0=hdf63c60_0
   - libgd=2.2.5=hceca4fd_3
+  - libgfortran-ng=7.3.0=hdf63c60_0
   - libidn=7.45.0=2
+  - libopenblas=0.3.7=h6e990d7_3
   - libpng=1.6.37=hbc83047_0
   - libssh2=1.8.2=h1ba5d50_0
   - libstdcxx-ng=9.1.0=hdf63c60_0
@@ -50,6 +57,7 @@ dependencies:
   - libxcb=1.13=h1bed415_1
   - libxml2=2.9.9=hea5a465_1
   - libxslt=1.1.33=h7d1a2b0_0
+  - mash=2.2.1=h3d38be6_1
   - minced=0.4.2=0
   - ncurses=6.1=he6710b0_1
   - openjdk=8.0.152=h46b5887_1
@@ -280,7 +288,7 @@ dependencies:
   - python=3.6.9=h265db76_0
   - readline=7.0=h7b6447c_5
   - samtools=1.9=h10a08f8_12
-  - setuptools=41.6.0=py36_0
+  - setuptools=44.0.0=py36_0
   - spades=3.13.1=0
   - sqlite=3.30.1=h7b6447c_0
   - tbb=2019.8=hfd86e86_0
@@ -292,5 +300,14 @@ dependencies:
   - xz=5.2.4=h14c3975_4
   - zlib=1.2.11=h7b6447c_3
   - zstd=1.3.7=h0b5b093_0
+  - pip:
+    - joblib==0.14.1
+    - numpy==1.18.1
+    - pandas==1.0.1
+    - python-dateutil==2.8.1
+    - pytz==2019.3
+    - scikit-learn==0.22.2.post1
+    - scipy==1.4.1
+    - six==1.14.0
 prefix: /home/pjsola/.conda/envs/plasmidID