ONT_pilot_w_GDB_samples.md

@@ -1025,6 +1025,63 @@ do
   echo "$file" >> minced_CRISPR_output.txt
   grep -c 'CRISPR' "$file".txt >> minced_CRISPR_output.txt
 done
+
+## Based on a discussion with Rob Edwards from UCSD, decided to try out CRISPRdetect-parser
+# from here: https://github.com/hwalinga/crisprdetect-parser
+cd /mnt/lscratch/users/sbusi/ONT/cedric_ont_basecalling/2019_GDB/crispr
+conda activate emboss
+conda install -c bioconda viennarna
+conda install -c anaconda perl
+
+git clone https://github.com/hwalinga/crisprdetect-parser.git
+cd crisprdetect-parser/CRISPRDetect_2.4_grep_patched
+export PATH=$PATH:/home/users/sbusi/apps/miniconda3/envs/cd-hit/bin     # for cd-hit
+export PATH=$PATH:/home/users/sbusi/apps/miniconda3/envs/anvio6/bin     # for blastn
+export PATH=$PATH:/mnt/lscratch/users/sbusi/ONT/cedric_ont_basecalling/2019_GDB/crispr/bin    # for perl
+export PERL5LIB=/mnt/lscratch/users/sbusi/ONT/cedric_ont_basecalling/2019_GDB/crispr/lib/site_perl      # for perl
+
+wget http://search.cpan.org/CPAN/authors/id/Y/YA/YANICK/Parallel-ForkManager-1.19.tar.gz
+tar xvzf Parallel-ForkManager-1.19.tar.gz
+cd Parallel-ForkManager-1.19
+perl Makefile.PL PREFIX=/mnt/lscratch/users/sbusi/ONT/cedric_ont_basecalling/2019_GDB/crispr/crisprdetect-parser/CRISPRDetect_2.4_grep_patched/Parallel-ForkManager-1.19
+make test && make install
+
+####### INSTALLATION NOT WORKING ########
+```
+
+##### PLASMIDS #####
+- checking the number of plasmids in the assemblies
+```
+# grep -hnr "plasmid" $i_plasflow_prediction_final.tsv > $i_plasmids_selected.tsv
+
+for file in /scratch/users/ldenies/ONT/PathoFact/PathoFact_results/MGE/plasmid/*final.tsv
+do 
+  echo $file
+  grep -c 'plasmid.' "$file"
+done
+# /scratch/users/ldenies/ONT/PathoFact/PathoFact_results/MGE/plasmid/flye_plasflow_prediction_final.tsv
+# 280
+# /scratch/users/ldenies/ONT/PathoFact/PathoFact_results/MGE/plasmid/megahit_plasflow_prediction_final.tsv
+# 5186
+# /scratch/users/ldenies/ONT/PathoFact/PathoFact_results/MGE/plasmid/metaspades_hybrid_plasflow_prediction_final.tsv
+# 3211
+# /scratch/users/ldenies/ONT/PathoFact/PathoFact_results/MGE/plasmid/metaspades_plasflow_prediction_final.tsv
+# 5718
+
+# number of contigs used as input:
+#   2533982 flye_filtered.part_001.fna
+#    975951 megahit_filtered.part_001.fna
+#    829650 megahit_filtered.part_002.fna
+#    677918 megahit_filtered.part_003.fna
+#   2483519 total
+#   1992017 metaspades_filtered.part_001.fna
+#    316220 metaspades_filtered.part_002.fna
+#    185613 metaspades_filtered.part_003.fna
+#   2493850 total
+#   2847904 metaspades_hybrid_filtered.part_001.fna
+#    306145 metaspades_hybrid_filtered.part_002.fna
+#      7023 metaspades_hybrid_filtered.part_003.fna
+#   3161072 total
 ```
 
 ###############