scripts/procedure.sh updated and scripts/00_create_py_env.sh and...

scripts/procedure.sh updated and scripts/00_create_py_env.sh and 01_quality_check.sh updated to new architecture

phages/scripts/00_create_py_env.sh

@@ -27,7 +27,7 @@ source  ${py_env_dir}/bin/activate
 pip install --upgrade pip
 
 ## 
-pip install  -r requirements_py-env.txt
+pip install  -r scripts/requirements_py-env.txt
 # pip  install  biopython  pandas   matplotlib  multiqc  pyvcf
 
 

phages/scripts/01_quality_check.sh

 #!/bin/bash
 
 
+## Launch example from coevolution/phages/
+## ./scripts/01_quality_check.sh  $PWD/  qc_rawd_data
+
+
 ## PATH TO WORKING DIRECTORY
 path=$1
 #path=/home/enrique/work/Gandon/coevolution/phages/
+step_name=$2
 
 
 
@@ -11,6 +16,9 @@ path=$1
 
 source ~/envs/coev/bin/activate
 
+## Some temporary files are created nearby the source files
+## Using links from a tmp will avoid errors in case the directory
+## containing the raw data is not writable
 
 ## SEPARATE THE FILES BY NAME 
 
@@ -20,47 +28,47 @@ W_seq=$(mktemp -d)
 R_seq=$(mktemp -d)
 Other_seq=$(mktemp -d)
 
-
+echo $W_seq $R_seq $Other_seq
 
 
     ### CREATE SYMBOLIC LINKS TO SEQUENCE FILES
     ### DIIVIDED IN 3 DIRECTORIES
 
-
 echo "CREATE SYMBOLIC LINKS"
 
-for i in $(ls ${path}raw_data/sequences/W*);
+for i in $(ls ${path}data/sequences/W*);
 do
   ln -s $i $W_seq;
 done
 
 
-for i in $(ls ${path}raw_data/sequences/R*);
+for i in $(ls ${path}data/sequences/R*);
 do
   ln -s $i $R_seq;
 done
 
 
-for i in $(ls ${path}raw_data/sequences/ | grep -v ^W | grep -v ^R);
+for i in $(ls ${path}data/sequences/ | grep -v ^W | grep -v ^R);
 do
   #echo $i;
   ln -s ${path}raw_data/sequences/$i $Other_seq
 done
 
 
+echo "CREATE SYMBOLIC LINKS -- DONE"
 
 ### MAKE RUN FASTQC ON EACH GROUPE
 
-mkdir -p ${path}qual/fastqc/{W_seq,R_seq,Other_seq}
+mkdir -p ${path}steps/${step_name}/fastqc/{W_seq,R_seq,Other_seq}
 
 
-fastqc -t 35 --noextract -o ${path}qual/fastqc/W_seq $W_seq/*
+fastqc -t 35 --noextract -o ${path}steps/$step_name/fastqc/W_seq $W_seq/*
 # multiqc -f -i W_seq -o ${path}qual/multiqc/   ${path}qual/fastqc/W_seq 
 
-fastqc -t 35 --noextract -o ${path}qual/fastqc/R_seq $R_seq/*
+fastqc -t 35 --noextract -o ${path}steps/$step_name/fastqc/R_seq $R_seq/*
 # multiqc -f -i R_seq -o ${path}qual/multiqc/ ${path}qual/fastqc/R_seq/
 
-fastqc -t 35 --noextract -o ${path}qual/fastqc/Other_seq $Other_seq/*
+fastqc -t 35 --noextract -o ${path}steps/$step_name/fastqc/Other_seq $Other_seq/*
 # multiqc -f -i Other_seq -o ${path}qual/multiqc/ ${path}qual/fastqc/Other_seq
 
 
@@ -71,17 +79,17 @@ fastqc -t 35 --noextract -o ${path}qual/fastqc/Other_seq $Other_seq/*
 
 ## LOOP MULTIQC DEPENDING ON THE INPUTS
 ## MAKE DIRECTORIES FOR THE DIFFERENT SAMPLES:
-mkdir -p ${path}qual/multiqc/{W,R,Other}
+mkdir -p ${path}steps/$step_name/multiqc/{W_seq,R_seq,Other_seq}
 
 for i in $(seq 8)
 do
-    multiqc -f -i W${i}_seq -n W${i} -o ${path}qual/multiqc/W   ${path}qual/fastqc/W_seq/W${i}*
-    multiqc -f -i R${i}_seq -n R${i} -o ${path}qual/multiqc/R   ${path}qual/fastqc/R_seq/R${i}*
+    multiqc -f -i W${i}_seq -n W${i} -o ${path}steps/$step_name/multiqc/W_seq   ${path}steps/$step_name/fastqc/W_seq/W${i}*
+    multiqc -f -i R${i}_seq -n R${i} -o ${path}steps/$step_name/multiqc/R_seq   ${path}steps/$step_name/fastqc/R_seq/R${i}*
 done
 
 for i in 2972 A B C D CTRL T Undetermined
 do
-    multiqc -f -i ${i}_seq -n ${i} -o ${path}qual/multiqc/Other ${path}qual/fastqc/Other_seq/${i}*
+    multiqc -f -i ${i}_seq -n ${i} -o ${path}steps/$step_name/multiqc/Other_seq  ${path}steps/$step_name/fastqc/Other_seq/${i}*
 done
 
 

phages/scripts/README.md

@@ -191,7 +191,7 @@ To run from ipython:
 
 The commands used to launch the scripts up here as well as the supplementary commands to separate the different data, extract and all other action is written here.
 
-It contains a pre-treatment of data to create sub-groups using symbolic links
+It contains a pre-treatment of data to create sub-groups using symbolic links.
 
 
 ### README.md

phages/scripts/procedure.sh

@@ -5,7 +5,7 @@
 # cd /home/user/work/coev/phages 
 
 
-## PREPARE DATA 
+## PREPARE DATA SUBGROUPS
 
 ## Uncompress raw data into data folder
 tar -xzvf data/sequences.tar.gz -C data
@@ -17,6 +17,8 @@ chmod -w data/sequences.tar.gz
 ## Make links to data to make sub-groups
 ## It makes it easier to handle groups of files
 
+
+## This step is also done on scripts/01_quality_check.sh
 mkdir -p  data/fastq_ln/{R_seq,W_seq,Other_seq}
 
 for i in $PWD/data/sequences/R*
@@ -39,5 +41,13 @@ done
 
 
 ###################################
+## CREATE PYTHON ENVIRONMENT  -- With virtualenv
+
+./scripts/00_create_py_env.sh
+## environment located in:
+## ~/envs/coev/
 
+###################################
+## QUALITY CHECK 
 
+./scripts/01_quality_check.sh  $PWD/  qc_raw_data