work in progress for packaging phageterm with poetry

README.md

+DESCRIPTION
+
+\-----------------------------------------------------------------------------------------------------------------------
+
+These tests aim at checking that refactoring in the code and porting it to python 3 do not induce changes in what is crucial in the final result.
+
+The file virome\_assembly\_raw.fa is the concatenation of all other .fasta files.
+
+AUTHOR
+
+\----------------------------------------------------------------------------------------------------------------------
+
+Véronique Legrand vlegrand@pasteur.fr
+
+Data for the tests were provided by Julian Garneau
+
+Explanation on what statistics should be carefully looked at was provided by Marc Monot

non-regression-tests/run_HK97.sh

 #/bin/bash
 DATA_PATH=./data
 REF_RES_PATH=./reference_results
+SCRIPT_PATH=../_modules
 
 echo "running PhageTerm on HK97 genome"
-python ../PhageTerm.py -f $DATA_PATH/R1_1M_READS_EACH_PHAGE.fastq.20 -p $DATA_PATH/R2_1M_READS_EACH_PHAGE.fastq.20 -r $DATA_PATH/HK97_assembly.fasta || exit 1
+python $SCRIPT_PATH/PhageTerm.py -f $DATA_PATH/R1_1M_READS_EACH_PHAGE.fastq.20 -p $DATA_PATH/R2_1M_READS_EACH_PHAGE.fastq.20 -r $DATA_PATH/HK97_assembly.fasta || exit 1
 python check_HK97_res.py || exit 2

non-regression-tests/run_HK97_long.sh

 #/bin/bash
 DATA_PATH=./data
+SCRIPT_PATH=../_modules
+
 
 echo "running PhageTerm on HK97 genome and a dataset with a minimum 50x coverage"
-python ../PhageTerm.py -f "$DATA_PATH/R1_1M_READS_EACH_PHAGE(1).fastq.4" -p "$DATA_PATH/R2_1M_READS_EACH_PHAGE(1).fastq.4" -r $DATA_PATH/HK97_assembly.fasta --nrt || exit 1
+python $SCRIPT_PATH/PhageTerm.py -f "$DATA_PATH/R1_1M_READS_EACH_PHAGE(1).fastq.4" -p "$DATA_PATH/R2_1M_READS_EACH_PHAGE(1).fastq.4" -r $DATA_PATH/HK97_assembly.fasta --nrt || exit 1
 python check_HK97_class.py || exit 2

non-regression-tests/run_HK97_long_multiproc.sh

 #/bin/bash
 DATA_PATH=./data
+SCRIPT_PATH=../_modules
 
 echo "running PhageTerm on HK97 genome and a dataset with a minimum 50x coverage"
-python ../PhageTerm.py -c 4 -f "$DATA_PATH/R1_1M_READS_EACH_PHAGE(1).fastq.4" -p "$DATA_PATH/R2_1M_READS_EACH_PHAGE(1).fastq.4" -r $DATA_PATH/HK97_assembly.fasta --nrt
+python $SCRIPT_PATH/PhageTerm.py -c 4 -f "$DATA_PATH/R1_1M_READS_EACH_PHAGE(1).fastq.4" -p "$DATA_PATH/R2_1M_READS_EACH_PHAGE(1).fastq.4" -r $DATA_PATH/HK97_assembly.fasta --nrt
 python check_HK97_class.py

non-regression-tests/run_Lamda_long.sh

 #/bin/bash
 DATA_PATH=./data
+SCRIPT_PATH=../_modules
 
 echo "running PhageTerm on Lamda genome and a dataset with a minimum 50x coverage"
-python ../PhageTerm.py -f "$DATA_PATH/R1_1M_READS_EACH_PHAGE(1).fastq.4" -p "$DATA_PATH/R2_1M_READS_EACH_PHAGE(1).fastq.4" -r $DATA_PATH/Lambda_assembly.fasta --nrt || exit 1
+python $SCRIPT_PATH/PhageTerm.py -f "$DATA_PATH/R1_1M_READS_EACH_PHAGE(1).fastq.4" -p "$DATA_PATH/R2_1M_READS_EACH_PHAGE(1).fastq.4" -r $DATA_PATH/Lambda_assembly.fasta --nrt || exit 1
 python check_Lamda_class.py || exit 2

non-regression-tests/run_Lamda_long_multiproc.sh

 #/bin/bash
 DATA_PATH=./data
+SCRIPT_PATH=../_modules
 
 echo "running PhageTerm on Lamda genome and a dataset with a minimum 50x coverage"
-python ../PhageTerm.py -c 4 -f "$DATA_PATH/R1_1M_READS_EACH_PHAGE(1).fastq.4" -p "$DATA_PATH/R2_1M_READS_EACH_PHAGE(1).fastq.4" -r $DATA_PATH/Lambda_assembly.fasta --nrt
+python $SCRIPT_PATH/PhageTerm.py -c 4 -f "$DATA_PATH/R1_1M_READS_EACH_PHAGE(1).fastq.4" -p "$DATA_PATH/R2_1M_READS_EACH_PHAGE(1).fastq.4" -r $DATA_PATH/Lambda_assembly.fasta --nrt
 python check_Lamda_class.py

non-regression-tests/run_N1.sh

 #/bin/bash
 DATA_PATH=./data
 REF_RES_PATH=./reference_results
+SCRIPT_PATH=../_modules
 
 echo "running PhageTerm on StaphN1 genome"
-python ../PhageTerm.py -f $DATA_PATH/R1_1M_READS_EACH_PHAGE.fastq.20 -p $DATA_PATH/R2_1M_READS_EACH_PHAGE.fastq.20 -r $DATA_PATH/Staph1N_assembly.fasta ||exit 1
+python $SCRIPT_PATH/PhageTerm.py -f $DATA_PATH/R1_1M_READS_EACH_PHAGE.fastq.20 -p $DATA_PATH/R2_1M_READS_EACH_PHAGE.fastq.20 -r $DATA_PATH/Staph1N_assembly.fasta ||exit 1
 python check_N1_res.py ||exit 1

non-regression-tests/run_P1.sh

 #/bin/bash
 DATA_PATH=./data
 REF_RES_PATH=./reference_results
+SCRIPT_PATH=../_modules
 
 echo "running PhageTerm on P1 genome"
-python ../PhageTerm.py -f $DATA_PATH/R1_1M_READS_EACH_PHAGE.fastq.20 -p $DATA_PATH/R2_1M_READS_EACH_PHAGE.fastq.20 -r $DATA_PATH/P1_assembly.fasta || exit 1
+python $SCRIPT_PATH/PhageTerm.py -f $DATA_PATH/R1_1M_READS_EACH_PHAGE.fastq.20 -p $DATA_PATH/R2_1M_READS_EACH_PHAGE.fastq.20 -r $DATA_PATH/P1_assembly.fasta || exit 1
 python check_P1_res.py || exit 2

non-regression-tests/run_P1_long.sh

 #/bin/bash
 DATA_PATH=./data
+SCRIPT_PATH=../_modules
 
 echo "running PhageTerm on P1 genome and a dataset with a minimum 50x coverage"
-python ../PhageTerm.py -f "$DATA_PATH/R1_1M_READS_EACH_PHAGE(1).fastq.4" -p "$DATA_PATH/R2_1M_READS_EACH_PHAGE(1).fastq.4" -r $DATA_PATH/P1_assembly.fasta --nrt || exit 1
+python $SCRIPT_PATH/PhageTerm.py -f "$DATA_PATH/R1_1M_READS_EACH_PHAGE(1).fastq.4" -p "$DATA_PATH/R2_1M_READS_EACH_PHAGE(1).fastq.4" -r $DATA_PATH/P1_assembly.fasta --nrt || exit 1
 python check_P1_class.py || exit 2

non-regression-tests/run_P1_long_multiproc.sh

 #/bin/bash
 DATA_PATH=./data
+SCRIPT_PATH=../_modules
 
 echo "running PhageTerm on P1 genome and a dataset with a minimum 50x coverage"
-python ../PhageTerm.py -c 4 -f "$DATA_PATH/R1_1M_READS_EACH_PHAGE(1).fastq.4" -p "$DATA_PATH/R2_1M_READS_EACH_PHAGE(1).fastq.4" -r $DATA_PATH/P1_assembly.fasta --nrt
+python $SCRIPT_PATH/PhageTerm.py -c 4 -f "$DATA_PATH/R1_1M_READS_EACH_PHAGE(1).fastq.4" -p "$DATA_PATH/R2_1M_READS_EACH_PHAGE(1).fastq.4" -r $DATA_PATH/P1_assembly.fasta --nrt
 python check_P1_class.py

non-regression-tests/run_StaphN1_long.sh

 #/bin/bash
 DATA_PATH=./data
+SCRIPT_PATH=../_modules
 
 echo "running PhageTerm on Staph1N genome and a dataset with a minimum 50x coverage"
-python ../PhageTerm.py --nrt -f "$DATA_PATH/R1_1M_READS_EACH_PHAGE(1).fastq.4" -p "$DATA_PATH/R2_1M_READS_EACH_PHAGE(1).fastq.4" -r $DATA_PATH/Staph1N_assembly.fasta || exit 1
+python $SCRIPT_PATH/PhageTerm.py --nrt -f "$DATA_PATH/R1_1M_READS_EACH_PHAGE(1).fastq.4" -p "$DATA_PATH/R2_1M_READS_EACH_PHAGE(1).fastq.4" -r $DATA_PATH/Staph1N_assembly.fasta || exit 1
 python check_Staph1N_class.py || exit 2

non-regression-tests/run_StaphN1_long_multiproc.sh

 #/bin/bash
 DATA_PATH=./data
+SCRIPT_PATH=../_modules
 
 echo "running PhageTerm on Staph1N genome and a dataset with a minimum 50x coverage"
-python ../PhageTerm.py -c 4 --nrt -f "$DATA_PATH/R1_1M_READS_EACH_PHAGE(1).fastq.4" -p "$DATA_PATH/R2_1M_READS_EACH_PHAGE(1).fastq.4" -r $DATA_PATH/Staph1N_assembly.fasta
+python $SCRIPT_PATH/PhageTerm.py -c 4 --nrt -f "$DATA_PATH/R1_1M_READS_EACH_PHAGE(1).fastq.4" -p "$DATA_PATH/R2_1M_READS_EACH_PHAGE(1).fastq.4" -r $DATA_PATH/Staph1N_assembly.fasta
 python check_Staph1N_class.py

non-regression-tests/run_T4.sh

 #/bin/bash
 DATA_PATH=./data
 REF_RES_PATH=./reference_results
+SCRIPT_PATH=../_modules
 
 echo "running PhageTerm on T4 genome"
-python ../PhageTerm.py -f $DATA_PATH/R1_1M_READS_EACH_PHAGE.fastq.20 -p $DATA_PATH/R2_1M_READS_EACH_PHAGE.fastq.20 -r $DATA_PATH/T4_assembly.fasta || exit 1
+python $SCRIPT_PATH/PhageTerm.py -f $DATA_PATH/R1_1M_READS_EACH_PHAGE.fastq.20 -p $DATA_PATH/R2_1M_READS_EACH_PHAGE.fastq.20 -r $DATA_PATH/T4_assembly.fasta || exit 1
 #python check_T4_res.py

non-regression-tests/run_T4_long.sh

 #/bin/bash
 DATA_PATH=./data
+SCRIPT_PATH=../_modules
 
 echo "running PhageTerm on T4 genome and a dataset with a minimum 50x coverage"
-python ../PhageTerm.py -f "$DATA_PATH/R1_1M_READS_EACH_PHAGE(1).fastq.4" -p "$DATA_PATH/R2_1M_READS_EACH_PHAGE(1).fastq.4" -r $DATA_PATH/T4_assembly.fasta --nrt || exit 1
+python $SCRIPT_PATH/PhageTerm.py -f "$DATA_PATH/R1_1M_READS_EACH_PHAGE(1).fastq.4" -p "$DATA_PATH/R2_1M_READS_EACH_PHAGE(1).fastq.4" -r $DATA_PATH/T4_assembly.fasta --nrt || exit 1
 python check_T4_class.py || exit 2

non-regression-tests/run_T4_long_multiproc.sh

 #/bin/bash
 DATA_PATH=./data
+SCRIPT_PATH=../_modules
 
 echo "running PhageTerm on T4 genome and a dataset with a minimum 50x coverage"
-python ../PhageTerm.py -c 4 -f "$DATA_PATH/R1_1M_READS_EACH_PHAGE(1).fastq.4" -p "$DATA_PATH/R2_1M_READS_EACH_PHAGE(1).fastq.4" -r $DATA_PATH/T4_assembly.fasta --nrt
+python $SCRIPT_PATH/PhageTerm.py -c 4 -f "$DATA_PATH/R1_1M_READS_EACH_PHAGE(1).fastq.4" -p "$DATA_PATH/R2_1M_READS_EACH_PHAGE(1).fastq.4" -r $DATA_PATH/T4_assembly.fasta --nrt
 python check_T4_class.py

non-regression-tests/run_T7.sh

 #/bin/bash
 DATA_PATH=./data
 REF_RES_PATH=./reference_results
+SCRIPT_PATH=../_modules
 
 echo "running PhageTerm on T7 genome"
-python ../PhageTerm.py -f $DATA_PATH/R1_1M_READS_EACH_PHAGE.fastq.20 -p $DATA_PATH/R2_1M_READS_EACH_PHAGE.fastq.20 -r $DATA_PATH/T7_assembly.fasta || exit 1
+python $SCRIPT_PATH/PhageTerm.py -f $DATA_PATH/R1_1M_READS_EACH_PHAGE.fastq.20 -p $DATA_PATH/R2_1M_READS_EACH_PHAGE.fastq.20 -r $DATA_PATH/T7_assembly.fasta || exit 1
 python check_T7_res.py || exit 2

non-regression-tests/run_T7_long.sh

 #/bin/bash
 DATA_PATH=./data
+SCRIPT_PATH=../_modules
 
 echo "running PhageTerm on T7 genome and a dataset with a minimum 50x coverage"
-python ../PhageTerm.py -f "$DATA_PATH/R1_1M_READS_EACH_PHAGE(1).fastq.4" -p "$DATA_PATH/R2_1M_READS_EACH_PHAGE(1).fastq.4" -r $DATA_PATH/T7_assembly.fasta --nrt || exit 1
+python $SCRIPT_PATH/PhageTerm.py -f "$DATA_PATH/R1_1M_READS_EACH_PHAGE(1).fastq.4" -p "$DATA_PATH/R2_1M_READS_EACH_PHAGE(1).fastq.4" -r $DATA_PATH/T7_assembly.fasta --nrt || exit 1
 python check_T7_class.py || exit 2

non-regression-tests/run_T7_long_multiproc.sh

 #/bin/bash
 DATA_PATH=./data
+SCRIPT_PATH=../_modules
 
 echo "running PhageTerm on T7 genome and a dataset with a minimum 50x coverage"
-python ../PhageTerm.py -c 4 -f "$DATA_PATH/R1_1M_READS_EACH_PHAGE(1).fastq.4" -p "$DATA_PATH/R2_1M_READS_EACH_PHAGE(1).fastq.4" -r $DATA_PATH/T7_assembly.fasta --nrt
+python $SCRIPT_PATH/PhageTerm.py -c 4 -f "$DATA_PATH/R1_1M_READS_EACH_PHAGE(1).fastq.4" -p "$DATA_PATH/R2_1M_READS_EACH_PHAGE(1).fastq.4" -r $DATA_PATH/T7_assembly.fasta --nrt
 python check_T7_class.py

non-regression-tests/run_lamda.sh

 #/bin/bash
 DATA_PATH=./data
 REF_RES_PATH=./reference_results
+SCRIPT_PATH=../_modules
 
 echo "running PhageTerm on lamda genome"
-python ../PhageTerm.py -f $DATA_PATH/R1_1M_READS_EACH_PHAGE.fastq.20 -p $DATA_PATH/R2_1M_READS_EACH_PHAGE.fastq.20 -r $DATA_PATH/Lambda_assembly.fasta || exit 1
+python $SCRIPT_PATH/PhageTerm.py -f $DATA_PATH/R1_1M_READS_EACH_PHAGE.fastq.20 -p $DATA_PATH/R2_1M_READS_EACH_PHAGE.fastq.20 -r $DATA_PATH/Lambda_assembly.fasta || exit 1
 python check_lamda_res.py || exit 2
 

non-regression-tests/run_nrt_long_multiproc.sh

 #/bin/bash
 ## VL: decided to write the checking of results in python scripts rather than shel script for portability.
-echo "running non regression tests (short version)"
+echo "running non regression tests (parallel version; requires 4 cores)"
 ./run_HK97_long_multiproc.sh || exit 1
 ./run_Lamda_long_multiproc.sh || exit 1
 ./run_StaphN1_long_multiproc.sh || exit 1