tanu/LSHTM_analysis
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity

refactor foldx pipeline to include:

Browse source 
* command-line args
* creating necessary dirs automagically
* code cleanup, syntax errors, etc etc
This commit is contained in:
Tanushree Tunstall 2020-06-30 17:14:30 +01:00
parent af65a86ff9
commit 4d686e2933
12 changed files with 700 additions and 56 deletions
Download patch file Download diff file Expand all files Collapse all files

69
foldx/mutrenamefiles.sh Executable file
View file

@ -0,0 +1,69 @@
PDB=$1
n=$2
OUTDIR=$3
cd ${OUTDIR}
logger "Running mutrenamefiles with PDB: ${PDB} n: ${n} OUTDIR: ${OUTDIR}"
cp Matrix_Hbonds_${PDB}_Repair_${n}_PN.fxout Matrix_Hbonds_${PDB}_Repair_${n}_PN.txt
sed -n '5,190p' Matrix_Hbonds_${PDB}_Repair_${n}_PN.fxout > Matrix_Hbonds_RR_${PDB}_Repair_${n}_PN.txt
sed -n '194,379p' Matrix_Hbonds_${PDB}_Repair_${n}_PN.fxout > Matrix_Hbonds_MM_${PDB}_Repair_${n}_PN.txt
sed -n '383,568p' Matrix_Hbonds_${PDB}_Repair_${n}_PN.fxout > Matrix_Hbonds_SM_${PDB}_Repair_${n}_PN.txt
sed -n '572,757p' Matrix_Hbonds_${PDB}_Repair_${n}_PN.fxout > Matrix_Hbonds_SS_${PDB}_Repair_${n}_PN.txt
cp Matrix_Distances_${PDB}_Repair_${n}_PN.fxout Matrix_Distances_${PDB}_Repair_${n}_PN.txt
sed -i '1,4d' Matrix_Distances_${PDB}_Repair_${n}_PN.txt
cp Matrix_Volumetric_${PDB}_Repair_${n}_PN.fxout Matrix_Volumetric_${PDB}_Repair_${n}_PN.txt
sed -n '5,190p' Matrix_Volumetric_${PDB}_Repair_${n}_PN.fxout > Matrix_Volumetric_RR_${PDB}_Repair_${n}_PN.txt
sed -n '194,379p' Matrix_Volumetric_${PDB}_Repair_${n}_PN.fxout > Matrix_Volumetric_MM_${PDB}_Repair_${n}_PN.txt
sed -n '383,568p' Matrix_Volumetric_${PDB}_Repair_${n}_PN.fxout > Matrix_Volumetric_SM_${PDB}_Repair_${n}_PN.txt
sed -n '572,757p' Matrix_Volumetric_${PDB}_Repair_${n}_PN.fxout > Matrix_Volumetric_SS_${PDB}_Repair_${n}_PN.txt
cp Matrix_Electro_${PDB}_Repair_${n}_PN.fxout Matrix_Electro_${PDB}_Repair_${n}_PN.txt
sed -n '5,190p' Matrix_Electro_${PDB}_Repair_${n}_PN.fxout > Matrix_Electro_RR_${PDB}_Repair_${n}_PN.txt
sed -n '194,379p' Matrix_Electro_${PDB}_Repair_${n}_PN.fxout > Matrix_Electro_MM_${PDB}_Repair_${n}_PN.txt
sed -n '383,568p' Matrix_Electro_${PDB}_Repair_${n}_PN.fxout > Matrix_Electro_SM_${PDB}_Repair_${n}_PN.txt
sed -n '572,757p' Matrix_Electro_${PDB}_Repair_${n}_PN.fxout > Matrix_Electro_SS_${PDB}_Repair_${n}_PN.txt
cp Matrix_Disulfide_${PDB}_Repair_${n}_PN.fxout Matrix_Disulfide_${PDB}_Repair_${n}_PN.txt
sed -n '5,190p' Matrix_Disulfide_${PDB}_Repair_${n}_PN.fxout > Matrix_Disulfide_RR_${PDB}_Repair_${n}_PN.txt
sed -n '194,379p' Matrix_Disulfide_${PDB}_Repair_${n}_PN.fxout > Matrix_Disulfide_MM_${PDB}_Repair_${n}_PN.txt
sed -n '383,568p' Matrix_Disulfide_${PDB}_Repair_${n}_PN.fxout > Matrix_Disulfide_SM_${PDB}_Repair_${n}_PN.txt
sed -n '572,757p' Matrix_Disulfide_${PDB}_Repair_${n}_PN.fxout > Matrix_Disulfide_SS_${PDB}_Repair_${n}_PN.txt
cp Matrix_Partcov_${PDB}_Repair_${n}_PN.fxout Matrix_Partcov_${PDB}_Repair_${n}_PN.txt
sed -n '5,190p' Matrix_Partcov_${PDB}_Repair_${n}_PN.fxout > Matrix_Partcov_RR_${PDB}_Repair_${n}_PN.txt
sed -n '194,379p' Matrix_Partcov_${PDB}_Repair_${n}_PN.fxout > Matrix_Partcov_MM_${PDB}_Repair_${n}_PN.txt
sed -n '383,568p' Matrix_Partcov_${PDB}_Repair_${n}_PN.fxout > Matrix_Partcov_SM_${PDB}_Repair_${n}_PN.txt
sed -n '572,757p' Matrix_Partcov_${PDB}_Repair_${n}_PN.fxout > Matrix_Partcov_SS_${PDB}_Repair_${n}_PN.txt
cp Matrix_VdWClashes_${PDB}_Repair_${n}_PN.fxout Matrix_VdWClashes_${PDB}_Repair_${n}_PN.txt
sed -n '5,190p' Matrix_VdWClashes_${PDB}_Repair_${n}_PN.fxout > Matrix_VdWClashes_RR_${PDB}_Repair_${n}_PN.txt
sed -n '194,379p' Matrix_VdWClashes_${PDB}_Repair_${n}_PN.fxout > Matrix_VdWClashes_MM_${PDB}_Repair_${n}_PN.txt
sed -n '383,568p' Matrix_VdWClashes_${PDB}_Repair_${n}_PN.fxout > Matrix_VdWClashes_SM_${PDB}_Repair_${n}_PN.txt
sed -n '572,757p' Matrix_VdWClashes_${PDB}_Repair_${n}_PN.fxout > Matrix_VdWClashes_SS_${PDB}_Repair_${n}_PN.txt
cp AllAtoms_Disulfide_${PDB}_Repair_${n}_PN.fxout AllAtoms_Disulfide_${PDB}_Repair_${n}_PN.txt
sed -i '1,2d' AllAtoms_Disulfide_${PDB}_Repair_${n}_PN.txt
cp AllAtoms_Electro_${PDB}_Repair_${n}_PN.fxout AllAtoms_Electro_${PDB}_Repair_${n}_PN.txt
sed -i '1,2d' AllAtoms_Electro_${PDB}_Repair_${n}_PN.txt
cp AllAtoms_Hbonds_${PDB}_Repair_${n}_PN.fxout AllAtoms_Hbonds_${PDB}_Repair_${n}_PN.txt
sed -i '1,2d' AllAtoms_Hbonds_${PDB}_Repair_${n}_PN.txt
cp AllAtoms_Partcov_${PDB}_Repair_${n}_PN.fxout AllAtoms_Partcov_${PDB}_Repair_${n}_PN.txt
sed -i '1,2d' AllAtoms_Partcov_${PDB}_Repair_${n}_PN.txt
cp AllAtoms_VdWClashes_${PDB}_Repair_${n}_PN.fxout AllAtoms_VdWClashes_${PDB}_Repair_${n}_PN.txt
sed -i '1,2d' AllAtoms_VdWClashes_${PDB}_Repair_${n}_PN.txt
cp AllAtoms_Volumetric_${PDB}_Repair_${n}_PN.fxout AllAtoms_Volumetric_${PDB}_Repair_${n}_PN.txt
sed -i '1,2d' AllAtoms_Volumetric_${PDB}_Repair_${n}_PN.txt
cp InteractingResidues_VdWClashes_${PDB}_Repair_${n}_PN.fxout InteractingResidues_VdWClashes_${PDB}_Repair_${n}_PN.txt
sed -i '1,5d' InteractingResidues_VdWClashes_${PDB}_Repair_${n}_PN.txt
cp InteractingResidues_Distances_${PDB}_Repair_${n}_PN.fxout InteractingResidues_Distances_${PDB}_Repair_${n}_PN.txt
sed -i '1,5d' InteractingResidues_Distances_${PDB}_Repair_${n}_PN.txt
cp InteractingResidues_Electro_${PDB}_Repair_${n}_PN.fxout InteractingResidues_Electro_${PDB}_Repair_${n}_PN.txt
sed -i '1,5d' InteractingResidues_Electro_${PDB}_Repair_${n}_PN.txt
cp InteractingResidues_Hbonds_${PDB}_Repair_${n}_PN.fxout InteractingResidues_Hbonds_${PDB}_Repair_${n}_PN.txt
sed -i '1,5d' InteractingResidues_Hbonds_${PDB}_Repair_${n}_PN.txt
cp InteractingResidues_Partcov_${PDB}_Repair_${n}_PN.fxout InteractingResidues_Partcov_${PDB}_Repair_${n}_PN.txt
sed -i '1,5d' InteractingResidues_Partcov_${PDB}_Repair_${n}_PN.txt
cp InteractingResidues_Volumetric_${PDB}_Repair_${n}_PN.fxout InteractingResidues_Volumetric_${PDB}_Repair_${n}_PN.txt
sed -i '1,5d' InteractingResidues_Volumetric_${PDB}_Repair_${n}_PN.txt
cp InteractingResidues_Disulfide_${PDB}_Repair_${n}_PN.fxout InteractingResidues_Disulfide_${PDB}_Repair_${n}_PN.txt
sed -i '1,5d' InteractingResidues_Disulfide_${PDB}_Repair_${n}_PN.txt

68
foldx/mutrenamefiles_mac.sh Executable file
View file

@ -0,0 +1,68 @@
PDB=$1
n=$2
#cd /home/tanu/git/LSHTM_analysis/foldx/
logger "Running mutrenamefiles_mac"
cp Matrix_Hbonds_${PDB}_Repair_${n}_PN.fxout Matrix_Hbonds_${PDB}_Repair_${n}_PN.txt
sed -n '5,190p' Matrix_Hbonds_${PDB}_Repair_${n}_PN.fxout > Matrix_Hbonds_RR_${PDB}_Repair_${n}_PN.txt
sed -n '194,379p' Matrix_Hbonds_${PDB}_Repair_${n}_PN.fxout > Matrix_Hbonds_MM_${PDB}_Repair_${n}_PN.txt
sed -n '383,568p' Matrix_Hbonds_${PDB}_Repair_${n}_PN.fxout > Matrix_Hbonds_SM_${PDB}_Repair_${n}_PN.txt
sed -n '572,757p' Matrix_Hbonds_${PDB}_Repair_${n}_PN.fxout > Matrix_Hbonds_SS_${PDB}_Repair_${n}_PN.txt
cp Matrix_Distances_${PDB}_Repair_${n}_PN.fxout Matrix_Distances_${PDB}_Repair_${n}_PN.txt
sed -i .bak -e 1,4d Matrix_Distances_${PDB}_Repair_${n}_PN.txt
cp Matrix_Volumetric_${PDB}_Repair_${n}_PN.fxout Matrix_Volumetric_${PDB}_Repair_${n}_PN.txt
sed -n '5,190p' Matrix_Volumetric_${PDB}_Repair_${n}_PN.fxout > Matrix_Volumetric_RR_${PDB}_Repair_${n}_PN.txt
sed -n '194,379p' Matrix_Volumetric_${PDB}_Repair_${n}_PN.fxout > Matrix_Volumetric_MM_${PDB}_Repair_${n}_PN.txt
sed -n '383,568p' Matrix_Volumetric_${PDB}_Repair_${n}_PN.fxout > Matrix_Volumetric_SM_${PDB}_Repair_${n}_PN.txt
sed -n '572,757p' Matrix_Volumetric_${PDB}_Repair_${n}_PN.fxout > Matrix_Volumetric_SS_${PDB}_Repair_${n}_PN.txt
cp Matrix_Electro_${PDB}_Repair_${n}_PN.fxout Matrix_Electro_${PDB}_Repair_${n}_PN.txt
sed -n '5,190p' Matrix_Electro_${PDB}_Repair_${n}_PN.fxout > Matrix_Electro_RR_${PDB}_Repair_${n}_PN.txt
sed -n '194,379p' Matrix_Electro_${PDB}_Repair_${n}_PN.fxout > Matrix_Electro_MM_${PDB}_Repair_${n}_PN.txt
sed -n '383,568p' Matrix_Electro_${PDB}_Repair_${n}_PN.fxout > Matrix_Electro_SM_${PDB}_Repair_${n}_PN.txt
sed -n '572,757p' Matrix_Electro_${PDB}_Repair_${n}_PN.fxout > Matrix_Electro_SS_${PDB}_Repair_${n}_PN.txt
cp Matrix_Disulfide_${PDB}_Repair_${n}_PN.fxout Matrix_Disulfide_${PDB}_Repair_${n}_PN.txt
sed -n '5,190p' Matrix_Disulfide_${PDB}_Repair_${n}_PN.fxout > Matrix_Disulfide_RR_${PDB}_Repair_${n}_PN.txt
sed -n '194,379p' Matrix_Disulfide_${PDB}_Repair_${n}_PN.fxout > Matrix_Disulfide_MM_${PDB}_Repair_${n}_PN.txt
sed -n '383,568p' Matrix_Disulfide_${PDB}_Repair_${n}_PN.fxout > Matrix_Disulfide_SM_${PDB}_Repair_${n}_PN.txt
sed -n '572,757p' Matrix_Disulfide_${PDB}_Repair_${n}_PN.fxout > Matrix_Disulfide_SS_${PDB}_Repair_${n}_PN.txt
cp Matrix_Partcov_${PDB}_Repair_${n}_PN.fxout Matrix_Partcov_${PDB}_Repair_${n}_PN.txt
sed -n '5,190p' Matrix_Partcov_${PDB}_Repair_${n}_PN.fxout > Matrix_Partcov_RR_${PDB}_Repair_${n}_PN.txt
sed -n '194,379p' Matrix_Partcov_${PDB}_Repair_${n}_PN.fxout > Matrix_Partcov_MM_${PDB}_Repair_${n}_PN.txt
sed -n '383,568p' Matrix_Partcov_${PDB}_Repair_${n}_PN.fxout > Matrix_Partcov_SM_${PDB}_Repair_${n}_PN.txt
sed -n '572,757p' Matrix_Partcov_${PDB}_Repair_${n}_PN.fxout > Matrix_Partcov_SS_${PDB}_Repair_${n}_PN.txt
cp Matrix_VdWClashes_${PDB}_Repair_${n}_PN.fxout Matrix_VdWClashes_${PDB}_Repair_${n}_PN.txt
sed -n '5,190p' Matrix_VdWClashes_${PDB}_Repair_${n}_PN.fxout > Matrix_VdWClashes_RR_${PDB}_Repair_${n}_PN.txt
sed -n '194,379p' Matrix_VdWClashes_${PDB}_Repair_${n}_PN.fxout > Matrix_VdWClashes_MM_${PDB}_Repair_${n}_PN.txt
sed -n '383,568p' Matrix_VdWClashes_${PDB}_Repair_${n}_PN.fxout > Matrix_VdWClashes_SM_${PDB}_Repair_${n}_PN.txt
sed -n '572,757p' Matrix_VdWClashes_${PDB}_Repair_${n}_PN.fxout > Matrix_VdWClashes_SS_${PDB}_Repair_${n}_PN.txt
cp AllAtoms_Disulfide_${PDB}_Repair_${n}_PN.fxout AllAtoms_Disulfide_${PDB}_Repair_${n}_PN.txt
sed -i .bak -e 1,2d AllAtoms_Disulfide_${PDB}_Repair_${n}_PN.txt
cp AllAtoms_Electro_${PDB}_Repair_${n}_PN.fxout AllAtoms_Electro_${PDB}_Repair_${n}_PN.txt
sed -i .bak -e 1,2d AllAtoms_Electro_${PDB}_Repair_${n}_PN.txt
cp AllAtoms_Hbonds_${PDB}_Repair_${n}_PN.fxout AllAtoms_Hbonds_${PDB}_Repair_${n}_PN.txt
sed -i .bak -e 1,2d AllAtoms_Hbonds_${PDB}_Repair_${n}_PN.txt
cp AllAtoms_Partcov_${PDB}_Repair_${n}_PN.fxout AllAtoms_Partcov_${PDB}_Repair_${n}_PN.txt
sed -i .bak -e 1,2d AllAtoms_Partcov_${PDB}_Repair_${n}_PN.txt
cp AllAtoms_VdWClashes_${PDB}_Repair_${n}_PN.fxout AllAtoms_VdWClashes_${PDB}_Repair_${n}_PN.txt
sed -i .bak -e 1,2d AllAtoms_VdWClashes_${PDB}_Repair_${n}_PN.txt
cp AllAtoms_Volumetric_${PDB}_Repair_${n}_PN.fxout AllAtoms_Volumetric_${PDB}_Repair_${n}_PN.txt
sed -i .bak -e 1,2d AllAtoms_Volumetric_${PDB}_Repair_${n}_PN.txt
cp InteractingResidues_VdWClashes_${PDB}_Repair_${n}_PN.fxout InteractingResidues_VdWClashes_${PDB}_Repair_${n}_PN.txt
sed -i .bak -e 1,5d InteractingResidues_VdWClashes_${PDB}_Repair_${n}_PN.txt
cp InteractingResidues_Distances_${PDB}_Repair_${n}_PN.fxout InteractingResidues_Distances_${PDB}_Repair_${n}_PN.txt
sed -i .bak -e 1,5d InteractingResidues_Distances_${PDB}_Repair_${n}_PN.txt
cp InteractingResidues_Electro_${PDB}_Repair_${n}_PN.fxout InteractingResidues_Electro_${PDB}_Repair_${n}_PN.txt
sed -i .bak -e 1,5d InteractingResidues_Electro_${PDB}_Repair_${n}_PN.txt
cp InteractingResidues_Hbonds_${PDB}_Repair_${n}_PN.fxout InteractingResidues_Hbonds_${PDB}_Repair_${n}_PN.txt
sed -i .bak -e 1,5d InteractingResidues_Hbonds_${PDB}_Repair_${n}_PN.txt
cp InteractingResidues_Partcov_${PDB}_Repair_${n}_PN.fxout InteractingResidues_Partcov_${PDB}_Repair_${n}_PN.txt
sed -i .bak -e 1,5d InteractingResidues_Partcov_${PDB}_Repair_${n}_PN.txt
cp InteractingResidues_Volumetric_${PDB}_Repair_${n}_PN.fxout InteractingResidues_Volumetric_${PDB}_Repair_${n}_PN.txt
sed -i .bak -e 1,5d InteractingResidues_Volumetric_${PDB}_Repair_${n}_PN.txt
cp InteractingResidues_Disulfide_${PDB}_Repair_${n}_PN.fxout InteractingResidues_Disulfide_${PDB}_Repair_${n}_PN.txt
sed -i .bak -e 1,5d InteractingResidues_Disulfide_${PDB}_Repair_${n}_PN.txt

10
foldx/mutruncomplex.sh Executable file
View file

@ -0,0 +1,10 @@
PDB=$1
A=$2
B=$3
n=$4
OUTDIR=$5
cd ${OUTDIR}
logger "Running mutruncomplex"
foldx --command=AnalyseComplex --pdb="${PDB}_Repair_${n}.pdb" --analyseComplexChains=${A},${B} --water=PREDICT --vdwDesign=1
cp ${OUTDIR}/Summary_${PDB}_Repair_${n}_AC.fxout ${OUTDIR}/Summary_${PDB}_Repair_${n}_AC.txt
#sed -i .bak -e 1,8d ${OUTDIR}/Summary_${PDB}_Repair_${n}_AC.txt

70
foldx/renamefiles.sh Executable file
View file

@ -0,0 +1,70 @@
PDB=$1
OUTDIR=$2
cd ${OUTDIR}
logger "Running renamefiles"
cp Dif_${PDB}_Repair.fxout Dif_${PDB}_Repair.txt
sed -i '1,8d' Dif_${PDB}_Repair.txt
cp Matrix_Hbonds_${PDB}_Repair_PN.fxout Matrix_Hbonds_${PDB}_Repair_PN.txt
sed -n '5,190p' Matrix_Hbonds_${PDB}_Repair_PN.fxout > Matrix_Hbonds_RR_${PDB}_Repair_PN.txt
sed -n '194,379p' Matrix_Hbonds_${PDB}_Repair_PN.fxout > Matrix_Hbonds_MM_${PDB}_Repair_PN.txt
sed -n '383,568p' Matrix_Hbonds_${PDB}_Repair_PN.fxout > Matrix_Hbonds_SM_${PDB}_Repair_PN.txt
sed -n '572,757p' Matrix_Hbonds_${PDB}_Repair_PN.fxout > Matrix_Hbonds_SS_${PDB}_Repair_PN.txt
cp Matrix_Distances_${PDB}_Repair_PN.fxout Matrix_Distances_${PDB}_Repair_PN.txt
sed -i '1,4d' Matrix_Distances_${PDB}_Repair_PN.txt
cp Matrix_Volumetric_${PDB}_Repair_PN.fxout Matrix_Volumetric_${PDB}_Repair_PN.txt
sed -n '5,190p' Matrix_Volumetric_${PDB}_Repair_PN.fxout > Matrix_Volumetric_RR_${PDB}_Repair_PN.txt
sed -n '194,379p' Matrix_Volumetric_${PDB}_Repair_PN.fxout > Matrix_Volumetric_MM_${PDB}_Repair_PN.txt
sed -n '383,568p' Matrix_Volumetric_${PDB}_Repair_PN.fxout > Matrix_Volumetric_SM_${PDB}_Repair_PN.txt
sed -n '572,757p' Matrix_Volumetric_${PDB}_Repair_PN.fxout > Matrix_Volumetric_SS_${PDB}_Repair_PN.txt
cp Matrix_Electro_${PDB}_Repair_PN.fxout Matrix_Electro_${PDB}_Repair_PN.txt
sed -n '5,190p' Matrix_Electro_${PDB}_Repair_PN.fxout > Matrix_Electro_RR_${PDB}_Repair_PN.txt
sed -n '194,379p' Matrix_Electro_${PDB}_Repair_PN.fxout > Matrix_Electro_MM_${PDB}_Repair_PN.txt
sed -n '383,568p' Matrix_Electro_${PDB}_Repair_PN.fxout > Matrix_Electro_SM_${PDB}_Repair_PN.txt
sed -n '572,757p' Matrix_Electro_${PDB}_Repair_PN.fxout > Matrix_Electro_SS_${PDB}_Repair_PN.txt
cp Matrix_Disulfide_${PDB}_Repair_PN.fxout Matrix_Disulfide_${PDB}_Repair_PN.txt
sed -n '5,190p' Matrix_Disulfide_${PDB}_Repair_PN.fxout > Matrix_Disulfide_RR_${PDB}_Repair_PN.txt
sed -n '194,379p' Matrix_Disulfide_${PDB}_Repair_PN.fxout > Matrix_Disulfide_MM_${PDB}_Repair_PN.txt
sed -n '383,568p' Matrix_Disulfide_${PDB}_Repair_PN.fxout > Matrix_Disulfide_SM_${PDB}_Repair_PN.txt
sed -n '572,757p' Matrix_Disulfide_${PDB}_Repair_PN.fxout > Matrix_Disulfide_SS_${PDB}_Repair_PN.txt
cp Matrix_Partcov_${PDB}_Repair_PN.fxout Matrix_Partcov_${PDB}_Repair_PN.txt
sed -n '5,190p' Matrix_Partcov_${PDB}_Repair_PN.fxout > Matrix_Partcov_RR_${PDB}_Repair_PN.txt
sed -n '194,379p' Matrix_Partcov_${PDB}_Repair_PN.fxout > Matrix_Partcov_MM_${PDB}_Repair_PN.txt
sed -n '383,568p' Matrix_Partcov_${PDB}_Repair_PN.fxout > Matrix_Partcov_SM_${PDB}_Repair_PN.txt
sed -n '572,757p' Matrix_Partcov_${PDB}_Repair_PN.fxout > Matrix_Partcov_SS_${PDB}_Repair_PN.txt
cp Matrix_VdWClashes_${PDB}_Repair_PN.fxout Matrix_VdWClashes_${PDB}_Repair_PN.txt
sed -n '5,190p' Matrix_VdWClashes_${PDB}_Repair_PN.fxout > Matrix_VdWClashes_RR_${PDB}_Repair_PN.txt
sed -n '194,379p' Matrix_VdWClashes_${PDB}_Repair_PN.fxout > Matrix_VdWClashes_MM_${PDB}_Repair_PN.txt
sed -n '383,568p' Matrix_VdWClashes_${PDB}_Repair_PN.fxout > Matrix_VdWClashes_SM_${PDB}_Repair_PN.txt
sed -n '572,757p' Matrix_VdWClashes_${PDB}_Repair_PN.fxout > Matrix_VdWClashes_SS_${PDB}_Repair_PN.txt
cp AllAtoms_Disulfide_${PDB}_Repair_PN.fxout AllAtoms_Disulfide_${PDB}_Repair_PN.txt
sed -i '1,2d' AllAtoms_Disulfide_${PDB}_Repair_PN.txt
cp AllAtoms_Electro_${PDB}_Repair_PN.fxout AllAtoms_Electro_${PDB}_Repair_PN.txt
sed -i '1,2d' AllAtoms_Electro_${PDB}_Repair_PN.txt
cp AllAtoms_Hbonds_${PDB}_Repair_PN.fxout AllAtoms_Hbonds_${PDB}_Repair_PN.txt
sed -i '1,2d' AllAtoms_Hbonds_${PDB}_Repair_PN.txt
cp AllAtoms_Partcov_${PDB}_Repair_PN.fxout AllAtoms_Partcov_${PDB}_Repair_PN.txt
sed -i '1,2d' AllAtoms_Partcov_${PDB}_Repair_PN.txt
cp AllAtoms_VdWClashes_${PDB}_Repair_PN.fxout AllAtoms_VdWClashes_${PDB}_Repair_PN.txt
sed -i '1,2d' AllAtoms_VdWClashes_${PDB}_Repair_PN.txt
cp AllAtoms_Volumetric_${PDB}_Repair_PN.fxout AllAtoms_Volumetric_${PDB}_Repair_PN.txt
sed -i '1,2d' AllAtoms_Volumetric_${PDB}_Repair_PN.txt
cp InteractingResidues_VdWClashes_${PDB}_Repair_PN.fxout InteractingResidues_VdWClashes_${PDB}_Repair_PN.txt
sed -i '1,5d' InteractingResidues_VdWClashes_${PDB}_Repair_PN.txt
cp InteractingResidues_Distances_${PDB}_Repair_PN.fxout InteractingResidues_Distances_${PDB}_Repair_PN.txt
sed -i '1,5d' InteractingResidues_Distances_${PDB}_Repair_PN.txt
cp InteractingResidues_Electro_${PDB}_Repair_PN.fxout InteractingResidues_Electro_${PDB}_Repair_PN.txt
sed -i '1,5d' InteractingResidues_Electro_${PDB}_Repair_PN.txt
cp InteractingResidues_Hbonds_${PDB}_Repair_PN.fxout InteractingResidues_Hbonds_${PDB}_Repair_PN.txt
sed -i '1,5d' InteractingResidues_Hbonds_${PDB}_Repair_PN.txt
cp InteractingResidues_Partcov_${PDB}_Repair_PN.fxout InteractingResidues_Partcov_${PDB}_Repair_PN.txt
sed -i '1,5d' InteractingResidues_Partcov_${PDB}_Repair_PN.txt
cp InteractingResidues_Volumetric_${PDB}_Repair_PN.fxout InteractingResidues_Volumetric_${PDB}_Repair_PN.txt
sed -i '1,5d' InteractingResidues_Volumetric_${PDB}_Repair_PN.txt
cp InteractingResidues_Disulfide_${PDB}_Repair_PN.fxout InteractingResidues_Disulfide_${PDB}_Repair_PN.txt
sed -i '1,5d' InteractingResidues_Disulfide_${PDB}_Repair_PN.txt

68
foldx/renamefiles_mac.sh Executable file
View file

@ -0,0 +1,68 @@
PDB=$1
logger "Running renamefiles_mac"
#cp Dif_${PDB}_Repair.fxout Dif_${PDB}_Repair.txt
sed -i '.bak' -e 1,8d Dif_${PDB}_Repair.txt
cp Matrix_Hbonds_${PDB}_Repair_PN.fxout Matrix_Hbonds_${PDB}_Repair_PN.txt
sed -n '5,190p' Matrix_Hbonds_${PDB}_Repair_PN.fxout > Matrix_Hbonds_RR_${PDB}_Repair_PN.txt
sed -n '194,379p' Matrix_Hbonds_${PDB}_Repair_PN.fxout > Matrix_Hbonds_MM_${PDB}_Repair_PN.txt
sed -n '383,568p' Matrix_Hbonds_${PDB}_Repair_PN.fxout > Matrix_Hbonds_SM_${PDB}_Repair_PN.txt
sed -n '572,757p' Matrix_Hbonds_${PDB}_Repair_PN.fxout > Matrix_Hbonds_SS_${PDB}_Repair_PN.txt
cp Matrix_Distances_${PDB}_Repair_PN.fxout Matrix_Distances_${PDB}_Repair_PN.txt
sed -i '.bak' -e 1,4d Matrix_Distances_${PDB}_Repair_PN.txt
cp Matrix_Volumetric_${PDB}_Repair_PN.fxout Matrix_Volumetric_${PDB}_Repair_PN.txt
sed -n '5,190p' Matrix_Volumetric_${PDB}_Repair_PN.fxout > Matrix_Volumetric_RR_${PDB}_Repair_PN.txt
sed -n '194,379p' Matrix_Volumetric_${PDB}_Repair_PN.fxout > Matrix_Volumetric_MM_${PDB}_Repair_PN.txt
sed -n '383,568p' Matrix_Volumetric_${PDB}_Repair_PN.fxout > Matrix_Volumetric_SM_${PDB}_Repair_PN.txt
sed -n '572,757p' Matrix_Volumetric_${PDB}_Repair_PN.fxout > Matrix_Volumetric_SS_${PDB}_Repair_PN.txt
cp Matrix_Electro_${PDB}_Repair_PN.fxout Matrix_Electro_${PDB}_Repair_PN.txt
sed -n '5,190p' Matrix_Electro_${PDB}_Repair_PN.fxout > Matrix_Electro_RR_${PDB}_Repair_PN.txt
sed -n '194,379p' Matrix_Electro_${PDB}_Repair_PN.fxout > Matrix_Electro_MM_${PDB}_Repair_PN.txt
sed -n '383,568p' Matrix_Electro_${PDB}_Repair_PN.fxout > Matrix_Electro_SM_${PDB}_Repair_PN.txt
sed -n '572,757p' Matrix_Electro_${PDB}_Repair_PN.fxout > Matrix_Electro_SS_${PDB}_Repair_PN.txt
cp Matrix_Disulfide_${PDB}_Repair_PN.fxout Matrix_Disulfide_${PDB}_Repair_PN.txt
sed -n '5,190p' Matrix_Disulfide_${PDB}_Repair_PN.fxout > Matrix_Disulfide_RR_${PDB}_Repair_PN.txt
sed -n '194,379p' Matrix_Disulfide_${PDB}_Repair_PN.fxout > Matrix_Disulfide_MM_${PDB}_Repair_PN.txt
sed -n '383,568p' Matrix_Disulfide_${PDB}_Repair_PN.fxout > Matrix_Disulfide_SM_${PDB}_Repair_PN.txt
sed -n '572,757p' Matrix_Disulfide_${PDB}_Repair_PN.fxout > Matrix_Disulfide_SS_${PDB}_Repair_PN.txt
cp Matrix_Partcov_${PDB}_Repair_PN.fxout Matrix_Partcov_${PDB}_Repair_PN.txt
sed -n '5,190p' Matrix_Partcov_${PDB}_Repair_PN.fxout > Matrix_Partcov_RR_${PDB}_Repair_PN.txt
sed -n '194,379p' Matrix_Partcov_${PDB}_Repair_PN.fxout > Matrix_Partcov_MM_${PDB}_Repair_PN.txt
sed -n '383,568p' Matrix_Partcov_${PDB}_Repair_PN.fxout > Matrix_Partcov_SM_${PDB}_Repair_PN.txt
sed -n '572,757p' Matrix_Partcov_${PDB}_Repair_PN.fxout > Matrix_Partcov_SS_${PDB}_Repair_PN.txt
cp Matrix_VdWClashes_${PDB}_Repair_PN.fxout Matrix_VdWClashes_${PDB}_Repair_PN.txt
sed -n '5,190p' Matrix_VdWClashes_${PDB}_Repair_PN.fxout > Matrix_VdWClashes_RR_${PDB}_Repair_PN.txt
sed -n '194,379p' Matrix_VdWClashes_${PDB}_Repair_PN.fxout > Matrix_VdWClashes_MM_${PDB}_Repair_PN.txt
sed -n '383,568p' Matrix_VdWClashes_${PDB}_Repair_PN.fxout > Matrix_VdWClashes_SM_${PDB}_Repair_PN.txt
sed -n '572,757p' Matrix_VdWClashes_${PDB}_Repair_PN.fxout > Matrix_VdWClashes_SS_${PDB}_Repair_PN.txt
cp AllAtoms_Disulfide_${PDB}_Repair_PN.fxout AllAtoms_Disulfide_${PDB}_Repair_PN.txt
sed -i '.bak' -e 1,2d AllAtoms_Disulfide_${PDB}_Repair_PN.txt
cp AllAtoms_Electro_${PDB}_Repair_PN.fxout AllAtoms_Electro_${PDB}_Repair_PN.txt
sed -i '.bak' -e 1,2d AllAtoms_Electro_${PDB}_Repair_PN.txt
cp AllAtoms_Hbonds_${PDB}_Repair_PN.fxout AllAtoms_Hbonds_${PDB}_Repair_PN.txt
sed -i '.bak' -e 1,2d AllAtoms_Hbonds_${PDB}_Repair_PN.txt
cp AllAtoms_Partcov_${PDB}_Repair_PN.fxout AllAtoms_Partcov_${PDB}_Repair_PN.txt
sed -i '.bak' -e 1,2d AllAtoms_Partcov_${PDB}_Repair_PN.txt
cp AllAtoms_VdWClashes_${PDB}_Repair_PN.fxout AllAtoms_VdWClashes_${PDB}_Repair_PN.txt
sed -i '.bak' -e 1,2d AllAtoms_VdWClashes_${PDB}_Repair_PN.txt
cp AllAtoms_Volumetric_${PDB}_Repair_PN.fxout AllAtoms_Volumetric_${PDB}_Repair_PN.txt
sed -i '.bak' -e 1,2d AllAtoms_Volumetric_${PDB}_Repair_PN.txt
cp InteractingResidues_VdWClashes_${PDB}_Repair_PN.fxout InteractingResidues_VdWClashes_${PDB}_Repair_PN.txt
sed -i '.bak' -e 1,5d InteractingResidues_VdWClashes_${PDB}_Repair_PN.txt
cp InteractingResidues_Distances_${PDB}_Repair_PN.fxout InteractingResidues_Distances_${PDB}_Repair_PN.txt
sed -i '.bak' -e 1,5d InteractingResidues_Distances_${PDB}_Repair_PN.txt
cp InteractingResidues_Electro_${PDB}_Repair_PN.fxout InteractingResidues_Electro_${PDB}_Repair_PN.txt
sed -i '.bak' -e 1,5d InteractingResidues_Electro_${PDB}_Repair_PN.txt
cp InteractingResidues_Hbonds_${PDB}_Repair_PN.fxout InteractingResidues_Hbonds_${PDB}_Repair_PN.txt
sed -i '.bak' -e 1,5d InteractingResidues_Hbonds_${PDB}_Repair_PN.txt
cp InteractingResidues_Partcov_${PDB}_Repair_PN.fxout InteractingResidues_Partcov_${PDB}_Repair_PN.txt
sed -i '.bak' -e 1,5d InteractingResidues_Partcov_${PDB}_Repair_PN.txt
cp InteractingResidues_Volumetric_${PDB}_Repair_PN.fxout InteractingResidues_Volumetric_${PDB}_Repair_PN.txt
sed -i '.bak' -e 1,5d InteractingResidues_Volumetric_${PDB}_Repair_PN.txt
cp InteractingResidues_Disulfide_${PDB}_Repair_PN.fxout InteractingResidues_Disulfide_${PDB}_Repair_PN.txt
sed -i '.bak' -e 1,5d InteractingResidues_Disulfide_${PDB}_Repair_PN.txt

9
foldx/repairPDB.sh Executable file
View file

@ -0,0 +1,9 @@
INDIR=$1
PDB=$2
OUTDIR=$3
logger "Running repairPDB"
#foldx --command=RepairPDB --pdb="${PDB}.pdb" --ionStrength=0.05 --pH=7 --water=PREDICT --vdwDesign=1 outPDB=true --output-dir=${OUTDIR}
foldx --command=RepairPDB --pdb-dir=${INDIR} --pdb=${PDB} --ionStrength=0.05 --pH=7 --water=PREDICT --vdwDesign=1 outPDB=true --output-dir=${OUTDIR}

332
foldx/runFoldx.py Executable file
View file

@ -0,0 +1,332 @@
#!/usr/bin/env python3
import subprocess
import os
import numpy as np
import pandas as pd
from contextlib import suppress
from pathlib import Path
import re
import csv
import argparse
#https://realpython.com/python-pathlib/
# FIXME
#strong dependency of file and path names
#cannot pass file with path. Need to pass them separately
#assumptions made for dir struc as standard
#datadir + drug + input
#=======================================================================
#%% specify input and curr dir
homedir = os.path.expanduser('~')
# set working dir
os.getcwd()
os.chdir(homedir + '/git/LSHTM_analysis/foldx/')
os.getcwd()
#=======================================================================
#%% command line args
arg_parser = argparse.ArgumentParser()
arg_parser.add_argument('-d', '--drug', help = 'drug name', default = 'pyrazinamide')
arg_parser.add_argument('-g', '--gene', help = 'gene name', default = 'pncA') # case sensitive
arg_parser.add_argument('-i', '--input_dir', help = 'Input dir containing pdb files. By default, it assmumes homedir + drug + input', default = None)
arg_parser.add_argument('-o', '--output_dir', help = 'Output dir for results. By default, it assmes homedir + drug + output', default = None)
arg_parser.add_argument('-f', '--pdb_file', help = 'PDB File to process. By default, it assmumes a file called gene_complex.pdb', default = None)
arg_parser.add_argument('-m', '--mutation_file', help = 'Mutation list. By default, assumes a file called gene_test_snps.csv exists', default = None)
arg_parser.add_argument('-c1', '--chain1', help = 'Chain1 ID', default = 'A') # case sensitive
arg_parser.add_argument('-c2', '--chain2', help = 'Chain2 ID', default = 'B') # case sensitive
args = arg_parser.parse_args()
#=======================================================================
#%% variable assignment: input and output
#drug = 'pyrazinamide'
#gene = 'pncA'
#gene_match = gene + '_p.'
#%%=====================================================================
# Command Line Options
drug = args.drug
gene = args.gene
indir = args.input_dir
outdir = args.output_dir
mut_filename = args.mutation_file
chainA = args.chain1
chainB = args.chain2
pdb_filename = args.pdb_file
# os.path.splitext will fail interestingly with file.pdb.txt.zip
#pdb_name = os.path.splitext(pdb_file)[0]
# Just the filename, thanks
#pdb_name = Path(in_filename_pdb).stem
#==========
# dir
#==========
datadir = homedir + '/' + 'git/Data'
if not indir:
indir = datadir + '/' + drug + '/' + 'input'
if not outdir:
outdir = datadir + '/' + drug + '/' + 'output'
# FIXME:
process_dir = datadir + '/' + drug +'/' + 'processing'
# FIXME: this is a temporary directory and should be correctly handled
os.mkdir(process_dir)
#=======
# input
#=======
# FIXME
if pdb_filename:
pdb_name = Path(pdb_filename).stem
else:
pdb_filename = gene.lower() + '_complex.pdb'
pdb_name = Path(pdb_filename).stem
infile_pdb = indir + '/' + pdb_filename
actual_pdb_filename = Path(infile_pdb).name
if mut_filename:
mutation_file = mut_filename
else:
#mutation_file = gene.lower() + '_mcsm_snps.csv' #real
mutation_file = gene.lower() + '_test_snps.csv' #test
infile_muts = outdir + '/' + mutation_file
#=======
# output
#=======
out_filename = gene.lower() + '_foldx_results.csv'
outfile_foldx = outdir + '/' + out_filename
print('Arguments being passed:'
, '\nDrug:', args.drug
, '\ngene:', args.gene
, '\ninput dir:', indir
, '\noutput dir:', outdir
, '\npdb file:', infile_pdb
, '\npdb name:', pdb_name
, '\nactual pdb name:', actual_pdb_filename
, '\nmutation file:', infile_muts
, '\nchain1:', args.chain1
, '\noutput file:', outfile_foldx
, '\n=============================================================')
#=======================================================================
def getInteractionEnergy(filename):
data = pd.read_csv(filename,sep = '\t')
return data['Interaction Energy'].loc[0]
def getInteractions(filename):
data = pd.read_csv(filename, index_col = 0, header = 0, sep = '\t')
contactList = getIndexes(data,1)
number = len(contactList)
return number
def formatMuts(mut_file,pdbname):
with open(mut_file) as csvfile:
readCSV = csv.reader(csvfile)
muts = []
for row in readCSV:
mut = row[0]
muts.append(mut)
mut_list = []
outfile = process_dir + '/individual_list_' + pdbname + '.txt'
with open(outfile, 'w') as output:
for m in muts:
print(m)
mut = m[:1] + chainA+ m[1:]
mut_list.append(mut)
mut = mut + ';'
print(mut)
output.write(mut)
output.write('\n')
return mut_list
def getIndexes(data, value):
colnames = data.columns.values
listOfPos = list()
result = data.isin([value])
result.columns = colnames
seriesdata = result.any()
columnNames = list(seriesdata[seriesdata==True].index)
for col in columnNames:
rows = list(result[col][result[col]==True].index)
for row in rows:
listOfPos.append((row,col))
return listOfPos
def loadFiles(df):
# load a text file in to np matrix
resultList = []
f = open(df,'r')
for line in f:
line = line.rstrip('\n')
aVals = line.split('\t')
fVals = list(map(np.float32, sVals))
resultList.append(fVals)
f.close()
return np.asarray(resultList, dtype=np.float32)
#=======================================================================
def main():
pdbname = pdb_name
comp = '' # for complex only
mut_filename = infile_muts #pnca_test_snps.csv
mutlist = formatMuts(mut_filename, pdbname)
print(mutlist)
nmuts = len(mutlist)
print(nmuts)
print(mutlist)
print('start')
#subprocess.check_output(['bash','repairPDB.sh', pdbname, process_dir])
subprocess.check_output(['bash','repairPDB.sh', indir, actual_pdb_filename, process_dir])
print('end')
output = subprocess.check_output(['bash', 'runfoldx.sh', pdbname, process_dir])
for n in range(1,nmuts+1):
print(n)
with suppress(Exception):
subprocess.check_output(['bash', 'runPrintNetworks.sh', pdbname, str(n), process_dir])
for n in range(1,nmuts+1):
print(n)
with suppress(Exception):
subprocess.check_output(['bash', 'mutrenamefiles.sh', pdbname, str(n), process_dir])
out = subprocess.check_output(['bash','renamefiles.sh', pdbname, process_dir])
if comp=='y':
chain1=chainA
chain2=chainB
with suppress(Exception):
subprocess.check_output(['bash','runcomplex.sh', pdbname, chain1, chain2, process_dir])
for n in range(1,nmuts+1):
with suppress(Exception):
subprocess.check_output(['bash','mutruncomplex.sh', pdbname, chain1, chain2, str(n), process_dir])
interactions = ['Distances','Electro_RR','Electro_MM','Electro_SM','Electro_SS','Disulfide_RR','Disulfide_MM','Disulfide_SM','Disulfide_SS',
'Hbonds_RR','Hbonds_MM','Hbonds_SM','Hbonds_SS','Partcov_RR','Partcov_MM','Partcov_SM','Partcov_SS','VdWClashes_RR','VdWClashes_MM',
'VdWClashes_SM','VdWClashes_SS','Volumetric_RR','Volumetric_MM','Volumetric_SM','Volumetric_SS']
dGdatafile = process_dir + '/Dif_' + pdbname + '_Repair.txt'
dGdata = pd.read_csv(dGdatafile, sep = '\t')
ddG=[]
print('ddG')
print(len(dGdata))
for i in range(0,len(dGdata)):
ddG.append(dGdata['total energy'].loc[i])
nint = len(interactions)
wt_int = []
for i in interactions:
filename = process_dir + '/Matrix_' + i + '_'+ pdbname + '_Repair_PN.txt'
wt_int.append(getInteractions(filename))
print('wt')
print(wt_int)
ntotal = nint+1
print(ntotal)
print(nmuts)
data = np.empty((ntotal,nmuts))
data[0] = ddG
print(data)
for i in range(0,len(interactions)):
d=[]
p=0
for n in range(1, nmuts+1):
print(i)
filename = process_dir + '/Matrix_' + interactions[i] + '_' + pdbname + '_Repair_' + str(n) + '_PN.txt'
mut = getInteractions(filename)
diff = wt_int[i] - mut
print(diff)
print(wt_int[i])
print(mut)
d.append(diff)
print(d)
data[i+1] = d
interactions = ['ddG', 'Distances','Electro_RR','Electro_MM','Electro_SM','Electro_SS','Disulfide_RR','Disulfide_MM','Disulfide_SM','Disulfide_SS', 'Hbonds_RR','Hbonds_MM','Hbonds_SM','Hbonds_SS','Partcov_RR','Partcov_MM','Partcov_SM','Partcov_SS','VdWClashes_RR','VdWClashes_MM',
'VdWClashes_SM','VdWClashes_SS','Volumetric_RR','Volumetric_MM','Volumetric_SM','Volumetric_SS']
print(interactions)
IE = []
if comp=='y':
wtfilename = process_dir + '/Summary_' + pdbname + '_Repair_AC.txt'
wtE = getInteractionEnergy(wtfilename)
print(wtE)
for n in range(1,nmuts+1):
print(n)
filename = process_dir + '/Summary_' + pdbname + '_Repair_' + str(n) + '_AC.txt'
mutE = getInteractionEnergy(filename)
print(mutE)
diff = wtE - mutE
print(diff)
IE.append(diff)
print(IE)
IEresults = pd.DataFrame(IE,columns = ['Interaction Energy'], index = mutlist)
IEfilename = 'foldx_complexresults_'+pdbname+'.csv'
IEresults.to_csv(IEfilename)
print(len(IE))
data = np.append(data,[IE], axis = 0)
print(data)
interactions = ['ddG','Distances','Electro_RR','Electro_MM','Electro_SM','Electro_SS','Disulfide_RR','Disulfide_MM','Disulfide_SM','Disulfide_SS', 'Hbonds_RR','Hbonds_MM','Hbonds_SM','Hbonds_SS','Partcov_RR','Partcov_MM','Partcov_SM','Partcov_SS','VdWClashes_RR','VdWClashes_MM',
'VdWClashes_SM','VdWClashes_SS','Volumetric_RR','Volumetric_MM','Volumetric_SM','Volumetric_SS','Interaction Energy']
mut_file = process_dir + '/individual_list_' + pdbname + '.txt'
with open(mut_file) as csvfile:
readCSV = csv.reader(csvfile)
mutlist = []
for row in readCSV:
mut = row[0]
mutlist.append(mut)
print(mutlist)
print(len(mutlist))
print(data)
results = pd.DataFrame(data, columns = mutlist, index = interactions)
results.append(ddG)
#print(results.head())
# my style formatted results
results2 = results.T # transpose df
results2.index.name = 'mutationinformation' # assign name to index
results2 = results2.reset_index() # turn it into a columns
results2['mutationinformation'] = results2['mutationinformation'].replace({r'([A-Z]{1})[A-Z]{1}([0-9]+[A-Z]{1});' : r'\1 \2'}, regex = True) # capture mcsm style muts (i.e not the chain id)
results2['mutationinformation'] = results2['mutationinformation'].str.replace(' ', '') # remove empty space
results2.rename(columns = {'Distances': 'Contacts'}, inplace = True)
# lower case columns
results2.columns = results2.columns.str.lower()
print('Writing file in the format below:\n'
, results2.head()
, '\nNo. of rows:', len(results2)
, '\nNo. of cols:', len(results2.columns))
outputfilename = outfile_foldx
#outputfilename = 'foldx_results_' + pdbname + '.csv'
#results.to_csv(outputfilename)
results2.to_csv(outputfilename, index = False)
if __name__ == '__main__':
main()

7
foldx/runPrintNetworks.sh Executable file
View file

@ -0,0 +1,7 @@
PDB=$1
n=$2
OUTDIR=$3
logger "Running runPrintNetworks"
cd ${OUTDIR}
foldx --command=PrintNetworks --pdb="${PDB}_Repair_${n}.pdb" --water=PREDICT --vdwDesign=1 --output-dir=${OUTDIR}

10
foldx/runcomplex.sh Executable file
View file

@ -0,0 +1,10 @@
PDB=$1
A=$2
B=$3
OUTDIR=$4
cd ${OUTDIR}
logger "Running runcomplex"
foldx --command=AnalyseComplex --pdb="${PDB}_Repair.pdb" --analyseComplexChains=${A},${B} --water=PREDICT --vdwDesign=1 --output-dir=${OUTDIR}
cp ${OUTDIR}/Summary_${PDB}_Repair_AC.fxout ${OUTDIR}/Summary_${PDB}_Repair_AC.txt
#sed -i .bak -e 1,8d ${OUTDIR}/Summary_${PDB}_Repair_AC.txt

9
foldx/runfoldx.sh Executable file
View file

@ -0,0 +1,9 @@
PDB=$1
OUTDIR=$2
cd ${OUTDIR}
pwd
ls
logger "Running runfoldx"
foldx --command=BuildModel --pdb="${PDB}_Repair.pdb" --mutant-file="individual_list_${PDB}.txt" --ionStrength=0.05 --pH=7 --water=PREDICT --vdwDesign=1 --out-pdb=true --numberOfRuns=1 --output-dir=${OUTDIR}
foldx --command=PrintNetworks --pdb="${PDB}_Repair.pdb" --water=PREDICT --vdwDesign=1 --output-dir=${OUTDIR}
foldx --command=SequenceDetail --pdb="${PDB}_Repair.pdb" --water=PREDICT --vdwDesign=1 --output-dir=${OUTDIR}

92
mcsm/mcsm.py
View file

@ -14,8 +14,6 @@ import numpy as np
from mcsm import * from mcsm import *
#============================== #==============================
#%% global variables for defs #%% global variables for defs
#============================== #==============================
#%% #%%
@ -194,9 +192,9 @@ def format_mcsm_output(mcsm_outputcsv):
############# #############
# format colnames: all lowercase, remove spaces and use '_' to join # format colnames: all lowercase, remove spaces and use '_' to join
print('Assigning meaningful colnames i.e without spaces and hyphen and reflecting units' print('Assigning meaningful colnames i.e without spaces and hyphen and reflecting units'
, '\n===================================================================') , '\n=======================================================')
my_colnames_dict = {'Predicted Affinity Change': 'PredAffLog' # relevant info from this col will be extracted and the column discarded my_colnames_dict = {'Predicted Affinity Change': 'PredAffLog' # relevant info from this col will be extracted and the column discarded
, 'Mutation information': 'mutation_information' # {wild_type}<position>{mutant_type} , 'Mutation information': 'mutationinformation' # {wild_type}<position>{mutant_type}
, 'Wild-type': 'wild_type' # one letter amino acid code , 'Wild-type': 'wild_type' # one letter amino acid code
, 'Position': 'position' # number , 'Position': 'position' # number
, 'Mutant-type': 'mutant_type' # one letter amino acid code , 'Mutant-type': 'mutant_type' # one letter amino acid code
@ -206,41 +204,41 @@ def format_mcsm_output(mcsm_outputcsv):
, 'DUET stability change': 'duet_stability_change'} # in kcal/mol , 'DUET stability change': 'duet_stability_change'} # in kcal/mol
mcsm_data.rename(columns = my_colnames_dict, inplace = True) mcsm_data.rename(columns = my_colnames_dict, inplace = True)
#%%=========================================================================== #%%=====================================================================
################################# #################################
# populate mutation_information # populate mutationinformation
# col which is currently blank # col which is currently blank
################################# #################################
# populate mutation_information column:mcsm style muts {WT}<POS>{MUT} # populate mutationinformation column:mcsm style muts {WT}<POS>{MUT}
print('Populating column : mutation_information which is currently empty\n', mcsm_data['mutation_information']) print('Populating column : mutationinformation which is currently empty\n', mcsm_data['mutationinformation'])
mcsm_data['mutation_information'] = mcsm_data['wild_type'] + mcsm_data['position'].astype(str) + mcsm_data['mutant_type'] mcsm_data['mutationinformation'] = mcsm_data['wild_type'] + mcsm_data['position'].astype(str) + mcsm_data['mutant_type']
print('checking after populating:\n', mcsm_data['mutation_information'] print('checking after populating:\n', mcsm_data['mutationinformation']
, '\n===================================================================') , '\n=======================================================')
# Remove spaces b/w pasted columns # Remove spaces b/w pasted columns
print('removing white space within column: \mutation_information') print('removing white space within column: \mutationinformation')
mcsm_data['mutation_information'] = mcsm_data['mutation_information'].str.replace(' ', '') mcsm_data['mutationinformation'] = mcsm_data['mutationinformation'].str.replace(' ', '')
print('Correctly formatted column: mutation_information\n', mcsm_data['mutation_information'] print('Correctly formatted column: mutationinformation\n', mcsm_data['mutationinformation']
, '\n===================================================================') , '\n=======================================================')
#%%=========================================================================== #%%=====================================================================
############# #############
# sanity check: drop dupliate muts # sanity check: drop dupliate muts
############# #############
# shouldn't exist as this should be eliminated at the time of running mcsm # shouldn't exist as this should be eliminated at the time of running mcsm
print('Sanity check:' print('Sanity check:'
, '\nChecking duplicate mutations') , '\nChecking duplicate mutations')
if mcsm_data['mutation_information'].duplicated().sum() == 0: if mcsm_data['mutationinformation'].duplicated().sum() == 0:
print('PASS: No duplicate mutations detected (as expected)' print('PASS: No duplicate mutations detected (as expected)'
, '\nDim of data:', mcsm_data.shape , '\nDim of data:', mcsm_data.shape
, '\n===============================================================') , '\n===================================================')
else: else:
print('WARNING: Duplicate mutations detected' print('WARNING: Duplicate mutations detected'
, '\nDim of df with duplicates:', mcsm_data.shape , '\nDim of df with duplicates:', mcsm_data.shape
, 'Removing duplicate entries') , 'Removing duplicate entries')
mcsm_data = mcsm_data.drop_duplicates(['mutation_information']) mcsm_data = mcsm_data.drop_duplicates(['mutationinformation'])
print('Dim of data after removing duplicate muts:', mcsm_data.shape print('Dim of data after removing duplicate muts:', mcsm_data.shape
, '\n===============================================================') , '\n===========================================================')
#%%=========================================================================== #%%=====================================================================
############# #############
# Create col: duet_outcome # Create col: duet_outcome
############# #############
@ -259,8 +257,8 @@ def format_mcsm_output(mcsm_outputcsv):
# print('FAIL: DUET outcome assigned incorrectly' # print('FAIL: DUET outcome assigned incorrectly'
# , '\nExpected no. of stabilising mutations:', DUET_pos # , '\nExpected no. of stabilising mutations:', DUET_pos
# , '\nGot no. of stabilising mutations', mcsm_data['duet_outcome'].value_counts()['Stabilising'] # , '\nGot no. of stabilising mutations', mcsm_data['duet_outcome'].value_counts()['Stabilising']
# , '\n===============================================================') # , '\n======================================================')
#%%=========================================================================== #%%=====================================================================
############# #############
# Extract numeric # Extract numeric
# part of ligand_distance col # part of ligand_distance col
@ -271,7 +269,7 @@ def format_mcsm_output(mcsm_outputcsv):
print('extracting numeric part of col: ligand_distance') print('extracting numeric part of col: ligand_distance')
mcsm_data['ligand_distance'] = mcsm_data['ligand_distance'].str.extract('(\d+\.?\d*)') mcsm_data['ligand_distance'] = mcsm_data['ligand_distance'].str.extract('(\d+\.?\d*)')
print('Ligand Distance:',mcsm_data['ligand_distance']) print('Ligand Distance:',mcsm_data['ligand_distance'])
#%%=========================================================================== #%%=====================================================================
############# #############
# Create 2 columns: # Create 2 columns:
# ligand_affinity_change and ligand_outcome # ligand_affinity_change and ligand_outcome
@ -282,7 +280,7 @@ def format_mcsm_output(mcsm_outputcsv):
# categorocal part: '\b(\w+ing)\b' # categorocal part: '\b(\w+ing)\b'
print('Extracting numerical and categorical parts from the col: PredAffLog') print('Extracting numerical and categorical parts from the col: PredAffLog')
print('to create two columns: ligand_affinity_change and ligand_outcome' print('to create two columns: ligand_affinity_change and ligand_outcome'
, '\n===================================================================') , '\n=======================================================')
# 1) Extracting the predicted affinity change (numerical part) # 1) Extracting the predicted affinity change (numerical part)
mcsm_data['ligand_affinity_change'] = mcsm_data['PredAffLog'].str.extract('(-?\d+\.?\d*)', expand = True) mcsm_data['ligand_affinity_change'] = mcsm_data['PredAffLog'].str.extract('(-?\d+\.?\d*)', expand = True)
@ -308,24 +306,24 @@ def format_mcsm_output(mcsm_outputcsv):
if check.all(): if check.all():
print('PASS: spelling change successfull' print('PASS: spelling change successfull'
, '\nNo. of predicted affinity changes:\n', british_spl , '\nNo. of predicted affinity changes:\n', british_spl
, '\n===============================================================') , '\n===================================================')
else: else:
sys.exit('FAIL: spelling change unsucessfull' sys.exit('FAIL: spelling change unsucessfull'
, '\nExpected:\n', american_spl , '\nExpected:\n', american_spl
, '\nGot:\n', british_spl , '\nGot:\n', british_spl
, '\n===============================================================') , '\n===================================================')
#%%=========================================================================== #%%=====================================================================
############# #############
# ensuring corrrect dtype for numeric columns # ensuring corrrect dtype for numeric columns
############# #############
# check dtype in cols # check dtype in cols
print('Checking dtypes in all columns:\n', mcsm_data.dtypes print('Checking dtypes in all columns:\n', mcsm_data.dtypes
, '\n===================================================================') , '\n=======================================================')
print('Converting the following cols to numeric:' print('Converting the following cols to numeric:'
, '\nligand_distance' , '\nligand_distance'
, '\nduet_stability_change' , '\nduet_stability_change'
, '\nligand_affinity_change' , '\nligand_affinity_change'
, '\n===================================================================') , '\n=======================================================')
# using apply method to change stabilty and affinity values to numeric # using apply method to change stabilty and affinity values to numeric
numeric_cols = ['duet_stability_change', 'ligand_affinity_change', 'ligand_distance'] numeric_cols = ['duet_stability_change', 'ligand_affinity_change', 'ligand_distance']
@ -336,12 +334,12 @@ def format_mcsm_output(mcsm_outputcsv):
if cols_check.all(): if cols_check.all():
print('PASS: dtypes for selected cols:', numeric_cols print('PASS: dtypes for selected cols:', numeric_cols
, '\nchanged to numeric' , '\nchanged to numeric'
, '\n===============================================================') , '\n===================================================')
else: else:
sys.exit('FAIL:dtype change to numeric for selected cols unsuccessful' sys.exit('FAIL:dtype change to numeric for selected cols unsuccessful'
, '\n===============================================================') , '\n===================================================')
print(mcsm_data.dtypes) print(mcsm_data.dtypes)
#%%=========================================================================== #%%=====================================================================
############# #############
# scale duet values # scale duet values
############# #############
@ -357,7 +355,7 @@ def format_mcsm_output(mcsm_outputcsv):
, '\n---------------------------------------------------------------' , '\n---------------------------------------------------------------'
, '\nScaled duet scores:\n', mcsm_data['duet_scaled']) , '\nScaled duet scores:\n', mcsm_data['duet_scaled'])
#%%=========================================================================== #%%=====================================================================
############# #############
# scale affinity values # scale affinity values
############# #############
@ -373,7 +371,7 @@ def format_mcsm_output(mcsm_outputcsv):
, '\n---------------------------------------------------------------' , '\n---------------------------------------------------------------'
, '\nScaled affinity scores:\n', mcsm_data['affinity_scaled']) , '\nScaled affinity scores:\n', mcsm_data['affinity_scaled'])
#%%=========================================================================== #%%=====================================================================
############# #############
# adding column: wild_position # adding column: wild_position
# useful for plots and db # useful for plots and db
@ -385,33 +383,33 @@ def format_mcsm_output(mcsm_outputcsv):
print('removing white space within column: wild_position') print('removing white space within column: wild_position')
mcsm_data['wild_position'] = mcsm_data['wild_position'].str.replace(' ', '') mcsm_data['wild_position'] = mcsm_data['wild_position'].str.replace(' ', '')
print('Correctly formatted column: wild_position\n', mcsm_data['wild_position'].head() print('Correctly formatted column: wild_position\n', mcsm_data['wild_position'].head()
, '\n===================================================================') , '\n=========================================================')
#%%=========================================================================== #%%=====================================================================
############# #############
# ensuring corrrect dtype in non-numeric cols # ensuring corrrect dtype in non-numeric cols
############# #############
#) char cols #) char cols
char_cols = ['PredAffLog', 'mutation_information', 'wild_type', 'mutant_type', 'chain', 'ligand_id', 'duet_outcome', 'ligand_outcome', 'wild_position'] char_cols = ['PredAffLog', 'mutationinformation', 'wild_type', 'mutant_type', 'chain', 'ligand_id', 'duet_outcome', 'ligand_outcome', 'wild_position']
#mcsm_data[char_cols] = mcsm_data[char_cols].astype(str) #mcsm_data[char_cols] = mcsm_data[char_cols].astype(str)
cols_check_char = mcsm_data.select_dtypes(include = 'object').columns.isin(char_cols) cols_check_char = mcsm_data.select_dtypes(include = 'object').columns.isin(char_cols)
if cols_check_char.all(): if cols_check_char.all():
print('PASS: dtypes for char cols:', char_cols, 'are indeed string' print('PASS: dtypes for char cols:', char_cols, 'are indeed string'
, '\n===============================================================') , '\n===================================================')
else: else:
sys.exit('FAIL:dtype change to numeric for selected cols unsuccessful' sys.exit('FAIL:dtype change to numeric for selected cols unsuccessful'
, '\n===============================================================') , '\n===================================================')
#mcsm_data['ligand_distance', 'ligand_affinity_change'].apply(is_numeric_dtype(mcsm_data['ligand_distance', 'ligand_affinity_change'])) #mcsm_data['ligand_distance', 'ligand_affinity_change'].apply(is_numeric_dtype(mcsm_data['ligand_distance', 'ligand_affinity_change']))
print(mcsm_data.dtypes) print(mcsm_data.dtypes)
#%%============================================================================= #%%=====================================================================
# Removing PredAff log column as it is not needed? # Removing PredAff log column as it is not needed?
print('Removing col: PredAffLog since relevant info has been extracted from it') print('Removing col: PredAffLog since relevant info has been extracted from it')
mcsm_dataf = mcsm_data.drop(columns = ['PredAffLog']) mcsm_dataf = mcsm_data.drop(columns = ['PredAffLog'])
#%%=========================================================================== #%%=====================================================================
############# #############
# sanity check before writing file # sanity check before writing file
############# #############
@ -421,14 +419,14 @@ def format_mcsm_output(mcsm_outputcsv):
if len(mcsm_dataf.columns) == expected_cols: if len(mcsm_dataf.columns) == expected_cols:
print('PASS: formatting successful' print('PASS: formatting successful'
, '\nformatted df has expected no. of cols:', expected_cols , '\nformatted df has expected no. of cols:', expected_cols
, '\n---------------------------------------------------------------' , '\n---------------------------------------------------'
, '\ncolnames:', mcsm_dataf.columns , '\ncolnames:', mcsm_dataf.columns
, '\n----------------------------------------------------------------' , '\n---------------------------------------------------'
, '\ndtypes in cols:', mcsm_dataf.dtypes , '\ndtypes in cols:', mcsm_dataf.dtypes
, '\n----------------------------------------------------------------' , '\n---------------------------------------------------'
, '\norig data shape:', dforig_shape , '\norig data shape:', dforig_shape
, '\nformatted df shape:', mcsm_dataf.shape , '\nformatted df shape:', mcsm_dataf.shape
, '\n===============================================================') , '\n===================================================')
else: else:
sys.exit('FAIL: something went wrong in formatting df' sys.exit('FAIL: something went wrong in formatting df'
, '\nLen of orig df:', dforig_len , '\nLen of orig df:', dforig_len
@ -438,7 +436,7 @@ def format_mcsm_output(mcsm_outputcsv):
, '\nCheck formatting:' , '\nCheck formatting:'
, '\ncheck hardcoded value:', expected_ncols_toadd , '\ncheck hardcoded value:', expected_ncols_toadd
, '\nis', expected_ncols_toadd, 'the no. of expected cols to add?' , '\nis', expected_ncols_toadd, 'the no. of expected cols to add?'
, '\n===============================================================') , '\n===================================================')
return mcsm_dataf return mcsm_dataf

12
scripts/combine_afs_ors.py
View file

@ -71,7 +71,7 @@ infile2 = outdir + '/' + in_filename_afor_kin
print('Input file0:', infile0 print('Input file0:', infile0
, '\nInput file1:', infile1 , '\nInput file1:', infile1
, '\nInput file2:', infile2 , '\nInput file2:', infile2
, '\n===================================================================') , '\n=============================================================')
#======= #=======
# output # output
@ -79,7 +79,7 @@ print('Input file0:', infile0
out_filename = gene.lower() + '_metadata_afs_ors.csv' out_filename = gene.lower() + '_metadata_afs_ors.csv'
outfile = outdir + '/' + out_filename outfile = outdir + '/' + out_filename
print('Output file:', outfile print('Output file:', outfile
, '\n===================================================================') , '\n=============================================================')
del(in_filename_afor, in_filename_afor_kin, datadir, indir, outdir) del(in_filename_afor, in_filename_afor_kin, datadir, indir, outdir)
@ -217,13 +217,7 @@ if fail:
del(left_df, right_df, common_cols, merging_cols, nmerging_cols, my_join, ndiff1, ndiff2, missing_mutinfo del(left_df, right_df, common_cols, merging_cols, nmerging_cols, my_join, ndiff1, ndiff2, missing_mutinfo
, expected_rows, expected_cols, fail) , expected_rows, expected_cols, fail)
del(afor_df, snpinfo_df) del(afor_df, snpinfo_df)
#=======================================================================
#%% Second merge: combined_df1 and afor_kin_df #%% Second merge: combined_df1 and afor_kin_df