Skip to content

refactor: all files are refactored #3

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
cmeesters merged 3 commits into from
Aug 6, 2025
Merged

refactor: all files are refactored #3

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
f85ac42
refactor: all scripts
cmeesters Aug 6, 2025
043abb5
refactor: Snakefile
cmeesters Aug 6, 2025
8834537
refactor: refactored all rule files
cmeesters Aug 6, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
141 changes: 102 additions & 39 deletions workflow/Snakefile
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,97 +3,160 @@ from os import path

from snakemake.utils import min_version

min_version("7.19.1") # this is where SLURM support was introduced
min_version("7.19.1") # this is where SLURM support was introduced

INPUT_DIR=config["INPUT_DIR"]
INPUT_DIR = config["INPUT_DIR"]

MIN_DIR=config["PREPARED_LIGAND_DIR"]
MIN_DIR = config["PREPARED_LIGAND_DIR"]

PREPARED_DIR=config["PREPARED_DATA_DIR"]
PREPARED_DIR = config["PREPARED_DATA_DIR"]

OUTPUT_DIR=config["OUTPUT_DIR"]
OUTPUT_DIR = config["OUTPUT_DIR"]

TMP_DIR=config["TEMP_DATA_DIR"]
TMP_DIR = config["TEMP_DATA_DIR"]

LOCAL_INPUT =config["LOCAL_INPUT_DIR"]
LOCAL_INPUT = config["LOCAL_INPUT_DIR"]

DATABASE = config["DATABASE"]

SUBSET = config["SUBSET"]

RESCREENING_TARGETS = config["RESCREENING_TARGETS"]


def generateOutput(wildcards):
irods = path.join(OUTPUT_DIR, "results", "irods.json")
if config["RESCREENING"] == "TRUE":
out = expand(path.join(OUTPUT_DIR, "results", "rescreening_{percentage}", "{receptorID}", "union.csv"),
receptorID = config["TARGETS"][0].split(',')[0],
percentage = config["RESULT_NUMBER"],
combAll = combAll)
hist = expand(path.join(OUTPUT_DIR, "results", "{receptorID}_hist.png"),
receptorID = config["TARGETS"][0].split(',')[0])
out = expand(
path.join(
OUTPUT_DIR,
"results",
"rescreening_{percentage}",
"{receptorID}",
"union.csv",
),
receptorID=config["TARGETS"][0].split(",")[0],
percentage=config["RESULT_NUMBER"],
combAll=combAll,
)
hist = expand(
path.join(OUTPUT_DIR, "results", "{receptorID}_hist.png"),
receptorID=config["TARGETS"][0].split(",")[0],
)

return hist + out + [irods]
return hist + out + [irods]

else:
out = expand(path.join(OUTPUT_DIR, "results", "{receptorID}_{percentage}.csv"),
receptorID = config["TARGETS"][0].split(',')[0],
percentage = config["RESULT_NUMBER"])
hist = expand(path.join(OUTPUT_DIR, "results", "{receptorID}_hist.png"),
receptorID = config["TARGETS"][0].split(',')[0])
out = expand(
path.join(OUTPUT_DIR, "results", "{receptorID}_{percentage}.csv"),
receptorID=config["TARGETS"][0].split(",")[0],
percentage=config["RESULT_NUMBER"],
)
hist = expand(
path.join(OUTPUT_DIR, "results", "{receptorID}_hist.png"),
receptorID=config["TARGETS"][0].split(",")[0],
)
return hist + out + [irods]


localrules: all, generateIRODS, dockingResultsTxt, removeDuplicateLigands, makeVenn, prepareLigands2, mergeDocking2, bestLigands, prepareSecondDocking, convertMol2, makeReceptorPDBQT, mergeDocking ,mergeLocalInput, split, split2, targetProtein, getZINCdata, getZINCSubsets, gunzip, ENAMINEdownload, prepareReceptor, prepareDocking, prepareLibrary, prepareGeometry, makeHistogram, cleanLigands

targetList=[] #get ProteinIDs from configfile for rescreening
localrules:
all,
generateIRODS,
dockingResultsTxt,
removeDuplicateLigands,
makeVenn,
prepareLigands2,
mergeDocking2,
bestLigands,
prepareSecondDocking,
convertMol2,
makeReceptorPDBQT,
mergeDocking,
mergeLocalInput,
split,
split2,
targetProtein,
getZINCdata,
getZINCSubsets,
gunzip,
ENAMINEdownload,
prepareReceptor,
prepareDocking,
prepareLibrary,
prepareGeometry,
makeHistogram,
cleanLigands,


targetList = [] # get ProteinIDs from configfile for rescreening
for i in config["RESCREENING_TARGETS"]:
targetList.append(i.split(',')[0])
targetList.append(i.split(",")[0])

combList = []
for comb in itertools.combinations(targetList, 2): # all combinations of two targets

combList.append('_'.join(comb))
combList.append("_".join(comb))

combAll = "_".join(targetList) # combine all rescreening targets

combAll = '_'.join(targetList) # combine all rescreening targets

def getAllVenn(wildcards):
path.join(OUTPUT_DIR, "output", "rescreening", "{receptorID}", "{RESCREENING_TARGETS}_union.txt")
path.join(
OUTPUT_DIR,
"output",
"rescreening",
"{receptorID}",
"{RESCREENING_TARGETS}_union.txt",
)


def IRODSinput(wildcards):
if config["RESCREENING"] == "TRUE":
out = expand(path.join(OUTPUT_DIR, "results", "rescreening_{percentage}", "{receptorID}", "union.csv"),
receptorID = config["TARGETS"][0].split(',')[0],
percentage = config["RESULT_NUMBER"],
combAll = combAll)
out = expand(
path.join(
OUTPUT_DIR,
"results",
"rescreening_{percentage}",
"{receptorID}",
"union.csv",
),
receptorID=config["TARGETS"][0].split(",")[0],
percentage=config["RESULT_NUMBER"],
combAll=combAll,
)
else:
out = expand(path.join(OUTPUT_DIR, "results", "{receptorID}_{percentage}.csv"),
receptorID = config["TARGETS"][0].split(',')[0],
percentage = config["RESULT_NUMBER"])
out = expand(
path.join(OUTPUT_DIR, "results", "{receptorID}_{percentage}.csv"),
receptorID=config["TARGETS"][0].split(",")[0],
percentage=config["RESULT_NUMBER"],
)
return out


def resources(RULE_NAME):
out_list = []
for key in config[RULE_NAME]:
out_list.append(f'{key} = {config[RULE_NAME][key]}')
out_str = ',\n'.join(out_list)
out_list.append(f"{key} = {config[RULE_NAME][key]}")
out_str = ",\n".join(out_list)
return out_str


rule all:
input:
generateOutput
generateOutput,


rule generateIRODS:
input:
IRODSinput
IRODSinput,
output:
path.join(OUTPUT_DIR, "results", "irods.json")
path.join(OUTPUT_DIR, "results", "irods.json"),
log:
"logs/generateIRODS.log"
"logs/generateIRODS.log",
script:
"scripts/generateIRODS.py"


include: "rules/analyse.smk"
include: "rules/docking.smk"
include: "rules/preparation.smk"
Loading