From 5d44efe6e61e3b11db6b2d8c8d46f2530507269c Mon Sep 17 00:00:00 2001
From: james94 <james94@mi.fu-berlin.de>
Date: Sat, 6 Aug 2022 12:45:43 +0200
Subject: [PATCH] comments
---
Snakefile | 82 ++++++++++++-------------------------------------------
1 file changed, 18 insertions(+), 64 deletions(-)
diff --git a/Snakefile b/Snakefile
index 3c70c40..3502a10 100644
--- a/Snakefile
+++ b/Snakefile
@@ -13,28 +13,34 @@ import argparse, subprocess
container: "docker://gepdocker/gep_dockerimage:latest"
configfile: "configuration/config.yaml"
+### LOAD IN RESOURCES CONFIG ###
with open(config['resources'], 'r') as f:
resource = yaml.safe_load(f)
+### GET BASENAME FOR READS WILDCARDS ###
def getBasename4Reads(path):
base=os.path.basename(path)
return os.path.splitext(base)[0]
-
+### CHECK IF INPUT IS GZIPPED ###
def gzipped_or_not(path):
trueORfalse=path.endswith('.gz')
return trueORfalse
+### CHECK IF HIC AND/OR ALT_ASM FILES ARE GIVEN, OR VALUE IS NONE ###
def FILE_present_or_not(path):
if path == 'None':
return False
return True
+
+### CHECK IF GENOME_SIZE IS PROVIDED, OR VALUE IS AUTO ###
def genomeSize_auto_or_not(given_size):
if given_size == 'auto':
return 0
return given_size
+
def addUniqueLibraryID(library):
string2Add=library + "_1"
@@ -51,18 +57,10 @@ if set(['sample', 'Library_R1', 'Library_R2', 'meryl_kmer_size', 'trim10X', 'tri
samples['readCounter'] = samples.groupby(['sample']).cumcount()+1
samples['readCounter'] = samples['readCounter'].astype(str)
samples['readCounter'] = samples['sample'] + "_LibraryPair" + samples['readCounter']
- # samples=samples.reset_index()
- # trim10x_table = samples[samples['trim10X'] == "True"]
- # trim10x_table=trim10x_table.set_index(['sample','readCounter'])
- # notrim10xwithAdapt= samples[(samples['trim10X'] == "False") & (samples['trimAdapters'] == "True") ]
- # notrim10xwithAdapt=notrim10xwithAdapt.set_index(['sample','readCounter'])
- # notrim10xorAdapt= samples[(samples['trim10X'] == "False") & (samples['trimAdapters'] == "False") ]
- # notrim10xorAdapt=notrim10xorAdapt.set_index(['sample','readCounter'])
- # d10xtrim = {}
+
samples['10xtrimorNot'] = np.where(samples['trim10X'] == "True", "10xTrimmed", "not10xTrimmed")
samples['AdpaterTrimorNot'] = np.where(samples['trimAdapters'] == "True", "AdaptTrimmed", "notAdaptTrimmed")
- # for i in samples['sample'].unique():
- # d10xtrim[i] = [samples['10xtrimorNot'][j] for j in samples[samples['sample']==i].index]
+
dictSamples=samples[['sample','meryl_kmer_size', '10xtrimorNot','AdpaterTrimorNot']]
dictSamples=dictSamples.set_index(['sample']).T.to_dict('list')
@@ -72,14 +70,7 @@ if set(['sample', 'Library_R1', 'Library_R2', 'meryl_kmer_size', 'trim10X', 'tri
testDictQC=testDictQC.set_index(['sample']).T.to_dict('list')
trimAdapters = samples[samples['trimAdapters'] == "True"]
- # dAdaptertrim = {}
- # for i in trimAdapters['sample'].unique():
- # dAdaptertrim[i] = [trimAdapters['readCounter'][j] for j in trimAdapters[trimAdapters['sample']==i].index]
- #
- # runQC = samples[samples['fastQC'] == "True"]
- # drunQCtrim = {}
- # for i in runQC['sample'].unique():
- # drunQCtrim[i] = [runQC['readCounter'][j] for j in runQC[runQC['sample']==i].index]
+
dictReadCounter = {}
for i in samples['sample'].unique():
dictReadCounter[i] = [samples['readCounter'][j] for j in samples[samples['sample']==i].index]
@@ -118,9 +109,7 @@ elif set(['sample', 'hifi_reads', 'meryl_kmer_size','trimSMRTbell', 'fastQC']).i
samples['readCounter'] = samples['readCounter'].astype(str)
samples['readCounter'] = samples['sample'] + "_Library" + samples['readCounter']
samples['smrtornot'] = np.where(samples['trimSMRTbell'] == "True", "smrtTrimmed", "notsmrtTrimmed")
- # samplesDict=samples.set_index('sample').T.to_dict('list')
- # samples=samples.reset_index()
dictSamples=samples[['sample','meryl_kmer_size', 'smrtornot']]
dictSamples=dictSamples.drop_duplicates('sample', keep='first')
dictSamples=dictSamples.set_index(['sample']).T.to_dict('list')
@@ -129,42 +118,10 @@ elif set(['sample', 'hifi_reads', 'meryl_kmer_size','trimSMRTbell', 'fastQC']).i
testDictQC=samples[['sample', 'smrtornot', 'fastQC']]
testDictQC = testDictQC[testDictQC['fastQC'] == "True"]
- # testDictQC=testDictQC.drop_duplicates('sample', keep='first')
+
testDictQC=testDictQC.set_index(['sample']).T.to_dict('list')
- # runQC = samples[samples['fastQC'] == "True"]
- #
- # drunQCtrim = {}
- # for i in runQC['sample'].unique():
- # drunQCtrim[i] = [runQC['readCounter'][j] for j in runQC[runQC['sample']==i].index]
- #
- # runQC=runQC.set_index(['sample','readCounter'])
- #
- #
- # trimSMRTbell=samples.loc[samples['trimSMRTbell'] == "True"]
- # dtrimSMRTbell = {}
- # for i in trimSMRTbell['sample'].unique():
- # dtrimSMRTbell[i] = [trimSMRTbell['readCounter'][j] for j in trimSMRTbell[trimSMRTbell['sample']==i].index]
- # trimSMRTbell=trimSMRTbell.set_index(['sample','readCounter'])
- # notrimSMRTbell = samples[samples['trimSMRTbell'] == "False"]
- # notrimSMRTbell=notrimSMRTbell.set_index(['sample','readCounter'])
-
-
- # dsmrtornot = {}
- # dfsmrtornot=samples.drop_duplicates('smrtornot', keep='first')
- #
- # for i in samples['sample'].unique():
- # dsmrtornot[i] = [dfsmrtornot['smrtornot'][j] for j in dfsmrtornot[dfsmrtornot['sample']==i].index]
-
- # for i in samples['sample'].unique():
- # dsmrtornot[i] = [samples['smrtornot'][j] for j in samples[samples['sample']==i].index]
- #
- #
- # dkmerSize = {}
- # dkmerDups=samples.drop_duplicates('meryl_kmer_size', keep='first')
- # for i in samples['sample'].unique():
- # dkmerSize[i] = [dkmerDups['meryl_kmer_size'][j] for j in dkmerDups[dkmerDups['sample']==i].index]
dictReadCounter = {}
for i in samples['sample'].unique():
dictReadCounter[i] = [samples['readCounter'][j] for j in samples[samples['sample']==i].index]
@@ -244,11 +201,13 @@ elif set(['ID', 'ASM_LEVEL', 'PRI_asm', 'ALT_asm', 'merylDB', 'merylDB_kmer', 'g
dictSamples=samples.T.to_dict('list')
ruleAllQCFiles=[]
- ruleAll=expand(os.path.join(config['Results'],"1_evaluation/{asmID}/06_keyResults/{asmID}_aggregatedResults.tsv"), asmID=list(dictSamples.keys())),\
- os.path.join(config['Results'],"1_evaluation/finalResults/Combined_Results_FULLTABLE.tsv"), \
+ ruleAll=expand(os.path.join(config['Results'],"1_evaluation/{asmID}/KEY_RESULTS/{asmID}_aggregatedResults.tsv"), asmID=list(dictSamples.keys())),\
+ os.path.join(config['Results'],"1_evaluation/finalResults/TABLE_OF_RESULTS.tsv"), \
os.path.join(config['Results'],"1_evaluation/finalResults/FULL_REPORT.pdf")
+### DOWNLOAD BUSCO LINEAGE (IF IT DOESN'T ALREADY EXIST) ####
+
args_o=os.path.join(workflow.basedir, "buscoLineage")
args_l=config['busco5Lineage']
checkLineagePath=args_o + "/" + args_l + "_odb10"
@@ -298,11 +257,6 @@ elif set(['ID', 'ASM_LEVEL', 'PRI_asm', 'ALT_asm', 'merylDB', 'merylDB_kmer', 'g
else:
raise ValueError("Error - could not identify lineage please check busco site for a correct prefix")
-
- # os.path.join(config['Results'],"1_evaluation/finalResults/FULL_Report_PDF.pdf"), \
- # os.path.join(config['Results'],"1_evaluation/finalResults/FULL_TABLE_PDF.pdf"), \
- # os.path.join(config['Results'],"1_evaluation/finalResults/FullTableCOLOUREDheatmap.pdf"), \
- # os.path.join(config['Results'],"1_evaluation/finalResults/FullTableGRADIENTheatmap.pdf")
else:
raise ValueError('Sample Sheet for not recognised. Please make sure you are using the correct sample sheet')
@@ -314,13 +268,13 @@ else:
if "Results" not in config:
config["Results"] = "results"
-report: "report/workflow.rst"
+
include: whichRule
-inputs = ruleAllQCFiles, ruleAll
+final_target_outputs = ruleAllQCFiles, ruleAll
rule all:
input:
- inputs
+ final_target_outputs
--
GitLab