From 3627958f1aa8b805999578cda9c99c7f3cec2bc6 Mon Sep 17 00:00:00 2001
From: Jens Preussner <jens.preussner@mpi-bn.mpg.de>
Date: Thu, 5 Apr 2018 10:30:15 +0200
Subject: [PATCH] Fixed cleaning to take fastq from samplesheet

---
 sc-preprocess.snake |  9 ++++++++-
 src/clean.snake     | 17 +++++++++++++----
 2 files changed, 21 insertions(+), 5 deletions(-)

diff --git a/sc-preprocess.snake b/sc-preprocess.snake
index a44d728..b4f9b3c 100644
--- a/sc-preprocess.snake
+++ b/sc-preprocess.snake
@@ -18,6 +18,10 @@ REFERENCE_FASTA = join(config['dirs']['ref'], config['reference']['organism'], c
 #-------------------------------------------------------------------------------#
 
 samplesheet = pd.read_table(config['samplesheet']['file'], sep = '\t', index_col = config['samplesheet']['index'])
+
+if 'URL_r1' not in list(samplesheet):
+	samplesheet['URL_r1'] = ['{dir}/{sample}.{format}'.format(dir = config['dirs']['fastq'], sample = sample, format = 'fastq.gz') for sample in list(samplesheet.index)]
+
 SAMPLES = samplesheet.to_dict(orient = 'index')
 SAMPLE_NAMES = sorted(SAMPLES.keys())
 
@@ -25,7 +29,9 @@ SAMPLE_NAMES = sorted(SAMPLES.keys())
 #--------------------------- Generate output files -----------------------------#
 #-------------------------------------------------------------------------------#
 
-output_files = []
+output_files = [
+	#join(config['dirs']['ref'], 'tx2gene', basename(REFERENCE_FASTA).rstrip(".fa"))
+]
 
 if config["action"]["demultiplex"]:
   demultiplexed_files = expand('{o}/{s}.fastq.gz', o = config['dirs']['fastq'], s = SAMPLE_NAMES)
@@ -41,6 +47,7 @@ if config["action"]["clean"]:
 
 include: "src/auxiliary.snake"
 #include: "src/demultiplex.snake" # not yet implemented
+#include: "src/reference.snake"
 include: "src/clean.snake"
 
 if config["debug"]:
diff --git a/src/clean.snake b/src/clean.snake
index d31442d..0244f1c 100644
--- a/src/clean.snake
+++ b/src/clean.snake
@@ -1,3 +1,12 @@
+# vim: syntax=python tabstop=4 expandtab
+# coding: utf-8
+
+'''
+@author: jpreuss
+
+Provides cleaning and QC from the HTStream toolkit
+'''
+
 def construct_htstream_partials(wildcards, log):
   template = 'hts_{prog} -L {log}/htstream/{sample}.txt {flags}'
   partials = [template.format(prog = k, log = log, flags = v, sample = wildcards.sample) for k, v in list(zip(config['htstream']['actions'], config['htstream']['flags']))]
@@ -6,9 +15,9 @@ def construct_htstream_partials(wildcards, log):
 rule htstream_clean_se_gz:
   version: "1.0"
   input:
-    '{out}/{sample}.fastq.gz'
+    lambda wildcards: SAMPLES[wildcards.sample]['URL_r1']
   output:
-    '{out}/{sample}.clean.fastq.gz'
+    config['dirs']['fastq'] + '/{sample}.clean.fastq.gz'
   params:
     call = lambda wildcards: construct_htstream_partials(wildcards, config['dirs']['log'])
   message: 'Cleaning {input} using HTStream.'
@@ -16,6 +25,6 @@ rule htstream_clean_se_gz:
   threads: 4
   shell:
     """
-    hts_Stats -U {input} -L {log} -tO | {params.call} -p {wildcards.out}/{wildcards.sample}
-    mv {wildcards.out}/{wildcards.sample}_SE.fastq.gz {output}
+    hts_Stats -U {input} -L {log} -tO | {params.call} -p {config[dirs][fastq]}/{wildcards.sample}
+    mv {config[dirs][fastq]}/{wildcards.sample}_SE.fastq.gz {output}
     """