#!/usr/bin/env python
# coding: utf-8

# ###Quality trim all fastq.gz files using [Trimmomatic (v0.30)](http://www.usadellab.org/cms/?page=trimmomatic)

# ####Code explanation of for loop below:
# 1. ```%%bash``` specifies to use the shell for this Jupyter cell
# 2. ```for file in /Volumes/nightingales/C_gigas/2212_lane2_[^N]*``` initiates a for loop to handle all files beginning with ```2212_lane2_``` and only those that do <em>not</em> have the letter "N" at that position in the file name.
# 3. ```do``` tells the for loop what to do with each of the files.
# 4. ```newname=${file##*/}``` takes the value of the ```$file``` variable (which is ```/Volumes/nightingales/C_gigas/2212_lane2_[^N]*```) and trims the longest match from the beginning of the pattern (the pattern is ```*/```; the ```##``` is a bash command to specifiy how to trim). The resulting output (which is just the file name without the full path) is then stored in the ```newname``` variable.
# 5. This line initiates Trimmomatic and uses the following arguments to specify order of execution:
#     1. single end reads (```SE```)
#     1. number of threads (```-threads 16```), 
#     2. type of quality score (```-phred33```),
#     3. input file location (```"$file"```),
#     4. output file name/location (```/Volumes/Data/Sam/scratch/20140414_trimmed_$newname```),
#     5. single end Illumina TruSeq adaptor trimming (```ILLUMINACLIP:/usr/local/bioinformatics/Trimmomatic-0.30/adapters/TruSeq3-SE.fa:2:30:10```),
#     6. cut number of bases at beginning of read if below quality threshold (```LEADING:3```)
#     7. cut number of bases at end of read if below quality threshold (```TRAILING:3```)
#     8. cut if average quality within 4 base window falls below 15 (```SLIDINGWINDOW:4:15```)
# 6. ```done``` closes for loop.

# In[14]:


get_ipython().run_cell_magic('bash', '', 'for file in /Volumes/nightingales/C_gigas/2212_lane2_[^N]*\ndo\nnewname=${file##*/}\njava -jar /usr/local/bioinformatics/Trimmomatic-0.30/trimmomatic-0.30.jar SE -threads 16 -phred33 "$file" /Volumes/Data/Sam/scratch/20140414_trimmed_$newname ILLUMINACLIP:/usr/local/bioinformatics/Trimmomatic-0.30/adapters/TruSeq3-SE.fa:2:30:10 LEADING:3 TRAILING:3 SLIDINGWINDOW:4:15;\ndone\n')


# ###FASTQC on all trimmed files using [FASTQC (v0.11.2)](http://www.bioinformatics.babraham.ac.uk/projects/fastqc/)

# In[16]:


get_ipython().run_cell_magic('bash', '', 'for file in /Volumes/Data/Sam/scratch/20150414_trimmed_2212*; do fastqc "$file" --outdir=/Volumes/Eagle/Arabidopsis/; done\n')


# ###Unzip all FASTQC .zip files

# In[17]:


cd /Volumes/Eagle/Arabidopsis/


# In[19]:


get_ipython().run_cell_magic('bash', '', 'for file in 20150414_trimmed_2212*.zip; do unzip "$file"; done\n')


# In[20]:


ls 20150414_*fastqc


# ###Concatenate two groups of sequences into single file

# ####400ppm (control) sequences - Index GCCAAT

# In[7]:


cd /Volumes/Data/Sam/scratch/


# In[8]:


get_ipython().run_cell_magic('bash', '', '#gunzips all matching files in folder and appends the data to a single file:\n#20150414_trimmed_2212_lane2_400ppm_GCCAAT.fastq\nfor file in 20150414_trimmed_2212_lane2_G*\ndo\ngunzip -c "$file"  >> 20150414_trimmed_2212_lane2_400ppm_GCCAAT.fastq\ndone\n')


# In[9]:


get_ipython().run_cell_magic('bash', '', '#Gzip file\ngzip 20150414_trimmed_2212_lane2_400ppm_GCCAAT.fastq\n')


# ####1000ppm (acidification) sequences - Index CTTGTA

# In[10]:


get_ipython().run_cell_magic('bash', '', '#gunzips all matching files in folder and appends the data to a single file:\n#20150414_trimmed_2212_lane2_1000ppm_CTTGTA.fastq\nfor file in 20150414_trimmed_2212_lane2_C*\ndo\ngunzip -c "$file" >> 20150414_trimmed_2212_lane2_1000ppm_CTTGTA.fastq\ndone\n')


# In[11]:


get_ipython().run_cell_magic('bash', '', '#Gzip file\ngzip 20150414_trimmed_2212_lane2_1000ppm_CTTGTA.fastq\n')


# ###Copy files to Eagle for web-based access

# In[12]:


get_ipython().run_cell_magic('bash', '', 'for file in 2015*e2_[14]*; do cp "$file" /Volumes/Eagle/Arabidopsis/; done\n')