adiamb

#!/bin/bash
#1 list of files
# command is spec_processing_parallel_JUL24.sh MS_PROCESSING_LIST
date
echo "processing raw spectra files"
NAMES=`cat $1` #names from names.txt file
for NAME in $NAMES; do
   
   spec_processing=" point_mutaions_code/spec_processing_main_JUL24.py $NAME"
   python $spec_processing &

adiamb

from itertools import chain
import pandas as pd
import numpy as np
#%matplotlib
import re 
from Bio import Entrez
from Bio import SeqIO
import sys
import time

adiamb

from itertools import chain
import pandas as pd
import numpy as np
#%matplotlib
import re 
from Bio import Entrez
from Bio import SeqIO
import sys
import time

adiamb

import pandas as pd
import numpy as np
import pandas as pd
import numpy as np
import numpy
from sklearn.manifold import TSNE
from sklearn.decomposition import PCA
import matplotlib.pyplot as plt
import seaborn
from sklearn import preprocessing

adiamb

import pandas as pd
import numpy as np
import pandas as pd
import numpy as np
import numpy
from sklearn.manifold import TSNE
from sklearn.decomposition import PCA
import matplotlib.pyplot as plt
import seaborn
from sklearn import preprocessing

adiamb

###PYTHON#############
#Purpose : Analyze frameshifts in the MS-tryspin/chemotrypsin digests
#Author : Aditya Ambati 
#date : June7 2017
#update : version 1
#####import libraries
from itertools import chain
import pandas as pd
import numpy as np
%matplotlib

adiamb

###PYTHON#############
#Purpose : Analyze frameshifts in the MS-tryspin/chemotrypsin digests
#Author : Aditya Ambati 
#date : June7 2017
#update : version 1
#####import libraries
from itertools import chain
import pandas as pd
import numpy as np
%matplotlib

adiamb

from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split
import matplotlib.pylot as plt
%matplotlib
import keras
from keras.models import Sequential
from keras.layers import Dense, Activation, Dropout
from keras.utils import to_categorical

adiamb

import pandas as pd
import numpy as np

arp = pd.read_csv('Arepanrix_trypsin_june16.csv')
pan = pd.read_csv('Pandemrix_trypsin_june16.csv')
prot=pan.strain_protein.unique()
refprot=[i.split('[')[0] for i in prot] 
refid=[i.split(' ')[0] for i in refprot]
refprotname= ['PB2', 'HA', 'NA', 'MA1', 'NP'] 
### try to simplify the protein ids

adiamb

from keras.models import Sequential
from keras.layers.core import Dense, Activation, Dropout, Flatten
from keras.layers.recurrent import LSTM
from keras import __version__ as keras_version
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt

from sklearn.model_selection import train_test_split