Simple code for reading in a FASTA file and accessing each sequence for analysis in localCIDER

analyse_sequence_data.py

from localcider.sequenceParameters import SequenceParameters
from pyfasta import Fasta

#
# This assumes you have previously installed localCIDER and pyfasta (both 
# are available via pip)
#

# read in the FASTA file using pyfasta
F = Fasta('swissprot_human_proteome.fasta')

# get all the header lines associated with each sequence
# (a header line is the line that starts with a ">" and
# generally contains identifying information about the 
# protein). This is going to be the dictionary key we're going
# use
all_fasta_keys = F.keys()

# for each header we use this to extract the full amino acid
# sequence
header_to_sequence = {}
for k in all_fasta_keys:

    # this assigns the value in the dictionary to 
    # the sequence
    header_to_sequence[k] = str(F[k][:])
    
    
# now header_to_sequence is a dictionary where each key-value pair
# is a FASTA file header line and the associated amino acid sequence