Number of SSMs for direct searches


In [1]:
import os
import sys

src_dir = os.path.abspath('../src')
if src_dir not in sys.path:
    sys.path.append(src_dir)

In [2]:
import pandas as pd

from ann_solo import reader

In [3]:
ssms_dir = '../../data/processed/iprg2012/brute_force'

ssms_std = reader.read_mztab_ssms(os.path.join(ssms_dir, 'bf_std.mztab'))
ssms_oms = reader.read_mztab_ssms(os.path.join(ssms_dir, 'bf_oms.mztab'))
ssms_oms_shifted = reader.read_mztab_ssms(os.path.join(
    ssms_dir, 'bf_oms_shifted.mztab'))
ssms_oms_nocascade = reader.read_mztab_ssms(os.path.join(
    ssms_dir, 'bf_oms_nocascade.mztab'))
ssms_oms_nocascade_shifted = reader.read_mztab_ssms(os.path.join(
    ssms_dir, 'bf_oms_nocascade_shifted.mztab'))

num_ssms = pd.DataFrame(
    {'search mode': ['20 ppm', '300 Da (cascade, dot)',
                     '300 Da (cascade, shifted dot)',
                     '300 Da (no cascade, dot)',
                     '300 Da (no cascade, shifted dot)'],
    'number of SSMs': [len(ssms_std), len(ssms_oms), len(ssms_oms_shifted),
                       len(ssms_oms_nocascade), len(ssms_oms_nocascade_shifted)]})

num_ssms


Out[3]:
search mode number of SSMs
0 20 ppm 4147
1 300 Da (cascade, dot) 5167
2 300 Da (cascade, shifted dot) 6011
3 300 Da (no cascade, dot) 3820
4 300 Da (no cascade, shifted dot) 5020