Commit d6a575d3 authored by Alexander, William's avatar Alexander, William
Browse files

Fixed issue where motif fails on 0 methyated datasets 

Also fixed overwrite flag (-w), works as intended now
parent 271e4801

scripts/motif

+8 −5
Original line number Diff line number Diff line
@@ -314,8 +314,12 @@ def memeLoop(folder: str, inDF, genomeDict: dict, threads: int, sampleSize: int, 
    complete = 'no'

    inDF = inDF.drop(columns=['end', 'start1', 'end1', 'color', 'score'])

    workingDF = dfFilter(inDF, 15, 90, 0)

    methylSet = set((dfFilter(inDF, 15, 40, 5, 1)

                     .sort_values(by=['coord']))['coord'].unique())

    methylDF = dfFilter(inDF, 15, 40, 5, 1)

    methylSet = None

    if len(methylDF) == 0:

        complete = 'yes'

    else:

        methylSet = set((methylDF.sort_values(by=['coord']))['coord'].unique())

    # below is an emperically determined cutoff that explains most Ecol data and finds all motifs off the bat

    # workingDF = dfFilter(inDF, 15, 95, 0)

    # methylSet = set((dfFilter(inDF, 15, 80, 5, 1)
@@ -443,8 +447,7 @@ if __name__ == '__main__': 
    # meant to delete the MEME output folder to make repetitive running on a dataset easier, currently throws an error

    os.chdir(args.folder)

    if os.path.isdir('./meme') and args.overwrite:

        os.rmdir('./meme')

    else:

        os.system('rm -rf ./meme')

    os.mkdir('./meme')



    # converts genome to a dict of sequences