odir_opt = options.odir
filter_noncoding = options.filter_noncoding
transdecoder = options.transdecoder
hmmer = options.hmmer
blastp = options.blastp
report = options.report
gene_list = options.gene_list
ref_organism = options.ref_organism
# set prefixes
if filter_noncoding: prefix += '_filtered'
if gene_list: dir_prefix = prefix + '_gene_list'
# get parent output file that everything's gonna go into
if not odir_opt:
odir = pp_utils().make_dated_folder(os.path.dirname(gtffile), dir_prefix)
else:
odir = odir_opt
# set reference files based on what organism we're using
# reference files that we'll keep hard coded for now
if ref_organism == 'human':
fastafile = '/data/users/freese/mortazavi_lab/ref/hg38/hg38.fa'
p_ref = '/data/users/freese/mortazavi_lab/ref/gencode.v24/gencode.v24.pc_translations.fasta'
elif ref_organism == 'mouse':
fastafile = '/data/users/freese/mortazavi_lab/ref/mm10/mm10.fa'
p_ref = '/data/users/freese/mortazavi_lab/ref/gencode.vM21/gencode.vM21.pc_translations.fasta'
# filter out known non-coding transcripts from talon gtf
if filter_noncoding:
gtffile = pp_utils().filter_coding_novel_gtf(gtffile, odir, prefix)
from pp_utils import pp_utils
t_tsv = pp_utils().reformat_transdecoder(
'/Users/fairliereese/mortazavi_lab/data/190313_HepG2/190502_HepG2_filtered_protein_pred/transdecoder/HepG2_filtered.fasta.transdecoder.pep',
'HepG2_filtered')
print(t_tsv)
from pp_utils import pp_utils
t_tsv = pp_utils().reformat_hmmer(
'/Users/fairliereese/mortazavi_lab/data/190313_HepG2/190502_HepG2_filtered_protein_pred/hmmer/HepG2_filtered.tab',
'HepG2_filtered')
print(t_tsv)
from pp_utils import pp_utils tid_gid_map = '/Users/fairliereese/mortazavi_lab/data/190313_HepG2/HepG2_filtered_talon_coding_novel_tid_gid_map.tsv' odir = '/Users/fairliereese/mortazavi_lab/data/190313_HepG2/190502_HepG2_filtered_protein_pred/' prefix = 'HepG2_filtered' gene_names = pp_utils().get_gene_names(tid_gid_map, odir, prefix) print(gene_names)
from pp_utils import pp_utils gene_names = '/data/users/freese/mortazavi_lab/data/190313_HepG2/190502_HepG2_filtered_protein_pred/blastp/HepG2_filtered_gene_IDS_mini.txt' p_ref = '/data/users/freese/mortazavi_lab/ref/gencode.v24/gencode.v24.pc_translations.fasta' odir = '/data/users/freese/mortazavi_lab/data/190313_HepG2/190502_HepG2_filtered_protein_pred/' prefix = 'HepG2_filtered' pepfile = '/data/users/freese/mortazavi_lab/data/190313_HepG2/190502_HepG2_filtered_protein_pred/transdecoder/HepG2_filtered.fasta.transdecoder.pep' b_tbl = pp_utils().run_blastp(gene_names, p_ref, odir, prefix, pepfile) print(b_tbl)
from pp_utils import pp_utils blastfile = '/Users/fairliereese/mortazavi_lab/data/190313_HepG2/190502_HepG2_filtered_protein_pred/blastp/HepG2_filtered_blast_results.tab' prefix = 'HepG2_filtered' b_tsv = pp_utils().reformat_blastp(blastfile, prefix) print(b_tsv)