tcrsampler
Sample TCRs according to VDJ gene usage frequency
Install
pip install tcrsampler
Example
import os
import pandas as pd
from tcrsampler.sampler import TCRsampler
t = TCRsampler()
fn= os.path.join('tcrsampler' ,'tests', 'pmbc_mixcr_example_data.txt')
t.clean_mixcr(filename = fn)
t.build_background(stratify_by_subject = True, use_frequency = True)
t.sample([['TRBV9*01','TRBJ2-7*01', 2],['TRBV7-7*01', 'TRBJ2-4*01', 4] ], depth = 1, use_frequency = True)
[['CASSRTGSLADEQYF', 'CASSATGVVSAQYF'],
['CASSLGQAARGIQYF', 'CASSLGQAARGIQYF', 'CASSLGQAARGIQYF', 'CASSLGQAARGIQYF']]
Download Default Background
python -c "from tcrsampler.setup_db import install_all_next_gen; install_all_next_gen(dry_run = False)"