python source code of plot_old_new

Project: SelfTarget (GitHub Link)

SelfTarget-master
- selftarget_pyutils
  - selftarget
    - data.py
    - util.py
    - profile.py
    - plot.py
    - indel.py
    - __init__.py
    - view.py
    - oligo.py
  - setup.py
- indel_analysis
  - microhomology
    - plot_mh_analysis.py
    - fetch_mh_indel_frequencies.py
    - run_all_collect_mh_frequencies_by_len.py
    - collect_mh_frequencies_by_len.py
    - run_all_mh_indel_frequencies.py
  - scaffold_compare
    - compute_old_new_kl.py
    - plot_old_new.py
  - plot_all.py
  - indel_details
    - run_all_compile_indel_details.py
    - run_all_compile_pie_summaries_per_oligo.py
    - compile_pie_summaries_per_oligo.py
    - compile_indel_details.py
    - plot_pie_indel_summaries.py
  - compute_indels
    - indelmap_subdir.py
    - run_correct_indel.sh
    - run_all_split_null_mappings.py
    - run_all_mapped_split.py
    - run_all_map.py
    - split_mapped_reads_by_id.py
    - run_all_compile_nulls.py
    - run_all_correct_indelmap.py
    - split_missing_mapped_reads_by_id.py
    - README.txt
    - run_all_indelmap.py
    - split_null_mappings.py
    - run_all_partition.py
    - example
      - ST_June_2017
        data
        oligos_for_customarray_Dec2016_pamlocations.txt
        K562_800x_LV7A_DPI7
        K562_800x_LV7A_DPI7_L3_R2.fastq
        K562_800x_LV7A_DPI7_L1_R2.fastq
        K562_800x_LV7A_DPI7_L1_R1.fastq
        K562_800x_LV7A_DPI7_L2_R2.fastq
        K562_800x_LV7A_DPI7_L3_R1.fastq
        K562_800x_LV7A_DPI7_L2_R1.fastq
        exp_target_pam_new.fasta
      - ST_Feb_2018
        data
        WT_12NA_DPI7
      - ST_April_2017
        data
        NULL_New
        2nd-NEW-scaffold-library-John-LIG3_S33_L002_R2_001.fastq
        2nd-NEW-scaffold-library-John-LIG3_S33_L001_R1_001.fastq
        2nd-NEW-scaffold-library-John-LIG3_S33_L002_R1_001.fastq
        2nd-NEW-scaffold-library-John-LIG3_S33_L001_R2_001.fastq
    - reformat_indel_profile.py
    - compile_mapped_null_profiles.py
    - run_example.py
    - correct_indelmap_subdir.py
    - run_all_pear.py
    - run_all_incomplete_indelmap.py
    - partition_pear.py
  - endogenous_comparisons
    - create_overbeek_templates.py
    - collect_overbeek_sams.py
    - compute_overbeek_indel_profiles.py
    - compare_overbeek_profiles.py
    - run_example.py
    - create_overbeek_fasta.py
  - microhomology_mismatch
    - run_all_fetch_mh_mismatch_frequencies.py
    - plot_mh_mismatch_frequencies.py
    - fetch_mh_mismatch_frequencies.py
    - map_mh_mismatch_oligos.py
  - indelmap
    - indelgen.cpp
    - indel.cpp
    - indelgen_i1.cpp
    - indelmh.cpp
    - indel.h
    - readmap.h
    - version.h.in
    - gen.cpp
    - oligo.h
    - readmap.cpp
    - indelmap.cpp
    - indelgentarget.cpp
    - CMakeLists.txt
    - gen.h
    - oligo.cpp
    - test.cpp
    - test.h
  - i1
    - plot_i1_summaries.py
    - run_all_compile_i1.py
    - compile_i1.py
  - combine_results_subdirs.py
  - kl_comparisons
    - run_all_compare_pairwise.py
    - plot_kl_analysis.py
    - compare_pairwise.py
  - combine_results_files.py
- README.md
- indel_prediction
  - predictor
    - features.py
    - FORECasT.py
    - predict.py
    - model.py
    - tests.py
    - __init__.py
    - example_batch.txt
  - model_testing
    - compile_gen_indel_features.py
    - compile_gen_indel_reads.py
    - test_model.py
    - plot_old_new_predictions.py
    - compute_predicted_old_new_kl.py
  - setup.py
- scripts
  - wge_to_ccid
    - farm_scripts
      - run_farm_jobs.sh
      - farm_process_cripr_files.sh
    - wge_retrievers.py
    - test_data
      - extracted_samples.txt
      - analyser_result.txt
      - filemap.txt
    - constants.py
    - wge_to_ccid.py
    - tests.py
    - __init__.py
    - crispr.py
    - helper.py
  - README.md
  - requirements.txt
- server
  - request_types.py
  - swagger.yml
  - server.py
  - uwsgi.ini
  - model.py
  - __init__.py
  - tests
    - integration_tests
      - tests.py
      - __init__.py
      - requirements.txt
      - conftest.py
  - helpers.py
- requirements.txt
- Dockerfile
- LICENSE.txt

import io, os, sys, csv, random
import pandas as pd
import numpy as np
import pylab as PL

from scipy.stats import pearsonr, spearmanr
from sklearn.manifold import TSNE

from selftarget.data import setHighDataDir, getHighDataDir
from selftarget.plot import saveFig

def renameCol(colname):
    replace_terms = [('Alt2',''),('Alt',''),('New v New', 'Within Library'),('Old v Old','Within Additional Library'),('Old v New','Between Library'),('Class KL',''), ('KL','')]
    for term1, term2 in replace_terms:
         colname = colname.replace(term1, term2)
    return colname.strip()

def runAnalysis():
	
    data = pd.read_csv(getHighDataDir() + '/old_new_kl_summaries.txt', sep='\t').fillna(-1.0)
    kl_cols = [x for x in data.columns if 'KL' in x and 'Class KL' not in x and 'Old v Old' not in x]
    max_kl = 9
    PL.figure(figsize=(2.5,4))
    bps= []
    box_types = [('C2','Within Library'),('C0','Between Library')]
    for i,(clr,box_type) in enumerate(box_types):
        col_box_data = [data[col] for col in kl_cols if renameCol(col) == box_type]
        pos = [2*x + i + 1 for x in range(len(col_box_data))]
        print('KL', box_type, np.median(col_box_data, axis=1))
        bps.append(PL.boxplot(col_box_data, positions=pos,patch_artist=True,boxprops=dict(facecolor=clr),showfliers=False))
    PL.xticks([1.5,3.5,5.5],['Same\ngRNA','Other\ngRNA','Other\ngRNA\n(Rpt)'])
    PL.plot([2.5, 2.5],[0, max_kl],'-', color='silver')
    PL.plot([4.5, 4.5],[0, max_kl],'-', color='silver')
    PL.xlim((0.5,6.5))
    PL.ylim((0,max_kl))
    PL.ylabel('KL')
    PL.subplots_adjust(left=0.1,right=0.95,top=0.95, bottom=0.25)
    PL.legend([bp["boxes"][0] for bp in bps],[x[1] for x in box_types], loc='upper left')
    PL.show(block=False)
    saveFig('kl_compare_old_new_KL')


if __name__ == '__main__':
    setHighDataDir('.')
    runAnalysis()
    import pdb; pdb.set_trace()