version control info updates

tahashmi · tahashmi · commit c2f14aab1bf3 · 2025-01-28T13:46:04.000-05:00
diff --git a/README.md b/README.md
@@ -54,19 +54,18 @@ git clone https://github.com/KolmogorovLab/Wakhan.git
 cd Wakhan/
 conda env create -f environment.yml -n Wakhan
 conda activate Wakhan
-cd src/
 ```
 
 ## Usage
 
 ### Tumor-Normal Mode (requires normal phased VCF)
 ```
-python main.py --threads <4> --reference <ref.fa>  --target-bam <data.tumor.bam>  --normal-phased-vcf <data.normal_phased.vcf.gz>  --genome-name <cellline/dataset name> --out-dir-plots <genome_abc_output> --breakpoints <severus-sv-VCF>
+python wakhan.py --threads <4> --reference <ref.fa>  --target-bam <data.tumor.bam>  --normal-phased-vcf <data.normal_phased.vcf.gz>  --genome-name <cellline/dataset name> --out-dir-plots <genome_abc_output> --breakpoints <severus-sv-VCF>
 ```
 
 ### Tumor-only (requires tumor phased/haplotagged BAM and phased VCF)
 ```
-python main.py --threads <4> --reference <ref.fa>  --target-bam <data.tumor_haplotagged.bam>  --tumor-vcf <data.tumor_phased.vcf.gz> --genome-name <cellline/dataset name> --out-dir-plots <genome_abc_output> --breakpoints <severus-sv-VCF>
+python wakhan.py --threads <4> --reference <ref.fa>  --target-bam <data.tumor_haplotagged.bam>  --tumor-vcf <data.tumor_phased.vcf.gz> --genome-name <cellline/dataset name> --out-dir-plots <genome_abc_output> --breakpoints <severus-sv-VCF>
 ```
 
 ##### Breakpoints/Structural variations or change point detection algo for copy number model
diff --git a/requirements.txt b/requirements.txt
@@ -0,0 +1,11 @@
+setuptools
+pysam
+pyfaidx
+numpy
+pandas
+plotly
+scikit-learn
+scipy
+ruptures
+vcf_parser
+kaleido
diff --git a/setup.py b/setup.py
@@ -0,0 +1,31 @@
+import os
+import sys
+import subprocess
+import shutil
+
+try:
+    import setuptools
+except ImportError:
+    sys.exit("setuptools package not found. "
+             "Please use 'pip install setuptools' first")
+
+from setuptools import setup
+
+# Make sure we're running from the setup.py directory.
+script_dir = os.path.dirname(os.path.realpath(__file__))
+if script_dir != os.getcwd():
+    os.chdir(script_dir)
+
+from src.__version__ import __version__
+
+setup(name='wakhan',
+      version=__version__,
+      description='A tool for haplotype-specific somatic copy number aberrations/profiling from long reads sequencing data',
+      url='https://github.com/KolmogorovLab/Wakhan',
+      author='Tanveer Ahmad',
+      author_email = 'tanveer.ahmad@nih.gov',
+      license='MIT',
+      packages=['src'],
+      package_data={'src': ['annotations/*']},
+      entry_points={'console_scripts': ['wakhan = src.main:main']},
+      )
diff --git a/src/__init__.py b/src/__init__.py
diff --git a/src/__version__.py b/src/__version__.py
@@ -0,0 +1 @@
+__version__ = "0.1"
diff --git a/src/breakpoints_arcs.py b/src/breakpoints_arcs.py
@@ -4,7 +4,7 @@
 
 logger = logging.getLogger()
 
-from utils import get_contigs_list, df_chromosomes_sorter
+from src.utils import get_contigs_list, df_chromosomes_sorter
 
 def get_all_breakpoints_data(edges, edges_chr, height, path, args):
     from vcf_parser import VCFParser
diff --git a/src/hapcorrect/src/__init__.py b/src/hapcorrect/src/__init__.py
diff --git a/src/hapcorrect/src/loh.py b/src/hapcorrect/src/loh.py
@@ -5,10 +5,10 @@
 import logging
 logger = logging.getLogger()
 
-from hapcorrect.src.process_vcf import get_snps_frquncies, het_homo_snps_gts, vcf_parse_to_csv_for_het_phased_snps_phasesets, cpd_mean, get_snps_frquncies_coverage, vcf_parse_to_csv_for_snps, get_snps_counts
-from hapcorrect.src.utils import csv_df_chromosomes_sorter, loh_regions_phasesets, detect_alter_loh_regions
-from hapcorrect.src.extras import get_contigs_list
-from hapcorrect.src.plots import add_scatter_trace_coverage, print_chromosome_html, plots_add_markers_lines, plots_layout_settings
+from src.hapcorrect.src.process_vcf import get_snps_frquncies, het_homo_snps_gts, vcf_parse_to_csv_for_het_phased_snps_phasesets, cpd_mean, get_snps_frquncies_coverage, vcf_parse_to_csv_for_snps, get_snps_counts
+from src.hapcorrect.src.utils import csv_df_chromosomes_sorter, loh_regions_phasesets, detect_alter_loh_regions
+from src.hapcorrect.src.extras import get_contigs_list
+from src.hapcorrect.src.plots import add_scatter_trace_coverage, print_chromosome_html, plots_add_markers_lines, plots_layout_settings
 
 def detect_loh_centromere_regions(chrom, args, centromere_region_starts, centromere_region_ends, loh_region_starts, loh_region_ends, ref_start_values, ref_end_values, haplotype_1_values, haplotype_2_values, unphased_reads_values, haplotype_1_values_phasesets, haplotype_2_values_phasesets, ref_start_values_phasesets, ref_end_values_phasesets):
     hp = []
diff --git a/src/hapcorrect/src/main_hapcorrect.py b/src/hapcorrect/src/main_hapcorrect.py
@@ -15,15 +15,15 @@
 
 logger = logging.getLogger()
 
-from hapcorrect.src.process_bam import get_all_reads_parallel, update_coverage_hist, get_segments_coverage, haplotype_update_all_bins_parallel, get_snps_frequencies, tumor_bam_haplotag
-from hapcorrect.src.process_vcf import vcf_parse_to_csv_for_het_phased_snps_phasesets, get_snp_frequencies_segments, snps_frequencies_chrom_mean, get_snps_frquncies_coverage, vcf_parse_to_csv_for_snps, index_vcf, rephase_vcf, get_phasingblocks, snps_frequencies_chrom_mean_phasesets, get_vafs_from_normal_phased_vcf
-from hapcorrect.src.phase_correction import generate_phasesets_bins, phaseblock_flipping, phase_correction_centers, contiguous_phaseblocks, detect_centromeres, flip_phaseblocks_contigous, remove_overlaping_contiguous, switch_inter_phaseblocks_bins, flip_phaseblocks_unresolved, flip_phaseblocks_unresolved_ends
-from hapcorrect.src.utils import get_chromosomes_bins, write_segments_coverage, csv_df_chromosomes_sorter, get_snps_frquncies_coverage_from_bam, \
+from src.hapcorrect.src.process_bam import get_all_reads_parallel, update_coverage_hist, get_segments_coverage, haplotype_update_all_bins_parallel, get_snps_frequencies, tumor_bam_haplotag
+from src.hapcorrect.src.process_vcf import vcf_parse_to_csv_for_het_phased_snps_phasesets, get_snp_frequencies_segments, snps_frequencies_chrom_mean, get_snps_frquncies_coverage, vcf_parse_to_csv_for_snps, index_vcf, rephase_vcf, get_phasingblocks, snps_frequencies_chrom_mean_phasesets, get_vafs_from_normal_phased_vcf
+from src.hapcorrect.src.phase_correction import generate_phasesets_bins, phaseblock_flipping, phase_correction_centers, contiguous_phaseblocks, detect_centromeres, flip_phaseblocks_contigous, remove_overlaping_contiguous, switch_inter_phaseblocks_bins, flip_phaseblocks_unresolved, flip_phaseblocks_unresolved_ends
+from src.hapcorrect.src.utils import get_chromosomes_bins, write_segments_coverage, csv_df_chromosomes_sorter, get_snps_frquncies_coverage_from_bam, \
                     infer_missing_phaseblocks, df_chromosomes_sorter, is_phasesets_check_simple_heuristics, write_df_csv, loh_regions_events, snps_frequencies_chrom_genes, genes_segments_coverage, genes_segments_list, extend_snps_ratios_df, get_chromosomes_regions, add_breakpoints
-from hapcorrect.src.extras import get_contigs_list
-from hapcorrect.src.plots import plot_coverage_data, change_point_detection, plot_coverage_data_after_correction, loh_plots_genome
-from hapcorrect.src.cpd import cpd_positions_means
-from hapcorrect.src.loh import detect_loh_centromere_regions, plot_snps
+from src.hapcorrect.src.extras import get_contigs_list
+from src.hapcorrect.src.plots import plot_coverage_data, change_point_detection, plot_coverage_data_after_correction, loh_plots_genome
+from src.hapcorrect.src.cpd import cpd_positions_means
+from src.hapcorrect.src.loh import detect_loh_centromere_regions, plot_snps
 
 MIN_SV_SIZE = 50
 def main_process(args, breakpoints_additional):
diff --git a/src/hapcorrect/src/phase_correction.py b/src/hapcorrect/src/phase_correction.py
@@ -2,8 +2,8 @@
 import statistics
 import numpy as np
 import pandas as pd
-from hapcorrect.src.utils import csv_df_chromosomes_sorter, write_segments_coverage_snps, merge_regions, get_contigs_list
-from hapcorrect.src.process_vcf import squash_regions
+from src.hapcorrect.src.utils import csv_df_chromosomes_sorter, write_segments_coverage_snps, merge_regions, get_contigs_list
+from src.hapcorrect.src.process_vcf import squash_regions
 
 import logging
 logger = logging.getLogger()
diff --git a/src/hapcorrect/src/plots.py b/src/hapcorrect/src/plots.py
@@ -7,7 +7,7 @@
 import logging
 logger = logging.getLogger()
 
-from hapcorrect.src.utils import get_contigs_list, get_chromosomes_regions
+from src.hapcorrect.src.utils import get_contigs_list, get_chromosomes_regions
 
 def plot_coverage_data(html_graphs, args, chrom, ref_start_values, ref_end_values, haplotype_1_values, haplotype_2_values, unphased_reads_values, haplotype_1_values_phasesets, haplotype_2_values_phasesets, ref_start_values_phasesets, ref_end_values_phasesets, sufix):
     fig = go.Figure()
diff --git a/src/hapcorrect/src/process_vcf.py b/src/hapcorrect/src/process_vcf.py
@@ -12,9 +12,9 @@
 
 logger = logging.getLogger()
 
-from hapcorrect.src.utils import write_segments_coverage_snps, csv_df_chromosomes_sorter
-from hapcorrect.src.process_bam import process_bam_for_snps_freqs
-from hapcorrect.src.smoothing import smoothing
+from src.hapcorrect.src.utils import write_segments_coverage_snps, csv_df_chromosomes_sorter
+from src.hapcorrect.src.process_bam import process_bam_for_snps_freqs
+from src.hapcorrect.src.smoothing import smoothing
 
 import csv
 import multiprocessing
diff --git a/src/hapcorrect/src/utils.py b/src/hapcorrect/src/utils.py
@@ -10,8 +10,8 @@
 import warnings
 warnings.simplefilter(action='ignore', category=FutureWarning)
 
-from hapcorrect.src.extras import get_contigs_list
-from hapcorrect.src.process_bam import get_segments_coverage
+from src.hapcorrect.src.extras import get_contigs_list
+from src.hapcorrect.src.process_bam import get_segments_coverage
 
 def get_chromosomes_bins(bam_file, bin_size, args):
     bed=[]
diff --git a/src/main.py b/src/main.py
@@ -13,21 +13,22 @@
 from multiprocessing import Pool
 from collections import defaultdict
 
-from hapcorrect.src.main_hapcorrect import main_process
+from src.hapcorrect.src.main_hapcorrect import main_process
+from src.__version__ import __version__
 
-from bam_processing import get_all_reads_parallel, update_coverage_hist, get_segments_coverage, haplotype_update_all_bins_parallel, get_snps_frequencies
-from utils import get_chromosomes_bins, write_segments_coverage, write_segments_coverage_dict, csv_df_chromosomes_sorter,\
+from src.bam_processing import get_all_reads_parallel, update_coverage_hist, get_segments_coverage, haplotype_update_all_bins_parallel, get_snps_frequencies
+from src.utils import get_chromosomes_bins, write_segments_coverage, write_segments_coverage_dict, csv_df_chromosomes_sorter,\
     seperate_dfs_coverage, flatten_smooth, get_contigs_list, write_copynumber_segments_csv, integer_fractional_cluster_means, \
     adjust_diversified_segments, get_chromosomes_bins_bam, normal_genome_proportion, update_subclonal_means_states, adjust_first_copy_mean, \
     merge_adjacent_regions_cn, merge_adjacent_regions_cn_unphased, parse_sv_vcf, weigted_means_ploidy, average_p_value_genome, collect_loh_centromere_regions, \
     find_optimized_normal_peaks, update_genes_phase_corrected_coverage, weighted_means, extract_breakpoints_additional, write_df_csv, adjust_bps_cn_segments_boundries
-from plots import coverage_plots_chromosomes, copy_number_plots_genome_details, copy_number_plots_genome, plots_genome_coverage, copy_number_plots_chromosomes, \
+from src.plots import coverage_plots_chromosomes, copy_number_plots_genome_details, copy_number_plots_genome, plots_genome_coverage, copy_number_plots_chromosomes, \
     copy_number_plots_genome_breakpoints, copy_number_plots_genome_breakpoints_subclonal, copy_number_plots_genome_subclonal, genes_copy_number_plots_genome, genes_plots_genome, heatmap_copy_number_plots_genome
-from vcf_processing import vcf_parse_to_csv_for_het_phased_snps_phasesets
-from snps_loh import plot_snps_frequencies_without_phasing, plot_snps_frequencies, plot_snps_ratios_genome, snps_df_loh, variation_plots, write_loh_regions
-from phasing_correction import generate_phasesets_bins, fix_inter_cn_phase_switch_errors, bins_correction_phaseblocks
-from optimization import peak_detection_optimization
-from extras import sv_vcf_bps_cn_check
+from src.vcf_processing import vcf_parse_to_csv_for_het_phased_snps_phasesets
+from src.snps_loh import plot_snps_frequencies_without_phasing, plot_snps_frequencies, plot_snps_ratios_genome, snps_df_loh, variation_plots, write_loh_regions
+from src.phasing_correction import generate_phasesets_bins, fix_inter_cn_phase_switch_errors, bins_correction_phaseblocks
+from src.optimization import peak_detection_optimization
+from src.extras import sv_vcf_bps_cn_check
 
 logger = logging.getLogger()
 def _enable_logging(log_file, debug, overwrite):
@@ -50,6 +51,8 @@ def _enable_logging(log_file, debug, overwrite):
     logger.addHandler(console_log)
     logger.addHandler(file_handler)
 
+def _version():
+    return __version__
 
 def main():
     # default tunable parameters
@@ -210,7 +213,7 @@ def main():
     # Disable propagation for this logger
     logger.propagate = False
 
-    #logger.info("Starting Wakhan " + _version())
+    logger.info("Starting Wakhan " + _version())
     logger.info("Cmd: %s", " ".join(sys.argv))
     logger.info("Python version: " + sys.version)
 
@@ -486,9 +489,6 @@ def main():
 
     return 0
 
-if __name__ == "__main__":
-    main()
-
 #UCSC tumor/normal celllines
 #--quick-start True --quick-start-coverage-path /home/rezkuh/gits/data/ --threads 1 --reference /home/rezkuh/GenData/reference/GRCh38_no_alt_analysis_set.fasta  --target-bam /home/rezkuh/GenData/COLO829/colo829_tumor_grch38_md_chr7:78318498-78486891_haplotagged.bam --out-dir-plots 1954  --normal-phased-vcf /home/rezkuh/gits/data/1954/1954BL.vcf.gz --copynumbers-enable True  --unphased-reads-coverage-enable True  --phaseblock-flipping-enable True --phaseblocks-enable True   --genome-name 1954  --cut-threshold 150
 
diff --git a/src/phasing_correction.py b/src/phasing_correction.py
@@ -1,24 +1,22 @@
 import os
 import statistics
 import numpy as np
-from utils import csv_df_chromosomes_sorter, write_segments_coverage_dict
-from vcf_processing import squash_regions
-from collections import  defaultdict, Counter
 import pysam
 import bisect
 import pandas as pd
 import logging
+from collections import  defaultdict, Counter
 
 logger = logging.getLogger()
-
-from utils import get_contigs_list, remove_outliers_iqr
+from src.vcf_processing import squash_regions
+from src.utils import get_contigs_list, remove_outliers_iqr, csv_df_chromosomes_sorter, write_segments_coverage_dict
 def generate_phasesets_bins(bam, path, bin_size, args):
     return get_phasesets_bins(bam, path, bin_size, args)
 def get_phasesets_bins(bam, phasesets, bin_size, args):
     indices, values = remove_overlapping_and_small_phasesets(phasesets, bin_size, args)
     head, tail = os.path.split(bam)
     bed = []
-    from utils import get_contigs_list
+
     chroms = get_contigs_list(args.contigs)
     for ind, chrom in enumerate(chroms) :
         for i in range(0, len(values[ind]), 2): #for i in range(len(values[ind])-1):
diff --git a/src/plots.py b/src/plots.py
@@ -14,13 +14,12 @@
 
 logger = logging.getLogger()
 
-#from cnvlib import cluster
-from phasing_correction import phaseblock_flipping, phase_correction_centers, contiguous_phaseblocks, detect_centromeres, flip_phaseblocks_contigous, remove_overlaping_contiguous, switch_inter_phaseblocks_bins
-from smoothing import smoothing
-from vcf_processing import get_snps_frquncies_coverage, get_snps_frquncies, het_homo_snps_gts, vcf_parse_to_csv_for_het_phased_snps_phasesets, snps_mean, cpd_mean, get_snp_segments, vcf_parse_to_csv_for_snps, het_snps_means_df
-from utils import subclonal_values_adjusted, get_chromosomes_bins, csv_df_chromosomes_sorter, get_breakpoints, flatten, get_snps_frquncies_coverage_from_bam, detect_alter_loh_regions, is_phasesets_check_simple_heuristics, change_point_detection_means, \
+from src.phasing_correction import phaseblock_flipping, phase_correction_centers, contiguous_phaseblocks, detect_centromeres, flip_phaseblocks_contigous, remove_overlaping_contiguous, switch_inter_phaseblocks_bins
+from src.smoothing import smoothing
+from src.vcf_processing import get_snps_frquncies_coverage, get_snps_frquncies, het_homo_snps_gts, vcf_parse_to_csv_for_het_phased_snps_phasesets, snps_mean, cpd_mean, get_snp_segments, vcf_parse_to_csv_for_snps, het_snps_means_df
+from src.utils import subclonal_values_adjusted, get_chromosomes_bins, csv_df_chromosomes_sorter, get_breakpoints, flatten, get_snps_frquncies_coverage_from_bam, detect_alter_loh_regions, is_phasesets_check_simple_heuristics, change_point_detection_means, \
     loh_regions_phasesets, get_chromosomes_regions, adjust_extreme_outliers, genes_phase_correction, write_df_csv, bins_with_copynumber_states
-from extras import get_contigs_list, sv_vcf_bps_cn_check
+from src.extras import get_contigs_list, sv_vcf_bps_cn_check
 
 pd.options.mode.chained_assignment = None
 
@@ -793,7 +792,7 @@ def copy_number_plots_genome_breakpoints(centers, integer_fractional_centers, df
         last_len = 0
         coords_single = [j for i in [x[1:2] for x in coords_single] for j in i]
 
-        from breakpoints_arcs import get_all_breakpoints_data
+        from src.breakpoints_arcs import get_all_breakpoints_data
         arcs_data = get_all_breakpoints_data(coords, coords_chr, 75, args.breakpoints, args)
         arcs_data1 = get_all_breakpoints_data(coords, coords_chr, -75, args.breakpoints, args)
 
@@ -1622,7 +1621,7 @@ def copy_number_plots_genome_breakpoints_subclonal(centers, integer_fractional_c
     indices = np.arange(0, len(df_cnr_hp1)*args.bin_size, args.bin_size, dtype=int)
 
     ###########################################################
-    from breakpoints_arcs import get_all_breakpoints_data
+    from src.breakpoints_arcs import get_all_breakpoints_data
 
     arcs_data = get_all_breakpoints_data(coords, coords_chr, 75, args.breakpoints, args)
     arcs_data1 = get_all_breakpoints_data(coords, coords_chr, -75, args.breakpoints, args)
@@ -3843,7 +3842,7 @@ def change_point_detection(hp_data, start, ends, ref_start_values_1, args, chrom
     change_points = sorted(list(set(change_points + cpd_zeros_points + cpd_peaks_points)))
     ############################################
     ############################################
-    from smoothing import smooth_triangle
+    from src.smoothing import smooth_triangle
     hp_data_new = []
 
     if len(hp_data[0:change_points[0]]) > 46:
diff --git a/src/snps_loh.py b/src/snps_loh.py
@@ -8,12 +8,12 @@
 
 logger = logging.getLogger()
 
-from vcf_processing import get_snps_frquncies, het_homo_snps_gts, vcf_parse_to_csv_for_het_phased_snps_phasesets, snps_mean, cpd_mean, get_snp_segments, get_snps_frquncies_coverage, vcf_parse_to_csv_for_snps, get_snps_counts, get_snps_counts_cn_regions, get_snps_frquncies_genome
-from utils import csv_df_chromosomes_sorter, get_vafs_from_tumor_phased_vcf
-from extras import get_contigs_list
-from plots import add_scatter_trace_coverage, print_chromosome_html, plots_add_markers_lines, plots_layout_settings,\
+from src.vcf_processing import get_snps_frquncies, het_homo_snps_gts, vcf_parse_to_csv_for_het_phased_snps_phasesets, snps_mean, cpd_mean, get_snp_segments, get_snps_frquncies_coverage, vcf_parse_to_csv_for_snps, get_snps_counts, get_snps_counts_cn_regions, get_snps_frquncies_genome
+from src.utils import csv_df_chromosomes_sorter, get_vafs_from_tumor_phased_vcf
+from src.extras import get_contigs_list
+from src.plots import add_scatter_trace_coverage, print_chromosome_html, plots_add_markers_lines, plots_layout_settings,\
 whole_genome_combined_df, copy_number_plots_per_chromosome, print_genome_pdf, add_annotation
-from utils import detect_alter_loh_regions, loh_regions_events, write_segments_coverage, write_header_comments, get_vafs_from_normal_phased_vcf, get_chromosomes_regions
+from src.utils import detect_alter_loh_regions, loh_regions_events, write_segments_coverage, write_header_comments, get_vafs_from_normal_phased_vcf, get_chromosomes_regions
 
 def plot_snps_ratios_genome(args, df_snps_in_csv, df_loh_regions):
     if not os.path.isdir(args.out_dir_plots + '/snps_loh_plots'):
diff --git a/src/utils.py b/src/utils.py
diff --git a/src/vcf_processing.py b/src/vcf_processing.py
diff --git a/wakhan.py b/wakhan.py
