creation of get_gene_regulated_by_ddx.py and adaption of other scripts

src/bed_handler/__main__.py

@@ -9,12 +9,14 @@ visualisation
 
 from .filter_gene import create_filtered_bed
 from .get_gene_locations import create_region_bed
+from .get_gene_regulated_by_ddx import write_regulated_gene_file
 
 
 def launcher():
     """
     Create the necessary bed file to visualise bigwig file
     """
+    write_regulated_gene_file()
     create_filtered_bed()
     create_region_bed()
 

src/bed_handler/config.py

@@ -19,6 +19,7 @@ class OutputBed:
     tss_gene = output / "tss_gene.bed"
     tts_gene = output / "tts_gene.bed"
     after_gene = output / "after_gene.bed"
+    ddx_genes = output / "DDX5_17_genes.txt"
 
 
 class BedConfig:
@@ -26,9 +27,9 @@ class BedConfig:
     A class containing all the variables used in this submodule
     """
     base = Path(__file__).parents[2]
-    ddx_genes = base / "data" / "DDX5_17_genes.txt"
     gene_bed = base / "data" / "bed" / "gene.bed"
     exon_bed = base / "data" / "bed" / "exon.bed"
+    sipp_vs_ctcf = base / "data" / "Sipp_exon_vs_CTCF.csv"
     bed = OutputBed
     size = 5000
 
@@ -39,4 +40,5 @@ class TestConfig:
     list_genes = base / "list_genes.txt"
     gene_bed = base / "genes.bed"
     exon_bed = base / "exons.bed"
-    small_bw = base / "small.bw"
\ No newline at end of file
+    small_bw = base / "small.bw"
+    sipp_vs_ctcf = base / 'Sipp_exon_vs_CTCF.csv'
\ No newline at end of file

src/bed_handler/filter_gene.py

@@ -51,9 +51,8 @@ def create_filtered_bed() -> None:
     """
     Create a bed file containing only the genes of interest.
     """
-    gene_list = select_gene_of_interest(BedConfig.ddx_genes)
+    gene_list = select_gene_of_interest(BedConfig.bed.ddx_genes)
     df = filter_bed(BedConfig.gene_bed, gene_list)
-    BedConfig.bed.output.mkdir(exist_ok=True, parents=True)
     df.to_csv(BedConfig.bed.filtered_gene, sep="\t", index=False)
 
 

src/bed_handler/get_gene_regulated_by_ddx.py

+#!/usr/bin/env python3
+
+# -*- coding: UTF-8 -*-
+
+"""
+Description: The goal of this script is to get genes regulated by \
+DDX5/17
+"""
+
+from .config import BedConfig, TestConfig
+from pathlib import Path
+import pandas as pd
+from doctest import testmod
+from typing import List
+
+
+def format_exon_bed(exon_bed: Path, gene_bed: Path) -> pd.DataFrame:
+    """
+
+    :param exon_bed: A bed file containing fasterDB exons
+    :param gene_bed: A bed file containing fasterDB genes
+    :return: A dataframe of exon with it's coordinate id + it's \
+    id corresponding to it's gene id and it's position within the gene
+
+    >>> format_exon_bed(TestConfig.exon_bed, TestConfig.gene_bed)
+                    exon_id   id  gene_id gene_name  exon_pos exon_name
+    0  18:28681866-28682388  1_1        1      DSC2         1    DSC2_1
+    1  18:28681184-28681432  1_2        1      DSC2         2    DSC2_2
+    2  18:28673522-28673606  1_3        1      DSC2         3    DSC2_3
+    3  18:28672064-28672263  1_4        1      DSC2         4    DSC2_4
+    4  18:28671490-28671530  1_5        1      DSC2         5    DSC2_5
+    5  18:28670991-28671110  1_6        1      DSC2         6    DSC2_6
+    6  18:28669402-28669557  1_7        1      DSC2         7    DSC2_7
+    7  18:28667632-28667776  1_8        1      DSC2         8    DSC2_8
+    8  18:28666539-28666705  1_9        1      DSC2         9    DSC2_9
+    """
+    exon_bed = pd.read_csv(exon_bed, sep="\t")
+    exon_bed['exon_id'] = exon_bed['#ref'].astype(str) + ':' + \
+                          (exon_bed['start'] + 1).astype(str) + '-' + \
+                          exon_bed['end'].astype(str)
+    exon_bed['gene_id'] = exon_bed['id'].str.replace(r'_\d+', '').astype(int)
+    exon_bed['exon_pos'] = exon_bed['id'].str.replace(r'\d+_', '').astype(int)
+    df_gene = pd.read_csv(gene_bed, sep="\t")[["id", "score"]]
+    df_gene.columns = ['gene_id', 'gene_name']
+    exon_bed = exon_bed.merge(df_gene, how="left", on=['gene_id'])
+    exon_bed['exon_name'] = exon_bed['gene_name'] + "_" + \
+                            exon_bed['exon_pos'].astype(str)
+    return exon_bed[['exon_id', 'id', 'gene_id', 'gene_name', 'exon_pos',
+                     'exon_name']]
+
+
+def load_sipp_vs_ctct(sipp_file: Path, exon_table: pd.DataFrame
+                      ) -> pd.DataFrame:
+    """
+    Load the file containing exons regulated by DDX5 17 and containing their \
+    distance to CTCF. Finaly merge this table to `exon_table` to get \
+    aditional data
+
+    :param sipp_file:file containing exons regulated by DDX5 17 and \
+    containing their distance to CTCF.
+    :return: Same input table as a dataframe
+
+    >>> df = load_sipp_vs_ctct(TestConfig.sipp_vs_ctcf,
+    ... format_exon_bed(TestConfig.exon_bed, TestConfig.gene_bed))
+    >>> df[['exon_name', "exon_id", 'group', 'id', 'gene_id']]
+      exon_name               exon_id      group   id  gene_id
+    0    DSC2_1  18:28681866-28682388  siPP_DOWN  1_1        1
+    1    DSC2_2  18:28681184-28681432  siPP_DOWN  1_2        1
+    2    DSC2_3  18:28673522-28673606  siPP_DOWN  1_3        1
+    3    DSC2_4  18:28672064-28672263    siPP_UP  1_4        1
+    4    DSC2_5  18:28671490-28671530  siPP_DOWN  1_5        1
+    5    DSC2_6  18:28670991-28671110  siPP_DOWN  1_6        1
+    6    DSC2_7  18:28669402-28669557  siPP_DOWN  1_7        1
+    7    DSC2_8  18:28667632-28667776  siPP_DOWN  1_8        1
+    8    DSC2_9  18:28666539-28666705  siPP_DOWN  1_9        1
+    """
+    df = pd.read_csv(sipp_file, sep="\t")
+    return df.merge(exon_table, how="left", on=["exon_id", "exon_name"])
+
+
+def get_ddx_genes(df: pd.DataFrame) -> List[int]:
+    """
+    Return the unique values in gene_id column.
+
+    :param df: A dataframe of DDX regulated exons
+    :return: Return the unique values in gene_id column.
+
+    >>> df = load_sipp_vs_ctct(TestConfig.sipp_vs_ctcf,
+    ... format_exon_bed(TestConfig.exon_bed, TestConfig.gene_bed))
+    >>> get_ddx_genes(df)
+    [1]
+    """
+    return list(df['gene_id'].unique())
+
+
+def write_regulated_gene_file():
+    """
+    Write file file containing the regulated exons by DDX5/17
+    """
+    BedConfig.bed.output.mkdir(exist_ok=True, parents=True)
+    exon_table = format_exon_bed(BedConfig.exon_bed, BedConfig.gene_bed)
+    final_table = load_sipp_vs_ctct(BedConfig.sipp_vs_ctcf, exon_table)
+    list_gene = get_ddx_genes(final_table)
+    with BedConfig.bed.ddx_genes.open('w')as outfile:
+        for gene in list_gene:
+            outfile.write(f"{gene}\n")
+
+
+if __name__ == "__main__":
+    testmod()

tests/files/Sipp_exon_vs_CTCF.csv

+exon_name	dist	exon_id	CTCF_hit_id	group	strand	deltaPSI
+DSC2_1	1	18:28681866-28682388	18:28681866-28682388	siPP_DOWN	-	-0.33
+DSC2_2	2	18:28681184-28681432	18:28681184-28681432	siPP_DOWN	+	-0.23
+DSC2_3	3	18:28673522-28673606	18:28673522-28673606	siPP_DOWN	+	-0.17
+DSC2_4	4	18:28672064-28672263	18:28672064-28672263	siPP_UP	-	0.20
+DSC2_5	5	18:28671490-28671530	18:28671490-28671530	siPP_DOWN	-	-0.17
+DSC2_6	6	18:28670991-28671110	18:28670991-28671110	siPP_DOWN	-	-0.49
+DSC2_7	7	18:28669402-28669557	18:28669402-28669557	siPP_DOWN	+	-0.32
+DSC2_8	8	18:28667632-28667776	18:28667632-28667776	siPP_DOWN	-	-0.32
+DSC2_9	9	18:28666539-28666705	18:28666539-28666705	siPP_DOWN	-	-0.14