make preserve default true, change to drop columns

Author: allx2100

src/peak2gene.py

@@ -34,7 +34,7 @@ def peak2gene(
     up_bound: int = None,
     down_bound: int = None,
     consensus: bool = False,
-    preserve: bool = False,
+    drop_columns: bool = False,
 ) -> None:
     """
     Find the nearest genes for a given list of peaks.
@@ -52,8 +52,8 @@ def peak2gene(
     boundary (int): Boundary for artificial peak boundary option. None if other options.
     up_bound (int): Maximum allowed distance between peak and upstream feature.
     down_bound (int): Maximum allowed distance between peak and downstream feature.
-    consnsesus (bool): Whether to use consensus peaks.
-    preserve (bool): Whether to preserve the original file columns.
+    consensus (bool): Whether to use consensus peaks. Default False.
+    drop_columns (bool): Whether to drop unnecessary columns from the original file. Default False.
 
     Returns:
     None
@@ -66,7 +66,7 @@ def peak2gene(
     peaks = process_peaks(peak_file, peak_type, option, boundary, consensus)
     decomposed_peaks = decompose_features(peaks)
     output = find_nearest(
-        decomposed_peaks, species, num_features, ref_dir, up_bound, down_bound, preserve
+        decomposed_peaks, species, num_features, ref_dir, up_bound, down_bound, drop_columns
     )
     if output_type == "xlsx":
         write_to_excel(output, output_name, out_dir)
@@ -83,7 +83,7 @@ def find_nearest(
     ref_dir: str,
     up_bound: int,
     down_bound: int,
-    preserve: bool,
+    drop_columns: bool,
 ) -> pd.DataFrame:
     """
     Find the nearest genes for a given list of peaks. Place these in a Pandas DataFrame.
@@ -96,6 +96,7 @@ def find_nearest(
     ref_dir (str): Directory containing decomposed reference data.
     up_bound (int): Maximum allowed distance between peak and upstream feature.
     down_bound (int): Maximum allowed distance between peak and downstream feature.
+    drop_columns (bool): Whether to drop unnecessary columns from the original file.
 
     Returns:
     output (pd.DataFrame): Pandas DataFrame containing peak data, the nearest k genes for each peak,
@@ -123,7 +124,7 @@ def find_nearest(
                         up_bound,
                         down_bound,
                         num_features,
-                        preserve,
+                        drop_columns,
                     ),
                 ]
             )

src/peakScout

@@ -37,7 +37,7 @@ def main(args):
     db = args.down_bound
     gtf_ref = args.gtf_ref
     consensus = args.consensus
-    preserve = args.preserve
+    drop_columns = args.drop_columns
 
     if function == "peak2gene":
         peak2gene(
@@ -54,7 +54,7 @@ def main(args):
             ub,
             db,
             consensus,
-            preserve
+            drop_columns
         )
     elif function == "decompose":
         decompose_gtf(ref, species, gtf_ref)
@@ -113,7 +113,7 @@ if __name__ == "__main__":
     )
     parser.add_argument("--gtf_ref", "--gtf", type=str, help="File path to gtf")
     parser.add_argument('--consensus', action='store_true', help='Consensus peak file')
-    parser.add_argument('--preserve', action='store_true', help='Preserve all columns in input file')
+    parser.add_argument('--drop_columns', action='store_true', help='Only keep necessary columns from input file')
 
     args = parser.parse_args()
 

src/process_features.py

@@ -23,7 +23,7 @@ def get_nearest_features(
     up_bound: int,
     down_bound: int,
     k: int,
-    preserve: bool,
+    drop_columns: bool,
 ) -> pl.DataFrame:
     """
     Determine the nearest k features to each peak in roi using the reference
@@ -37,7 +37,7 @@ def get_nearest_features(
     up_bound (int): Maximum allowed distance between peak and upstream feature.
     down_bound (int): Maximum allowed distance between peak and downstream feature.
     k (int): Number of nearest features to collect.
-    preserve (bool): If True, preserve the original columns of the roi DataFrame.
+    drop_columns (bool): Whether to drop unnecessary columns from the original file.
 
     Returns:
     return_roi (pl.DataFrame): Polars DataFrame containing peak information, the
@@ -55,7 +55,7 @@ def get_nearest_features(
     start_features = starts.select(feature).to_numpy().flatten()
     end_features = ends.select(feature).to_numpy().flatten()
 
-    if not preserve:
+    if drop_columns:
         return_roi = roi.select(["name", "chr", "start", "end"]).clone()
     else:
         return_roi = roi.clone()
@@ -325,24 +325,14 @@ def gen_return_roi(
     None
     """
     for i in range(1, k + 1):
-        if feature == "gene_name":
-            return_roi = return_roi.with_columns(
-                [
-                    pl.Series("closest_" + feature + "_" + str(i), features_to_add[i]),
-                    pl.Series(
-                        "closest_" + "gene" + "_" + str(i) + "_dist", dists_to_add[i]
-                    ),
-                ]
-            )
-        else:
-            return_roi = return_roi.with_columns(
-                [
-                    pl.Series("closest_" + feature + "_" + str(i), features_to_add[i]),
-                    pl.Series(
-                        "closest_" + feature + "_" + str(i) + "_dist", dists_to_add[i]
-                    ),
-                ]
-            )
+        return_roi = return_roi.with_columns(
+            [
+                pl.Series("closest_" + feature + "_" + str(i), features_to_add[i]),
+                pl.Series(
+                    "closest_" + feature + "_" + str(i) + "_dist", dists_to_add[i]
+                ),
+            ]
+        )
     return return_roi
 
 

src/process_input.py

@@ -251,7 +251,7 @@ def process_genes(file_path: str, species: str, ref_dir: str) -> pl.DataFrame:
     gene_df = pl.DataFrame()
     for csv in os.listdir(os.path.join(ref_dir, species, "gene")):
         cur = pl.read_csv(os.path.join(ref_dir, species, "gene", csv))
-        for gene in genes:
+        for gene in genes[:]:
             if gene in cur.select(["gene_name"]).to_numpy():
                 gene_df = pl.concat([gene_df, cur.filter(pl.col("gene_name") == gene)])
                 genes.remove(gene)

test/test_peak2gene_BED6_expected_results.csv

@@ -1,11 +1,11 @@
-name,chr,start,end,closest_gene_name_1,closest_gene_1_dist,closest_gene_name_2,closest_gene_2_dist,closest_gene_name_3,closest_gene_3_dist
-peak_name_1,1,4344147,4344187,Rp1,0,Gm37483,19159,Gm6101,-83628
-peak_name_2,1,5258993,5259502,Gm7182,16604,Gm37567,48237,Atp6v1h,-96464
-peak_name_3,1,7405722,7406909,Gm18984,3770,Gm26901,-7853,Gm19002,-89260
-peak_name_4,1,8406429,8407654,Sntg1,0,Gm38024,43306,Gm16284,60772
-peak_name_5,1,10551123,10551732,Cpa6,0,Gm15604,2366,Gm25253,3822
-peak_name_6,2,3361888,3361958,Olah,0,Gm37525,-7884,Acbd7,-20895
-peak_name_7,2,5641105,5641105,Camk1d,0,Gm13216,-36944,Cdc123,153189
-peak_name_8,2,7365263,7365293,Celf2,0,Gm24340,-15070,Gm28641,164646
-peak_name_9,2,8372018,8372078,Gm24534,100016,Gm13254,-224153,Gm13255,261859
-peak_name_10,2,11082018,11082078,Gm26478,5703,Gm13297,8752,Gm13294,16855
+chr,start,end,name,score,strand,closest_gene_name_1,closest_gene_name_1_dist,closest_gene_name_2,closest_gene_name_2_dist,closest_gene_name_3,closest_gene_name_3_dist
+1,4344147,4344187,peak_name_1,178,.,Rp1,0,Gm37483,19159,Gm6101,-83628
+1,5258993,5259502,peak_name_2,708,+,Gm7182,16604,Gm37567,48237,Atp6v1h,-96464
+1,7405722,7406909,peak_name_3,687,+,Gm18984,3770,Gm26901,-7853,Gm19002,-89260
+1,8406429,8407654,peak_name_4,100,-,Sntg1,0,Gm38024,43306,Gm16284,60772
+1,10551123,10551732,peak_name_5,137,-,Cpa6,0,Gm15604,2366,Gm25253,3822
+2,3361888,3361958,peak_name_6,578,+,Olah,0,Gm37525,-7884,Acbd7,-20895
+2,5641105,5641105,peak_name_7,181,.,Camk1d,0,Gm13216,-36944,Cdc123,153189
+2,7365263,7365293,peak_name_8,707,.,Celf2,0,Gm24340,-15070,Gm28641,164646
+2,8372018,8372078,peak_name_9,634,-,Gm24534,100016,Gm13254,-224153,Gm13255,261859
+2,11082018,11082078,peak_name_10,542,+,Gm26478,5703,Gm13297,8752,Gm13294,16855

test/test_peak2gene_MACS2_expected_results.csv

@@ -1,11 +1,11 @@
-name,chr,start,end,closest_gene_name_1,closest_gene_1_dist,closest_gene_name_2,closest_gene_2_dist,closest_gene_name_3,closest_gene_3_dist
-sampleName.macs2_peak_1,1,4344147,4344187,Rp1,0,Gm37483,19159,Gm6101,-83628
-sampleName.macs2_peak_2,1,5258993,5259502,Gm7182,16604,Gm37567,48237,Atp6v1h,-96464
-sampleName.macs2_peak_3,1,7405722,7406909,Gm18984,3770,Gm26901,-7853,Gm19002,-89260
-sampleName.macs2_peak_4,1,8406429,8407654,Sntg1,0,Gm38024,43306,Gm16284,60772
-sampleName.macs2_peak_5,1,10551123,10551732,Cpa6,0,Gm15604,2366,Gm25253,3822
-sampleName.macs2_peak_6,2,3361888,3361958,Olah,0,Gm37525,-7884,Acbd7,-20895
-sampleName.macs2_peak_7,2,5641105,5641105,Camk1d,0,Gm13216,-36944,Cdc123,153189
-sampleName.macs2_peak_8,2,7365263,7365293,Celf2,0,Gm24340,-15070,Gm28641,164646
-sampleName.macs2_peak_9,2,8372018,8372078,Gm24534,100016,Gm13254,-224153,Gm13255,261859
-sampleName.macs2_peak_10,2,11082018,11082078,Gm26478,5703,Gm13297,8752,Gm13294,16855
+chr,start,end,name,score,strand,signal,pvalue,qvalue,peak,closest_gene_name_1,closest_gene_name_1_dist,closest_gene_name_2,closest_gene_name_2_dist,closest_gene_name_3,closest_gene_name_3_dist
+1,4344147,4344187,sampleName.macs2_peak_1,178,.,12.3818,22.1235,17.8494,95,Rp1,0,Gm37483,19159,Gm6101,-83628
+1,5258993,5259502,sampleName.macs2_peak_2,123,.,9.35221,16.2172,12.3039,104,Gm7182,16604,Gm37567,48237,Atp6v1h,-96464
+1,7405722,7406909,sampleName.macs2_peak_3,52,.,6.43619,8.41372,5.22019,144,Gm18984,3770,Gm26901,-7853,Gm19002,-89260
+1,8406429,8407654,sampleName.macs2_peak_4,51,.,6.0389,8.23617,5.18458,352,Sntg1,0,Gm38024,43306,Gm16284,60772
+1,10551123,10551732,sampleName.macs2_peak_5,28,.,4.12402,5.46401,2.82539,133,Cpa6,0,Gm15604,2366,Gm25253,3822
+2,3361888,3361958,sampleName.macs2_peak_6,39,.,5.11495,6.90568,3.99502,68,Olah,0,Gm37525,-7884,Acbd7,-20895
+2,5641105,5641105,sampleName.macs2_peak_7,28,.,4.12402,5.46401,2.82539,107,Camk1d,0,Gm13216,-36944,Cdc123,153189
+2,7365263,7365293,sampleName.macs2_peak_8,39,.,5.44526,6.90568,3.99502,100,Celf2,0,Gm24340,-15070,Gm28641,164646
+2,8372018,8372078,sampleName.macs2_peak_9,80,.,7.42712,11.5959,8.0246,109,Gm24534,100016,Gm13254,-224153,Gm13255,261859
+2,11082018,11082078,sampleName.macs2_peak_10,28,.,4.12402,5.46401,2.82539,111,Gm26478,5703,Gm13297,8752,Gm13294,16855

test/test_peak2gene_SEACR_expected_results.csv

@@ -1,11 +1,11 @@
-name,chr,start,end,closest_gene_name_1,closest_gene_1_dist,closest_gene_name_2,closest_gene_2_dist,closest_gene_name_3,closest_gene_3_dist
-420.473,1,4344147,4344187,Rp1,0,Gm37483,19159,Gm6101,-83628
-503.23,1,5258993,5259502,Gm7182,16604,Gm37567,48237,Atp6v1h,-96464
-390.202,1,7405722,7406909,Gm18984,3770,Gm26901,-7853,Gm19002,-89260
-435.462,1,8406429,8407654,Sntg1,0,Gm38024,43306,Gm16284,60772
-409.048,1,10551123,10551732,Cpa6,0,Gm15604,2366,Gm25253,3822
-437.073,2,3361888,3361958,Olah,0,Gm37525,-7884,Acbd7,-20895
-402.774,2,5641105,5641105,Camk1d,0,Gm13216,-36944,Cdc123,153189
-446.691,2,7365263,7365293,Celf2,0,Gm24340,-15070,Gm28641,164646
-398.332,2,8372018,8372078,Gm24534,100016,Gm13254,-224153,Gm13255,261859
-448.351,2,11082018,11082078,Gm26478,5703,Gm13297,8752,Gm13294,16855
+chr,start,end,name,max_signal,region,closest_gene_name_1,closest_gene_name_1_dist,closest_gene_name_2,closest_gene_name_2_dist,closest_gene_name_3,closest_gene_name_3_dist
+1,4344147,4344187,420.473,1.31825,1:4344146-4344186,Rp1,0,Gm37483,19159,Gm6101,-83628
+1,5258993,5259502,503.23,1.78208,1:5258992-5259501,Gm7182,16604,Gm37567,48237,Atp6v1h,-96464
+1,7405722,7406909,390.202,0.683537,1:7405721-7406908,Gm18984,3770,Gm26901,-7853,Gm19002,-89260
+1,8406429,8407654,435.462,1.00089,1:8406428-8407653,Sntg1,0,Gm38024,43306,Gm16284,60772
+1,10551123,10551732,409.048,1.36707,1:10551122-10551731,Cpa6,0,Gm15604,2366,Gm25253,3822
+2,3361888,3361958,437.073,1.58678,2:3361887-3361957,Olah,0,Gm37525,-7884,Acbd7,-20895
+2,5641105,5641105,402.774,1.85531,2:5641104-5641104,Camk1d,0,Gm13216,-36944,Cdc123,153189
+2,7365263,7365293,446.691,1.36707,2:7365262-7365292,Celf2,0,Gm24340,-15070,Gm28641,164646
+2,8372018,8372078,398.332,1.26943,2:8372017-8372077,Gm24534,100016,Gm13254,-224153,Gm13255,261859
+2,11082018,11082078,448.351,0.830009,2:11082017-11082077,Gm26478,5703,Gm13297,8752,Gm13294,16855