add option to skip filtering

bean/mapping/GuideEditCounter.py

@@ -152,6 +152,7 @@ def __init__(self, **kwargs):
         if not self.objectify_allele:
             info(f"{self.name}: Storing allele as strings.")
         self.keep_intermediate = kwargs["keep_intermediate"]
+        self.skip_filtering = kwargs["skip_filtering"]
         self.id_number = random.randint(0, int(1e6))
         self.semimatch = 0
         self.bcmatch = 0
@@ -197,15 +198,24 @@ def _set_sgRNA_df(self):
     def check_filter_fastq(self):
         """Checks if the quality filtered fastq files already exists,
         and use them if the do."""
-        self.filtered_R1_filename = self._jp(
-            os.path.basename(self.R1_filename).replace(".fastq", "").replace(".gz", "")
-            + "_filtered.fastq.gz"
-        )
-        self.filtered_R2_filename = self._jp(
-            os.path.basename(self.R2_filename).replace(".fastq", "").replace(".gz", "")
-            + "_filtered.fastq.gz"
-        )
-        self._check_names_filter_fastq()
+        if self.skip_filtering:
+            self.filtered_R1_filename = self.R1_filename
+            self.filtered_R2_filename = self.R2_filename
+            self.n_reads_after_filtering = self.n_total_reads
+        else:
+            self.filtered_R1_filename = self._jp(
+                os.path.basename(self.R1_filename)
+                .replace(".fastq", "")
+                .replace(".gz", "")
+                + "_filtered.fastq.gz"
+            )
+            self.filtered_R2_filename = self._jp(
+                os.path.basename(self.R2_filename)
+                .replace(".fastq", "")
+                .replace(".gz", "")
+                + "_filtered.fastq.gz"
+            )
+            self._check_names_filter_fastq()
         # if (
         #     path.exists(self.filtered_R1_filename)
         #     and path.exists(self.filtered_R2_filename)

bean/mapping/utils.py

@@ -161,6 +161,11 @@ def _get_input_parser(parser=None):
         help="Keep all the  intermediate files",
         action="store_true",
     )
+    parser.add_argument(
+        "--skip-filtering",
+        help="Keep the read filtering",
+        action="store_true",
+    )
     parser.add_argument(
         "--qstart-R1",
         help="Start position of the read when filtering for quality score of the read 1",

tests/test_count.py

@@ -45,6 +45,19 @@ def test_count_samples():
 
 
 @pytest.mark.order(105)
+def test_count_samples_nofilter():
+    cmd = "bean count-samples -i tests/data/sample_list.csv -b A -f tests/data/test_guide_info.csv -o tests/test_res/var/ -r --guide-start-seq=GGAAAGGACGAAACACCG --skip-filtering"
+    try:
+        subprocess.check_output(
+            cmd,
+            shell=True,
+            universal_newlines=True,
+        )
+    except subprocess.CalledProcessError as exc:
+        raise exc
+
+
+@pytest.mark.order(106)
 def test_count_samples_dual():
     cmd = "bean count-samples -i tests/data/sample_list.csv -b A,C -f tests/data/test_guide_info.csv -o tests/test_res/var/ -r --guide-start-seq=GGAAAGGACGAAACACCG"
     try:
@@ -57,7 +70,7 @@ def test_count_samples_dual():
         raise exc
 
 
-@pytest.mark.order(106)
+@pytest.mark.order(107)
 def test_count_samples_bcstart():
     cmd = "bean count-samples -i tests/data/sample_list.csv -b A -f tests/data/test_guide_info.csv -o tests/test_res/var2/ -r --barcode-start-seq=GGAA"
     try:
@@ -95,7 +108,7 @@ def test_barcode_start_idx():
     assert bc == "AGAA"
 
 
-@pytest.mark.order(106)
+@pytest.mark.order(108)
 def test_count_samples_tiling():
     cmd = "bean count-samples -i tests/data/sample_list_tiling.csv -b A -f tests/data/test_guide_info_tiling_chrom.csv -o tests/test_res/tiling/ -r"
     try:
@@ -108,7 +121,7 @@ def test_count_samples_tiling():
         raise exc
 
 
-@pytest.mark.order(107)
+@pytest.mark.order(109)
 def test_count_chroms():
     cmd = "bean count --R1 tests/data/test_tiling_R1.fastq --R2 tests/data/test_tiling_R2.fastq -b A -f tests/data/test_guide_info_tiling_chrom.csv -o tests/test_res/tiling_chrom/ -r"
     try: