separate parser

bean/annotate/utils.py

@@ -248,6 +248,27 @@ def get_splice_positions_from_gene_name(
     return cds_chrom, np.array(splice_donor_pos), np.array(splice_acceptor_pos)
 
 
+def get_splice_parser(parser=None):
+    if parser is None:
+        parser = argparse.ArgumentParser(
+            "Get splice site position",
+            usage="Get splice site position from exon fasta and target editing base.",
+        )
+
+    parser.add_argument(
+        "exon_fa_path", help="File path to fasta file with exon position information."
+    )
+    parser.add_argument(
+        "--gene-name",
+        action="store_true",
+        help="File path to fasta file with exon position information.",
+    )
+    parser.add_argument("edited_base", help="Edited base, either A or C.")
+    parser.add_argument("output_path", help="output path of the splice site csv file.")
+
+    return parser
+
+
 def parse_args(parser=None):
     if parser is None:
         parser = argparse.ArgumentParser(

bean/cli/execute.py

@@ -6,7 +6,7 @@
 from bean.annotate.utils import parse_args as get_filter_parser
 from bean.model.parser import parse_args as get_run_parser
 from bean.framework.parser import get_input_parser as get_create_screen_parser
-from bean.cli.get_splice_sites import get_parser as get_splice_site_parser
+from bean.annotate.utils import get_splice_parser as get_splice_site_parser
 from bean.cli.count import main as count
 from bean.cli.count_samples import main as count_samples
 from bean.cli.profile import main as profile

bean/cli/get_splice_sites.py

@@ -6,27 +6,6 @@
 from bean.annotate.utils import get_splice_positions_from_gene_name
 
 
-def get_parser(parser=None):
-    if parser is None:
-        parser = argparse.ArgumentParser(
-            "Get splice site position",
-            usage="Get splice site position from exon fasta and target editing base.",
-        )
-
-    parser.add_argument(
-        "exon_fa_path", help="File path to fasta file with exon position information."
-    )
-    parser.add_argument(
-        "--gene-name",
-        action="store_true",
-        help="File path to fasta file with exon position information.",
-    )
-    parser.add_argument("edited_base", help="Edited base, either A or C.")
-    parser.add_argument("output_path", help="output path of the splice site csv file.")
-
-    return parser
-
-
 def get_splice_positions(exon_fa_path) -> Tuple[str, np.ndarray, np.ndarray]:
     splice_donor_pos = []
     splice_acceptor_pos = []

docs/_filter.md

@@ -36,8 +36,3 @@ bean filter my_sorting_screen.h5ad \
   2. Feed `--translate-fastas-csv gene_exon_fas.csv` where `gene_exon_fas.csv` is the csv file with lines `gene_id,gene_exon_fasta_path` without header. Each FASTA file in `gene_exon_fasta_path` is formatted [as the single-gene FASTA file](https://github.com/pinellolab/crispr-bean/blob/main/docs/exon_fa_format.md).
 * Translation will keep the variants outside the coding sequence as nucleotide-level variants, while aggregating variants leading to the same coding sequence variants.
 
-# Getting splice sites
-We provide the utility script to obtain the splice sites if you use the MANE transcript with gene symbol (`--translate-gene-name GENE_SYMBOL` or `--translate-genes-list path_to_gene_names_file.txt`).
-```bash
-bean get-splice-sites LDLR A LDLR_splice_sites.csv --gene-name
-```

docs/_get_splice_sites.md

@@ -0,0 +1,5 @@
+# Getting splice sites
+We provide the utility script to obtain the splice sites if you use the MANE transcript with gene symbol (`--translate-gene-name GENE_SYMBOL` or `--translate-genes-list path_to_gene_names_file.txt`).
+```bash
+bean get-splice-sites LDLR A LDLR_splice_sites.csv --gene-name
+```