Added --skip-failed

CHANGELOG.md

@@ -10,6 +10,12 @@ This project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.htm
 
 ## [Unreleased]
 
+## [1.4.6-rc3] - 2025-03-10
+
+- Added --skip-failed flag to callVariant, parseArriba, parserSTARFusion, parseFusionCatcher.
+
+- Added tally table to parseREDITools, parseCIRCExplorer, and parseRMATS
+
 ## [1.4.6-rc2] - 2025-03-03
 
 ### Fixed

moPepGen/__init__.py

@@ -8,7 +8,7 @@
 from . import constant
 
 
-__version__ = '1.4.6-rc2'
+__version__ = '1.4.6-rc3'
 
 ## Error messages
 ERROR_INDEX_IN_INTRON = 'The genomic index seems to be in an intron'

moPepGen/cli/parse_arriba.py

@@ -2,13 +2,18 @@
 [Arriba](https://github.com/suhrig/arriba) and saves as a GVF file. The GVF
 file can be later used to call variant peptides using
 [callVariant](call-variant.md)."""
-from typing import List
+from __future__ import annotations
+from typing import TYPE_CHECKING
 from pathlib import Path
 import argparse
 from moPepGen import get_logger, seqvar, parser, err
 from moPepGen.cli import common
 
 
+if TYPE_CHECKING:
+    from typing import List
+    from logging import Logger
+
 INPUT_FILE_FORMATS = ['.tsv', '.txt']
 OUTPUT_FILE_FORMATS = ['.gvf']
 
@@ -50,16 +55,50 @@ def add_subparser_parse_arriba(subparsers:argparse._SubParsersAction):
         metavar='<choice>',
         default='medium'
     )
+    common.add_args_skip_failed(p)
     common.add_args_source(p)
     common.add_args_reference(p, proteome=False)
     common.add_args_debug_level(p)
     p.set_defaults(func=parse_arriba)
     common.print_help_if_missing_args(p)
     return p
 
+class TallyTable():
+    """ Tally table """
+    def __init__(self, logger:Logger):
+        """ Constructor """
+        self.total:int = 0
+        self.succeed:int = 0
+        self.skipped:TallyTableSkipped = TallyTableSkipped()
+        self.logger = logger
+
+    def log(self):
+        """ Show tally results """
+        self.logger.info("Summary:")
+        self.logger.info("Totally records read: %i", self.total)
+        self.logger.info("Records successfully processed: %i", self.succeed)
+        self.logger.info("Records skipped: %i", self.skipped.total)
+        if self.skipped.total > 0:
+            self.logger.info("Out of those skipped,")
+            self.logger.info("    Invalid gene ID: %i", self.skipped.invalid_gene_id)
+            self.logger.info("    Invalid position: %i", self.skipped.invalid_position)
+            self.logger.info("    Insufficient evidence: %i", self.skipped.insufficient_evidence)
+            self.logger.info("    Antisense strand: %i", self.skipped.antisense_strand)
+
+class TallyTableSkipped():
+    """ Tally table for failed ones """
+    def __init__(self):
+        """ constructor """
+        self.invalid_gene_id:int = 0
+        self.invalid_position:int = 0
+        self.insufficient_evidence:int = 0
+        self.antisense_strand:int = 0
+        self.total:int = 0
+
 def parse_arriba(args:argparse.Namespace) -> None:
     """ Parse Arriba output and save it in GVF format. """
     logger = get_logger()
+    tally = TallyTable(logger)
     # unpack args
     fusion = args.input_path
     output_path:Path = args.output_path
@@ -82,17 +121,33 @@ def parse_arriba(args:argparse.Namespace) -> None:
 
     with open(fusion, 'rt') as handle:
         for record in parser.ArribaParser.parse(handle):
+            tally.total += 1
             if not record.gene_id1 in anno.genes or not record.gene_id2 in anno.genes:
+                tally.skipped.invalid_gene_id += 1
+                tally.skipped.total += 1
                 continue
             if not record.is_valid(min_split_read1, min_split_read2, min_confidence):
+                tally.skipped.insufficient_evidence += 1
+                tally.skipped.total += 1
                 continue
             if record.transcript_on_antisense_strand(anno):
+                tally.skipped.antisense_strand += 1
+                tally.skipped.total += 1
                 continue
             try:
                 var_records = record.convert_to_variant_records(anno, genome)
+                variants.extend(var_records)
+                tally.succeed += 1
             except err.GeneNotFoundError:
+                tally.skipped.invalid_gene_id += 1
+                tally.skipped.total += 1
                 continue
-            variants.extend(var_records)
+            except:
+                if args.skip_failed:
+                    tally.skipped.invalid_position += 1
+                    tally.skipped.total += 1
+                    continue
+                raise
 
     logger.info('Arriba output %s loaded.', fusion)
 
@@ -110,3 +165,5 @@ def parse_arriba(args:argparse.Namespace) -> None:
     seqvar.io.write(variants, output_path, metadata)
 
     logger.info("Variants written to disk.")
+
+    tally.log()

moPepGen/cli/parse_circexplorer.py

@@ -4,14 +4,18 @@
 [callVariant](call-variant.md). Noted that only known circRNA is supported (
 \*_circular_known.txt) """
 from __future__ import annotations
+from typing import TYPE_CHECKING
 import argparse
-from typing import List, Dict
 from pathlib import Path
 from moPepGen import get_logger, circ, err
 from moPepGen.parser import CIRCexplorerParser
 from moPepGen.cli import common
 
 
+if TYPE_CHECKING:
+    from typing import List, Dict
+    from logging import Logger
+
 INPUT_FILE_FORMATS = ['.tsv', '.txt']
 OUTPUT_FILE_FORMATS = ['.gvf']
 
@@ -74,16 +78,48 @@ def add_subparser_parse_circexplorer(subparsers:argparse._SubParsersAction):
         default='-100,5',
         metavar='<number>'
     )
+    common.add_args_skip_failed(p)
     common.add_args_source(p)
     common.add_args_reference(p, genome=False, proteome=False)
     common.add_args_debug_level(p)
     p.set_defaults(func=parse_circexplorer)
     common.print_help_if_missing_args(p)
     return p
 
+class TallyTable():
+    """ Tally table """
+    def __init__(self, logger:Logger):
+        """ Constructor """
+        self.total:int = 0
+        self.succeed:int = 0
+        self.skipped:TallyTableSkipped = TallyTableSkipped()
+        self.logger = logger
+
+    def log(self):
+        """ Show tally results """
+        self.logger.info("Summary:")
+        self.logger.info("Totally records read: %i", self.total)
+        self.logger.info("Records successfully processed: %i", self.succeed)
+        self.logger.info("Records skipped: %i", self.skipped.total)
+        if self.skipped.total > 0:
+            self.logger.info("Out of those skipped,")
+            self.logger.info("    Invalid circRNA record: %i", self.skipped.invalid_record)
+            self.logger.info("    Insufficient evidence: %i", self.skipped.insufficient_evidence)
+
+class TallyTableSkipped():
+    """ Tally table for failed ones """
+    def __init__(self):
+        """ constructor """
+        self.invalid_gene_id:int = 0
+        self.invalid_position:int = 0
+        self.insufficient_evidence:int = 0
+        self.invalid_record:int = 0
+        self.total:int = 0
+
 def parse_circexplorer(args:argparse.Namespace):
     """ Parse circexplorer known circRNA results. """
     logger = get_logger()
+    tally = TallyTable(logger)
 
     input_path:Path = args.input_path
     output_path:Path = args.output_path
@@ -104,11 +140,16 @@ def parse_circexplorer(args:argparse.Namespace):
     circ_records:Dict[str, List[circ.CircRNAModel]] = {}
 
     for record in CIRCexplorerParser.parse(input_path, args.circexplorer3):
+        tally.total += 1
         if not args.circexplorer3:
             if not record.is_valid(args.min_read_number):
+                tally.skipped.total += 1
+                tally.skipped.insufficient_evidence += 1
                 continue
         elif not record.is_valid(args.min_read_number, args.min_fbr_circ, \
                 args.min_circ_score):
+            tally.skipped.total += 1
+            tally.skipped.insufficient_evidence += 1
             continue
         try:
             circ_record = record.convert_to_circ_rna(anno, intron_start_range,
@@ -119,13 +160,17 @@ def parse_circexplorer(args:argparse.Namespace):
                 " Skipping it from parsing.",
                 record.name, record.isoform_name
             )
+            tally.skipped.invalid_record += 1
+            tally.skipped.total += 1
             continue
         except err.IntronNotFoundError:
             logger.warning(
                 "The CIRCexplorer record %s from transcript %s contains an unknown"
                 " intron. Skipping it from parsing.",
                 record.name, record.isoform_name
             )
+            tally.skipped.invalid_record += 1
+            tally.skipped.total += 1
             continue
         except:
             logger.error('Exception raised from record: %s', record.name)
@@ -135,21 +180,20 @@ def parse_circexplorer(args:argparse.Namespace):
             circ_records[gene_id] = []
         circ_records[gene_id].append(circ_record)
 
-    if not circ_records:
-        logger.warning('No variant record is saved.')
-        return
+    if circ_records:
+        genes_rank = anno.get_genes_rank()
+        ordered_keys = sorted(circ_records.keys(), key=lambda x:genes_rank[x])
 
-    genes_rank = anno.get_genes_rank()
-    ordered_keys = sorted(circ_records.keys(), key=lambda x:genes_rank[x])
+        records = []
+        for key in ordered_keys:
+            val = circ_records[key]
+            records.extend(val)
 
-    records = []
-    for key in ordered_keys:
-        val = circ_records[key]
-        records.extend(val)
+        metadata = common.generate_metadata(args)
 
-    metadata = common.generate_metadata(args)
+        with open(output_path, 'w') as handle:
+            circ.io.write(records, metadata, handle)
 
-    with open(output_path, 'w') as handle:
-        circ.io.write(records, metadata, handle)
+        logger.info("CircRNA records written to disk.")
 
-    logger.info("CircRNA records written to disk.")
+    tally.log()

moPepGen/cli/parse_fusion_catcher.py

@@ -2,13 +2,18 @@
 [FusionCatcher](https://github.com/ndaniel/fusioncatcher) and save as a
 GVF file. The GVF file can be later used to call variant peptides using
 [callVariant](call-variant.md)."""
-from typing import List
+from __future__ import annotations
+from typing import TYPE_CHECKING
 from pathlib import Path
 import argparse
 from moPepGen import get_logger, seqvar, parser, err
 from moPepGen.cli import common
 
 
+if TYPE_CHECKING:
+    from typing import List
+    from logging import Logger
+
 INPUT_FILE_FORMATS = ['.tsv', '.txt']
 OUTPUT_FILE_FORMATS = ['.gvf']
 
@@ -42,16 +47,48 @@ def add_subparser_parse_fusion_catcher(subparsers:argparse._SubParsersAction):
         default=5,
         metavar='<number>'
     )
+    common.add_args_skip_failed(p)
     common.add_args_source(p)
     common.add_args_reference(p, proteome=False)
     common.add_args_debug_level(p)
     p.set_defaults(func=parse_fusion_catcher)
     common.print_help_if_missing_args(p)
     return p
 
+class TallyTable():
+    """ Tally table """
+    def __init__(self, logger:Logger):
+        """ Constructor """
+        self.total:int = 0
+        self.succeed:int = 0
+        self.skipped:TallyTableSkipped = TallyTableSkipped()
+        self.logger = logger
+
+    def log(self):
+        """ Show tally results """
+        self.logger.info("Summary:")
+        self.logger.info("Totally records read: %i", self.total)
+        self.logger.info("Records successfully processed: %i", self.succeed)
+        self.logger.info("Records skipped: %i", self.skipped.total)
+        if self.skipped.total > 0:
+            self.logger.info("Out of those skipped,")
+            self.logger.info("    Invalid gene ID: %i", self.skipped.invalid_gene_id)
+            self.logger.info("    Invalid position: %i", self.skipped.invalid_position)
+            self.logger.info("    Insufficient evidence: %i", self.skipped.insufficient_evidence)
+
+class TallyTableSkipped():
+    """ Tally table for failed ones """
+    def __init__(self):
+        """ constructor """
+        self.invalid_gene_id:int = 0
+        self.invalid_position:int = 0
+        self.insufficient_evidence:int = 0
+        self.total:int = 0
+
 def parse_fusion_catcher(args:argparse.Namespace) -> None:
     """ Parse FusionCatcher output and save it in GVF format. """
     logger = get_logger()
+    tally = TallyTable(logger)
     # unpack args
     fusion = args.input_path
     output_path:Path = args.output_path
@@ -69,15 +106,26 @@ def parse_fusion_catcher(args:argparse.Namespace) -> None:
     variants:List[seqvar.VariantRecord] = []
 
     for record in parser.FusionCatcherParser.parse(fusion):
-        if record.counts_of_common_mapping_reads > args.max_common_mapping:
-            continue
-        if record.spanning_unique_reads < args.min_spanning_unique:
+        tally.total += 1
+        if record.counts_of_common_mapping_reads > args.max_common_mapping \
+                or record.spanning_unique_reads < args.min_spanning_unique:
+            tally.skipped.insufficient_evidence += 1
+            tally.skipped.total += 1
             continue
         try:
             var_records = record.convert_to_variant_records(anno, genome)
+            variants.extend(var_records)
+            tally.succeed += 1
         except err.GeneNotFoundError:
+            tally.skipped.invalid_gene_id += 1
+            tally.skipped.total += 1
             continue
-        variants.extend(var_records)
+        except:
+            if args.skip_failed:
+                tally.skipped.total += 1
+                tally.skipped.invalid_position += 1
+                continue
+            raise
 
     logger.info('FusionCatcher output %s loaded.', fusion)
 
@@ -95,3 +143,5 @@ def parse_fusion_catcher(args:argparse.Namespace) -> None:
     seqvar.io.write(variants, output_path, metadata)
 
     logger.info("Variants written to disk.")
+
+    tally.log()