REDItools3 3.2a0__py3-none-any.whl → 3.4__py3-none-any.whl

reditools/__main__.py

@@ -2,12 +2,12 @@
 
 import sys
 
-from reditools import analyze, homopolymerics, index
+from reditools import analyze, homopolymerics, index, annotate
 
 
 def usage():
     """Print program usage."""
-    print("""usage: reditools {analyze,find-repeats,index}
+    print("""usage: reditools {analyze,find-repeats,index,annotate}
 
 REDItools3
 
@@ -18,6 +18,8 @@ Run Modes:
 
   index              Calculate editing indices from the output of `analyze`
                      mode.
+
+  annotate           Annotate REDItools RNA output with DNA output
 """)
 
 
@@ -31,6 +33,8 @@ if __name__ == '__main__':
                 homopolymerics.main()
             case 'index':
                 index.main()
+            case 'annotate':
+                annotate.main()
             case _:
                 usage()
     else:

reditools/alignment_file.py

@@ -118,9 +118,8 @@ class RTAlignmentFile(PysamAlignmentFile):
     # 141: NOT_MAPPED
     # 512: QC_FAIL
     # 256: IS_SECONDARY
-    # 2048: IS_SUPPLEMENTARY
     # 1024: IS_DUPLICATE
-    _flags_to_toss = {77, 141, 512, 256, 2048, 1024}
+    _flags_to_toss = {77, 141, 512, 256, 1024}
     _paired_flags_to_keep = {99, 147, 83, 163}
 
     def _check_quality(self, read):

reditools/analyze.py

@@ -88,8 +88,12 @@ def setup_rtools(options):  # noqa:WPS213,WPS231
             options.splicing_span,
         )
 
+    if options.variants:
+        rtools.specific_edits = [_.upper() for _ in options.variants]
+
     if options.bed_file:
-        rtools.load_target_positions(options.bed_file)
+        regions = file_utils.read_bed_file(options.bed_file)
+        rtools.target_positions = regions
     if options.exclude_regions:
         for fname in options.exclude_regions:
             regions = file_utils.read_bed_file(fname)
@@ -172,7 +176,7 @@ def write_results(rtools, sam_manager, file_name, region, output_format):
                 rt_result.per_base_depth,
                 ' '.join(sorted(variants)) if variants else '-',
                 f'{rt_result.edit_ratio:.2f}',
-                '\t'.join(['-' for _ in range(5)]),
+                '-', '-', '-', '-', '-',
             ])
         return stream.name
 
@@ -208,7 +212,7 @@ def run(options, in_queue, out_queue):
     except Exception as exc:
         if options.debug:
             traceback.print_exception(*sys.exc_info())
-        sys.stderr.write(f'[ERROR] {exc}\n')
+        sys.stderr.write(f'[ERROR] ({type(exc)}) {exc}\n')
 
 
 def parse_options():  # noqa:WPS213
@@ -344,7 +348,7 @@ def parse_options():  # noqa:WPS213
         '-me',
         '--min-edits',
         type=int,
-        default=0,  # noqa:WPS432
+        default=1,
         help='The minimum number of editing events (per position). ' +
         'Positions with fewer than -me edits will be discarded.',
     )
@@ -425,6 +429,14 @@ def parse_options():  # noqa:WPS213
         help='Run in debug mode.',
         action='store_true',
     )
+    parser.add_argument(
+        '-v',
+        '--variants',
+        nargs='*',
+        default=['CT', 'AG'],
+        help='Which editing events to report. Edits should be two characters, '
+        'separated by spaces. Use "all" to report all variants.',
+    )
 
     return parser.parse_args()
 

reditools/annotate.py

@@ -0,0 +1,126 @@
+import argparse
+from reditools import file_utils
+import csv
+import sys
+
+
+class RTAnnotater:
+    def __init__(self, rna_file, dna_file):
+        self.rna_file = rna_file
+        self.dna_file = dna_file
+        self.contig_order = self._load_contig_order()
+
+    def _load_contig_order(self):
+        contigs = {}
+        idx = 1
+        with file_utils.open_stream(self.rna_file, 'r') as stream:
+            reader = csv.reader(stream, delimiter='\t')
+            last_contig = next(reader)[0]
+            contigs[last_contig] = 0
+            for row in reader:
+                if row[0] == last_contig:
+                    continue
+                contigs[row[0]] = idx
+                idx += 1
+                last_contig = row[0]
+        return contigs
+
+    def _cmp_position(self, rna_contig, rna_pos, dna_contig, dna_pos):
+        rna_contig = self.contig_order[rna_contig]
+        dna_contig = self.contig_order.get(dna_contig, len(self.contig_order))
+        if rna_contig < dna_contig:
+            return -1
+        if rna_contig > dna_contig:
+            return 1
+        rna_pos = int(rna_pos)
+        dna_pos = int(dna_pos)
+        if rna_pos < dna_pos:
+            return -1
+        if rna_pos > dna_pos:
+            return 1
+        return 0
+
+    def _annotate_row(self, rna_row, dna_row):
+        rna_row['gCoverage-q30'] = dna_row['Coverage-q30']
+        rna_row['gMeanQ'] = dna_row['MeanQ']
+        rna_row['gBaseCount[A,C,G,T]'] = dna_row['BaseCount[A,C,G,T]']
+        rna_row['gAllSubs'] = dna_row['AllSubs']
+        rna_row['gFrequency'] = dna_row['Frequency']
+        return rna_row
+
+    def _compare_files(self):
+        with file_utils.open_stream(self.rna_file, 'r') as rna_stream, \
+                file_utils.open_stream(self.dna_file, 'r') as dna_stream:
+            rna_reader = csv.DictReader(rna_stream, delimiter='\t')
+            dna_reader = csv.DictReader(dna_stream, delimiter='\t')
+
+            rna_entry = next(rna_reader, None)
+            dna_entry = next(dna_reader, None)
+
+            while rna_entry is not None:
+                if dna_entry is None:
+                    yield rna_entry
+                    rna_entry = next(rna_reader, None)
+                    continue
+                cmp = self._cmp_position(
+                    rna_entry['Region'],
+                    rna_entry['Position'],
+                    dna_entry['Region'],
+                    dna_entry['Position'])
+                if cmp == 0:
+                    yield self._annotate_row(rna_entry, dna_entry)
+                    rna_entry = next(rna_reader, None)
+                    dna_entry = next(dna_reader, None)
+                elif cmp > 0:
+                    dna_entry = next(dna_reader, None)
+                else:
+                    yield rna_entry
+                    rna_entry = next(rna_reader, None)
+
+    def annotate(self, stream):
+        writer = csv.DictWriter(stream, delimiter='\t', fieldnames=[
+            'Region',
+            'Position',
+            'Reference',
+            'Strand',
+            'Coverage-q30',
+            'MeanQ',
+            'BaseCount[A,C,G,T]',
+            'AllSubs',
+            'Frequency',
+            'gCoverage-q30',
+            'gMeanQ',
+            'gBaseCount[A,C,G,T]',
+            'gAllSubs',
+            'gFrequency'])
+        writer.writeheader()
+        writer.writerows(self._compare_files())
+
+
+def parse_options():
+    """
+    Parse commandline options for REDItools.
+
+    Returns:
+        namespace: commandline args
+    """
+    parser = argparse.ArgumentParser(
+        prog='reditools annotate',
+        description='Annotates RNA REDItools output with DNA output.',
+        formatter_class=argparse.ArgumentDefaultsHelpFormatter,
+    )
+    parser.add_argument(
+        'rna_file',
+        help='The REDItools output from RNA data',
+    )
+    parser.add_argument(
+        'dna_file',
+        help='The REDItools output from corresponding DNA data',
+    )
+    return parser.parse_args()
+
+
+def main():
+    options = parse_options()
+    x = RTAnnotater(options.rna_file, options.dna_file)
+    x.annotate(sys.stdout)

reditools/reditools.py

@@ -134,7 +134,7 @@ class REDItools(object):
         self._include_refs = None
 
     @property
-    def includ_refs(self):
+    def include_refs(self):
         """
         Genome reference bases to report on.
 
@@ -149,22 +149,29 @@ class REDItools(object):
         Specific edit events to report.
 
         Returns:
-            iterable
+            set
         """
         return self._specific_edits
 
     @specific_edits.setter
-    def specific_edits(self, alts):
-        function_a = self._rtqc.check_specific_edits
-        function_b = self._rtqc.check_ref
-        self._specific_edits = set(alts)
-        self._include_refs = [_[0] for _ in alts]
-        if self._include_refs:
-            self._rtqc.add(function_a)
-            self._rtqc.add(function_b)
-        else:
-            self._rtqc.discard(function_a)
-            self._rtqc.discard(function_b)
+    def specific_edits(self, edits):
+        if edits == ["ALL"]:
+            edits = []
+        for alt in edits:
+            if not self._verify_alt(alt):
+                raise Exception(
+                        f'Specific edit "{alt}" is not valid. ' +
+                        'Edits must be two character strings of ATCG.')
+        self._specific_edits = set(edits)
+
+    def _verify_alt(self, alt):
+        if not isinstance(alt, str):
+            return False
+        if len(alt) != 2:
+            return False
+        if alt[0] not in 'ATCG' and alt[1] not in 'ATCG':
+            return False
+        return True
 
     @property
     def splice_positions(self):
@@ -389,13 +396,12 @@ class REDItools(object):
             if column is None:
                 self.log(Logger.debug_level, 'Bad column - skipping')
                 continue
-            if self._specific_edits:
-                if not self._specific_edits & set(column.variants):
-                    self.log(
-                        Logger.debug_level,
-                        'Requested edits not found - skipping',
-                    )
-                    continue
+            if self._specific_edits and not self._specific_edits & set(column.variants):
+                self.log(
+                    Logger.debug_level,
+                    'Requested edits not found - skipping',
+                )
+                continue
             self.log(
                 Logger.debug_level,
                 'Yielding output for {} reads',

reditools/rtchecks.py

@@ -149,12 +149,14 @@ class RTChecks(object):
         Returns:
             (bool): True if there are sufficient edits
         """
-        for num_edits in bases.get_min_edits():
-            if 0 < num_edits < rtools.min_edits_per_nucleotide:
+        for base in "ATCG":
+            if base == bases.ref:
+                continue
+            if bases[base] < rtools.min_edits_per_nucleotide:
                 rtools.log(
                     Logger.debug_level,
                     'DISCARDING COLUMN edits={} < {}',
-                    num_edits,
+                    bases[base],
                     rtools.min_edits_per_nucleotide,
                 )
                 return False
@@ -216,26 +218,6 @@ class RTChecks(object):
             return False
         return True
 
-    def check_ref(self, bases, rtools):
-        """
-        Check if the reference base is of interest.
-
-        Parameters:
-            bases (CompiledPosition): Data for analysis
-            rtools (REDItools): Object running the analysis
-
-        Returns:
-            (bool): True if reference base was specified
-        """
-        if bases.ref not in rtools.include_refs:
-            rtools.log(
-                Logger.debug_level,
-                'DISCARD COLUMN base "{}" not listed for reporting',
-                bases.ref,
-            )
-            return False
-        return True
-
     def check_exclusions(self, bases, rtools):
         """
         Check if the bases object is in an excluded position.
@@ -252,27 +234,6 @@ class RTChecks(object):
             return False
         return True
 
-    def check_specific_edits(self, bases, rtools):
-        """
-        Check whether specified edits are present.
-
-        Parameters:
-            bases (CompiledPosition): Data for analysis
-            rtools (REDItools): Object running the analysis
-
-        Returns:
-            (bool): True if the edit was specified
-        """
-        for ref, alt in rtools.specific_edits:
-            if not bases[ref] or not bases[alt]:
-                rtools.log(
-                    Logger.debug_level,
-                    'DISCARD COLUMN edit "{}" not specified for output',
-                    ref + alt,
-                )
-                return False
-        return True
-
     def check_max_alts(self, bases, rtools):
         """
         Check that there are no more than a max number of alts.

reditools3-3.4.dist-info/METADATA

@@ -0,0 +1,99 @@
+Metadata-Version: 2.4
+Name: REDItools3
+Version: 3.4
+Author: Ernesto Picardi
+Author-email: Adam Handen <adam.handen@gmail.com>
+Project-URL: homepage, https://github.com/BioinfoUNIBA/REDItools3
+Project-URL: repository, https://github.com/BioinfoUNIBA/REDItools3
+Project-URL: issues, https://github.com/BioinfoUNIBA/REDItools3/issues
+Keywords: bioinformatics,RNA,RNA-editing
+Classifier: Development Status :: 5 - Production/Stable
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: Science/Research
+Classifier: License :: OSI Approved :: GNU General Public License (GPL)
+Classifier: Operating System :: MacOS :: MacOS X
+Classifier: Operating System :: Unix
+Classifier: Programming Language :: Python :: 3.7
+Classifier: Topic :: Scientific/Engineering :: Bio-Informatics
+Requires-Python: >=3.7
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: pysam>=0.22.0
+Requires-Dist: sortedcontainers>=2.4.0
+Dynamic: license-file
+
+# REDItools3
+A new REDItools implementation to speed-up the RNA editing profiling in massive RNAseq data
+
+# Installation
+Install from PyPi.
+`pip install REDItools3`
+
+Use the whl file under the dist directory.
+`pip install dist/reditools-0.1-py3-none-any.whl`
+
+# Usage
+Once installed, reditools can be run from the commandline.
+`python -m reditools`
+
+## Tools
+
+### analyze
+This is the core reditools function: detecting editing events from one or more BAM file.
+
+The output is a tab separated table with these columns:
+| Field | Description |
+| --- | --- |
+| Region        | Chromosome or contig |
+| Position      | Position in the region |
+| Reference     | Base from the reference sequence |
+| Strand        | DNA strand (+, -, or \*) |
+| Coverage-q30  | How many reads had a quality of at least 30 |
+| MeanQ         | Mean read quality |
+| BaseCount[A,C,G,T] | Total count of each base found |
+| AllSubs       | All the detected substitutions |
+| Frequency     | Ratio of non-reference bases to reference bases |
+| gCoverage-q30 | Genomic Coverage-q30 (see `annotate`) |
+| gMeanQ        | Genomic MeanQ (see `annotate`) |
+| gBaseCount[A,C,G,T] | Genomic BaseCount (see `annotate`) |
+| gAllSubs      | Genomic variants (see `annotate`) |
+| gFrequency    | Genomic variant frequency (see `annotate`) |
+
+The last 5 columns will always be blank (`-`). They are reserved for output
+from the `annotate` tool.
+
+### annotate
+Annotate RNA editing output with variant detection from genomic data.
+
+`annotate` takes two reditools output files and fills in the last five columns
+of the first file with positional matches from the second.
+
+For example, this RNA file:
+```
+Region	Position	Reference	Strand	Coverage-q30	MeanQ	BaseCount[A,C,G,T]	AllSubs	Frequency	gCoverage-q30	gMeanQ	gBaseCount[A,C,G,T]	gAllSubs	gFrequency
+chr1	1115715	C	*	2	38.00	[0, 2, 0, 0]	-	0.00	-	-	-	-	-
+chr1	1115716	A	*	2	38.00	[2, 0, 0, 0]	-	0.00	-	-	-	-	-
+```
+
+With this DNA file:
+```
+Region	Position	Reference	Strand	Coverage-q30	MeanQ	BaseCount[A,C,G,T]	AllSubs	Frequency	gCoverage-q30	gMeanQ	gBaseCount[A,C,G,T]	gAllSubs	gFrequency
+chr1	1115716	A	*	2	38.00	[2, 0, 0, 0]	-	0.00	-	-	-	-	-
+chr1	1115717	C	*	2	38.00	[0, 2, 0, 0]	-	0.00	-	-	-	-	-
+```
+
+Produces:
+```
+Region	Position	Reference	Strand	Coverage-q30	MeanQ	BaseCount[A,C,G,T]	AllSubs	Frequency	gCoverage-q30	gMeanQ	gBaseCount[A,C,G,T]	gAllSubs	gFrequency
+chr1	1115715	C	*	2	38.00	[0, 2, 0, 0]	-	0.00	-	-	-	-	-
+chr1    1115716 A       *       2       38.00   [2, 0, 0, 0]    -       0.00    2       38.00   [2, 0, 0, 0]    -       0.00
+```
+
+### find-repeats
+Identify repetitive elements in a FASTQ file.
+
+### index
+Compute RNA editing index from reditools `analyze` output
+([PMDI: 31636457](https://pubmed.ncbi.nlm.nih.gov/31636457/)).
+The `index` tool computes the editing indices for all possible variants, not
+just A-to-I (listed as A-G in the output).

{REDItools3-3.2a0.dist-info → reditools3-3.4.dist-info}/RECORD

@@ -1,8 +1,9 @@
 reditools/__init__.py,sha256=7nSB0hrQznxrn6l95cv_pSonJTG6jZCQdbn7aT1TtvY,46
-reditools/__main__.py,sha256=mWJ9O2LDiOpBWDBJJUN7OiM4SyltW-kVXXAGBe_JxgQ,842
-reditools/alignment_file.py,sha256=YFyCEhMek2t93DpmpwEst5v3gDZkmRotbd6Fy_mP0aE,4258
+reditools/__main__.py,sha256=kKe2duIlmqnk7lUMZGWnzQzra2J5SzjqVehOSJv80VA,990
+reditools/alignment_file.py,sha256=tb_UZGsGkLf7aquScOJERPb9QdnlD4p6u2Ip9P8O8PI,4223
 reditools/alignment_manager.py,sha256=_FXwvqGWoXRdzVrwBxki2heaVZA2cQbGXqCopr-g1Hs,4138
-reditools/analyze.py,sha256=tW9Rz-R_8R-mJ2uQP5fpGFTH7TEv-2pOsigtbKqwYDY,14649
+reditools/analyze.py,sha256=5QUGpRk7DYDWnIuEK866Hn-jiysVL8uvC3o72GxKUso,15043
+reditools/annotate.py,sha256=Am27SAELiHyD78LZs2uRWPDlkWT14TXYUU54O6rj0A8,4089
 reditools/compiled_position.py,sha256=v540uUEie_HHUwsYQmBqeeOkUvtYlcnWj1v8gAhLUiE,3858
 reditools/compiled_reads.py,sha256=7Hm5f7g1T8q1zDOOxZUD7aZax9b7SdQ0PlmT93hmcaE,4154
 reditools/fasta_file.py,sha256=KBsJBs7OnBpew2PGWGp0mTxPLlpBmRrtXL4uvQw4t34,2212
@@ -10,12 +11,12 @@ reditools/file_utils.py,sha256=MfQPzJ4ogbwNvIiEu1oooS64EJH1CFdRS8eoqT9Zo4w,2763
 reditools/homopolymerics.py,sha256=UsHTr0e_OP_dkGq5te-oTSe5u6kzi5UJOF9t9QAunUk,2269
 reditools/index.py,sha256=jLgWwKXIA_e-bqVu74SDZXmrdWch_syDSmMnFZPbqz4,7537
 reditools/logger.py,sha256=u4L2SYxy4vJ4KDHEymd0b1sCa8BXXHchx8LR_wcFq1A,1210
-reditools/reditools.py,sha256=RNH7aKC2QnbafA7T9E6UpV5Llv3FjfDIabjPCuwDgW0,13111
+reditools/reditools.py,sha256=5kE0FXgRO6hWOj16oebWjkwdYDYLBBO2c8fdESy_YTw,13259
 reditools/region.py,sha256=_BiKDc5lCl1snjkokRiUWOgzA57ME3yLydEIwK9ku7U,3780
-reditools/rtchecks.py,sha256=TmCow38fCRwSICvx3nlOxy6Q216BcDXESGhM7bB_ixo,8878
+reditools/rtchecks.py,sha256=-wzDkjnGI4Tjoy05fIxvf7JnTssd91HpmPEL_mJg7Cc,7656
 reditools/utils.py,sha256=a2qfhMcrH2QlK-JoR-HHF6_bnlo5v3jihAqqknvVIjc,2733
-REDItools3-3.2a0.dist-info/LICENSE,sha256=OXLcl0T2SZ8Pmy2_dmlvKuetivmyPd5m1q-Gyd-zaYY,35149
-REDItools3-3.2a0.dist-info/METADATA,sha256=NRwZTGGmlHBkP6XiQ4Sdql-XXRR2Ii27beCDf_jCt90,1288
-REDItools3-3.2a0.dist-info/WHEEL,sha256=R06PA3UVYHThwHvxuRWMqaGcr-PuniXahwjmQRFMEkY,91
-REDItools3-3.2a0.dist-info/top_level.txt,sha256=wrvvbFXhmNg7s6LQqjlV_fVQYUZOOpF93IcMu_hBCx4,10
-REDItools3-3.2a0.dist-info/RECORD,,
+reditools3-3.4.dist-info/licenses/LICENSE,sha256=OXLcl0T2SZ8Pmy2_dmlvKuetivmyPd5m1q-Gyd-zaYY,35149
+reditools3-3.4.dist-info/METADATA,sha256=Z-SBdl-YRU8SRrlbKmSEqar0TyfYlFJIl1RVJGp3IBA,3848
+reditools3-3.4.dist-info/WHEEL,sha256=CmyFI0kx5cdEMTLiONQRbGQwjIoR1aIYB7eCAQ4KPJ0,91
+reditools3-3.4.dist-info/top_level.txt,sha256=wrvvbFXhmNg7s6LQqjlV_fVQYUZOOpF93IcMu_hBCx4,10
+reditools3-3.4.dist-info/RECORD,,

{REDItools3-3.2a0.dist-info → reditools3-3.4.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (75.5.0)
+Generator: setuptools (78.1.0)
 Root-Is-Purelib: true
 Tag: py3-none-any
 

REDItools3-3.2a0.dist-info/METADATA

@@ -1,36 +0,0 @@
-Metadata-Version: 2.1
-Name: REDItools3
-Version: 3.2a0
-Author: Ernesto Picardi
-Author-email: Adam Handen <adam.handen@gmail.com>
-Project-URL: homepage, https://github.com/BioinfoUNIBA/REDItools3
-Project-URL: repository, https://github.com/BioinfoUNIBA/REDItools3
-Project-URL: issues, https://github.com/BioinfoUNIBA/REDItools3/issues
-Keywords: bioinformatics,RNA,RNA-editing
-Classifier: Development Status :: 3 - Alpha
-Classifier: Intended Audience :: Developers
-Classifier: Intended Audience :: Science/Research
-Classifier: License :: OSI Approved :: GNU General Public License (GPL)
-Classifier: Operating System :: MacOS :: MacOS X
-Classifier: Operating System :: Unix
-Classifier: Programming Language :: Python :: 3.7
-Classifier: Topic :: Scientific/Engineering :: Bio-Informatics
-Requires-Python: >=3.7
-Description-Content-Type: text/markdown
-License-File: LICENSE
-Requires-Dist: pysam >=0.22.0
-Requires-Dist: sortedcontainers >=2.4.0
-
-# REDItools3
-A new REDItools implementation to speed-up the RNA editing profiling in massive RNAseq data
-
-# Installation
-Install from PyPi.
-`pip install REDItools3`
-
-Use the whl file under the dist directory.
-`pip install dist/reditools-0.1-py3-none-any.whl`
-
-# Usage
-Once installed, reditools can be run from the commandline.
-`python -m reditools`