ssi-analysis-result-parsers 0.0.10__tar.gz → 0.0.11__tar.gz

{ssi_analysis_result_parsers-0.0.10/ssi_analysis_result_parsers.egg-info → ssi_analysis_result_parsers-0.0.11}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ssi_analysis_result_parsers
-Version: 0.0.10
+Version: 0.0.11
 Summary: TODO
 Home-page: https://github.com/thej-ssi/ssi_analysis_result_parsers
 Author: Thor Bech Johannesen

{ssi_analysis_result_parsers-0.0.10 → ssi_analysis_result_parsers-0.0.11}/settings.ini

@@ -5,7 +5,7 @@
 ### Python library ###
 repo = ssi_analysis_result_parsers
 lib_name = %(repo)s
-version = 0.0.10
+version = 0.0.11
 min_python = 3.9
 license = MIT
 black_formatting = True
@@ -54,3 +54,5 @@ console_scripts =
     get_ecoli_results=ssi_analysis_result_parsers.Ecoli_parser:ecoli_parser
     get_Spyogenes_results=ssi_analysis_result_parsers.Spyogenes_parser:Spyogenes_parser
     get_Spyogenes_results_batch=ssi_analysis_result_parsers.Spyogenes_parser:Spyogenes_batch_parser
+    get_Nmeningitidis_results=ssi_analysis_result_parsers.Nmeningitidis_parser:Nmeningitidis_parser
+    get_Nmeningitidis_results_batch=ssi_analysis_result_parsers.Nmeningitidis_parser:Nmeningitidis_batch_parser

{ssi_analysis_result_parsers-0.0.10 → ssi_analysis_result_parsers-0.0.11}/ssi_analysis_result_parsers/Legionella_parser.py

@@ -32,6 +32,7 @@ from ssi_analysis_result_parsers import (
 # Project specific libraries
 from pathlib import Path
 import pandas
+import numpy
 import sys
 
 # %% ../nbs/39_Legionella_parser.ipynb 6
@@ -49,7 +50,7 @@ def extract_legionella_sbt(legionella_sbt_results_tsv: Path) -> dict:
             return d[fname]
         except pandas.errors.EmptyDataError:
             print(
-                f"No Legionella SBT output empty at {legionella_sbt_results_tsv}",
+                f"Legionella SBT output empty at {legionella_sbt_results_tsv}",
                 file=sys.stderr,
             )
             return None
@@ -98,6 +99,7 @@ class LegionellaResults(core.PipelineResults):
         Alternative constructor for initializing results for multiple samples,
         Initializes LegionellaResults instance by providing a DataFrame of paths to outputs from tools (legionella sbt and lag1 presence blast)
         """
+        file_paths_df.replace(numpy.nan, None, inplace=True)
         file_paths = file_paths_df.to_dict(orient="index")
         results_dict = {}
         for sample_name, path_dict in file_paths.items():

ssi_analysis_result_parsers-0.0.11/ssi_analysis_result_parsers/Nmeningitidis_parser.py

@@ -0,0 +1,178 @@
+# AUTOGENERATED! DO NOT EDIT! File to edit: ../nbs/37_Nmeningitidis_parser.ipynb.
+
+# %% auto 0
+__all__ = ['extract_meningotype', 'extract_cc_from_mlst', 'NmeningitidisResults', 'Nmeningitidis_parser',
+           'Nmeningitidis_batch_parser']
+
+# %% ../nbs/37_Nmeningitidis_parser.ipynb 3
+# standard libs
+import os
+import re
+
+# Common to template
+# add into settings.ini, requirements, package name is python-dotenv, for conda build ensure `conda config --add channels conda-forge`
+import dotenv  # for loading config from .env files, https://pypi.org/project/python-dotenv/
+import envyaml  # Allows to loads env vars into a yaml file, https://github.com/thesimj/envyaml
+import fastcore  # To add functionality related to nbdev development, https://github.com/fastai/fastcore/
+from fastcore import (
+    test,
+)
+from fastcore.script import (
+    call_parse,
+)  # for @call_parse, https://fastcore.fast.ai/script
+import json  # for nicely printing json and yaml
+
+# import functions from core module (optional, but most likely needed).
+from ssi_analysis_result_parsers import (
+    core,
+    blast_parser,
+)
+
+# from ssi_analysis_result_parsers.blast_parser import extract_presence_absence
+
+# Project specific libraries
+from pathlib import Path
+import pandas
+import numpy
+import sys
+
+# %% ../nbs/37_Nmeningitidis_parser.ipynb 6
+def extract_meningotype(meningotype_tsv: Path):
+    if meningotype_tsv.exists():
+        try:
+            df = pandas.read_csv(meningotype_tsv, sep="\t")
+            PorA_split = df["PorA"][0].split(",")
+            return {
+                "SEROGROUP": df["SEROGROUP"][0],
+                "VR1": PorA_split[0],
+                "VR2": PorA_split[1],
+                "FetA": df["FetA"][0],
+            }
+        except pandas.errors.EmptyDataError:
+            print(
+                f"Meningotype output file empty at {meningotype_tsv}", file=sys.stderr
+            )
+            return None
+    else:
+        print(f"No meningotype output found at {meningotype_tsv}", file=sys.stderr)
+        return None
+
+    return None
+
+
+def extract_cc_from_mlst(
+    MLST: str,
+    mlst_scheme_tsv: Path = "/users/data/Projects/MICROBIAL_SURVEILLANCE/Resources/Databases/mlst/neisseria/neisseria.txt",
+):
+    CC = {"CC": ""}
+    if mlst_scheme_tsv.exists():
+        try:
+            with open(mlst_scheme_tsv) as f:
+                for line in f:
+                    line = line.strip("\n").split("\t")
+                    if line[0] == MLST:
+                        if line[8][:3] == "ST-":
+                            CC["CC"] = line[8].split(" ")[0][3:]
+                        return CC
+        except Exception as e:
+            CC["CC"] = f"Failed to load mlst scheme tsv: {e}"
+    else:
+        CC["CC"] = "Failed to load mlst scheme tsv, file not found"
+    return CC
+
+
+class NmeningitidisResults(core.PipelineResults):
+
+    @classmethod
+    def from_tool_paths(
+        cls, meningotype_tsv: Path, MLST: str, mlst_scheme_tsv: Path, sample_name=None
+    ):
+        """
+        Alternative constructor for initializing results for single sample,
+        Initializes NmeningitidisResults instance provided paths to outputs from tools (legionella sbt and lag1 presence blast)
+        """
+        mgk_results = cls.summary(
+            meningotype_tsv=Path(meningotype_tsv),
+            MLST=MLST,
+            mlst_scheme_tsv=Path(mlst_scheme_tsv),
+        )
+        return cls({sample_name: mgk_results})
+
+    @classmethod
+    def from_tool_paths_dict(cls, file_paths: dict):
+        """
+        Alternative constructor for initializing results for multiple samples,
+        Initializes NmeningitidisResults instance by providing a dictionary of paths to outputs from tools (legionella sbt and lag1 presence blast)
+        """
+        results_dict = {}
+        for sample_name, path_dict in file_paths.items():
+            mgk_results = cls.summary(
+                meningotype_tsv=Path(path_dict["meningotype_results"]),
+                MLST=path_dict["MLST"],
+                mlst_scheme_tsv=path_dict["mlst_scheme_tsv"],
+            )
+            results_dict[sample_name] = mgk_results
+        return cls(results_dict)
+
+    @classmethod
+    def from_tool_paths_dataframe(cls, file_paths_df: pandas.DataFrame):
+        """
+        Alternative constructor for initializing results for multiple samples,
+        Initializes NmeningitidisResults instance by providing a DataFrame of paths to outputs from tools (legionella sbt and lag1 presence blast)
+        """
+        file_paths = file_paths_df.to_dict(orient="index")
+
+        return cls.from_tool_paths_dict(file_paths=file_paths)
+
+    @classmethod
+    def from_tool_paths_tsv(cls, tool_paths_tsv: Path):
+        """
+        Alternative constructor for initializing results for multiple samples,
+        Initializes NmeningitidisResults instance by providing a tsv-file with paths to outputs from tools (legionella sbt and lag1 presence blast)
+        """
+        file_paths_df = pandas.read_csv(tool_paths_tsv, sep="\t")
+        file_paths_df.set_index("sample_name", inplace=True, drop=True)
+        return cls.from_tool_paths_dataframe(file_paths_df)
+
+    @staticmethod
+    def summary(meningotype_tsv: Path, MLST: str, mlst_scheme_tsv: Path) -> dict:
+        meningotype_results = extract_meningotype(meningotype_tsv=Path(meningotype_tsv))
+        results_dict = meningotype_results
+        cc_dict = extract_cc_from_mlst(MLST=MLST, mlst_scheme_tsv=Path(mlst_scheme_tsv))
+        results_dict = core.update_results_dict(
+            results_dict, cc_dict, old_duplicate_key_prefix="Clonal_complex: "
+        )
+        if results_dict is None:
+            return {}
+        return results_dict
+
+    def __repr__(self):
+        return f"< Spyogenes analysis results object. {len(self.results_df)} samples with {len(self.results_df.columns)} result variables > "
+
+# %% ../nbs/37_Nmeningitidis_parser.ipynb 9
+@call_parse
+def Nmeningitidis_parser(
+    meningotype_tsv: Path = None,  # Blast output from blasting EMM and emm-like genes
+    MLST: str = None,  # MLST to deduce Clonal complex from
+    mlst_scheme_tsv: Path = None,  # Path to pubmlst scheme for neisseria for MLST: CC table
+    sample_name: str = None,
+    output_file: Path = None,
+) -> None:
+    """ """
+    results = NmeningitidisResults.from_tool_paths(
+        meningotype_tsv=meningotype_tsv,
+        MLST=MLST,
+        mlst_scheme_tsv=mlst_scheme_tsv,
+        sample_name=sample_name,
+    )
+    results.write_tsv(output_file=output_file)
+
+
+@call_parse
+def Nmeningitidis_batch_parser(
+    file_path_tsv: Path = None,  # Path to tsv containing file paths to the outputs from tools to be parsed. Must contain headers "sample_name", "sbt_results", and "lag1_blast_results"
+    output_file: Path = None,  # Path to output tsv
+) -> None:
+    """ """
+    results = NmeningitidisResults.from_tool_paths_tsv(tool_paths_tsv=file_path_tsv)
+    results.write_tsv(output_file)

{ssi_analysis_result_parsers-0.0.10 → ssi_analysis_result_parsers-0.0.11}/ssi_analysis_result_parsers/_modidx.py

@@ -45,6 +45,28 @@ d = { 'settings': { 'branch': 'main',
                                                                                                                                           'ssi_analysis_result_parsers/Legionella_parser.py'),
                                                                'ssi_analysis_result_parsers.Legionella_parser.legionella_parser': ( 'legionella_parser.html#legionella_parser',
                                                                                                                                     'ssi_analysis_result_parsers/Legionella_parser.py')},
+            'ssi_analysis_result_parsers.Nmeningitidis_parser': { 'ssi_analysis_result_parsers.Nmeningitidis_parser.NmeningitidisResults': ( 'nmeningitidis_parser.html#nmeningitidisresults',
+                                                                                                                                             'ssi_analysis_result_parsers/Nmeningitidis_parser.py'),
+                                                                  'ssi_analysis_result_parsers.Nmeningitidis_parser.NmeningitidisResults.__repr__': ( 'nmeningitidis_parser.html#nmeningitidisresults.__repr__',
+                                                                                                                                                      'ssi_analysis_result_parsers/Nmeningitidis_parser.py'),
+                                                                  'ssi_analysis_result_parsers.Nmeningitidis_parser.NmeningitidisResults.from_tool_paths': ( 'nmeningitidis_parser.html#nmeningitidisresults.from_tool_paths',
+                                                                                                                                                             'ssi_analysis_result_parsers/Nmeningitidis_parser.py'),
+                                                                  'ssi_analysis_result_parsers.Nmeningitidis_parser.NmeningitidisResults.from_tool_paths_dataframe': ( 'nmeningitidis_parser.html#nmeningitidisresults.from_tool_paths_dataframe',
+                                                                                                                                                                       'ssi_analysis_result_parsers/Nmeningitidis_parser.py'),
+                                                                  'ssi_analysis_result_parsers.Nmeningitidis_parser.NmeningitidisResults.from_tool_paths_dict': ( 'nmeningitidis_parser.html#nmeningitidisresults.from_tool_paths_dict',
+                                                                                                                                                                  'ssi_analysis_result_parsers/Nmeningitidis_parser.py'),
+                                                                  'ssi_analysis_result_parsers.Nmeningitidis_parser.NmeningitidisResults.from_tool_paths_tsv': ( 'nmeningitidis_parser.html#nmeningitidisresults.from_tool_paths_tsv',
+                                                                                                                                                                 'ssi_analysis_result_parsers/Nmeningitidis_parser.py'),
+                                                                  'ssi_analysis_result_parsers.Nmeningitidis_parser.NmeningitidisResults.summary': ( 'nmeningitidis_parser.html#nmeningitidisresults.summary',
+                                                                                                                                                     'ssi_analysis_result_parsers/Nmeningitidis_parser.py'),
+                                                                  'ssi_analysis_result_parsers.Nmeningitidis_parser.Nmeningitidis_batch_parser': ( 'nmeningitidis_parser.html#nmeningitidis_batch_parser',
+                                                                                                                                                   'ssi_analysis_result_parsers/Nmeningitidis_parser.py'),
+                                                                  'ssi_analysis_result_parsers.Nmeningitidis_parser.Nmeningitidis_parser': ( 'nmeningitidis_parser.html#nmeningitidis_parser',
+                                                                                                                                             'ssi_analysis_result_parsers/Nmeningitidis_parser.py'),
+                                                                  'ssi_analysis_result_parsers.Nmeningitidis_parser.extract_cc_from_mlst': ( 'nmeningitidis_parser.html#extract_cc_from_mlst',
+                                                                                                                                             'ssi_analysis_result_parsers/Nmeningitidis_parser.py'),
+                                                                  'ssi_analysis_result_parsers.Nmeningitidis_parser.extract_meningotype': ( 'nmeningitidis_parser.html#extract_meningotype',
+                                                                                                                                            'ssi_analysis_result_parsers/Nmeningitidis_parser.py')},
             'ssi_analysis_result_parsers.Spyogenes_parser': { 'ssi_analysis_result_parsers.Spyogenes_parser.SpyogenesResults': ( 'spyogenes_parser.html#spyogenesresults',
                                                                                                                                  'ssi_analysis_result_parsers/Spyogenes_parser.py'),
                                                               'ssi_analysis_result_parsers.Spyogenes_parser.SpyogenesResults.__repr__': ( 'spyogenes_parser.html#spyogenesresults.__repr__',

{ssi_analysis_result_parsers-0.0.10 → ssi_analysis_result_parsers-0.0.11/ssi_analysis_result_parsers.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ssi_analysis_result_parsers
-Version: 0.0.10
+Version: 0.0.11
 Summary: TODO
 Home-page: https://github.com/thej-ssi/ssi_analysis_result_parsers
 Author: Thor Bech Johannesen

{ssi_analysis_result_parsers-0.0.10 → ssi_analysis_result_parsers-0.0.11}/ssi_analysis_result_parsers.egg-info/SOURCES.txt

@@ -6,6 +6,7 @@ settings.ini
 setup.py
 ssi_analysis_result_parsers/Ecoli_parser.py
 ssi_analysis_result_parsers/Legionella_parser.py
+ssi_analysis_result_parsers/Nmeningitidis_parser.py
 ssi_analysis_result_parsers/Spyogenes_parser.py
 ssi_analysis_result_parsers/__init__.py
 ssi_analysis_result_parsers/_modidx.py
@@ -31,7 +32,13 @@ test_input/Legionella/batch_parser_file_paths.tsv
 test_input/Legionella/lag-1_blast.tsv
 test_input/Legionella/lag-1_blast_2.tsv
 test_input/Legionella/test.sbt.tsv
+test_input/Legionella/test.tsv
 test_input/Legionella/test2.sbt.tsv
+test_input/Nmeningitidis/batch_parser_file_paths.tsv
+test_input/Nmeningitidis/neisseria_mlst_scheme.tsv
+test_input/Nmeningitidis/meningotype/meningotype1.tsv
+test_input/Nmeningitidis/meningotype/meningotype2.tsv
+test_input/Nmeningitidis/meningotype/meningotype3.tsv
 test_input/Spyogenes/batch_parser_file_paths.tsv
 test_input/Spyogenes/emm_typing/Mga.fasta
 test_input/Spyogenes/emm_typing/emm_clusters.txt

{ssi_analysis_result_parsers-0.0.10 → ssi_analysis_result_parsers-0.0.11}/ssi_analysis_result_parsers.egg-info/entry_points.txt

@@ -1,6 +1,8 @@
 [console_scripts]
 blast_parser_allele_matches = ssi_analysis_result_parsers.blast_parser:allele_matches
 blast_parser_presence_absence = ssi_analysis_result_parsers.blast_parser:presence_absence
+get_Nmeningitidis_results = ssi_analysis_result_parsers.Nmeningitidis_parser:Nmeningitidis_parser
+get_Nmeningitidis_results_batch = ssi_analysis_result_parsers.Nmeningitidis_parser:Nmeningitidis_batch_parser
 get_Spyogenes_results = ssi_analysis_result_parsers.Spyogenes_parser:Spyogenes_parser
 get_Spyogenes_results_batch = ssi_analysis_result_parsers.Spyogenes_parser:Spyogenes_batch_parser
 get_ecoli_results = ssi_analysis_result_parsers.Ecoli_parser:ecoli_parser

ssi_analysis_result_parsers-0.0.11/test_input/Legionella/test.tsv

@@ -0,0 +1,2 @@
+sample_name	ST	flaA	pilE	asd	mip	mompS	proA	neuA	notes	lag-1
+	23	2	3	9	10	2	1	6	Exact ST match, Heterozygous mompS alleles, High confidence mompS allele call	1

ssi_analysis_result_parsers-0.0.11/test_input/Nmeningitidis/batch_parser_file_paths.tsv

@@ -0,0 +1,6 @@
+sample_name	meningotype_results	MLST	mlst_scheme_tsv
+sample_1	test_input/Nmeningitidis/meningotype/meningotype1.tsv	1466	test_input/Nmeningitidis/neisseria_mlst_scheme.tsv
+sample_2	test_input/Nmeningitidis/meningotype/meningotype2.tsv	1157	test_input/Nmeningitidis/neisseria_mlst_scheme.tsv
+sample_3	test_input/Nmeningitidis/meningotype/meningotype3.tsv	-	test_input/Nmeningitidis/neisseria_mlst_scheme.tsv
+sample_4	test_input/Nmeningitidis/meningotype/meningotype4.tsv	fdafd	test_input/Nmeningitidis/neisseria_mlst_scheme.tsv
+sample_5	test_input/empty_file.txt	fdafd	test_input/Nmeningitidis/neisseria_mlst_scheme.tsv

ssi_analysis_result_parsers-0.0.11/test_input/Nmeningitidis/meningotype/meningotype1.tsv

@@ -0,0 +1,2 @@
+SAMPLE_ID	SEROGROUP	ctrA	MLST	PorA	FetA	PorB	fHbp	NHBA	NadA	BAST
+/users/data/Projects/SB_surveillance/proj/Results/MGK/2025/250410_VL00760_37_N_WGS_915_AAGLJKNM5/MGK-2025-0011/meningotype/contigs.fasta	Y	ctrA	1466	21,16	F3-7	NEIS2020_44	21	6	new	-

ssi_analysis_result_parsers-0.0.11/test_input/Nmeningitidis/meningotype/meningotype2.tsv

@@ -0,0 +1,2 @@
+SAMPLE_ID	SEROGROUP	ctrA	MLST	PorA	FetA	PorB	fHbp	NHBA	NadA	BAST
+MGK-2023-014_S39.fasta	X	ctrA	1157	5,2-67	F5-36	NEIS2020_43	13	114	new	-

ssi_analysis_result_parsers-0.0.11/test_input/Nmeningitidis/meningotype/meningotype3.tsv

@@ -0,0 +1,2 @@
+SAMPLE_ID	SEROGROUP	ctrA	MLST	PorA	FetA	PorB	fHbp	NHBA	NadA	BAST
+MGK-2023-015_S51.fasta	B	ctrA	-	18-1,30-4	F3-3	NEIS2020_27	0	29	1	-