ssi-analysis-result-parsers 0.0.4__py3-none-any.whl → 0.0.6__py3-none-any.whl

ssi_analysis_result_parsers/Legionella_parser.py

@@ -1,8 +1,7 @@
 # AUTOGENERATED! DO NOT EDIT! File to edit: ../nbs/39_Legionella_parser.ipynb.
 
 # %% auto 0
-__all__ = ['extract_legionella_sbt', 'legionella_summary', 'legionella_batch_from_sheet', 'LegionellaResults',
-           'legionella_batch_from_dict', 'legionella_parser', 'legionella_batch_parser']
+__all__ = ['extract_legionella_sbt', 'LegionellaResults', 'legionella_parser', 'legionella_batch_parser']
 
 # %% ../nbs/39_Legionella_parser.ipynb 3
 # standard libs
@@ -25,8 +24,10 @@ 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 .blast_parser import extract_presence_absence
+
+# from ssi_analysis_result_parsers.blast_parser import extract_presence_absence
 
 # Project specific libraries
 from pathlib import Path
@@ -36,14 +37,22 @@ import sys
 # %% ../nbs/39_Legionella_parser.ipynb 6
 def extract_legionella_sbt(legionella_sbt_results_tsv: Path) -> dict:
     """
-    Returns dictionary of results found in the Legionella SBT summary output
+    Extract results from Legionella SBT results file
+    Returns a dictionary with ST, allele variant for each gene, and notes from output
     """
     if os.path.exists(legionella_sbt_results_tsv):
-        df = pandas.read_csv(legionella_sbt_results_tsv, sep="\t")
-        df.set_index("sample", inplace=True, drop=True)
-        d = df.to_dict(orient="index")
-        fname = next(iter(d))
-        return d[fname]
+        try:
+            df = pandas.read_csv(legionella_sbt_results_tsv, sep="\t")
+            df.set_index("sample", inplace=True, drop=True)
+            d = df.to_dict(orient="index")
+            fname = next(iter(d))
+            return d[fname]
+        except pandas.errors.EmptyDataError:
+            print(
+                f"No Legionella SBT output empty at {legionella_sbt_results_tsv}",
+                file=sys.stderr,
+            )
+            return None
     else:
         print(
             f"No Legionella SBT output found at {legionella_sbt_results_tsv}",
@@ -52,46 +61,16 @@ def extract_legionella_sbt(legionella_sbt_results_tsv: Path) -> dict:
         return None
 
 
-def legionella_summary(legionella_sbt_results_tsv: Path, lag1_blast_tsv: Path) -> dict:
-    sbt_results_dict = extract_legionella_sbt(
-        legionella_sbt_results_tsv=legionella_sbt_results_tsv
-    )
-    lag1_blast_dict = extract_presence_absence(
-        blast_output_tsv=lag1_blast_tsv,
-        hits_as_string=False,
-        include_match_stats=False,
-        gene_names=["lag-1"],
-    )
-    results_dict = core.update_results_dict(
-        sbt_results_dict, lag1_blast_dict, old_duplicate_key_prefix="SBT: "
-    )
-    if results_dict is None:
-        return {}
-    return results_dict
-
-
-def legionella_batch_from_sheet(file_paths: dict, output_file: Path = None):
-    results_dict = {}
-    for sample_name, path_dict in file_paths.items():
-        legionella_results = legionella_summary(
-            legionella_sbt_results_tsv=Path(path_dict["sbt_results"]),
-            lag1_blast_tsv=Path(path_dict["lag1_blast_results"]),
-        )
-        results_dict[sample_name] = legionella_results
-    if output_file is not None:
-        df = pandas.DataFrame.from_dict(results_dict, orient="index").reset_index(
-            names="sample_name"
-        )
-        df.to_csv(output_file, sep="\t", index=False)
-    return results_dict
-
-
 class LegionellaResults(core.PipelineResults):
 
     @classmethod
     def from_tool_paths(
         cls, legionella_sbt_results_tsv: Path, lag1_blast_tsv: Path, sample_name=None
     ):
+        """
+        Alternative constructor for initializing results for single sample,
+        Initializes LegionellaResults instance provided paths to outputs from tools (legionella sbt and lag1 presence blast)
+        """
         legionella_results = cls.legionella_summary(
             legionella_sbt_results_tsv=legionella_sbt_results_tsv,
             lag1_blast_tsv=lag1_blast_tsv,
@@ -100,6 +79,10 @@ class LegionellaResults(core.PipelineResults):
 
     @classmethod
     def from_tool_paths_dict(cls, file_paths: dict):
+        """
+        Alternative constructor for initializing results for multiple samples,
+        Initializes LegionellaResults 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():
             legionella_results = cls.legionella_summary(
@@ -111,6 +94,10 @@ class LegionellaResults(core.PipelineResults):
 
     @classmethod
     def from_tool_paths_dataframe(cls, file_paths_df: pandas.DataFrame):
+        """
+        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 = file_paths_df.to_dict(orient="index")
         results_dict = {}
         for sample_name, path_dict in file_paths.items():
@@ -124,24 +111,22 @@ class LegionellaResults(core.PipelineResults):
 
     @classmethod
     def from_tool_paths_tsv(cls, tool_paths_tsv: Path):
+        """
+        Alternative constructor for initializing results for multiple samples,
+        Initializes LegionellaResults 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 =
-        # results_dict = file_paths_df.to_dict(orient="index")
         return cls.from_tool_paths_dataframe(file_paths_df)
-        """for sample_name, path_dict in file_paths.items():
-            legionella_results = cls.legionella_summary(legionella_sbt_results_tsv=Path(path_dict["sbt_results"]),
-                                                    lag1_blast_tsv=Path(path_dict["lag1_blast_results"]))
-            results_dict[sample_name] = legionella_results
-        return cls(results_dict)"""
 
+    @staticmethod
     def legionella_summary(
         legionella_sbt_results_tsv: Path, lag1_blast_tsv: Path
     ) -> dict:
         sbt_results_dict = extract_legionella_sbt(
             legionella_sbt_results_tsv=legionella_sbt_results_tsv
         )
-        lag1_blast_dict = extract_presence_absence(
+        lag1_blast_dict = blast_parser.extract_presence_absence(
             blast_output_tsv=lag1_blast_tsv,
             hits_as_string=False,
             include_match_stats=False,
@@ -150,43 +135,13 @@ class LegionellaResults(core.PipelineResults):
         results_dict = core.update_results_dict(
             sbt_results_dict, lag1_blast_dict, old_duplicate_key_prefix="SBT: "
         )
+        if results_dict is None:
+            return {}
         return results_dict
 
     def __repr__(self):
         return f"< Legionella analysis results object. {len(self.results_df)} samples with {len(self.results_df.columns)} result variables > "
 
-
-def legionella_batch_from_dict(file_paths: dict, output_file: Path = None):
-    results_dict = {}
-    for sample_name, path_dict in file_paths.items():
-        legionella_results = legionella_summary(
-            legionella_sbt_results_tsv=Path(path_dict["sbt_results"]),
-            lag1_blast_tsv=Path(path_dict["lag1_blast_results"]),
-        )
-        results_dict[sample_name] = legionella_results
-    if output_file is not None:
-        df = pandas.DataFrame.from_dict(results_dict, orient="index").reset_index(
-            names="sample_name"
-        )
-        df.to_csv(output_file, sep="\t", index=False)
-    return results_dict
-
-
-def legionella_batch_from_sheet(file_paths: dict, output_file: Path = None):
-    results_dict = {}
-    for sample_name, path_dict in file_paths.items():
-        legionella_results = legionella_summary(
-            legionella_sbt_results_tsv=Path(path_dict["sbt_results"]),
-            lag1_blast_tsv=Path(path_dict["lag1_blast_results"]),
-        )
-        results_dict[sample_name] = legionella_results
-    if output_file is not None:
-        df = pandas.DataFrame.from_dict(results_dict, orient="index").reset_index(
-            names="sample_name"
-        )
-        df.to_csv(output_file, sep="\t", index=False)
-    return results_dict
-
 # %% ../nbs/39_Legionella_parser.ipynb 9
 @call_parse
 def legionella_parser(

ssi_analysis_result_parsers/__init__.py

@@ -1 +1 @@
-__version__ = "0.0.3"
+__version__ = "0.0.5"

ssi_analysis_result_parsers/_modidx.py

@@ -21,16 +21,10 @@ d = { 'settings': { 'branch': 'main',
                                                                                                                                                        'ssi_analysis_result_parsers/Legionella_parser.py'),
                                                                'ssi_analysis_result_parsers.Legionella_parser.extract_legionella_sbt': ( 'legionella_parser.html#extract_legionella_sbt',
                                                                                                                                          'ssi_analysis_result_parsers/Legionella_parser.py'),
-                                                               'ssi_analysis_result_parsers.Legionella_parser.legionella_batch_from_dict': ( 'legionella_parser.html#legionella_batch_from_dict',
-                                                                                                                                             'ssi_analysis_result_parsers/Legionella_parser.py'),
-                                                               'ssi_analysis_result_parsers.Legionella_parser.legionella_batch_from_sheet': ( 'legionella_parser.html#legionella_batch_from_sheet',
-                                                                                                                                              'ssi_analysis_result_parsers/Legionella_parser.py'),
                                                                'ssi_analysis_result_parsers.Legionella_parser.legionella_batch_parser': ( 'legionella_parser.html#legionella_batch_parser',
                                                                                                                                           '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.Legionella_parser.legionella_summary': ( 'legionella_parser.html#legionella_summary',
-                                                                                                                                     'ssi_analysis_result_parsers/Legionella_parser.py')},
+                                                                                                                                    'ssi_analysis_result_parsers/Legionella_parser.py')},
             'ssi_analysis_result_parsers.blast_parser': { 'ssi_analysis_result_parsers.blast_parser.allele_matches': ( 'blast_parser.html#allele_matches',
                                                                                                                        'ssi_analysis_result_parsers/blast_parser.py'),
                                                           'ssi_analysis_result_parsers.blast_parser.extract_allele_matches': ( 'blast_parser.html#extract_allele_matches',

ssi_analysis_result_parsers/blast_parser.py

@@ -51,21 +51,31 @@ def extract_presence_absence(
     if os.path.exists(blast_output_tsv):
         try:
             blast_df = pandas.read_csv(blast_output_tsv, sep="\t", header=None)
+            header_list = tsv_header.split(" ")
+            if len(header_list) == len(blast_df.columns):
+                blast_df.columns = tsv_header.split(" ")
+                blast_df["plen"] = blast_df["length"] / blast_df["qlen"] * 100
+                blast_df_unique = (
+                    blast_df.sort_values(by=["bitscore"], ascending=False)
+                    .groupby("qseqid")
+                    .first()
+                )
+                blast_df_filtered = blast_df_unique.query(
+                    "plen > @plen_threshold and pident > @pident_threshold"
+                )
+                blast_dict = dict(blast_df_filtered.to_dict(orient="index"))
+            else:
+                print(
+                    f"Failed to parse {blast_output_tsv}. Number of columns do not match length of provided header string",
+                    file=sys.stderr,
+                )
+                return None
 
-            blast_df.columns = tsv_header.split(" ")
-            blast_df["plen"] = blast_df["length"] / blast_df["qlen"] * 100
-            blast_df_unique = (
-                blast_df.sort_values(by=["bitscore"], ascending=False)
-                .groupby("qseqid")
-                .first()
-            )
-            blast_df_filtered = blast_df_unique.query(
-                "plen > @plen_threshold and pident > @pident_threshold"
-            )
-            blast_dict = dict(blast_df_filtered.to_dict(orient="index"))
         except pandas.errors.EmptyDataError:
             blast_dict = {}
             print(f"Blast output file {blast_output_tsv} empty. Assuming 0 blast hits.")
+        except Exception as e:
+            print(f"Error parsing blast: e")
         if hits_as_string:
 
             results = []

ssi_analysis_result_parsers/core.py

@@ -196,7 +196,6 @@ def get_samplesheet(sample_sheet_config: dict) -> pd.DataFrame:
 class PipelineResults:
 
     def __init__(self, results_dict):
-        print(results_dict)
         self.results_dict = results_dict
         self.results_df = pandas.DataFrame.from_dict(results_dict, orient="index")
 
@@ -207,12 +206,17 @@ class PipelineResults:
 
     @classmethod
     def from_results_dataframe(cls, results_df: pandas.DataFrame):
-        # results_df = results_df.set_index("sample_name")
+        """
+        Alternative constructor for initializing from DataFrame instead of dictionary
+        """
         results_dict = results_df.to_dict(orient="index")
         return cls(results_dict)
 
     @classmethod
     def from_results_tsv(cls, results_tsv: Path):
+        """
+        Alternative constructor for initializing from a tsv-file instead of dictionary
+        """
         results_df = pandas.read_csv(results_tsv, sep="\t")
         results_df.set_index("sample_name", inplace=True, drop=True)
         results_dict = results_df.to_dict(orient="index")

{ssi_analysis_result_parsers-0.0.4.dist-info → ssi_analysis_result_parsers-0.0.6.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ssi_analysis_result_parsers
-Version: 0.0.4
+Version: 0.0.6
 Summary: TODO
 Home-page: https://github.com/thej-ssi/ssi_analysis_result_parsers
 Author: Thor Bech Johannesen

{ssi_analysis_result_parsers-0.0.4.dist-info → ssi_analysis_result_parsers-0.0.6.dist-info}/RECORD

@@ -1,15 +1,16 @@
-ssi_analysis_result_parsers/Legionella_parser.py,sha256=CP5r1RriVd4zxeTBokLJYcu5iS6xbK3pBzI6xwITSm0,8894
-ssi_analysis_result_parsers/__init__.py,sha256=4GZKi13lDTD25YBkGakhZyEQZWTER_OWQMNPoH_UM2c,22
-ssi_analysis_result_parsers/_modidx.py,sha256=JY_GM0tMojzTtX9O4D8as4k5a-sXqkxkb7ZUEPzhuMk,12232
-ssi_analysis_result_parsers/blast_parser.py,sha256=L7EdW2LUwSS2OQO7WZUAxP6whJXdvTILE2a3O59uv-s,7441
-ssi_analysis_result_parsers/core.py,sha256=6TGURv8spPdBpwKv6LvqvbVzJChdeHwsG3WQ6QLUuvE,12124
+ssi_analysis_result_parsers/Legionella_parser.py,sha256=an9Rm9r4N3wQXy0qhUpvacy4Wb6HxUXFdDA7D6YsQyY,7237
+ssi_analysis_result_parsers/__init__.py,sha256=S7u1lbuWmM3A3ajykBialmPoJUK6Jg-WmNqM-9OZFdk,22
+ssi_analysis_result_parsers/_modidx.py,sha256=ysvICOsqtGaXuCYPu-UuRGVRhZDJ-O9X3o9lE7rzzGI,11089
+ssi_analysis_result_parsers/blast_parser.py,sha256=EBqWlx8bDlaSzqAZomiUGnT2DGaaA-L7ukny7SEJbpk,7915
+ssi_analysis_result_parsers/core.py,sha256=8CzFMDrGJ24D9aoIebLsG8tx-OxvYJod1cxBITqNfaY,12258
 ssi_analysis_result_parsers/hello_world.py,sha256=jpN94sqYuNHqUbUZMCJ35qGY5iLPB_emucgnDGDUk_U,1895
 ssi_analysis_result_parsers/some_string.py,sha256=JwmAXKbX_JgY8UGh4FAu5-7ZjezcAEhq4Q2B73pWp2M,923
 ssi_analysis_result_parsers/config/config.default.env,sha256=Zt6bfPbVV3rYCksoebX1ruAdFgeD9wqAnKDtswhtJJM,1390
 ssi_analysis_result_parsers/config/config.default.yaml,sha256=3qgUrUtQpxrzYv7WQaHsvz9dQB0RALKNU0idxv7oRqM,460
-ssi_analysis_result_parsers-0.0.4.dist-info/licenses/LICENSE,sha256=p6aTb6QIfqyZ2Uux2VjV4F2zthdUSHZOjB4mfwGc7fo,1094
+ssi_analysis_result_parsers-0.0.6.dist-info/licenses/LICENSE,sha256=p6aTb6QIfqyZ2Uux2VjV4F2zthdUSHZOjB4mfwGc7fo,1094
 test_input/.DS_Store,sha256=sdTEvl9DTKPHNPYYjMqDepX7q7ZETlonk21tGEuWLao,6148
-test_input/Legionella/batch_parser_file_paths.tsv,sha256=zls11lmEA5U89d8RsX6PR8M1zXNVimeL4raqdZ3ijvQ,210
+test_input/empty_file.txt,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+test_input/Legionella/batch_parser_file_paths.tsv,sha256=AikBS_Ez1xO3UrEQ19AY3z6drBDdMAiSGK66NLeyYj4,356
 test_input/Legionella/lag-1_blast.tsv,sha256=MN5QL_iBn9gQ8VTYEcTnT0JwKgpkD8G15-QFOrSWxkU,1133
 test_input/Legionella/lag-1_blast_2.tsv,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 test_input/Legionella/test.sbt.tsv,sha256=ibhaH3is2dxHaABPvR2QM2HAq9bKOs1AwOTmrwSrcd8,168
@@ -20,8 +21,8 @@ test_input/blast_parser/gene_presence_absence_test.tsv,sha256=qCvMkBC-1GuXx83RDh
 test_output/output_with_sample_name.tsv,sha256=NQG7WaxczuWCCsX2a9MUxCCYpbuAirz9gw08OLdEdUo,41
 test_output/test.tsv,sha256=6DGzarXMkUP03Z58vZimc-gu1K2k84zxZLWWF2HROCg,277
 test_output/test_batch_output.tsv,sha256=6DGzarXMkUP03Z58vZimc-gu1K2k84zxZLWWF2HROCg,277
-ssi_analysis_result_parsers-0.0.4.dist-info/METADATA,sha256=r6IJQQ7JgRD_--UlM80lNMH5ZzlxYQCmvaVBIyPhF7k,2765
-ssi_analysis_result_parsers-0.0.4.dist-info/WHEEL,sha256=CmyFI0kx5cdEMTLiONQRbGQwjIoR1aIYB7eCAQ4KPJ0,91
-ssi_analysis_result_parsers-0.0.4.dist-info/entry_points.txt,sha256=eG2NzlNDoG__0PPHl3eoKK5EXIz02BGhRX-L2aWgKCY,447
-ssi_analysis_result_parsers-0.0.4.dist-info/top_level.txt,sha256=3q56bBc2Wv2a6ZQ1l_9m66vot2-Qu6tM9tDr3QQ8auM,81
-ssi_analysis_result_parsers-0.0.4.dist-info/RECORD,,
+ssi_analysis_result_parsers-0.0.6.dist-info/METADATA,sha256=WUMU9Lfanw3DLtDNZUzKIZaBU071v00068cENqOkpq8,2765
+ssi_analysis_result_parsers-0.0.6.dist-info/WHEEL,sha256=CmyFI0kx5cdEMTLiONQRbGQwjIoR1aIYB7eCAQ4KPJ0,91
+ssi_analysis_result_parsers-0.0.6.dist-info/entry_points.txt,sha256=eG2NzlNDoG__0PPHl3eoKK5EXIz02BGhRX-L2aWgKCY,447
+ssi_analysis_result_parsers-0.0.6.dist-info/top_level.txt,sha256=3q56bBc2Wv2a6ZQ1l_9m66vot2-Qu6tM9tDr3QQ8auM,81
+ssi_analysis_result_parsers-0.0.6.dist-info/RECORD,,

test_input/Legionella/batch_parser_file_paths.tsv

@@ -1,3 +1,5 @@
 sample_name	sbt_results	lag1_blast_results
 sample_1	test_input/Legionella/test.sbt.tsv	test_input/Legionella/lag-1_blast.tsv
 sample_2	test_input/Legionella/test2.sbt.tsv	test_input/Legionella/lag-1_blast_2.tsv
+sample_3	test_input/Legionella/test2.sbt.tsv	test_input/empty_file.txt
+sample_4	test_input/empty_file.txt	test_input/Legionella/lag-1_blast_2.tsv