Added setuptools-scm

.gitignore

@@ -356,4 +356,4 @@ package
 
 # Custom rules (everything added below won't be overriden by 'Generate .gitignore File' if you use 'Update' option)
 
-src/output.csv
+output

.vscode/launch.json

@@ -6,7 +6,7 @@
     "configurations": [
         
         {
-            "name": "Python Debugger: Current File with Arguments",
+            "name": "CLI ipdbmlst",
             "type": "debugpy",
             "request": "launch",
             "program": "${workspaceFolder}/src/nsbdiagnosistoolkit/cli/root.py",

Jenkinsfile

@@ -37,7 +37,7 @@ pipeline {
         }
         stage("publish") {
             environment {
-                CREDS = credentials('git.reslate.systems/ydeng')
+                CREDS = credentials('4d6f64be-d26d-4f95-8de3-b6a9b0beb311')
             }
             when {
                 branch '**/main'

README.md

@@ -0,0 +1,13 @@
+# NSBDiagnosis Toolkit
+
+A software suite automating the diagnostic steps from Sanger Trace Files (ABIFs) and FASTAs. Namely, this tool is (or will be) capable of:
+
+- [ ] Improved consensus conflict resolution via a peak strength metric
+- [ ] Automatic reporting on variations from a reference file
+- [x] Automatic annotating based off pre-existing GenBank data from NCBI
+- [x] Automatic pulling GenBank Data
+- [x] Automatic querying of Institut Pasteur's MLST databases
+- [x] Automatic export of spreadsheet file in the form of a CSV
+- [x] User friendly, and automatable (Galaxy compatible) command-line interface
+- [ ] Interactive Web UI
+

output/MLST_20250103204147.csv

@@ -1,2 +0,0 @@
-st,clonal-complex,fumC,pepA,icd,adk,pgm,tyrB,glyA
-1,ST-2 complex,['1'],['1'],['1'],['1'],['1'],['1'],['1']

pyproject.toml

@@ -1,5 +1,5 @@
 [build-system]
-requires = ["setuptools >= 61.0"]
+requires = ["setuptools>=64", "setuptools-scm>=8"]
 build-backend = "setuptools.build_meta"
 
 [project]

requirements.txt

@@ -2,4 +2,5 @@ aiohttp[speedups]
 biopython
 pytest
 pytest-asyncio
-build
+build
+twine

src/nsbdiagnosistoolkit/cli/aggregator.py

@@ -7,17 +7,15 @@ from nsbdiagnosistoolkit.engine.local.fasta import read_fasta
 from nsbdiagnosistoolkit.engine.remote.databases.institutpasteur.profiling import InstitutPasteurProfiler
 
 
-async def aggregate_sequences(fastas: Iterable[str], abifs: Iterable[str]) -> AsyncGenerator[str, Any]:
+async def read_all_fastas(fastas: Iterable[str]) -> AsyncGenerator[NamedString, Any]:
     for fasta_path in fastas:
         async for fasta in read_fasta(fasta_path):
-            yield fasta.sequence
+            yield fasta
-    for abif_path in abifs:
-        abif_data = await read_abif(abif_path)
-        yield "".join(abif_data.sequence)
 
-async def profile_all_genetic_strings(strings: AsyncIterable[str], database_name: str) -> Sequence[MLSTProfile]:
+
+async def profile_all_genetic_strings(strings: AsyncIterable[NamedString], database_name: str) -> Sequence[tuple[str, MLSTProfile]]:
     profiles = list()
     async with InstitutPasteurProfiler(database_name=database_name) as profiler:
-        async for string in strings:
+        async for named_string in strings:
-            profiles.append(await profiler.profile_string(string))
+            profiles.append((named_string.name, await profiler.profile_string(named_string.sequence)))
     return profiles

src/nsbdiagnosistoolkit/cli/root.py

@@ -57,14 +57,17 @@ parser.add_argument(
 
 def cli():
     args = parser.parse_args()
-    gen_strings = aggregator.aggregate_sequences(args.fastas, args.abifs)
+    gen_strings = aggregator.read_all_fastas(args.fastas)
-    os.makedirs(args.out)
+    os.makedirs(args.out, exist_ok=True)
     if args.institut_pasteur_db is not None:
         mlst_profiles = aggregator.profile_all_genetic_strings(
             gen_strings, args.institut_pasteur_db)
         asyncio.run(write_mlst_profiles_as_csv(
-            asyncio.run(mlst_profiles), str(path.join(args.out, "MLST_" + args.run_name + ".csv"))))
+            asyncio.run(mlst_profiles),
+            str(path.join(args.out, "MLST_" + args.run_name + ".csv")
+                )
+        ))
 
 
 if __name__ == "__main__":
-    cli()
+    cli()

src/nsbdiagnosistoolkit/engine/local/csv.py

@@ -1,7 +1,7 @@
 import csv
 from io import TextIOWrapper
 from os import PathLike
-from typing import AsyncIterable, Iterable, Mapping, Sequence, Union
+from typing import AsyncIterable, Iterable, Mapping, Sequence, Tuple, Union
 
 from nsbdiagnosistoolkit.engine.data.MLST import Allele, MLSTProfile
 
@@ -15,16 +15,17 @@ def loci_alleles_variants_from_loci(alleles_map: Mapping[str, Sequence[Allele]])
     return result_dict
 
 
-async def write_mlst_profiles_as_csv(mlst_profiles_iterable: Iterable[MLSTProfile], handle: Union[str, bytes, PathLike[str], PathLike[bytes]]):
+async def write_mlst_profiles_as_csv(mlst_profiles_iterable: Iterable[tuple[str, MLSTProfile]], handle: Union[str, bytes, PathLike[str], PathLike[bytes]]):
     mlst_profiles = list(mlst_profiles_iterable)
-    header = ["st", "clonal-complex", *mlst_profiles[0].alleles.keys()]
+    header = ["name", "st", "clonal-complex", *mlst_profiles[0][1].alleles.keys()]
     with open(handle, "w", newline='') as filehandle:
         writer = csv.DictWriter(filehandle, fieldnames=header)
         writer.writeheader()
-        for mlst_profile in mlst_profiles:
+        for name, mlst_profile in mlst_profiles:
             row_dictionary = {
                 "st": mlst_profile.sequence_type,
                 "clonal-complex": mlst_profile.clonal_complex,
+                "name": name,
                 **loci_alleles_variants_from_loci(mlst_profile.alleles)
             }