+ Standardize to use dataclass instead of NamedTuple.

src/DAJIN2/core/consensus/consensus.py

@@ -1,7 +1,7 @@
 from __future__ import annotations
 
 from pathlib import Path
-from typing import NamedTuple
+from dataclasses import dataclass
 from itertools import groupby
 from collections import defaultdict
 
@@ -90,7 +90,8 @@ def call_percentage(cssplits: list[list[str]], mutation_loci: list[set[str]]) ->
 ###########################################################
 
 
-class ConsensusKey(NamedTuple):
+@dataclass(frozen=True)
+class ConsensusKey:
     allele: str
     label: int
     percent: float

src/DAJIN2/core/consensus/name_handler.py

@@ -1,13 +1,7 @@
 from __future__ import annotations
 
 import re
-from typing import NamedTuple
-
-
-class ConsensusKey(NamedTuple):
-    allele: str
-    label: int
-    percent: float
+from DAJIN2.core.consensus.consensus import ConsensusKey
 
 
 def _detect_sv(cons_percentages: dict[ConsensusKey, list], threshold: int = 50) -> list[bool]:

src/DAJIN2/core/core.py

@@ -4,27 +4,14 @@
 import logging
 
 from pathlib import Path
-from typing import NamedTuple
 
 from DAJIN2.utils import io, fastx_handler
 from DAJIN2.core import classification, clustering, consensus, preprocess, report
+from DAJIN2.core.preprocess.input_formatter import FormattedInputs
 
 logger = logging.getLogger(__name__)
 
 
-class FormattedInputs(NamedTuple):
-    path_sample: str
-    path_control: str
-    path_allele: str
-    sample_name: str
-    control_name: str
-    fasta_alleles: dict[str, str]
-    tempdir: Path
-    genome_coordinates: dict[str, str]
-    threads: int
-    uuid: str
-
-
 ###########################################################
 # main
 ###########################################################

src/DAJIN2/core/preprocess/input_formatter.py

@@ -3,7 +3,7 @@
 import uuid
 
 from pathlib import Path
-from typing import NamedTuple
+from dataclasses import dataclass
 from collections import defaultdict
 
 from DAJIN2.utils import io, config, fastx_handler
@@ -64,18 +64,15 @@ def get_genome_coordinates(genome_urls: dict, fasta_alleles: dict, is_cache_geno
         if is_cache_genome:
             genome_coordinates = next(io.read_jsonl(Path(tempdir, "cache", "genome_coordinates.jsonl")))
         else:
-            genome_coordinates = preprocess.fetch_coordinates(
-                genome_coordinates, genome_urls, fasta_alleles["control"]
-            )
-            genome_coordinates["chrom_size"] = preprocess.fetch_chromosome_size(
-                genome_coordinates, genome_urls
-            )
+            genome_coordinates = preprocess.fetch_coordinates(genome_coordinates, genome_urls, fasta_alleles["control"])
+            genome_coordinates["chrom_size"] = preprocess.fetch_chromosome_size(genome_coordinates, genome_urls)
             io.write_jsonl([genome_coordinates], Path(tempdir, "cache", "genome_coordinates.jsonl"))
 
     return genome_coordinates
 
 
-class FormattedInputs(NamedTuple):
+@dataclass(frozen=True)
+class FormattedInputs:
     path_sample: str
     path_control: str
     path_allele: str