diff --git a/depthcharge/data/parsers.py b/depthcharge/data/parsers.py index 79ba27a..a72ae37 100644 --- a/depthcharge/data/parsers.py +++ b/depthcharge/data/parsers.py @@ -520,7 +520,7 @@ def parse_spectrum(self, spectrum: dict) -> MassSpectrum: if self.valid_charge is None or precursor_charge in self.valid_charge: return MassSpectrum( filename=str(self.peak_file), - scan_id=self._counter, + scan_id=f"index={self._counter}", mz=spectrum["m/z array"], intensity=spectrum["intensity array"], ms_level=self._assumed_ms_level, diff --git a/tests/unit_tests/test_data/test_datasets.py b/tests/unit_tests/test_data/test_datasets.py index f9b7237..bfbc338 100644 --- a/tests/unit_tests/test_data/test_datasets.py +++ b/tests/unit_tests/test_data/test_datasets.py @@ -48,7 +48,7 @@ def test_indexing(tokenizer, mgf_small, tmp_path): spec = dataset[0] assert len(spec) == 7 assert spec["peak_file"] == ["small.mgf"] - assert spec["scan_id"] == ["0"] + assert spec["scan_id"] == ["index=0"] assert spec["ms_level"].item() == 2 assert (spec["precursor_mz"].item() - 416.2448) < 0.001 @@ -124,7 +124,7 @@ def test_load(tokenizer, tmp_path, mgf_small): spec = dataset[0] assert len(spec) == 8 assert spec["peak_file"] == ["small.mgf"] - assert spec["scan_id"] == ["0"] + assert spec["scan_id"] == ["index=0"] assert spec["ms_level"] == 2 assert (spec["precursor_mz"] - 416.2448) < 0.001 diff --git a/tests/unit_tests/test_data/test_parsers.py b/tests/unit_tests/test_data/test_parsers.py index b730a77..d7caf26 100644 --- a/tests/unit_tests/test_data/test_parsers.py +++ b/tests/unit_tests/test_data/test_parsers.py @@ -72,7 +72,7 @@ def test_mgf_and_base(mgf_small): expected = pl.DataFrame( { "peak_file": [mgf_small.name] * 2, - "scan_id": ["0", "1"], + "scan_id": ["index=0", "index=1"], "ms_level": [2, 2], "precursor_mz": [416.24474357, 257.464565], "precursor_charge": [2, 3],