feat: Thermo Fisher Scientific NanoDrop Eight - add unread data to asm (#1096)

<img width="1821" height="171" alt="image"
src="https://github.com/user-attachments/assets/0f97fec0-7bbf-4f04-97b0-1dc923315548"
/>

Author: joshua-benchling

src/allotropy/allotrope/converter.py

@@ -113,6 +113,7 @@
     "@": "_AT_",
     "'": "_QUOTE_",
     ",": "_COMMA_",
+    "&": "_AMPERSAND_",
     # NOTE: this MUST be at the end, or it will break other key replacements.
     " ": "_",
 }

src/allotropy/parsers/thermo_fisher_nanodrop_eight/constants.py

@@ -8,4 +8,14 @@
     (260, 230),
 ]
 
-CONCENTRATION_UNITS = ["ng/μL", "μg/mL", "μg/µL", "mg/mL", "μg,mL"]
+CONCENTRATION_UNITS = [
+    "ng/μL",
+    "ng/µL",
+    "ng/μl",
+    "ng/µl",
+    "ng/âμl",
+    "μg/mL",
+    "μg/µL",
+    "mg/mL",
+    "μg,mL",
+]

src/allotropy/parsers/thermo_fisher_nanodrop_eight/nanodrop_eight_parser.py

@@ -17,7 +17,7 @@
     create_metadata,
     SpectroscopyRow,
 )
-from allotropy.parsers.utils.pandas import map_rows
+from allotropy.parsers.utils.pandas import map_rows, SeriesData
 from allotropy.parsers.vendor_parser import VendorParser
 
 
@@ -40,7 +40,10 @@ def create_data(self, named_file_contents: NamedFileContents) -> Data:
         return Data(
             metadata=metadata,
             measurement_groups=[
-                create_measurement_group(row, reader.header) for row in rows
+                create_measurement_group(
+                    row, reader.header, SeriesData(reader.data.iloc[0])
+                )
+                for row in rows
             ],
             # NOTE: in current implementation, calculated data is reported at global level for some reason.
             # TODO(nstender): should we move this inside of measurements?

src/allotropy/parsers/thermo_fisher_nanodrop_eight/nanodrop_eight_structure.py

@@ -49,12 +49,16 @@ def create(data: SeriesData, header: SeriesData) -> SpectroscopyRow:
         )
         mass_concentration = get_first_not_none(
             lambda key: data.get(float, key),
-            ["conc.", "conc", "concentration"],
+            ["conc.", "conc", "concentration", "ng/âμl", "ng/μl", "ng/µL", "ng/µl"],
         )
         unit = get_first_not_none(
             lambda key: key if data.get(float, key.lower()) else None,
             constants.CONCENTRATION_UNITS,
         )
+        # Normalize the unit to a standard format that ASM recognizes
+        if unit and "ng/" in unit:
+            # Normalize all variants to ng/µL (micro sign + uppercase L)
+            unit = "ng/µL"
 
         spectra_data_cube = None
         float_cols = [col for col in data.series.index if try_float_or_none(col)]
@@ -78,6 +82,26 @@ def create(data: SeriesData, header: SeriesData) -> SpectroscopyRow:
             str, ["sample id", "uid"], NOT_APPLICABLE, SeriesData.NOT_NAN
         )
         location_id = data.get(str, "location")
+
+        # Fields to skip from data as they're already captured elsewhere
+        data_skip_fields = {
+            "date",
+            "date & time",
+            "a260/a230",
+            "a260/a280",
+            "sample",
+            "username",
+            "weirdextra:",
+            "andmore",
+        }
+
+        # Fields to skip from header as they're already captured elsewhere
+        header_skip_fields = {
+            "serial number",
+            "application",
+            "user name",
+        }
+
         measurements: list[Measurement] = []
         for wavelength, absorbance in absorbances.items():
             if not absorbance:
@@ -103,6 +127,15 @@ def create(data: SeriesData, header: SeriesData) -> SpectroscopyRow:
                     and mass_concentration
                     and unit
                     else None,
+                    sample_custom_info={
+                        "Sample Name": data.get(
+                            str, "sample name", validate=SeriesData.NOT_NAN
+                        )
+                    },
+                    custom_info={
+                        **data.get_unread(skip=data_skip_fields),
+                        **header.get_unread(skip=header_skip_fields),
+                    },
                 )
             )
         if spectra_data_cube:
@@ -113,6 +146,10 @@ def create(data: SeriesData, header: SeriesData) -> SpectroscopyRow:
                     data_cube=spectra_data_cube,
                     sample_identifier=sample_id,
                     location_identifier=location_id,
+                    custom_info={
+                        **data.get_unread(skip=data_skip_fields),
+                        **header.get_unread(skip=header_skip_fields),
+                    },
                 )
             )
 
@@ -138,11 +175,13 @@ def create_metadata(data: SeriesData, file_path: str) -> Metadata:
 
 
 def create_measurement_group(
-    row: SpectroscopyRow, header: SeriesData
+    row: SpectroscopyRow, header: SeriesData, data: SeriesData
 ) -> MeasurementGroup:
+    analyst = header.get(str, "user name") or data.get(str, "username")
+    data.get_unread()
     return MeasurementGroup(
         measurement_time=row.timestamp,
-        analyst=header.get(str, "user name"),
+        analyst=analyst,
         experiment_type=row.experiment_type,
         measurements=row.measurements,
     )

tests/parsers/thermo_fisher_nanodrop_eight/testdata/thermo_nanodrop_eight_RNA.json

@@ -25,6 +25,16 @@
                             "absorbance": {
                                 "value": 17.62,
                                 "unit": "mAU"
+                            },
+                            "processed data aggregate document": {
+                                "processed data document": [
+                                    {
+                                        "mass concentration": {
+                                            "value": 704.986,
+                                            "unit": "ng/µL"
+                                        }
+                                    }
+                                ]
                             }
                         },
                         {
@@ -50,7 +60,8 @@
                         }
                     ],
                     "experiment type": "RNA"
-                }
+                },
+                "analyst": "GN104564"
             },
             {
                 "measurement aggregate document": {
@@ -75,6 +86,16 @@
                             "absorbance": {
                                 "value": 17.16,
                                 "unit": "mAU"
+                            },
+                            "processed data aggregate document": {
+                                "processed data document": [
+                                    {
+                                        "mass concentration": {
+                                            "value": 686.535,
+                                            "unit": "ng/µL"
+                                        }
+                                    }
+                                ]
                             }
                         },
                         {
@@ -100,7 +121,8 @@
                         }
                     ],
                     "experiment type": "RNA"
-                }
+                },
+                "analyst": "GN104564"
             },
             {
                 "measurement aggregate document": {
@@ -125,6 +147,16 @@
                             "absorbance": {
                                 "value": 17.75,
                                 "unit": "mAU"
+                            },
+                            "processed data aggregate document": {
+                                "processed data document": [
+                                    {
+                                        "mass concentration": {
+                                            "value": 710.13,
+                                            "unit": "ng/µL"
+                                        }
+                                    }
+                                ]
                             }
                         },
                         {
@@ -150,7 +182,8 @@
                         }
                     ],
                     "experiment type": "RNA"
-                }
+                },
+                "analyst": "GN104564"
             }
         ],
         "device system document": {
@@ -162,7 +195,7 @@
             "file name": "thermo_nanodrop_eight_RNA.txt",
             "UNC path": "tests/parsers/thermo_fisher_nanodrop_eight/testdata/thermo_nanodrop_eight_RNA.txt",
             "ASM converter name": "allotropy_thermo_fisher_scientific_nanodrop_eight",
-            "ASM converter version": "0.1.62"
+            "ASM converter version": "0.1.106"
         },
         "calculated data aggregate document": {
             "calculated data document": [