Merge branch 'main' into felipenarv/mass_spectrometry_mapper

Author: felipenarv

CHANGELOG.md

@@ -5,6 +5,17 @@ All notable changes to this packages will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [0.1.111] - 2025-11-19
+
+### Added
+
+- JSON-to-CSV - improve list parsing to better support datacubes (#1124)
+- Cytiva Biacore T200 control - add unread data (#1120)
+- Qiacuity dPCR - Added unread data (#1103)
+- Migrate biorad_bioplex_manager to use SeriesData.get_unread (#1100)
+- Mass spectrometer ASM schema (#1121)
+- Roche Cedex BioHT - Add support for mM unit (mmol/L) (#1119)
+
 ## [0.1.110] - 2025-11-03
 
 ### Added

pyproject.toml

@@ -151,6 +151,7 @@ download-schema = "scripts/download_schema.py {args:}"
 create-parser = "scripts/create_parser.py {args:}"
 update-instrument-table = "scripts/update_supported_instruments_table.py {args:}"
 update-version = "scripts/update_version.py {args:}"
+json-to-csv = "scripts/json_to_csv_convert.py {args:}"
 
 [tool.hatch.envs.win-scripts]
 platforms = ["windows"]
@@ -161,6 +162,7 @@ download-schema = "python scripts\\download_schema.py {args:}"
 create-parser = "python scripts\\create_parser.py {args:}"
 update-instrument-table = "python scripts\\update_supported_instruments_table.py {args:}"
 update-version = "python scripts\\update_version.py {args:}"
+json-to-csv = "python scripts\\json_to_csv_convert.py {args:}"
 
 [tool.hatch.envs.viz.scripts]
 run = "scripts/visualization.py {args:}"

src/allotropy/__about__.py

@@ -1 +1 @@
-__version__ = "0.1.110"
+__version__ = "0.1.111"

src/allotropy/allotrope/schema_mappers/adm/binding_affinity_analyzer/benchling/_2024/_12/binding_affinity_analyzer.py

@@ -56,6 +56,7 @@ class MeasurementType(Enum):
 class DeviceDocument:
     device_type: str
     device_identifier: str
+    device_custom_info: DictType | None = None
 
 
 @dataclass(frozen=True)
@@ -79,6 +80,7 @@ class Metadata:
     lot_number: str | None = None
     sensor_chip_custom_info: DictType | None = None
     data_system_custom_info: DictType | None = None
+    device_system_custom_info: DictType | None = None
 
 
 @dataclass(frozen=True)
@@ -172,23 +174,29 @@ def map_model(self, data: Data) -> Model:
                     ),
                     data.metadata.data_system_custom_info,
                 ),
-                device_system_document=DeviceSystemDocument(
-                    device_identifier=data.metadata.device_identifier,
-                    model_number=data.metadata.model_number,
-                    brand_name=data.metadata.brand_name,
-                    product_manufacturer=data.metadata.product_manufacturer,
-                    equipment_serial_number=data.metadata.equipment_serial_number,
-                    device_document=(
-                        [
-                            DeviceDocumentItem(
-                                device_type=device_document_item.device_type,
-                                device_identifier=device_document_item.device_identifier,
-                            )
-                            for device_document_item in data.metadata.device_document
-                        ]
-                        if data.metadata.device_document
-                        else None
+                device_system_document=add_custom_information_document(
+                    DeviceSystemDocument(
+                        device_identifier=data.metadata.device_identifier,
+                        model_number=data.metadata.model_number,
+                        brand_name=data.metadata.brand_name,
+                        product_manufacturer=data.metadata.product_manufacturer,
+                        equipment_serial_number=data.metadata.equipment_serial_number,
+                        device_document=(
+                            [
+                                add_custom_information_document(
+                                    DeviceDocumentItem(
+                                        device_type=device_document_item.device_type,
+                                        device_identifier=device_document_item.device_identifier,
+                                    ),
+                                    custom_info_doc=device_document_item.device_custom_info,
+                                )
+                                for device_document_item in data.metadata.device_document
+                            ]
+                            if data.metadata.device_document
+                            else None
+                        ),
                     ),
+                    data.metadata.device_system_custom_info,
                 ),
                 binding_affinity_analyzer_document=[
                     self._get_technique_document(measurement_group, data.metadata)

src/allotropy/allotrope/schema_mappers/adm/pcr/BENCHLING/_2023/_09/dpcr.py

@@ -90,6 +90,7 @@ class Measurement:
     errors: list[Error] | None = None
 
     # custom
+    sample_custom_info: dict[str, Any] | None = None
     custom_info: dict[str, Any] | None = None
 
 
@@ -182,6 +183,15 @@ def _get_technique_document(
     def _get_measurement_document(
         self, measurement: Measurement, metadata: Metadata
     ) -> MeasurementDocumentItem:
+        sample_document = SampleDocument(
+            sample_identifier=measurement.sample_identifier,
+            well_location_identifier=measurement.location_identifier,
+            well_plate_identifier=measurement.plate_identifier,
+            sample_role_type=measurement.sample_role_type,
+        )
+        sample_document = add_custom_information_document(
+            sample_document, measurement.sample_custom_info
+        )
         measurement_doc = MeasurementDocumentItem(
             measurement_identifier=measurement.identifier,
             measurement_time=self.get_date_time(measurement.measurement_time),
@@ -198,12 +208,7 @@ def _get_measurement_document(
             error_aggregate_document=self._get_error_aggregate_document(
                 measurement.errors
             ),
-            sample_document=SampleDocument(
-                sample_identifier=measurement.sample_identifier,
-                well_location_identifier=measurement.location_identifier,
-                well_plate_identifier=measurement.plate_identifier,
-                sample_role_type=measurement.sample_role_type,
-            ),
+            sample_document=sample_document,
             device_control_aggregate_document=DeviceControlAggregateDocument(
                 device_control_document=[
                     DeviceControlDocumentItem(
@@ -244,6 +249,7 @@ def _get_measurement_document(
                 ]
             ),
         )
+
         return add_custom_information_document(measurement_doc, measurement.custom_info)
 
     def _get_calculated_data_aggregate_document(

src/allotropy/json_to_csv/json_to_csv.py

@@ -141,11 +141,22 @@ def _map_dataset(
                 msg = f"Invalid transform type in dataset config: {transform.type_}"
                 raise ValueError(msg)
 
-        df = (
-            df
-            if path_df.empty
-            else (path_df if df.empty else df.merge(path_df, how="cross"))
-        )
+        # Combine the current dataframe with the path dataframe
+        if path_df.empty:
+            # No new data to add
+            pass
+        elif df.empty:
+            # First data, use it as the base
+            df = path_df
+        elif len(df) == len(path_df):
+            # Same length: concatenate side-by-side (zip parallel arrays)
+            # This handles datacube dimensions/measures that should be paired element-wise
+            df = pd.concat(
+                [df.reset_index(drop=True), path_df.reset_index(drop=True)], axis=1
+            )
+        else:
+            # Different lengths: cross product (Cartesian product)
+            df = df.merge(path_df, how="cross")
 
     return df
 

src/allotropy/parsers/cytiva_biacore_t200_control/cytiva_biacore_t200_control_data_creator.py

@@ -68,16 +68,44 @@ def _get_sensorgram_datacube(sensorgram_data: pd.DataFrame) -> DataCube:
 
 
 def _get_device_control_custom_info(data: Data) -> DictType:
-    custom_ifo: dict[str, Any] = {
+    application_template_details = data.application_template_details
+
+    custom_info: dict[str, Any] = {
         "number of flow cells": data.chip_data.number_of_flow_cells,
         "number of spots": data.chip_data.number_of_spots,
         "buffer volume": quantity_or_none(
             TQuantityValueMilliliter, data.run_metadata.buffer_volume
         ),
     }
     if detection_setting := data.run_metadata.detection_setting:
-        custom_ifo.update({detection_setting.key: detection_setting.value})
-    return custom_ifo
+        custom_info.update({detection_setting.key: detection_setting.value})
+
+    detection_info = application_template_details.get_nested("detection")
+    custom_info.update(
+        detection_info.get(key={"FlowCellSingle", "FlowCellDual", "FlowCellMulti"})
+    )
+
+    temp_info = application_template_details.get_nested("RackTemperature")
+    custom_info.update(
+        temp_info.get_keys_as_dict(
+            {
+                "minimum operating temperature": (float, "min", None),
+                "maximum operating temperature": (float, "max", None),
+            }
+        )
+    )
+
+    system_preparations = application_template_details.get_nested("system_preparations")
+    custom_info.update(
+        system_preparations.get_keys_as_dict(
+            {
+                "analysis temperature": (float, "AnalTemp", None),
+                "prime": (bool, "Prime", None),
+                "normalize": (bool, "Normalize", None),
+            }
+        )
+    )
+    return custom_info
 
 
 def create_metadata(data: Data, named_file_contents: NamedFileContents) -> Metadata:
@@ -103,15 +131,19 @@ def create_metadata(data: Data, named_file_contents: NamedFileContents) -> Metad
         lot_number=chip_data.lot_number,
         sensor_chip_identifier=chip_data.sensor_chip_identifier,
         device_document=[
-            DeviceDocument(device.type_, device.identifier)
+            DeviceDocument(device.type_, device.identifier, device.custom_info)
             for device in run_metadata.devices
         ],
         sensor_chip_custom_info=chip_data.custom_info,
+        data_system_custom_info=system_information.data_system_custom_info,
+        device_system_custom_info=system_information.device_system_custom_info,
     )
 
 
 def create_measurements(
-    measurements_data: list[MeasurementData], device_control_custom_info: DictType
+    measurements_data: list[MeasurementData],
+    device_control_custom_info: DictType,
+    data: Data,
 ) -> list[Measurement]:
     return [
         Measurement(
@@ -129,13 +161,25 @@ def create_measurements(
                     flow_rate=measurement.flow_rate,
                     contact_time=measurement.contact_time,
                     dilution=measurement.dilution,
-                    device_control_custom_info=device_control_custom_info,
+                    device_control_custom_info=dict(
+                        device_control_custom_info
+                    ),  # copy to avoid modifying the original
                 )
             ],
             sample_custom_info={
+                **data.application_template_details.get_nested(
+                    "racks"
+                ).get_keys_as_dict(
+                    {
+                        "Rack1": (str, "_Rack1", None),
+                        "Rack2": (str, "_Rack2", None),
+                        "Lock Positions": (bool, "_LockPositions", None),
+                    }
+                ),
                 "molecular weight": quantity_or_none(
                     TQuantityValueDalton, measurement.molecular_weight
-                )
+                ),
+                **measurement.sample_custom_info,
             },
             sensorgram_data_cube=_get_sensorgram_datacube(measurement.sensorgram_data),
             report_point_data=(
@@ -168,7 +212,7 @@ def create_measurement_groups(data: Data) -> list[MeasurementGroup]:
         MeasurementGroup(
             measurement_time=system_information.measurement_time,
             measurements=create_measurements(
-                measurements_data, device_control_custom_info
+                measurements_data, device_control_custom_info, data
             ),
             experiment_type=system_information.experiment_type,
             analytical_method_identifier=system_information.analytical_method_identifier,
@@ -181,6 +225,10 @@ def create_measurement_groups(data: Data) -> list[MeasurementGroup]:
                     TQuantityValueHertz,
                     try_float_or_none(data.run_metadata.data_collection_rate),
                 ),
+                **data.application_template_details.get_nested(
+                    "properties"
+                ).get_keys_as_dict({"Run Type": (str, "TypeName", None)}),
+                **system_information.measurement_aggregate_custom_info,
             },
         )
         for measurements_data in data.sample_data.measurements.values()

src/allotropy/parsers/cytiva_biacore_t200_control/cytiva_biacore_t200_control_parser.py

@@ -1,3 +1,7 @@
+import json
+from pathlib import Path, PureWindowsPath
+import warnings
+
 from allotropy.allotrope.models.adm.binding_affinity_analyzer.wd._2024._12.binding_affinity_analyzer import (
     Model,
 )
@@ -30,9 +34,26 @@ class CytivaBiacoreT200ControlParser(VendorParser[MapperData, Model]):
     SCHEMA_MAPPER = Mapper
 
     def create_data(self, named_file_contents: NamedFileContents) -> MapperData:
-        data = Data.create(DictData(decode_data(named_file_contents)))
-        return MapperData(
+        base_data = DictData(decode_data(named_file_contents))
+        data = Data.create(base_data)
+        mapper_data = MapperData(
             metadata=create_metadata(data, named_file_contents),
             measurement_groups=create_measurement_groups(data),
             calculated_data=create_calculated_data(data),
         )
+        try:
+            unread = base_data.get_unread_deep()
+            original_path = named_file_contents.original_file_path
+            # Derive file stem robustly for both POSIX and Windows-style paths
+            stem = (
+                PureWindowsPath(original_path).stem
+                if "\\" in original_path and "/" not in original_path
+                else Path(original_path).stem
+            )
+            out_name = f"{stem}data_unread_2.json"
+            with open(out_name, "w", encoding="utf-8") as f:
+                json.dump(unread, f, ensure_ascii=False, indent=2)
+        except Exception as e:
+            # Best-effort debug artifact; do not break parsing on failure
+            warnings.warn(f"Failed to write unread debug file: {e!s}", stacklevel=1)
+        return mapper_data