nmdc-runtime 1.1.0__py3-none-any.whl → 1.3.0__py3-none-any.whl

nmdc_runtime/site/translation/{neon_translator.py → neon_soil_translator.py}

@@ -1,17 +1,34 @@
 import re
-import math
 import sqlite3
-from typing import Union, List
+from typing import List
 
 import pandas as pd
 
 from nmdc_schema import nmdc
 from nmdc_runtime.site.translation.translator import Translator
 from nmdc_runtime.site.util import get_basename
-
-
-class NeonDataTranslator(Translator):
-    def __init__(self, mms_data: dict, sls_data: dict, *args, **kwargs) -> None:
+from nmdc_runtime.site.translation.neon_utils import (
+    _get_value_or_none,
+    _create_controlled_identified_term_value,
+    _create_controlled_term_value,
+    _create_geolocation_value,
+    _create_quantity_value,
+    _create_timestamp_value,
+    _create_text_value,
+    _create_double_value,
+)
+
+
+class NeonSoilDataTranslator(Translator):
+    def __init__(
+        self,
+        mms_data: dict,
+        sls_data: dict,
+        neon_envo_mappings_file: pd.DataFrame,
+        neon_raw_data_file_mappings_file: pd.DataFrame,
+        *args,
+        **kwargs,
+    ) -> None:
         super().__init__(*args, **kwargs)
 
         self.conn = sqlite3.connect("neon.db")
@@ -73,155 +90,15 @@ class NeonDataTranslator(Translator):
                 f"You are missing one of the soil periodic tables: {neon_sls_data_tables}"
             )
 
-        neon_envo_mappings_file = "https://raw.githubusercontent.com/microbiomedata/nmdc-schema/main/assets/neon_mixs_env_triad_mappings/neon-nlcd-local-broad-mappings.tsv"
-        neon_envo_terms = pd.read_csv(neon_envo_mappings_file, delimiter="\t")
-        neon_envo_terms.to_sql(
+        neon_envo_mappings_file.to_sql(
             "neonEnvoTerms", self.conn, if_exists="replace", index=False
         )
 
-        neon_raw_data_file_mappings_file = "https://raw.githubusercontent.com/microbiomedata/nmdc-schema/main/assets/misc/neon_raw_data_file_mappings.tsv"
-        self.neon_raw_data_file_mappings_df = pd.read_csv(
-            neon_raw_data_file_mappings_file, delimiter="\t"
-        )
+        self.neon_raw_data_file_mappings_df = neon_raw_data_file_mappings_file
         self.neon_raw_data_file_mappings_df.to_sql(
             "neonRawDataFile", self.conn, if_exists="replace", index=False
         )
 
-    def _get_value_or_none(
-        self, data: pd.DataFrame, column_name: str
-    ) -> Union[str, float, None]:
-        """
-        Get the value from the specified column in the data DataFrame.
-        If the column value is NaN, return None. However, there are handlers
-        for a select set of columns - horizon, qaqcStatus, sampleTopDepth,
-        and sampleBottomDepth.
-
-        :param data: DataFrame to read the column value from.
-        :return: Either a string, float or None depending on the column/column values.
-        """
-        if column_name in data and not data[column_name].isna().any():
-            if column_name == "horizon":
-                return f"{data[column_name].values[0]} horizon"
-            elif column_name == "qaqcStatus":
-                return data[column_name].values[0].lower()
-            elif column_name == "sampleTopDepth":
-                return float(data[column_name].values[0]) / 100
-            elif column_name == "sampleBottomDepth":
-                return float(data[column_name].values[0]) / 100
-            else:
-                return data[column_name].values[0]
-
-        return None
-
-    def _create_controlled_identified_term_value(
-        self, id: str = None, name: str = None
-    ) -> nmdc.ControlledIdentifiedTermValue:
-        """
-        Create a ControlledIdentifiedTermValue object with the specified id and name.
-
-        :param id: CURIE (with defined prefix expansion) or full URI of term.
-        :param name: Name of term.
-        :return: ControlledIdentifiedTermValue with mandatorily specified value for `id`.
-        """
-        if id is None or name is None:
-            return None
-        return nmdc.ControlledIdentifiedTermValue(
-            term=nmdc.OntologyClass(id=id, name=name)
-        )
-
-    def _create_controlled_term_value(
-        self, name: str = None
-    ) -> nmdc.ControlledTermValue:
-        """
-        Create a ControlledIdentifiedTermValue object with the specified id and name.
-
-        :param name: Name of term. This may or may not have an `id` associated with it,
-        hence the decision to record it in `has_raw_value` meaning, record as it is
-        in the data source.
-        :return: ControlledTermValue object with name in `has_raw_value`.
-        """
-        if id is None or name is None:
-            return None
-        return nmdc.ControlledTermValue(has_raw_value=name)
-
-    def _create_timestamp_value(self, value: str = None) -> nmdc.TimestampValue:
-        """
-        Create a TimestampValue object with the specified value.
-
-        :param value: Timestamp value recorded in ISO-8601 format.
-        Example: 2021-07-07T20:14Z.
-        :return: ISO-8601 timestamp wrapped in TimestampValue object.
-        """
-        if value is None:
-            return None
-        return nmdc.TimestampValue(has_raw_value=value)
-
-    def _create_quantity_value(
-        self, numeric_value: Union[str, int, float] = None, unit: str = None
-    ) -> nmdc.QuantityValue:
-        """
-        Create a QuantityValue object with the specified numeric value and unit.
-
-        :param numeric_value: Numeric value from a dataframe column that typically
-        records numerical values.
-        :param unit: Unit corresponding to the numeric value. Example: biogeochemical
-        measurement value like organic Carbon Nitrogen ratio.
-        :return: Numeric value and unit stored together in nested QuantityValue object.
-        """
-        if numeric_value is None or math.isnan(numeric_value):
-            return None
-        return nmdc.QuantityValue(has_numeric_value=float(numeric_value), has_unit=unit)
-
-    def _create_text_value(self, value: str = None) -> nmdc.TextValue:
-        """
-        Create a TextValue object with the specified value.
-
-        :param value: column that we expect to primarily have text values.
-        :return: Text wrapped in TextValue object.
-        """
-        if value is None:
-            return None
-        return nmdc.TextValue(has_raw_value=value)
-
-    def _create_double_value(self, value: str = None) -> nmdc.Double:
-        """
-        Create a Double object with the specified value.
-
-        :param value: Values from a column which typically records numeric
-        (double) values like pH.
-        :return: String (possibly) cast/converted to nmdc Double object.
-        """
-        if value is None or math.isnan(value):
-            return None
-        return nmdc.Double(value)
-
-    def _create_geolocation_value(
-        self, latitude: str = None, longitude: str = None
-    ) -> nmdc.GeolocationValue:
-        """
-        Create a GeolocationValue object with latitude and longitude from the
-        biosample DataFrame. Takes in values from the NEON API table with
-        latitude (decimalLatitude) and longitude (decimalLongitude) values and
-        puts it in the respective slots in the GeolocationValue class object.
-
-        :param latitude: Value corresponding to `decimalLatitude` column.
-        :param longitude: Value corresponding to `decimalLongitude` column.
-        :return: Latitude and Longitude values wrapped in nmdc GeolocationValue
-        object.
-        """
-        if (
-            latitude is None
-            or math.isnan(latitude)
-            or longitude is None
-            or math.isnan(longitude)
-        ):
-            return None
-
-        return nmdc.GeolocationValue(
-            latitude=nmdc.DecimalDegree(latitude),
-            longitude=nmdc.DecimalDegree(longitude),
-        )
-
     def _translate_biosample(
         self, neon_id: str, nmdc_id: str, biosample_row: pd.DataFrame
     ) -> nmdc.Biosample:
@@ -240,64 +117,58 @@ class NeonDataTranslator(Translator):
         return nmdc.Biosample(
             id=nmdc_id,
             part_of="nmdc:sty-11-34xj1150",
-            env_broad_scale=self._create_controlled_identified_term_value(
+            env_broad_scale=_create_controlled_identified_term_value(
                 "ENVO:00000446", "terrestrial biome"
             ),
-            env_local_scale=self._create_controlled_identified_term_value(
+            env_local_scale=_create_controlled_identified_term_value(
                 biosample_row["envo_id"].values[0],
                 biosample_row["envo_label"].values[0],
             ),
-            env_medium=self._create_controlled_identified_term_value(
+            env_medium=_create_controlled_identified_term_value(
                 "ENVO:00001998", "soil"
             ),
             name=neon_id,
-            lat_lon=self._create_geolocation_value(
+            lat_lon=_create_geolocation_value(
                 biosample_row["decimalLatitude"].values[0],
                 biosample_row["decimalLongitude"].values[0],
             ),
             elev=nmdc.Float(biosample_row["elevation"].values[0]),
-            collection_date=self._create_timestamp_value(
+            collection_date=_create_timestamp_value(
                 biosample_row["collectDate"].values[0]
             ),
-            temp=self._create_quantity_value(
-                biosample_row["soilTemp"].values[0], "Celsius"
-            ),
+            temp=_create_quantity_value(biosample_row["soilTemp"].values[0], "Celsius"),
             depth=nmdc.QuantityValue(
-                has_minimum_numeric_value=self._get_value_or_none(
+                has_minimum_numeric_value=_get_value_or_none(
                     biosample_row, "sampleTopDepth"
                 ),
-                has_maximum_numeric_value=self._get_value_or_none(
+                has_maximum_numeric_value=_get_value_or_none(
                     biosample_row, "sampleBottomDepth"
                 ),
                 has_unit="m",
             ),
-            samp_collec_device=self._get_value_or_none(
-                biosample_row, "soilSamplingDevice"
-            ),
-            soil_horizon=self._get_value_or_none(biosample_row, "horizon"),
-            analysis_type=self._get_value_or_none(
-                biosample_row, "sequenceAnalysisType"
-            ),
-            env_package=self._create_text_value(biosample_row["sampleType"].values[0]),
-            nitro=self._create_quantity_value(
+            samp_collec_device=_get_value_or_none(biosample_row, "soilSamplingDevice"),
+            soil_horizon=_get_value_or_none(biosample_row, "horizon"),
+            analysis_type=_get_value_or_none(biosample_row, "sequenceAnalysisType"),
+            env_package=_create_text_value(biosample_row["sampleType"].values[0]),
+            nitro=_create_quantity_value(
                 biosample_row["nitrogenPercent"].values[0], "percent"
             ),
-            org_carb=self._create_quantity_value(
+            org_carb=_create_quantity_value(
                 biosample_row["organicCPercent"].values[0], "percent"
             ),
-            carb_nitro_ratio=self._create_quantity_value(
+            carb_nitro_ratio=_create_quantity_value(
                 biosample_row["CNratio"].values[0], None
             ),
-            ph=self._create_double_value(biosample_row["soilInWaterpH"].values[0]),
+            ph=_create_double_value(biosample_row["soilInWaterpH"].values[0]),
             water_content=[
                 f"{biosample_row['soilMoisture'].values[0]} g of water/g of dry soil"
             ]
             if not biosample_row["soilMoisture"].isna().any()
             else None,
-            ammonium_nitrogen=self._create_quantity_value(
+            ammonium_nitrogen=_create_quantity_value(
                 biosample_row["kclAmmoniumNConc"].values[0], "mg/L"
             ),
-            tot_nitro_content=self._create_quantity_value(
+            tot_nitro_content=_create_quantity_value(
                 biosample_row["kclNitrateNitriteNConc"].values[0], "mg/L"
             ),
             type="nmdc:Biosample",
@@ -325,8 +196,8 @@ class NeonDataTranslator(Translator):
             id=nmdc_id,
             has_output=processed_sample_id,
             has_input=bsm_input_values_list,
-            start_date=self._get_value_or_none(pooling_row, "startDate"),
-            end_date=self._get_value_or_none(pooling_row, "collectDate"),
+            start_date=_get_value_or_none(pooling_row, "startDate"),
+            end_date=_get_value_or_none(pooling_row, "collectDate"),
         )
 
     def _translate_processed_sample(
@@ -393,7 +264,7 @@ class NeonDataTranslator(Translator):
         :return: Extraction process object.
         """
         processing_institution = None
-        laboratory_name = self._get_value_or_none(extraction_row, "laboratoryName")
+        laboratory_name = _get_value_or_none(extraction_row, "laboratoryName")
         if laboratory_name is not None:
             if re.search("Battelle", laboratory_name, re.IGNORECASE):
                 processing_institution = "Battelle"
@@ -404,13 +275,13 @@ class NeonDataTranslator(Translator):
             id=extraction_id,
             has_input=extraction_input,
             has_output=processed_sample_id,
-            start_date=self._get_value_or_none(extraction_row, "collectDate"),
-            end_date=self._get_value_or_none(extraction_row, "processedDate"),
-            sample_mass=self._create_quantity_value(
-                self._get_value_or_none(extraction_row, "sampleMass"), "g"
+            start_date=_get_value_or_none(extraction_row, "collectDate"),
+            end_date=_get_value_or_none(extraction_row, "processedDate"),
+            input_mass=_create_quantity_value(
+                _get_value_or_none(extraction_row, "sampleMass"), "g"
             ),
             quality_control_report=nmdc.QualityControlReport(
-                status=self._get_value_or_none(extraction_row, "qaqcStatus")
+                status=_get_value_or_none(extraction_row, "qaqcStatus")
             ),
             processing_institution=processing_institution,
         )
@@ -436,9 +307,7 @@ class NeonDataTranslator(Translator):
         :return: Object that using LibraryPreparation process model.
         """
         processing_institution = None
-        laboratory_name = self._get_value_or_none(
-            library_preparation_row, "laboratoryName"
-        )
+        laboratory_name = _get_value_or_none(library_preparation_row, "laboratoryName")
         if laboratory_name is not None:
             if re.search("Battelle", laboratory_name, re.IGNORECASE):
                 processing_institution = "Battelle"
@@ -449,8 +318,8 @@ class NeonDataTranslator(Translator):
             id=library_preparation_id,
             has_input=library_preparation_input,
             has_output=processed_sample_id,
-            start_date=self._get_value_or_none(library_preparation_row, "collectDate"),
-            end_date=self._get_value_or_none(library_preparation_row, "processedDate"),
+            start_date=_get_value_or_none(library_preparation_row, "collectDate"),
+            end_date=_get_value_or_none(library_preparation_row, "processedDate"),
             processing_institution=processing_institution,
         )
 
@@ -475,7 +344,7 @@ class NeonDataTranslator(Translator):
         :return: OmicsProcessing object that models a Bioinformatics workflow process/run.
         """
         processing_institution = None
-        sequencing_facility = self._get_value_or_none(
+        sequencing_facility = _get_value_or_none(
             omics_processing_row, "sequencingFacilityID"
         )
         if sequencing_facility is not None:
@@ -489,15 +358,13 @@ class NeonDataTranslator(Translator):
             has_input=processed_sample_id,
             has_output=raw_data_file_data,
             processing_institution=processing_institution,
-            ncbi_project_name=self._get_value_or_none(
-                omics_processing_row, "ncbiProjectID"
-            ),
-            omics_type=self._create_controlled_term_value(
+            ncbi_project_name=_get_value_or_none(omics_processing_row, "ncbiProjectID"),
+            omics_type=_create_controlled_term_value(
                 omics_processing_row["investigation_type"].values[0]
             ),
-            instrument_name=f"{self._get_value_or_none(omics_processing_row, 'sequencingMethod')} {self._get_value_or_none(omics_processing_row, 'instrument_model')}",
+            instrument_name=f"{_get_value_or_none(omics_processing_row, 'sequencingMethod')} {_get_value_or_none(omics_processing_row, 'instrument_model')}",
             part_of="nmdc:sty-11-34xj1150",
-            name=f"Terrestrial soil microbial communities - {self._get_value_or_none(omics_processing_row, 'dnaSampleID')}",
+            name=f"Terrestrial soil microbial communities - {_get_value_or_none(omics_processing_row, 'dnaSampleID')}",
             type="nmdc:OmicsProcessing",
         )
 

nmdc_runtime/site/translation/neon_utils.py

@@ -0,0 +1,146 @@
+import math
+from typing import Union
+
+import pandas as pd
+from nmdc_schema import nmdc
+
+
+def _get_value_or_none(data: pd.DataFrame, column_name: str) -> Union[str, float, None]:
+    """
+    Get the value from the specified column in the data DataFrame.
+    If the column value is NaN, return None. However, there are handlers
+    for a select set of columns - horizon, qaqcStatus, sampleTopDepth,
+    and sampleBottomDepth.
+
+    :param data: DataFrame to read the column value from.
+    :return: Either a string, float or None depending on the column/column values.
+    """
+    if (
+        column_name in data
+        and not data[column_name].isna().any()
+        and not data[column_name].empty
+    ):
+        if column_name == "horizon":
+            return f"{data[column_name].values[0]} horizon"
+        elif column_name == "qaqcStatus":
+            return data[column_name].values[0].lower()
+        elif column_name == "sampleTopDepth":
+            return float(data[column_name].values[0]) / 100
+        elif column_name == "sampleBottomDepth":
+            return float(data[column_name].values[0]) / 100
+        else:
+            return data[column_name].values[0]
+
+    return None
+
+
+def _create_controlled_identified_term_value(
+    id: str = None, name: str = None
+) -> nmdc.ControlledIdentifiedTermValue:
+    """
+    Create a ControlledIdentifiedTermValue object with the specified id and name.
+
+    :param id: CURIE (with defined prefix expansion) or full URI of term.
+    :param name: Name of term.
+    :return: ControlledIdentifiedTermValue with mandatorily specified value for `id`.
+    """
+    if id is None or name is None:
+        return None
+    return nmdc.ControlledIdentifiedTermValue(term=nmdc.OntologyClass(id=id, name=name))
+
+
+def _create_controlled_term_value(name: str = None) -> nmdc.ControlledTermValue:
+    """
+    Create a ControlledIdentifiedTermValue object with the specified id and name.
+
+    :param name: Name of term. This may or may not have an `id` associated with it,
+    hence the decision to record it in `has_raw_value` meaning, record as it is
+    in the data source.
+    :return: ControlledTermValue object with name in `has_raw_value`.
+    """
+    if name is None:
+        return None
+    return nmdc.ControlledTermValue(has_raw_value=name)
+
+
+def _create_timestamp_value(value: str = None) -> nmdc.TimestampValue:
+    """
+    Create a TimestampValue object with the specified value.
+
+    :param value: Timestamp value recorded in ISO-8601 format.
+    Example: 2021-07-07T20:14Z.
+    :return: ISO-8601 timestamp wrapped in TimestampValue object.
+    """
+    if value is None:
+        return None
+    return nmdc.TimestampValue(has_raw_value=value)
+
+
+def _create_quantity_value(
+    numeric_value: Union[str, int, float] = None, unit: str = None
+) -> nmdc.QuantityValue:
+    """
+    Create a QuantityValue object with the specified numeric value and unit.
+
+    :param numeric_value: Numeric value from a dataframe column that typically
+    records numerical values.
+    :param unit: Unit corresponding to the numeric value. Example: biogeochemical
+    measurement value like organic Carbon Nitrogen ratio.
+    :return: Numeric value and unit stored together in nested QuantityValue object.
+    """
+    if numeric_value is None or math.isnan(numeric_value):
+        return None
+    return nmdc.QuantityValue(has_numeric_value=float(numeric_value), has_unit=unit)
+
+
+def _create_text_value(value: str = None) -> nmdc.TextValue:
+    """
+    Create a TextValue object with the specified value.
+
+    :param value: column that we expect to primarily have text values.
+    :return: Text wrapped in TextValue object.
+    """
+    if value is None:
+        return None
+    return nmdc.TextValue(has_raw_value=value)
+
+
+def _create_double_value(value: str = None) -> nmdc.Double:
+    """
+    Create a Double object with the specified value.
+
+    :param value: Values from a column which typically records numeric
+    (double) values like pH.
+    :return: String (possibly) cast/converted to nmdc Double object.
+    """
+    if value is None or math.isnan(value):
+        return None
+    return nmdc.Double(value)
+
+
+def _create_geolocation_value(
+    latitude: str = None, longitude: str = None
+) -> nmdc.GeolocationValue:
+    """
+    Create a GeolocationValue object with latitude and longitude from the
+    biosample DataFrame. Takes in values from the NEON API table with
+    latitude (decimalLatitude) and longitude (decimalLongitude) values and
+    puts it in the respective slots in the GeolocationValue class object.
+
+    :param latitude: Value corresponding to `decimalLatitude` column.
+    :param longitude: Value corresponding to `decimalLongitude` column.
+    :return: Latitude and Longitude values wrapped in nmdc GeolocationValue
+    object.
+    """
+    if (
+        latitude is None
+        or math.isnan(latitude)
+        or longitude is None
+        or math.isnan(longitude)
+    ):
+        return None
+
+    return nmdc.GeolocationValue(
+        latitude=nmdc.DecimalDegree(latitude),
+        longitude=nmdc.DecimalDegree(longitude),
+    )

{nmdc_runtime-1.1.0.dist-info → nmdc_runtime-1.3.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
-Name: nmdc-runtime
-Version: 1.1.0
+Name: nmdc_runtime
+Version: 1.3.0
 Summary: A runtime system for NMDC data management and orchestration
 Home-page: https://github.com/microbiomedata/nmdc-runtime
 Author: Donny Winston

{nmdc_runtime-1.1.0.dist-info → nmdc_runtime-1.3.0.dist-info}/RECORD

@@ -1,5 +1,5 @@
 nmdc_runtime/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-nmdc_runtime/containers.py,sha256=WBzPue0PRoyKXFxgLR-aQcuHetTa8yC5JjI0dGBblYA,419
+nmdc_runtime/containers.py,sha256=8m_S1wiFu8VOWvY7tyqzf-02X9gXY83YGc8FgjWzLGA,418
 nmdc_runtime/main.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 nmdc_runtime/util.py,sha256=o74ZKOmSD79brPFAcQFsYpA6wh9287m0hDhDlIpn9VM,19872
 nmdc_runtime/client/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -23,8 +23,8 @@ nmdc_runtime/lib/__init__.py,sha256=AbpHGcgLb-kRsJGnwFEktk7uzpZOCcBY74-YBdrKVGs,
 nmdc_runtime/lib/extract_nmdc_data.py,sha256=xDFPoYsgkauN48R4v-tJIF0cP_p3J-sBjnyHd0InD9Y,1177
 nmdc_runtime/lib/load_nmdc_data.py,sha256=KO2cIqkY3cBCVcFIwsGokZNOKntOejZVG8ecq43NjFM,3934
 nmdc_runtime/lib/nmdc_dataframes.py,sha256=rVTczY2Jey1yE3x3nZ-RTgtdc2XkzLtKhB_PM3FIb-E,28849
-nmdc_runtime/lib/nmdc_etl_class.py,sha256=x83nKGi7peATlPLf3LGGU6cf42ZmpE__s1XQV2DpkPc,13523
-nmdc_runtime/lib/transform_nmdc_data.py,sha256=3w8Em5byzzOSgjC1LX2nq_d2O4FsTpkDC3UBiZYi9EM,39907
+nmdc_runtime/lib/nmdc_etl_class.py,sha256=tVh3rKVMkBHQE65_LhKeIjCsaCZQk_HJzbc9K4xUNCs,13522
+nmdc_runtime/lib/transform_nmdc_data.py,sha256=hij4lR3IMQRJQdL-rsP_I-m_WyFPsBMchV2MNFUkh0M,39906
 nmdc_runtime/minter/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 nmdc_runtime/minter/bootstrap.py,sha256=5Ej6pJVBRryRIi0ZwEloY78Zky7iE2okF6tPwRI2axM,822
 nmdc_runtime/minter/config.py,sha256=mq_s0xjLZK-zwjwk3IGgnk9ZIvvejyyZ7_qZkLt3V-c,1409
@@ -35,9 +35,9 @@ nmdc_runtime/minter/domain/model.py,sha256=WMOuKub3dVzkOt_EZSRDLeTsJPqFbKx01SMQ5
 nmdc_runtime/minter/entrypoints/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 nmdc_runtime/minter/entrypoints/fastapi_app.py,sha256=JC4thvzfFwRc1mhWQ-kHy3yvs0SYxF6ktE7LXNCwqlI,4031
 nmdc_runtime/site/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-nmdc_runtime/site/graphs.py,sha256=Wto684CPjzMny-V3ZuVJ0QupLFryImkBJK9znH_gm9A,6757
-nmdc_runtime/site/ops.py,sha256=1uukcNd8qBgRJ2C9OHmhH4Mg7usQjP3c2FkyRw34ACE,29693
-nmdc_runtime/site/repository.py,sha256=cqw1RpaS6JnfPXwL6bT92HhC_O_PJrZUzTh78HPPO4k,24472
+nmdc_runtime/site/graphs.py,sha256=siHlRnD2eS9nw3Ne049TcGG6I6IYFvjgWQuuSHzEOqc,9492
+nmdc_runtime/site/ops.py,sha256=YzDm7Dm2sELptwTew8DTOcS3nYBH_JegXhu3wzZuuiY,32482
+nmdc_runtime/site/repository.py,sha256=UgY9eMnNgZxa-Y0QeDyENh4KHtxuBWkYCjxltM4mTzA,30938
 nmdc_runtime/site/resources.py,sha256=pQSwg1dRpL_D91gYLzzaOIDZ3qa69rPqSlsq5dS9i_M,17783
 nmdc_runtime/site/util.py,sha256=6hyVPpb6ZkWEG8Nm7uQxnZ-QmuPOG9hgWvl0mUBr5JU,1303
 nmdc_runtime/site/backup/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -60,9 +60,11 @@ nmdc_runtime/site/terminusdb/schema.py,sha256=3e39rHUSZsNbN_F0SHHNsvcEGRWtYa6O9K
 nmdc_runtime/site/translation/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 nmdc_runtime/site/translation/emsl.py,sha256=l6Q9Jj3RNJFQNYAU_TtKTJ7cyFcR93xBRs_lLdX0bMQ,1244
 nmdc_runtime/site/translation/gold.py,sha256=R3W99sdQb7Pgu_esN7ruIC-tyREQD_idJ4xCzkqWuGw,1622
-nmdc_runtime/site/translation/gold_translator.py,sha256=vqTmZ5dqmaExIgA8nXpBYCs0d2OedNZgwbWJrt5Tm_M,26441
+nmdc_runtime/site/translation/gold_translator.py,sha256=8i5FxrgAG4rLbM0mcCSBaZEzyReht6xwmpm4xeX4HwI,26451
 nmdc_runtime/site/translation/jgi.py,sha256=bh73r0uq5BT3ywXwIa1OEKKtz9LbFsSng472tdr-xtg,875
-nmdc_runtime/site/translation/neon_translator.py,sha256=RjLMm2VHm1ASFr8J7p-EEWqPiE4KpUWtQdbTLsKha58,43440
+nmdc_runtime/site/translation/neon_benthic_translator.py,sha256=e_7tXFrP0PpdhqUCxXmOaFViSuG36IIMDqyj3FHLcgQ,23069
+nmdc_runtime/site/translation/neon_soil_translator.py,sha256=x-FfNKsIv0efgxty9v4wOxNu5nrrS-N8phx12IqfLOI,37624
+nmdc_runtime/site/translation/neon_utils.py,sha256=k8JYMnm-L981BTOdAMomR1CulS_Hz5v7aYxrJ94KEJc,5086
 nmdc_runtime/site/translation/submission_portal_translator.py,sha256=lHcrfPR5wk3BcZ0Uw5zUyWu5XRVikgOzdzSb5nFVS9I,27964
 nmdc_runtime/site/translation/translator.py,sha256=xM9dM-nTgSWwu5HFoUVNHf8kqk9iiH4PgWdSx4OKxEk,601
 nmdc_runtime/site/translation/util.py,sha256=w_l3SiExGsl6cXRqto0a_ssDmHkP64ITvrOVfPxmNpY,4366
@@ -71,9 +73,9 @@ nmdc_runtime/site/validation/emsl.py,sha256=TgckqKkFquHDLso77sn-jZRu5ZaBevGCt5p8
 nmdc_runtime/site/validation/gold.py,sha256=kJ1L081SZb-8qKpF731r5aQOueM206SUfUYMTTNTFMc,802
 nmdc_runtime/site/validation/jgi.py,sha256=lBo-FCtEYedT74CpW-Kdj512Ib963ik-4YIYmY5puDo,1298
 nmdc_runtime/site/validation/util.py,sha256=GGbMDSwR090sr_E_fHffCN418gpYESaiot6XghS7OYk,3349
-nmdc_runtime-1.1.0.dist-info/LICENSE,sha256=VWiv65r7gHGjgtr3jMJYVmQny5GRpQ6H-W9sScb1x70,2408
-nmdc_runtime-1.1.0.dist-info/METADATA,sha256=SU6AEjUwgOorLBlJnisGp0fh2mSnWCH9Sn5fzo80gqE,7424
-nmdc_runtime-1.1.0.dist-info/WHEEL,sha256=oiQVh_5PnQM0E3gPdiz09WCNmwiHDMaGer_elqB3coM,92
-nmdc_runtime-1.1.0.dist-info/entry_points.txt,sha256=nfH6-K9tDKv7va8ENfShsBnxVQoYJdEe7HHdwtkbh1Y,289
-nmdc_runtime-1.1.0.dist-info/top_level.txt,sha256=b0K1s09L_iHH49ueBKaLrB5-lh6cyrSv9vL6x4Qvyz8,13
-nmdc_runtime-1.1.0.dist-info/RECORD,,
+nmdc_runtime-1.3.0.dist-info/LICENSE,sha256=VWiv65r7gHGjgtr3jMJYVmQny5GRpQ6H-W9sScb1x70,2408
+nmdc_runtime-1.3.0.dist-info/METADATA,sha256=XiOhRGoaBESF48sWor9SMpTdCL8X9yPKIh6mnA9xZtY,7424
+nmdc_runtime-1.3.0.dist-info/WHEEL,sha256=oiQVh_5PnQM0E3gPdiz09WCNmwiHDMaGer_elqB3coM,92
+nmdc_runtime-1.3.0.dist-info/entry_points.txt,sha256=nfH6-K9tDKv7va8ENfShsBnxVQoYJdEe7HHdwtkbh1Y,289
+nmdc_runtime-1.3.0.dist-info/top_level.txt,sha256=b0K1s09L_iHH49ueBKaLrB5-lh6cyrSv9vL6x4Qvyz8,13
+nmdc_runtime-1.3.0.dist-info/RECORD,,