ghga-transpiler 2.3.1__py3-none-any.whl → 3.0.0rc1__py3-none-any.whl

ghga_transpiler/workbook_parser.py

@@ -0,0 +1,177 @@
+# Copyright 2021 - 2025 Universität Tübingen, DKFZ, EMBL, and Universität zu Köln
+# for the German Human Genome-Phenome Archive (GHGA)
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+"Module containing logic to parse a GHGA workbook"
+
+from openpyxl import Workbook
+from openpyxl.worksheet.worksheet import Worksheet
+from pydantic import BaseModel, ConfigDict, Field
+
+from .config import WorkbookConfig, WorksheetSettings
+from .models import GHGAWorkbook, GHGAWorksheet
+
+
+class WorksheetParser(BaseModel):
+    """Group worksheet parser functions."""
+
+    config: WorksheetSettings
+
+    def _header(self, worksheet: Worksheet):
+        """Return a list of column names of a worksheet."""
+        return [
+            cell.value
+            for row in worksheet.iter_rows(
+                self.config.settings.header_row,
+                self.config.settings.header_row,
+                self.config.settings.start_column,
+                self.config.settings.end_column,
+            )
+            for cell in row
+        ]
+
+    def _rows(self, worksheet: Worksheet) -> list:
+        """Create a list of non-empty rows of a worksheet."""
+        return [
+            row
+            for row in worksheet.iter_rows(
+                self.config.settings.start_row,
+                worksheet.max_row,
+                self.config.settings.start_column,
+                self.config.settings.end_column,
+                values_only=True,
+            )
+            if not all(cell is None for cell in row)
+        ]
+
+    def _content(self, worksheet: Worksheet) -> list[dict]:
+        """Compute and return the content of the worksheet, rows as worksheet row values and
+        column names as keys
+        """
+        return [
+            {
+                key: value
+                for key, value in zip(self._header(worksheet), row, strict=True)
+                if value is not None and value != ""
+            }
+            for row in self._rows(worksheet)
+        ]
+
+    def _transformed_content(self, worksheet: Worksheet) -> list:
+        """Processes each row of the provided worksheet, applying transformations to
+        specific fields as defined in the configuration and returns the worksheet content.
+        """
+        transformed_data = []
+        for row in self._content(worksheet):
+            transformed_row = {}
+            for key, value in row.items():
+                transformations = self.config.get_transformations()
+                if transformations and key in transformations:
+                    transformed_row[key] = transformations[key](value)
+                else:
+                    transformed_row[key] = value
+            transformed_data.append(transformed_row)
+        return transformed_data
+
+
+class GHGAWorksheetParser(WorksheetParser):
+    """Extend WorksheetParser with GHGA worksheet specific parsers."""
+
+    def parse(self, worksheet: Worksheet):
+        """Render a worksheet into GHGAWorksheet model"""
+        return GHGAWorksheet.model_validate(
+            {"worksheet": {self.config.settings.name: self._parse(worksheet)}}
+        )
+
+    def _parse(self, worksheet: Worksheet) -> dict[str, dict]:
+        """Parse a worksheet row by row into a dictionary of row-primary-keys as keys and
+        a dictionary of content and relations as the values.
+        """
+        worksheet_data = self._transformed_content(worksheet)
+        return {
+            row[self.config.settings.primary_key]: {
+                "content": self._relation_free_content(row),
+                "relations": self._relations(row),
+            }
+            for row in worksheet_data
+        }
+
+    def _relations(self, row: dict) -> dict:
+        """Get relations to a dictionary that contains relation name as key and the
+        resource that is in the relation as the value
+        """
+        relations = self.config.get_relations()
+        return {
+            relation.name: {
+                "targetClass": relation.target_class,
+                "targetResources": row[relation.name],
+            }
+            for relation in relations
+            if relation.name in row
+        }
+
+    def _relation_free_content(self, row: dict) -> dict:
+        """Clean up the content data from the relation, i.e., remove the key value pairs
+        belonging to a relation from the row content.
+        """
+        relations = self._relations(row)
+        relations[self.config.settings.primary_key] = None
+        return {key: value for key, value in row.items() if key not in relations}
+
+
+class GHGAWorkbookParser(BaseModel):
+    """Parser class for converting a workbook into a GHGAWorkbook."""
+
+    model_config = ConfigDict(arbitrary_types_allowed=True)
+    config: WorkbookConfig = Field(
+        ...,
+        description="Configuration for processing the workbook, including worksheet"
+        + " settings and column transformations.",
+    )
+
+    workbook: Workbook = Field(
+        ...,
+        description="Path to the Excel workbook file (.xlsx) that will be parsed."
+        + " This file contains the data to be transformed and processed.",
+    )
+
+    exclude: list = Field(
+        default=[
+            "__transpiler_protocol",
+            "__sheet_meta",
+            "__column_meta",
+        ],
+        description="List of sheet names to exclude from processing."
+        + " These are typically meta sheets that contain configuration data or metadata"
+        + " rather than actual worksheet data. Default value corresponds to the GHGA"
+        + " standard configuration sheets on the GHGA submission workbook.",
+    )
+
+    def parse(self) -> GHGAWorkbook:
+        """Converts the given workbook into a GHGAWorkbook instance.
+
+        This method iterates through the sheets of the provided workbook, excluding
+        any meta sheets (i.e., '__transpiler_protocol', '__sheet_meta', '__column_meta').
+        """
+        return GHGAWorkbook.model_validate(
+            {
+                "workbook": tuple(
+                    GHGAWorksheetParser(config=self.config.worksheets[name]).parse(
+                        self.workbook[name]
+                    )
+                    for name in self.workbook.sheetnames
+                    if name not in self.exclude
+                )
+            }
+        )

{ghga_transpiler-2.3.1.dist-info → ghga_transpiler-3.0.0rc1.dist-info}/METADATA

@@ -1,11 +1,11 @@
 Metadata-Version: 2.4
 Name: ghga_transpiler
-Version: 2.3.1
+Version: 3.0.0rc1
 Summary: GHGA-Transpiler - excel to JSON converter
 Author-email: "German Human Genome Phenome Archive (GHGA)" <contact@ghga.de>
 License: Apache 2.0
 Project-URL: Repository, https://github.com/ghga-de/ghga-transpiler
-Classifier: Development Status :: 1 - Planning
+Classifier: Development Status :: 5 - Production/Stable
 Classifier: Operating System :: POSIX :: Linux
 Classifier: Programming Language :: Python :: 3
 Classifier: Programming Language :: Python :: 3.12
@@ -13,16 +13,15 @@ Classifier: License :: OSI Approved :: Apache Software License
 Classifier: Topic :: Internet :: WWW/HTTP :: HTTP Servers
 Classifier: Topic :: Software Development :: Libraries
 Classifier: Intended Audience :: Developers
-Requires-Python: >=3.9
+Requires-Python: >=3.12
 Description-Content-Type: text/markdown
 License-File: LICENSE
-Requires-Dist: typer>=0.12
 Requires-Dist: openpyxl==3.*,>=3.1.2
 Requires-Dist: defusedxml==0.*,>=0.7
-Requires-Dist: pydantic<3,>=2.6
+Requires-Dist: pydantic<3,>=2
 Requires-Dist: PyYAML~=6.0
 Requires-Dist: semver==3.*
-Requires-Dist: click==8.1.0
+Requires-Dist: schemapack==2.0.0
 Dynamic: license-file
 
 

ghga_transpiler-3.0.0rc1.dist-info/RECORD

@@ -0,0 +1,17 @@
+ghga_transpiler/__init__.py,sha256=b_JlBjNvngOiIolsfKKbwonyfOtS7b5_LJKLuB5LyNQ,908
+ghga_transpiler/__main__.py,sha256=k82ZsGuAOTrbqB4rCNkGOS-AWU8GICtD1_owfiey-Sk,847
+ghga_transpiler/cli.py,sha256=D7MdNSIaKdYWLRMxdvzgsyN_t-brrzLqKrX84qHytjc,2988
+ghga_transpiler/config.py,sha256=R1J8oN3fkv3vlhqj2HuvviExJbL_FooMvDVkS0XUJlA,4411
+ghga_transpiler/exceptions.py,sha256=yHK5m9nb7uPyEmQKv_FBYjpuveuNnc3rzWEXKxxLlYw,1444
+ghga_transpiler/metasheet_parser.py,sha256=Zv9fOBNf7FuCG5RtOnOZNnS2hdrnDVUXaDSROSBC6c4,4883
+ghga_transpiler/models.py,sha256=0HQOwWmYiFmj6gRlf1wXivmwvdjaTD2O1YlwKfi8rC8,3721
+ghga_transpiler/transformations.py,sha256=j5buL8V9aOwJc5VlOS7fOrzgCG7FOvn1JxQvkPr9hLE,2235
+ghga_transpiler/transpile.py,sha256=BVSIh_W6qo92iczea9TGniBhxIyUBbYrqiduyfY44IY,1975
+ghga_transpiler/transpiler_io.py,sha256=ZDnNN5LhCf6ltDr14r_dqeZsbExum4-NAr6g1_liYqo,1809
+ghga_transpiler/workbook_parser.py,sha256=PUySMzLBJxOQTFV5L1XngSLQr5zhKCl2GMbCMv8kIXM,6740
+ghga_transpiler-3.0.0rc1.dist-info/licenses/LICENSE,sha256=nKgIWA3zoWy18_YSW6e9Gd6_p7d7ccwjNZrfJzvKALE,11452
+ghga_transpiler-3.0.0rc1.dist-info/METADATA,sha256=WGeGf-KelIslFxO0U761SC2eYe_bY-WxdNSHl9ggSUY,4441
+ghga_transpiler-3.0.0rc1.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+ghga_transpiler-3.0.0rc1.dist-info/entry_points.txt,sha256=Fr_VQJynZZl95NXjrQW2gE0bCocgjKVNEZQpaLls8po,65
+ghga_transpiler-3.0.0rc1.dist-info/top_level.txt,sha256=TksRpDO3Y4mvK-B09UhQU3ceZpG19fljNlVDGTfjg8o,16
+ghga_transpiler-3.0.0rc1.dist-info/RECORD,,

{ghga_transpiler-2.3.1.dist-info → ghga_transpiler-3.0.0rc1.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (80.7.1)
+Generator: setuptools (80.9.0)
 Root-Is-Purelib: true
 Tag: py3-none-any
 

ghga_transpiler/config/__init__.py

@@ -1,20 +0,0 @@
-# Copyright 2021 - 2025 Universität Tübingen, DKFZ, EMBL, and Universität zu Köln
-# for the German Human Genome-Phenome Archive (GHGA)
-
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-
-#     http://www.apache.org/licenses/LICENSE-2.0
-
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-#
-#
-
-"""Module to load workbook configurations and convert it to transpiler config"""
-
-from .config import Config, load_config  # noqa

ghga_transpiler/config/config.py

@@ -1,106 +0,0 @@
-# Copyright 2021 - 2025 Universität Tübingen, DKFZ, EMBL, and Universität zu Köln
-# for the German Human Genome-Phenome Archive (GHGA)
-
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-
-#     http://www.apache.org/licenses/LICENSE-2.0
-
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-#
-#
-
-"""Module to process config file"""
-
-from __future__ import annotations
-
-from collections import Counter
-from collections.abc import Callable
-from importlib import resources
-
-import yaml
-from pydantic import BaseModel, model_validator
-
-from .exceptions import DuplicatedName, UnknownVersionError
-
-
-class DefaultSettings(BaseModel):
-    """A data model for the defaults of the per-worksheet settings of a transpiler config"""
-
-    header_row: int = 0
-    start_row: int = 0
-    start_column: int = 0
-    end_column: int = 0
-    transformations: dict[str, Callable] = {}
-
-
-class WorksheetSettings(BaseModel):
-    """A data model for the per-worksheet settings of a transpiler config"""
-
-    name: str
-    header_row: int | None = None
-    start_row: int | None = None
-    start_column: int | None = None
-    end_column: int | None = None
-    transformations: dict[str, Callable] | None = None
-
-
-class Worksheet(BaseModel):
-    """A data model for worksheets in the transpiler config"""
-
-    sheet_name: str
-    settings: WorksheetSettings | None
-
-
-class Config(BaseModel):
-    """A data model for the transpiler config"""
-
-    ghga_metadata_version: str
-    default_settings: DefaultSettings
-    worksheets: list[Worksheet]
-
-    @model_validator(mode="after")
-    def get_param(cls, values):  # noqa
-        """Function to manage parameters of global and worksheet specific configuration"""
-        for sheet in values.worksheets:
-            for key in values.default_settings.__dict__:
-                if getattr(sheet.settings, key) is None:
-                    val = getattr(values.default_settings, key)
-                    setattr(sheet.settings, key, val)
-        return values
-
-    @model_validator(mode="after")
-    def check_name(cls, values):  # noqa
-        """Function to ensure that each worksheets has a unique sheet_name and name attributes."""
-        # Check for duplicate attribute names
-        attrs_counter = Counter(ws.settings.name for ws in values.worksheets)
-        dup_attrs = [name for name, count in attrs_counter.items() if count > 1]
-        if dup_attrs:
-            raise DuplicatedName(
-                "Duplicate target attribute names: " + ", ".join(dup_attrs)
-            )
-
-        # Check for duplicate worksheet names
-        attrs_counter = Counter(ws.sheet_name for ws in values.worksheets)
-        dup_ws_names = [name for name, count in attrs_counter.items() if count > 1]
-        if dup_ws_names:
-            raise DuplicatedName(
-                "Duplicate worksheet names: " + ", ".join(dup_ws_names)
-            )
-        return values
-
-
-def load_config(version: str, package: resources.Package) -> Config:
-    """Reads configuration yaml file from default location and creates a Config object"""
-    config_resource = resources.files(package).joinpath(f"{version}.yaml")
-    try:
-        config_str = config_resource.read_text(encoding="utf8")
-    except FileNotFoundError:
-        # pylint: disable=raise-missing-from
-        raise UnknownVersionError(f"Unknown metadata version: {version}") from None
-    return Config.model_validate(yaml.load(config_str, yaml.Loader))  # noqa # nosec

ghga_transpiler/configs/0.10.yaml

@@ -1,135 +0,0 @@
-ghga_metadata_version: 0.10.0
-default_settings:
-  header_row: 1
-  start_row: 7
-  start_column: 1
-  transformations:
-    attributes: !!python/object/apply:ghga_transpiler.transformations.to_attributes []
-    format: !!python/object/apply:ghga_transpiler.transformations.to_snake_case []
-    forward_or_reverse: !!python/object/apply:ghga_transpiler.transformations.to_snake_case []
-worksheets:
-  - settings:
-      end_column: 6
-      name: analyses
-    sheet_name: Analysis
-  - settings:
-      end_column: 8
-      name: analysis_process_output_files
-    sheet_name: AnalysisProcessOutputFile
-  - settings:
-      end_column: 5
-      name: analysis_processes
-      transformations:
-        study_input_files: !!python/object/apply:ghga_transpiler.transformations.to_list []
-        sample_input_files: !!python/object/apply:ghga_transpiler.transformations.to_list []
-        sequencing_process_input_files: !!python/object/apply:ghga_transpiler.transformations.to_list []
-    sheet_name: AnalysisProcess
-  - settings:
-      end_column: 9
-      name: biospecimens
-      transformations:
-        vital_status_at_sampling: !!python/object/apply:ghga_transpiler.transformations.to_snake_case []
-        age_at_sampling: !!python/object/apply:ghga_transpiler.transformations.to_snake_case []
-    sheet_name: Biospecimen
-  - settings:
-      end_column: 9
-      name: conditions
-      transformations:
-        disease_or_healthy: !!python/object/apply:ghga_transpiler.transformations.to_snake_case []
-        case_control_status: !!python/object/apply:ghga_transpiler.transformations.to_snake_case []
-        mutant_or_wildtype: !!python/object/apply:ghga_transpiler.transformations.to_snake_case []
-    sheet_name: Condition
-  - settings:
-      end_column: 3
-      name: data_access_committees
-    sheet_name: DataAccessCommittee
-  - settings:
-      end_column: 8
-      name: data_access_policies
-      transformations:
-        data_use_modifiers: !!python/object/apply:ghga_transpiler.transformations.to_snake_case_list []
-        data_use_permission: !!python/object/apply:ghga_transpiler.transformations.to_snake_case []
-    sheet_name: DataAccessPolicy
-  - settings:
-      end_column: 5
-      name: datasets
-      transformations:
-        types: !!python/object/apply:ghga_transpiler.transformations.to_list []
-    sheet_name: Dataset
-  - settings:
-      end_column: 8
-      name: individuals
-      transformations:
-        ancestries: !!python/object/apply:ghga_transpiler.transformations.to_list []
-        phenotypic_features: !!python/object/apply:ghga_transpiler.transformations.to_list []
-        karyotype: !!python/object/apply:ghga_transpiler.transformations.to_snake_case []
-        sex: !!python/object/apply:ghga_transpiler.transformations.to_snake_case []
-    sheet_name: Individual
-  - settings:
-      end_column: 14
-      name: library_preparation_protocols
-      transformations:
-        target_regions: !!python/object/apply:ghga_transpiler.transformations.to_list []
-        attributes: !!python/object/apply:ghga_transpiler.transformations.to_attributes []
-        library_layout: !!python/object/apply:ghga_transpiler.transformations.to_snake_case []
-        library_type: !!python/object/apply:ghga_transpiler.transformations.to_snake_case []
-        library_selection: !!python/object/apply:ghga_transpiler.transformations.to_snake_case []
-        library_preparation_kit_retail_name: !!python/object/apply:ghga_transpiler.transformations.to_snake_case []
-        rnaseq_strandedness: !!python/object/apply:ghga_transpiler.transformations.to_snake_case []
-        primer: !!python/object/apply:ghga_transpiler.transformations.to_snake_case []
-        end_bias: !!python/object/apply:ghga_transpiler.transformations.to_snake_case []
-    sheet_name: LibraryPreparationProtocol
-  - settings:
-      end_column: 9
-      name: publications
-      transformations:
-        xref: !!python/object/apply:ghga_transpiler.transformations.to_list []
-    sheet_name: Publication
-  - settings:
-      end_column: 8
-      name: sample_files
-    sheet_name: SampleFile
-  - settings:
-      end_column: 10
-      name: samples
-      transformations:
-        xref: !!python/object/apply:ghga_transpiler.transformations.to_list []
-        type: !!python/object/apply:ghga_transpiler.transformations.to_snake_case []
-    sheet_name: Sample
-  - settings:
-      end_column: 7
-      name: sequencing_experiments
-    sheet_name: SequencingExperiment
-  - settings:
-      end_column: 8
-      name: sequencing_process_files
-    sheet_name: SequencingProcessFile
-  - settings:
-      end_column: 10
-      name: sequencing_processes
-    sheet_name: SequencingProcess
-  - settings:
-      end_column: 20
-      name: sequencing_protocols
-      transformations:
-        instrument_model: !!python/object/apply:ghga_transpiler.transformations.to_snake_case []
-        flow_cell_type: !!python/object/apply:ghga_transpiler.transformations.to_snake_case []
-        umi_barcode_read: !!python/object/apply:ghga_transpiler.transformations.to_snake_case []
-        sample_barcode_read: !!python/object/apply:ghga_transpiler.transformations.to_snake_case []
-    sheet_name: SequencingProtocol
-  - settings:
-      end_column: 6
-      name: studies
-      transformations:
-        affiliations: !!python/object/apply:ghga_transpiler.transformations.to_list []
-        attributes: !!python/object/apply:ghga_transpiler.transformations.to_attributes []
-        type: !!python/object/apply:ghga_transpiler.transformations.to_snake_case []
-    sheet_name: Study
-  - settings:
-      end_column: 8
-      name: study_files
-    sheet_name: StudyFile
-  - settings:
-      end_column: 4
-      name: trios
-    sheet_name: Trio

ghga_transpiler/configs/1.0.yaml

@@ -1,135 +0,0 @@
-ghga_metadata_version: 1.0.0
-default_settings:
-  header_row: 1
-  start_row: 7
-  start_column: 1
-  transformations:
-    attributes: !!python/object/apply:ghga_transpiler.transformations.to_attributes []
-    format: !!python/object/apply:ghga_transpiler.transformations.to_snake_case []
-    forward_or_reverse: !!python/object/apply:ghga_transpiler.transformations.to_snake_case []
-worksheets:
-  - settings:
-      end_column: 6
-      name: analyses
-    sheet_name: Analysis
-  - settings:
-      end_column: 9
-      name: analysis_process_output_files
-    sheet_name: AnalysisProcessOutputFile
-  - settings:
-      end_column: 5
-      name: analysis_processes
-      transformations:
-        study_input_files: !!python/object/apply:ghga_transpiler.transformations.to_list []
-        sample_input_files: !!python/object/apply:ghga_transpiler.transformations.to_list []
-        sequencing_process_input_files: !!python/object/apply:ghga_transpiler.transformations.to_list []
-    sheet_name: AnalysisProcess
-  - settings:
-      end_column: 10
-      name: biospecimens
-      transformations:
-        vital_status_at_sampling: !!python/object/apply:ghga_transpiler.transformations.to_snake_case []
-        age_at_sampling: !!python/object/apply:ghga_transpiler.transformations.to_snake_case []
-    sheet_name: Biospecimen
-  - settings:
-      end_column: 9
-      name: conditions
-      transformations:
-        disease_or_healthy: !!python/object/apply:ghga_transpiler.transformations.to_snake_case []
-        case_control_status: !!python/object/apply:ghga_transpiler.transformations.to_snake_case []
-        mutant_or_wildtype: !!python/object/apply:ghga_transpiler.transformations.to_snake_case []
-    sheet_name: Condition
-  - settings:
-      end_column: 3
-      name: data_access_committees
-    sheet_name: DataAccessCommittee
-  - settings:
-      end_column: 8
-      name: data_access_policies
-      transformations:
-        data_use_modifiers: !!python/object/apply:ghga_transpiler.transformations.to_snake_case_list []
-        data_use_permission: !!python/object/apply:ghga_transpiler.transformations.to_snake_case []
-    sheet_name: DataAccessPolicy
-  - settings:
-      end_column: 5
-      name: datasets
-      transformations:
-        types: !!python/object/apply:ghga_transpiler.transformations.to_list []
-    sheet_name: Dataset
-  - settings:
-      end_column: 6
-      name: individuals
-      transformations:
-        ancestries: !!python/object/apply:ghga_transpiler.transformations.to_list []
-        phenotypic_features: !!python/object/apply:ghga_transpiler.transformations.to_list []
-        karyotype: !!python/object/apply:ghga_transpiler.transformations.to_snake_case []
-        sex: !!python/object/apply:ghga_transpiler.transformations.to_snake_case []
-    sheet_name: Individual
-  - settings:
-      end_column: 14
-      name: library_preparation_protocols
-      transformations:
-        target_regions: !!python/object/apply:ghga_transpiler.transformations.to_list []
-        attributes: !!python/object/apply:ghga_transpiler.transformations.to_attributes []
-        library_layout: !!python/object/apply:ghga_transpiler.transformations.to_snake_case []
-        library_type: !!python/object/apply:ghga_transpiler.transformations.to_snake_case []
-        library_selection: !!python/object/apply:ghga_transpiler.transformations.to_snake_case []
-        library_preparation_kit_retail_name: !!python/object/apply:ghga_transpiler.transformations.to_snake_case []
-        rnaseq_strandedness: !!python/object/apply:ghga_transpiler.transformations.to_snake_case []
-        primer: !!python/object/apply:ghga_transpiler.transformations.to_snake_case []
-        end_bias: !!python/object/apply:ghga_transpiler.transformations.to_snake_case []
-    sheet_name: LibraryPreparationProtocol
-  - settings:
-      end_column: 9
-      name: publications
-      transformations:
-        xref: !!python/object/apply:ghga_transpiler.transformations.to_list []
-    sheet_name: Publication
-  - settings:
-      end_column: 9
-      name: sample_files
-    sheet_name: SampleFile
-  - settings:
-      end_column: 10
-      name: samples
-      transformations:
-        xref: !!python/object/apply:ghga_transpiler.transformations.to_list []
-        type: !!python/object/apply:ghga_transpiler.transformations.to_snake_case []
-    sheet_name: Sample
-  - settings:
-      end_column: 7
-      name: sequencing_experiments
-    sheet_name: SequencingExperiment
-  - settings:
-      end_column: 9
-      name: sequencing_process_files
-    sheet_name: SequencingProcessFile
-  - settings:
-      end_column: 12
-      name: sequencing_processes
-    sheet_name: SequencingProcess
-  - settings:
-      end_column: 17
-      name: sequencing_protocols
-      transformations:
-        instrument_model: !!python/object/apply:ghga_transpiler.transformations.to_snake_case []
-        flow_cell_type: !!python/object/apply:ghga_transpiler.transformations.to_snake_case []
-        umi_barcode_read: !!python/object/apply:ghga_transpiler.transformations.to_snake_case []
-        sample_barcode_read: !!python/object/apply:ghga_transpiler.transformations.to_snake_case []
-    sheet_name: SequencingProtocol
-  - settings:
-      end_column: 6
-      name: studies
-      transformations:
-        affiliations: !!python/object/apply:ghga_transpiler.transformations.to_list []
-        attributes: !!python/object/apply:ghga_transpiler.transformations.to_attributes []
-        type: !!python/object/apply:ghga_transpiler.transformations.to_snake_case []
-    sheet_name: Study
-  - settings:
-      end_column: 9
-      name: study_files
-    sheet_name: StudyFile
-  - settings:
-      end_column: 4
-      name: trios
-    sheet_name: Trio