napistu 0.1.0__py3-none-any.whl

napistu-0.1.0.dist-info/METADATA

@@ -0,0 +1,56 @@
+Metadata-Version: 2.4
+Name: napistu
+Version: 0.1.0
+Summary: Connecting high-dimensional data to curated pathways
+Home-page: https://github.com/napistu/napistu-py
+Author: Sean Hackett
+Author-email: seanmchackett@gmail.com
+Project-URL: Bug Tracker, https://github.com/napistu/napistu-py/issues
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3 :: Only
+Requires-Python: >=3.11
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: Jinja2
+Requires-Dist: PyYAML==6.*
+Requires-Dist: click==8.*
+Requires-Dist: click-logging
+Requires-Dist: fs==2.4.*
+Requires-Dist: fs-gcsfs==1.5.*
+Requires-Dist: igraph
+Requires-Dist: matplotlib==3.*
+Requires-Dist: numpy==1.26.*
+Requires-Dist: pandas==1.5.*
+Requires-Dist: pydantic==2.*
+Requires-Dist: python-libsbml
+Requires-Dist: requests>=2
+Requires-Dist: scipy==1.14.*
+Requires-Dist: tqdm
+Requires-Dist: zeep==3.*
+Provides-Extra: dev
+Requires-Dist: black==25.*; extra == "dev"
+Requires-Dist: ipykernel; extra == "dev"
+Requires-Dist: pre-commit==3.3.*; extra == "dev"
+Requires-Dist: pytest==7.*; extra == "dev"
+Requires-Dist: pytest-cov; extra == "dev"
+Requires-Dist: ruff; extra == "dev"
+Requires-Dist: testcontainers; extra == "dev"
+Provides-Extra: rpy2
+Requires-Dist: pyarrow==18.0.0; extra == "rpy2"
+Requires-Dist: rpy2==3.5.*; extra == "rpy2"
+Requires-Dist: rpy2-arrow==0.1.1; extra == "rpy2"
+Dynamic: license-file
+
+# Napistu Python Library
+
+This Python package hosts the majority of the algorithmic code for the [Napistu project](https://github.com/napistu/napistu).
+
+## Setup
+
+Currently the only way to use this repository is to clone the repo and perform a local install. e.g., from this directory:
+
+```bash
+pip install .
+```

napistu-0.1.0.dist-info/RECORD

@@ -0,0 +1,77 @@
+napistu/__init__.py,sha256=rz6NdV9Fm6a6bBR17VQPHeJQD4DUZWC7zR9a7nNMOhw,269
+napistu/__main__.py,sha256=i1OyReHD58GjyGYShXmMuBfA0VoGBF9dirg2nA4JCa8,28334
+napistu/consensus.py,sha256=p8GjWFzq1cvBB-H-LVSatWL_9fxbdYq2wsF4-JZnc_M,54641
+napistu/constants.py,sha256=hQ1OLH07xFTxMukJLCptzqqHk22vgrByej8lvMb2qbc,14702
+napistu/identifiers.py,sha256=wque0qsMZK2AMsAhkF1ERSMrEF7h6b5SMp3iqVu8e1o,28796
+napistu/indices.py,sha256=UeJjjsYs0sGvZIKz1y4ZQ6aUkABn-6TCUDZ2VCVT9JI,7534
+napistu/mechanism_matching.py,sha256=CPhtM6GERmGlBK8zH1cEvSpsasa0mG7ojLKDOze3dyE,21704
+napistu/sbml_dfs_core.py,sha256=iSng-3cpJVpVMb340YGM6s0pFBTA9SyYCdYvHdZRSMA,79387
+napistu/sbml_dfs_utils.py,sha256=j6Bu3acqOFSEbyVzASXhlnV8hQvi4k-vdMYzVMPzz5A,10318
+napistu/source.py,sha256=oBgw2OZLVBETQG8Mwoc5ZUe-6cg_Yt6Mxsto3fCdw1k,13386
+napistu/utils.py,sha256=G4IfG_WBSxkn5RBdPPn9sAkzrz2BdKgXlFFmMsB9wsA,28038
+napistu/gcs/__init__.py,sha256=1kqmRHlEyI7VpILzurZb1URwC_UIc1PTMEBHQnjXW6s,246
+napistu/gcs/constants.py,sha256=rc-oQBh6pdu7cjqTCerHG_fDub-FQcEjzWh2ic715cs,2844
+napistu/gcs/downloads.py,sha256=EiOxLW1MMexdPTSiakWknTB-BGY1y__s2n1z9Sd8VYM,5033
+napistu/ingestion/__init__.py,sha256=1kqmRHlEyI7VpILzurZb1URwC_UIc1PTMEBHQnjXW6s,246
+napistu/ingestion/bigg.py,sha256=XPJZv64mrIMCuKe1mjQfS5QPR9tmengGvndSjc3QFLA,5559
+napistu/ingestion/constants.py,sha256=TYATiVNrLyuQ1AvLVt35F1xQ8pQ3U19o_N6ZSkdW3PA,9941
+napistu/ingestion/cpr_edgelist.py,sha256=eVT9M7gmdBuGHcAYlvkD_zzvTtyzXufKWjwDiT8OxF4,3572
+napistu/ingestion/identifiers_etl.py,sha256=6ppDUA6lEZurdmVbiFLOUzphYbr-hndMhtqsQnq_yAc,5009
+napistu/ingestion/obo.py,sha256=pszLLfImZxDYjL3WQUCow2hQFURROGHqIq3qbgVtzAM,8836
+napistu/ingestion/psi_mi.py,sha256=Icj73EK75ytFPBw-TH2B6yW1ZWAmckmn5mtPl9pIxuA,9389
+napistu/ingestion/reactome.py,sha256=-Q3GsAsfVkTD7cDD1fLEEnWQbI6vs7nxsdYInk7ZvVE,7907
+napistu/ingestion/sbml.py,sha256=gK6_jHgo6oaiG16WlrbBSvxq_0VzFR4a5fG9IQrp5bU,24153
+napistu/ingestion/string.py,sha256=tsaHrjppgFbl9NnRcB2DytpoontqrpfQL65zD9HPgEM,11668
+napistu/ingestion/trrust.py,sha256=ccjZc_eF3PdxxurnukiEo_e0-aKc_3z22NYbaJBtHdY,9774
+napistu/ingestion/yeast.py,sha256=bwFBNxRq-dLDaddgBL1hpfZj0eQ56nBXyR_9n0NZT9Y,5233
+napistu/modify/__init__.py,sha256=1kqmRHlEyI7VpILzurZb1URwC_UIc1PTMEBHQnjXW6s,246
+napistu/modify/constants.py,sha256=KHigix_8A8kCLWYVGR9_6_n34UNDcq2guDLC1KLeNZ4,2648
+napistu/modify/curation.py,sha256=UNeAfJ26XDFvSwkPL8WHCAP0FQYiVUrSvJn3UIt5jy8,21607
+napistu/modify/gaps.py,sha256=XqwfvzgJywA7ws5hzDlj22xs5tRGc4xOdbQ2v51UJqc,23983
+napistu/modify/pathwayannot.py,sha256=onbQy9YNYPbeOih8fSxymxUQJc1jXjRIQOABv3xkvng,47183
+napistu/modify/uncompartmentalize.py,sha256=U5X4Q7Z-YIkC8_711x3sU21vTVdv9rKfauwz4JNzl6c,9690
+napistu/network/__init__.py,sha256=1kqmRHlEyI7VpILzurZb1URwC_UIc1PTMEBHQnjXW6s,246
+napistu/network/constants.py,sha256=jz8vRjgns74piUcvmoIP_f-8s9w15SxWAEw2lf6XmDY,3661
+napistu/network/neighborhoods.py,sha256=TopPpcUD09bAfJuT_L4dkHwJhV1VJJlzXpyzldYi85A,55512
+napistu/network/net_create.py,sha256=9Rb5I6uLlL50SNADucsT_90F9k7rzmp2EQfEgNlr37E,60343
+napistu/network/net_utils.py,sha256=cMWLOHlz4XvPA8PlPiSFYNDjAEv4t1qlZxwabBaZrK8,21188
+napistu/network/paths.py,sha256=a2J3JWIdMufdNs8Amh6I7s3TOVD2EzLV9khqbWHvGlA,16652
+napistu/network/precompute.py,sha256=83Vr2pxCmEtJJmE_Lq1BI-pEmESDNG0N7vByXjBf_oQ,7517
+napistu/rpy2/__init__.py,sha256=B9tZHiEp6bvysjqvBRQ1aGY493Ks9kouwb0pW7KsKqA,4100
+napistu/rpy2/callr.py,sha256=76ICWj7Jso-qrYLNfiV-DgPyrMTdRXz_EhyGOD9CbFM,4301
+napistu/rpy2/constants.py,sha256=JpJqsxImZis8fFFfePXYdbkhUZhXDZoHSHVf92w1h8U,2619
+napistu/rpy2/netcontextr.py,sha256=gkpBgrASNeH_8IjFyY-Tj-S87HjNOkGdfMta0WRdEnU,16278
+napistu/rpy2/rids.py,sha256=sGMTRuOQRDpHBHZwfTS7uKUW9TBI_yMpht6SFhup8vw,23937
+napistu-0.1.0.dist-info/licenses/LICENSE,sha256=kW8wVT__JWoHjl2BbbJDAZInWa9AxzJeR_uv6-i5x1g,1063
+tests/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+tests/conftest.py,sha256=uDuqgZKR37csoUI4t4U-pzEoANMFAIyTA4k8XLRu_Bw,2572
+tests/test_consensus.py,sha256=u_5Hyocz2peNbJMd5ydgoAwQ4il0lFm-PrzrckTCitI,9403
+tests/test_constants.py,sha256=gJLDv7QMeeBiiupyMazj6mumk20KWvGMgm2myHMKKfc,531
+tests/test_curation.py,sha256=-Q2J0D7qs9PGjHZX-rM4NxRLLdwxoapytSo_98q9ItY,3864
+tests/test_edgelist.py,sha256=bdEtQJdd4MeQsNtng9afHYNVDsEy0U07sfVwguAdIBM,560
+tests/test_gcs.py,sha256=sq-zIDfmLIpZ5oFKCmyuaw9tfSzAY5hSnpuN-xqiqpk,561
+tests/test_identifiers.py,sha256=RyuPAMhYI8cDOl2r62idweLxgy7rAs9omeZQ62h56kY,5019
+tests/test_igraph.py,sha256=HoYeFAAFXWtxdonnUTpV59-jCLicNa0_utPaaGKXMAw,10926
+tests/test_indices.py,sha256=-TrKfX4qXsofg_TPQEhHaQc_CuQMEd4_0maJgGCgSfE,2468
+tests/test_mechanism_matching.py,sha256=gD_n2saM7yYa56QU0RMAYMKMAk7oF8ESbM7GHbI6bFY,4156
+tests/test_net_utils.py,sha256=4HqfFF6yycAz7oQYRz6MefzQVQ_ZjWpeUEA4lUDOMJc,1614
+tests/test_netcontextr.py,sha256=PKH0D-8EL0HNrCMtF-fAaYv5Lao4mwVPDZLQ5LHJXqc,3399
+tests/test_obo.py,sha256=47qNCElPzu2nA36Oq83Dqp1RGhITqztjl7UyZ5cMsj4,959
+tests/test_pathwayannot.py,sha256=bceosccNy9tgxQei_7j7ATBSSvBSxOngJvK-mAzR_K0,3312
+tests/test_precomputed_distances.py,sha256=ht7lVz0wGOOQl9UTI1o9ftm0Dk7q8E40UV2jxVmE-Tg,7203
+tests/test_rpy2.py,sha256=beihvGlWsQA9U7V3tfqBIOUL-S8m8Nj84Bg2Wt2sNH8,1491
+tests/test_sbml.py,sha256=w_VU06psAP0Ku3B0flbP4hKhBfx2ZWV3oOdUgWzrMP4,1276
+tests/test_sbml_dfs_create.py,sha256=w29mUcnC6g9Yqp8Q3b-oRQc5GiDvzjS5_GOE_LjwGZo,9982
+tests/test_sbml_dfs_utils.py,sha256=onFWdhrTix30XR1-CMrMXld37BYxEGi6TZrweugLDzI,505
+tests/test_sbo.py,sha256=x_PENFaXYsrZIzOZu9cj_Wrej7i7SNGxgBYYvcigLs0,308
+tests/test_set_coverage.py,sha256=gM6Zl3MhVRHUi0_z0ISqpeXckWT8XdpXb58ipCoWyHU,1606
+tests/test_source.py,sha256=hT0IlpexR5zP0OhWl5BBaho9d1aCYQlFZLwRIRRnw_Y,1969
+tests/test_uncompartmentalize.py,sha256=nAk5kfAVLU9a2VWe2x2HYVcKqj-EnwmwddERIPRax8c,1289
+tests/test_utils.py,sha256=knOWMN9xgaNLDj_4T_ZI3f22p1ZqovRLVDBFaMhOnFs,14845
+tests/utils.py,sha256=SoWQ_5roJteFGcMaOeEiQ5ucwq3Z2Fa3AAs9iXHTsJY,749
+tests/test_data/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+napistu-0.1.0.dist-info/METADATA,sha256=bFJYn_d8Q0WfF5fpnE5tRZAqU3jNHuxXV0xyI-bt0yk,1830
+napistu-0.1.0.dist-info/WHEEL,sha256=CmyFI0kx5cdEMTLiONQRbGQwjIoR1aIYB7eCAQ4KPJ0,91
+napistu-0.1.0.dist-info/entry_points.txt,sha256=_QnaPOvJNA3IltxmZgWIiBoen-L1bPYX18YQfC7oJgQ,41
+napistu-0.1.0.dist-info/top_level.txt,sha256=Gpvk0a_PjrtqhYcQ9IDr3zR5LqpZ-uIHidQMIpjlvhY,14
+napistu-0.1.0.dist-info/RECORD,,

napistu-0.1.0.dist-info/WHEEL

@@ -0,0 +1,5 @@
+Wheel-Version: 1.0
+Generator: setuptools (78.1.0)
+Root-Is-Purelib: true
+Tag: py3-none-any
+

napistu-0.1.0.dist-info/entry_points.txt

@@ -0,0 +1,2 @@
+[console_scripts]
+cpr = cpr.__main__:cli

napistu-0.1.0.dist-info/licenses/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2025 Calico
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

napistu-0.1.0.dist-info/top_level.txt

@@ -0,0 +1,2 @@
+napistu
+tests

tests/conftest.py

@@ -0,0 +1,83 @@
+from __future__ import annotations
+
+import os
+import sys
+
+from napistu import consensus
+from napistu import indices
+from napistu import sbml_dfs_core
+from napistu.ingestion import sbml
+from pytest import fixture
+from pytest import skip
+
+
+@fixture
+def sbml_path():
+    test_path = os.path.abspath(os.path.join(__file__, os.pardir))
+    sbml_path = os.path.join(test_path, "test_data", "R-HSA-1237044.sbml")
+
+    if not os.path.isfile(sbml_path):
+        raise ValueError(f"{sbml_path} not found")
+    return sbml_path
+
+
+@fixture
+def sbml_model(sbml_path):
+    sbml_model = sbml.SBML(sbml_path)
+    return sbml_model
+
+
+@fixture
+def sbml_dfs(sbml_model):
+    sbml_dfs = sbml_dfs_core.SBML_dfs(sbml_model)
+    return sbml_dfs
+
+
+@fixture
+def sbml_dfs_metabolism():
+    test_path = os.path.abspath(os.path.join(__file__, os.pardir))
+    test_data = os.path.join(test_path, "test_data")
+
+    pw_index = indices.PWIndex(os.path.join(test_data, "pw_index_metabolism.tsv"))
+    sbml_dfs_dict = consensus.construct_sbml_dfs_dict(pw_index)
+    sbml_dfs = consensus.construct_consensus_model(sbml_dfs_dict, pw_index)
+
+    return sbml_dfs
+
+
+@fixture
+def sbml_dfs_glucose_metabolism():
+    test_path = os.path.abspath(os.path.join(__file__, os.pardir))
+    test_data = os.path.join(test_path, "test_data")
+    sbml_path = os.path.join(test_data, "reactome_glucose_metabolism.sbml")
+
+    sbml_model = sbml.SBML(sbml_path).model
+    sbml_dfs = sbml_dfs_core.SBML_dfs(sbml_model)
+
+    return sbml_dfs
+
+
+# Define custom markers for platforms
+def pytest_configure(config):
+    config.addinivalue_line("markers", "skip_on_windows: mark test to skip on Windows")
+    config.addinivalue_line("markers", "skip_on_macos: mark test to skip on macOS")
+    config.addinivalue_line("markers", "unix_only: mark test to run only on Unix/Linux systems")
+
+# Define platform conditions
+is_windows = sys.platform == "win32"
+is_macos = sys.platform == "darwin"
+is_unix = not (is_windows or is_macos)
+
+# Apply skipping based on platform
+def pytest_runtest_setup(item):
+    # Skip tests marked to be skipped on Windows
+    if is_windows and any(mark.name == "skip_on_windows" for mark in item.iter_markers()):
+        skip("Test skipped on Windows")
+    
+    # Skip tests marked to be skipped on macOS
+    if is_macos and any(mark.name == "skip_on_macos" for mark in item.iter_markers()):
+        skip("Test skipped on macOS")
+    
+    # Skip tests that should run only on Unix
+    if not is_unix and any(mark.name == "unix_only" for mark in item.iter_markers()):
+        skip("Test runs only on Unix systems")

tests/test_consensus.py

@@ -0,0 +1,255 @@
+from __future__ import annotations
+
+import os
+
+import pandas as pd
+import pytest
+from napistu import consensus
+from napistu import indices
+from napistu import source
+from napistu.ingestion import sbml
+from napistu.modify import pathwayannot
+
+test_path = os.path.abspath(os.path.join(__file__, os.pardir))
+test_data = os.path.join(test_path, "test_data")
+
+
+def test_reduce_to_consensus_ids():
+    sbml_path = os.path.join(test_data, "R-HSA-1237044.sbml")
+
+    # test aggregating by IDs, by moving from compartmentalized_species -> species
+
+    sbml_model = sbml.SBML(sbml_path).model
+    comp_species_df = sbml.setup_cspecies(sbml_model)
+    comp_species_df.index.names = ["s_id"]
+    consensus_species, species_lookup = consensus.reduce_to_consensus_ids(
+        comp_species_df, {"pk": "s_id", "id": "s_Identifiers"}
+    )
+
+    assert isinstance(consensus_species, pd.DataFrame)
+    assert consensus_species.shape == (18, 4)
+    assert isinstance(species_lookup, pd.Series)
+    assert species_lookup.size == 23
+
+
+def test_consensus():
+    pw_index = indices.PWIndex(os.path.join(test_data, "pw_index.tsv"))
+    sbml_dfs_dict = consensus.construct_sbml_dfs_dict(pw_index)
+
+    consensus_model = consensus.construct_consensus_model(sbml_dfs_dict, pw_index)
+    assert consensus_model.species.shape == (38, 3)
+    assert consensus_model.reactions.shape == (30, 4)
+    assert consensus_model.reaction_species.shape == (137, 4)
+
+    consensus_model = pathwayannot.drop_cofactors(consensus_model)
+    assert consensus_model.species.shape == (38, 3)
+    assert consensus_model.reaction_species.shape == (52, 4)
+    # update reaction_species.shape after more cofactors identified
+
+    consensus_model.validate()
+
+
+def test_source_tracking():
+    # create input data
+    table_schema = {"source": "source_var", "pk": "primary_key"}
+
+    # define existing sources and the new_id entity they belong to
+    # here, we are assuming that each model has a blank source object
+    # as if it came from a non-consensus model
+    agg_tbl = pd.DataFrame(
+        {
+            "new_id": [0, 0, 1, 1],
+        }
+    )
+    agg_tbl[table_schema["source"]] = source.Source(init=True)
+
+    # define new_ids and the models they came from
+    # these models will be matched to the pw_index to flush out metadata
+    lookup_table = pd.DataFrame(
+        {
+            "new_id": [0, 0, 1, 1],
+            "model": ["R-HSA-1237044", "R-HSA-425381", "R-HSA-1237044", "R-HSA-425381"],
+        }
+    )
+
+    # use an existing pw_index since pw_index currently checks for the existence of the source file
+    pw_index = indices.PWIndex(os.path.join(test_data, "pw_index.tsv"))
+
+    # test create source table
+    source_table = source.create_source_table(lookup_table, table_schema, pw_index)
+    assert source_table["source_var"][0].source.shape == (2, 8)
+
+    # test create_consensus_sources
+    consensus_sources = consensus.create_consensus_sources(
+        agg_tbl, lookup_table, table_schema, pw_index
+    )
+    assert consensus_sources[0].source.shape == (2, 8)
+
+    # lets add a model which does not have a reference in the pw_index
+    invalid_lookup_table = pd.DataFrame(
+        {
+            "new_id": [0, 0, 1, 1],
+            "model": ["R-HSA-1237044", "R-HSA-425381", "R-HSA-1237044", "typo"],
+        }
+    )
+
+    # expect a ValueError when the model is not found
+    with pytest.raises(ValueError) as _:
+        source.create_source_table(invalid_lookup_table, table_schema, pw_index)
+
+    # now we will aggregate the consensus model above with a new single model (which has some
+    # overlapping entries with the consensusd (id 1) and some new ids (id 2)
+
+    agg_tbl2 = pd.DataFrame(
+        {
+            "new_id": [0, 1, 1, 2],
+        }
+    )
+
+    agg_tbl2[table_schema["source"]] = consensus_sources.tolist() + [
+        source.Source(init=True) for i in range(0, 2)
+    ]
+
+    lookup_table2 = pd.DataFrame(
+        {
+            "new_id": [0, 1, 1, 2],
+            # the model for the first two entries should really correspond to the "consensus"
+            # but since this is not a file I will stub with one of the pw_index entries
+            "model": [
+                "R-HSA-1247673",
+                "R-HSA-1247673",
+                "R-HSA-1475029",
+                "R-HSA-1475029",
+            ],
+        }
+    )
+
+    source_table = source.create_source_table(lookup_table2, table_schema, pw_index)
+    assert source_table.shape == (3, 1)
+    assert [
+        source_table["source_var"][i].source.shape
+        for i in range(0, source_table.shape[0])
+    ] == [(1, 8), (2, 8), (1, 8)]
+
+    consensus_sources = consensus.create_consensus_sources(
+        agg_tbl2, lookup_table2, table_schema, pw_index
+    )
+    assert [
+        consensus_sources[i].source.shape for i in range(0, consensus_sources.shape[0])
+    ] == [(3, 8), (4, 8), (1, 8)]
+
+
+def test_passing_entity_data():
+    pw_index = indices.PWIndex(os.path.join(test_data, "pw_index.tsv"))
+    sbml_dfs_dict = consensus.construct_sbml_dfs_dict(pw_index)
+
+    for model in list(sbml_dfs_dict.keys())[0:3]:
+        sbml_dfs_dict[model].add_species_data(
+            "my_species_data",
+            sbml_dfs_dict[model]
+            .species.iloc[0:5]
+            .assign(my_species_data_var="testing")["my_species_data_var"]
+            .to_frame(),
+        )
+        sbml_dfs_dict[model].add_reactions_data(
+            "my_reactions_data",
+            sbml_dfs_dict[model]
+            .reactions.iloc[0:5]
+            .assign(my_reactions_data_var1="testing")
+            .assign(my_reactions_data_var2="testing2")[
+                ["my_reactions_data_var1", "my_reactions_data_var2"]
+            ],
+        )
+
+    # create a consensus with perfect merges of overlapping id-table-variable values
+    # i.e., when combined all merged entries have the same attributes
+    consensus_model = consensus.construct_consensus_model(sbml_dfs_dict, pw_index)
+
+    assert len(consensus_model.species_data) == 1
+    assert consensus_model.species_data["my_species_data"].shape == (10, 1)
+    assert len(consensus_model.reactions_data) == 1
+    assert consensus_model.reactions_data["my_reactions_data"].shape == (14, 2)
+
+    # add different tables from different models
+    for model in list(sbml_dfs_dict.keys())[3:5]:
+        sbml_dfs_dict[model].add_species_data(
+            "my_other_species_data",
+            sbml_dfs_dict[model]
+            .species.iloc[0:5]
+            .assign(my_species_data="testing")["my_species_data"]
+            .to_frame(),
+        )
+
+    consensus_model = consensus.construct_consensus_model(sbml_dfs_dict, pw_index)
+    assert len(consensus_model.species_data) == 2
+
+    # create a case where reactions will be merged and the same reaction
+    # in different models has a different value for its reactions_data
+    minimal_pw_index = pw_index
+    minimal_pw_index.index = minimal_pw_index.index.iloc[0:2]
+    minimal_pw_index.index["file"].loc[1] = minimal_pw_index.index["file"][0]
+
+    duplicated_sbml_dfs_dict = consensus.construct_sbml_dfs_dict(minimal_pw_index)
+    # explicitely define the order we'll loop through models so that
+    # the position of a model can be used to set mismatching attributes
+    # for otherwise identical models
+    model_order = list(duplicated_sbml_dfs_dict.keys())
+
+    for model in duplicated_sbml_dfs_dict.keys():
+        model_index = model_order.index(model)
+
+        duplicated_sbml_dfs_dict[model].add_reactions_data(
+            "my_mismatched_data",
+            duplicated_sbml_dfs_dict[model]
+            .reactions.iloc[0:5]
+            .assign(my_reactions_data_var1=model)["my_reactions_data_var1"]
+            .to_frame()
+            .assign(numeric_var=[x + model_index for x in range(0, 5)])
+            .assign(bool_var=[x + model_index % 2 == 0 for x in range(0, 5)]),
+        )
+
+    # assign reversibility is True for one model to
+    # confirm that reversibility trumps irreversible
+    # when merging reactions with identical stoichiometry but
+    # different reversibility attributes
+
+    duplicated_sbml_dfs_dict["R-HSA-1237044"].reactions = duplicated_sbml_dfs_dict[
+        "R-HSA-1237044"
+    ].reactions.assign(r_isreversible=True)
+
+    consensus_model = consensus.construct_consensus_model(
+        duplicated_sbml_dfs_dict, pw_index
+    )
+    assert consensus_model.reactions_data["my_mismatched_data"].shape == (5, 3)
+    assert consensus_model.reactions["r_isreversible"].eq(True).all()
+
+
+def test_consensus_ontology_check():
+    pw_index = indices.PWIndex(os.path.join(test_data, "pw_index.tsv"))
+
+    test_sbml_dfs_dict = consensus.construct_sbml_dfs_dict(pw_index)
+    test_consensus_model = consensus.construct_consensus_model(
+        test_sbml_dfs_dict, pw_index
+    )
+
+    pre_shared_onto_sp_list, pre_onto_df = consensus.pre_consensus_ontology_check(
+        test_sbml_dfs_dict, "species"
+    )
+    assert set(pre_shared_onto_sp_list) == {"chebi", "reactome", "uniprot"}
+
+    post_shared_onto_sp_set = consensus.post_consensus_species_ontology_check(
+        test_consensus_model
+    )
+    assert post_shared_onto_sp_set == {"chebi", "reactome", "uniprot"}
+
+
+################################################
+# __main__
+################################################
+
+if __name__ == "__main__":
+    test_reduce_to_consensus_ids()
+    test_consensus()
+    test_source_tracking()
+    test_passing_entity_data()
+    test_consensus_ontology_check()

tests/test_constants.py

@@ -0,0 +1,20 @@
+from __future__ import annotations
+
+from napistu import constants
+
+
+def test_sbo_constants():
+    # all SBO terms in "MINI_SBO" set have a role
+    assert set(constants.SBO_NAME_TO_ROLE.keys()) == set(
+        constants.MINI_SBO_FROM_NAME.keys()
+    )
+    # all roles are valid
+    assert [x in constants.VALID_SBO_ROLES for x in constants.SBO_NAME_TO_ROLE.values()]
+
+
+################################################
+# __main__
+################################################
+
+if __name__ == "__main__":
+    test_sbo_constants()

tests/test_curation.py

@@ -0,0 +1,134 @@
+from __future__ import annotations
+
+import os
+
+import pandas as pd
+from napistu import sbml_dfs_core
+from napistu.ingestion import sbml
+from napistu.modify import curation
+
+test_path = os.path.abspath(os.path.join(__file__, os.pardir))
+sbml_path = os.path.join(test_path, "test_data", "R-HSA-1237044.sbml")
+
+if not os.path.isfile(sbml_path):
+    raise ValueError(f"{sbml_path} not found")
+
+# setup mock curations
+curation_dict = dict()
+curation_dict["species"] = pd.DataFrame(
+    [
+        {
+            "species": "hello",
+            "uri": "http://www.ebi.ac.uk/chebi/searchId.do?chebiId=CHEBI:35828",
+            "curator": "Sean",
+        },
+        {"species": "good day", "uri": None, "curator": "Sean"},
+    ]
+)
+
+curation_dict["compartmentalized_species"] = pd.DataFrame(
+    [
+        {
+            "compartmentalized_species": "hello [cytosol]",
+            "s_name": "hello",
+            "c_name": "cytosol",
+            "curator": "Sean",
+        }
+    ]
+)
+
+curation_dict["reactions"] = pd.DataFrame(
+    [
+        {
+            "reactions": "there",
+            "stoichiometry": "hello [cytosol] -> CO2 [cytosol]",
+            "uri": None,
+            "evidence": "how is",
+            "curator": "Sean",
+        },
+        {
+            "reactions": "where",
+            "stoichiometry": "CO2 [cytosol] -> hello [cytosol]",
+            "uri": None,
+            "evidence": "your family",
+            "curator": "Sean",
+        },
+    ]
+)
+
+curation_dict["reaction_species"] = pd.DataFrame(
+    [
+        {
+            "reaction_species": "NADH [cytosol]",
+            "r_name": "CYB5Rs reduce MetHb to HbA",
+            "stoichiometry": 0,
+            "sbo_term_name": "stimulator",
+            "evidence": "weeeee",
+            "curator": "Sean",
+        }
+    ]
+)
+
+curation_dict["remove"] = pd.DataFrame(
+    [
+        {"remove": "reaction_1237042", "table": "reactions", "variable": "r_id"},
+        {
+            "remove": "CYB5Rs reduce MetHb to HbA",
+            "table": "reactions",
+            "variable": "r_name",
+        },
+        {"remove": "CO2", "table": "species", "variable": "s_name"},
+    ]
+)
+
+
+def test_remove_entities():
+    sbml_model = sbml.SBML(sbml_path)
+    sbml_dfs = sbml_dfs_core.SBML_dfs(sbml_model)
+    sbml_dfs.validate()
+
+    invalid_entities_dict = curation._find_invalid_entities(
+        sbml_dfs, curation_dict["remove"]
+    )
+    invalid_pks = set(invalid_entities_dict.keys())
+
+    assert invalid_pks == {"sc_id", "rsc_id", "r_id", "s_id"}
+
+    n_species = sbml_dfs.species.shape[0]
+    n_reactions = sbml_dfs.reactions.shape[0]
+    n_compartmentalized_species = sbml_dfs.compartmentalized_species.shape[0]
+    n_reaction_species = sbml_dfs.reaction_species.shape[0]
+    # should be untouched
+    n_compartments = sbml_dfs.compartments.shape[0]
+
+    sbml_dfs = curation._remove_entities(sbml_dfs, invalid_entities_dict)
+
+    assert n_species - sbml_dfs.species.shape[0] == 1
+    assert n_reactions - sbml_dfs.reactions.shape[0] == 2
+    assert (
+        n_compartmentalized_species - sbml_dfs.compartmentalized_species.shape[0] == 2
+    )
+    assert n_reaction_species - sbml_dfs.reaction_species.shape[0] == 14
+    assert n_compartments - sbml_dfs.compartments.shape[0] == 0
+
+
+def test_add_entities():
+    sbml_model = sbml.SBML(sbml_path)
+    sbml_dfs = sbml_dfs_core.SBML_dfs(sbml_model)
+    sbml_dfs.validate()
+
+    new_entities = curation.format_curations(curation_dict, sbml_dfs)
+
+    assert new_entities["species"].shape == (2, 3)
+    assert new_entities["reactions"].shape == (2, 4)
+    assert new_entities["compartmentalized_species"].shape == (1, 4)
+    assert new_entities["reaction_species"].shape == (5, 4)
+
+
+################################################
+# __main__
+################################################
+
+if __name__ == "__main__":
+    test_remove_entities()
+    test_add_entities()