napistu 0.3.3__py3-none-any.whl → 0.3.4__py3-none-any.whl

napistu/constants.py

@@ -403,12 +403,6 @@ ONTOLOGIES = SimpleNamespace(
 
 ONTOLOGIES_LIST = list(ONTOLOGIES.__dict__.values())
 
-CHARACTERISTIC_COMPLEX_ONTOLOGIES = [
-    ONTOLOGIES.ENSEMBL_GENE,
-    ONTOLOGIES.NCBI_ENTREZ_GENE,
-    ONTOLOGIES.MIRBASE,
-]
-
 ONTOLOGY_SPECIES_ALIASES = {
     ONTOLOGIES.NCBI_ENTREZ_GENE: {"ncbigene", "ncbi_gene"},
     ONTOLOGIES.ENSEMBL_GENE: {"ensembl_gene_id"},

napistu/network/precompute.py

@@ -120,7 +120,7 @@ def save_precomputed_distances(
     OSError
         If the file cannot be written to (permission issues, etc.)
     """
-    save_json(str(uri), precomputed_distances.to_dict(orient="index"))
+    save_json(str(uri), precomputed_distances.to_json())
 
 
 def load_precomputed_distances(uri: Union[str, Path]) -> pd.DataFrame:
@@ -143,12 +143,18 @@ def load_precomputed_distances(uri: Union[str, Path]) -> pd.DataFrame:
         If the specified file does not exist
     """
     try:
-        data_dict = load_json(str(uri))
+        json_string = load_json(str(uri))
+        df = pd.read_json(json_string)
+
+        # Convert integer columns to float
+        for col in df.columns:
+            if df[col].dtype in ["int64", "int32", "int16", "int8"]:
+                df[col] = df[col].astype(float)
+
+        return df
     except ResourceNotFound as e:
         raise FileNotFoundError(f"File not found: {uri}") from e
 
-    return pd.DataFrame.from_dict(data_dict, orient="index").rename(index=int)
-
 
 def _calculate_distances_subset(
     napistu_graph: NapistuGraph,

napistu/sbml_dfs_core.py

@@ -32,7 +32,6 @@ from napistu.constants import SBOTERM_NAMES
 from napistu.constants import SBO_ROLES_DEFS
 from napistu.constants import ENTITIES_W_DATA
 from napistu.constants import ENTITIES_TO_ENTITY_DATA
-from napistu.constants import CHARACTERISTIC_COMPLEX_ONTOLOGIES
 from napistu.ingestion.constants import GENERIC_COMPARTMENT
 from napistu.ingestion.constants import COMPARTMENT_ALIASES
 from napistu.ingestion.constants import COMPARTMENTS_GO_TERMS
@@ -1471,12 +1470,6 @@ def filter_to_characteristic_species_ids(
     # add components within modestly sized protein complexes
     # look at HAS_PART IDs
     bqb_has_parts_species = species_ids[species_ids[IDENTIFIERS.BQB] == BQB.HAS_PART]
-    # filter to genes
-    bqb_has_parts_species = bqb_has_parts_species[
-        bqb_has_parts_species[IDENTIFIERS.ONTOLOGY].isin(
-            CHARACTERISTIC_COMPLEX_ONTOLOGIES
-        )
-    ]
 
     # number of species in a complex
     n_species_components = bqb_has_parts_species.value_counts(
@@ -1488,38 +1481,10 @@ def filter_to_characteristic_species_ids(
         ].index.get_level_values(SBML_DFS.S_ID)
     )
 
-    # number of complexes a species is part of
-    n_complexes_involvedin = bqb_has_parts_species.value_counts(
-        [IDENTIFIERS.ONTOLOGY, IDENTIFIERS.IDENTIFIER]
-    )
-    promiscuous_component_identifiers_index = n_complexes_involvedin[
-        n_complexes_involvedin > max_promiscuity
-    ].index
-    promiscuous_component_identifiers = pd.Series(
-        data=[True] * len(promiscuous_component_identifiers_index),
-        index=promiscuous_component_identifiers_index,
-        name="is_shared_component",
-        dtype=bool,
-    )
-
-    if len(promiscuous_component_identifiers) == 0:
-        # no complexes to filter
-        return species_ids
-
-    filtered_bqb_has_parts = bqb_has_parts_species.merge(
-        promiscuous_component_identifiers,
-        left_on=[IDENTIFIERS.ONTOLOGY, IDENTIFIERS.IDENTIFIER],
-        right_index=True,
-        how="left",
+    filtered_bqb_has_parts = _filter_promiscuous_components(
+        bqb_has_parts_species, max_promiscuity
     )
 
-    filtered_bqb_has_parts["is_shared_component"] = filtered_bqb_has_parts[
-        "is_shared_component"
-    ].fillna(False)
-    # drop identifiers shared as components across many species
-    filtered_bqb_has_parts = filtered_bqb_has_parts[
-        ~filtered_bqb_has_parts["is_shared_component"]
-    ].drop(["is_shared_component"], axis=1)
     # drop species parts if there are many components
     filtered_bqb_has_parts = filtered_bqb_has_parts[
         ~filtered_bqb_has_parts[SBML_DFS.S_ID].isin(big_complex_sids)
@@ -2595,3 +2560,42 @@ def _perform_sbml_dfs_table_validation(
     # check for empty table
     if table_data.shape[0] == 0:
         raise ValueError(f"{table_name} contained no entries")
+
+
+def _filter_promiscuous_components(
+    bqb_has_parts_species: pd.DataFrame, max_promiscuity: int
+) -> pd.DataFrame:
+
+    # number of complexes a species is part of
+    n_complexes_involvedin = bqb_has_parts_species.value_counts(
+        [IDENTIFIERS.ONTOLOGY, IDENTIFIERS.IDENTIFIER]
+    )
+    promiscuous_component_identifiers_index = n_complexes_involvedin[
+        n_complexes_involvedin > max_promiscuity
+    ].index
+    promiscuous_component_identifiers = pd.Series(
+        data=[True] * len(promiscuous_component_identifiers_index),
+        index=promiscuous_component_identifiers_index,
+        name="is_shared_component",
+        dtype=bool,
+    )
+
+    if len(promiscuous_component_identifiers) == 0:
+        return bqb_has_parts_species
+
+    filtered_bqb_has_parts = bqb_has_parts_species.merge(
+        promiscuous_component_identifiers,
+        left_on=[IDENTIFIERS.ONTOLOGY, IDENTIFIERS.IDENTIFIER],
+        right_index=True,
+        how="left",
+    )
+
+    filtered_bqb_has_parts["is_shared_component"] = (
+        filtered_bqb_has_parts["is_shared_component"].astype("boolean").fillna(False)
+    )
+    # drop identifiers shared as components across many species
+    filtered_bqb_has_parts = filtered_bqb_has_parts[
+        ~filtered_bqb_has_parts["is_shared_component"]
+    ].drop(["is_shared_component"], axis=1)
+
+    return filtered_bqb_has_parts

{napistu-0.3.3.dist-info → napistu-0.3.4.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: napistu
-Version: 0.3.3
+Version: 0.3.4
 Summary: Connecting high-dimensional data to curated pathways
 Home-page: https://github.com/napistu/napistu-py
 Author: Sean Hackett
@@ -19,7 +19,7 @@ Requires-Dist: Jinja2
 Requires-Dist: PyYAML<7.0.0,>=6.0.0
 Requires-Dist: click<9.0.0,>=8.0.0
 Requires-Dist: click-logging
-Requires-Dist: fs<3.0.0,>=2.4.0
+Requires-Dist: fs<3.0.0,>=2.4.16
 Requires-Dist: fs-gcsfs<2.0.0,>=1.5.0
 Requires-Dist: igraph
 Requires-Dist: matplotlib<4.0.0,>=3.5.0

{napistu-0.3.3.dist-info → napistu-0.3.4.dist-info}/RECORD

@@ -1,10 +1,10 @@
 napistu/__init__.py,sha256=dFXAhIqlTLJMwowS4BUDT08-Vy3Q0u1L0CMCErSZT1Y,239
 napistu/__main__.py,sha256=PbzIsFAoFHNQuSyi-ql-D7tQLEOuqgmTcgk0PY-OGeU,28636
 napistu/consensus.py,sha256=UbKKSLP1O46e3Rk8d_aqNlhRHeR3sZRztAgIm7-XK6Y,69960
-napistu/constants.py,sha256=M-zGc85bo1DDRe7uvyeEMUoD9Qf59Qz53nx4R6PwHvk,12483
+napistu/constants.py,sha256=10SuKl19koWvCaeM2k-5GDQxvJpKY3GaGFY_4VZivXw,12356
 napistu/identifiers.py,sha256=wsVriQdvPllA5uvh5CiREklA2tYW2MIB14dV7CPaMVU,34003
 napistu/indices.py,sha256=E_djN1XWc6l1lrFw_QnQXfZTKYTaUv8-jFPP7cHkY5A,9780
-napistu/sbml_dfs_core.py,sha256=TUPp2nzaxRWkHKsXrbFzgp0_p5CzEGAmA5cg3dOUm84,91794
+napistu/sbml_dfs_core.py,sha256=w4hoggMAXJ4Np45_2j-l92vOZg134eYa5Sg7SIdCaFo,91804
 napistu/sbml_dfs_utils.py,sha256=LJo6WWTrmnE58ZLDuibeeHk88uCdfunWdja7XxdZpps,11525
 napistu/source.py,sha256=9uUJrkY4jHaKlzz5nNcQQ8wUAep2pfqhlHxHw1hmEkI,13648
 napistu/utils.py,sha256=TcholWrFbRSu_sn9ODMA8y2YyAhekEKZjwf4S0WQNzI,33241
@@ -67,7 +67,7 @@ napistu/network/net_create.py,sha256=2N5ocGmibdBxIUVtv3H36iFWwkbys9ECCERFRlByhLc
 napistu/network/net_propagation.py,sha256=89ZR4p2mGpkCCIemofZ53XbUjQsuNABxIc6UmF8A5n8,4935
 napistu/network/ng_utils.py,sha256=ijWDa5MTuULJpdV6dcVFGmLmtB_xy87jaUG7F5nvC_k,15240
 napistu/network/paths.py,sha256=S4ZaV0yVmI-o8sXfom5eXA3yy2IEbleYUyXEvnmVw98,17468
-napistu/network/precompute.py,sha256=xDIHWxGWwDyEw1sF1bQKHVbunI8qmeJvo3Iv7wADUys,8960
+napistu/network/precompute.py,sha256=_TyztdHucczZg1JacWuXfNp5NGRKBFMGfp8Imx7OBMM,9118
 napistu/ontologies/__init__.py,sha256=dFXAhIqlTLJMwowS4BUDT08-Vy3Q0u1L0CMCErSZT1Y,239
 napistu/ontologies/constants.py,sha256=GyOFvezSxDK1VigATcruTKtNhjcYaid1ggulEf_HEtQ,4345
 napistu/ontologies/dogma.py,sha256=jGZS-J3d29AoUOow-HVjfVZQJ87lnqO5L1aozieN1ec,8825
@@ -81,7 +81,7 @@ napistu/rpy2/rids.py,sha256=AfXLTfTdonfspgAHYO0Ph7jSUWv8YuyT8x3fyLfAqc8,3413
 napistu/scverse/__init__.py,sha256=Lgxr3iMQAkTzXE9BNz93CndNP5djzerLvmHM-D0PU3I,357
 napistu/scverse/constants.py,sha256=0iAkhyJUIeFGHdLLU3fCaEU1O3Oix4qAsxr3CxGTjVs,653
 napistu/scverse/loading.py,sha256=jqiE71XB-wdV50GyZrauFNY0Lai4bX9Fm2Gv80VR8t8,27016
-napistu-0.3.3.dist-info/licenses/LICENSE,sha256=kW8wVT__JWoHjl2BbbJDAZInWa9AxzJeR_uv6-i5x1g,1063
+napistu-0.3.4.dist-info/licenses/LICENSE,sha256=kW8wVT__JWoHjl2BbbJDAZInWa9AxzJeR_uv6-i5x1g,1063
 tests/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 tests/conftest.py,sha256=XVkd0tQywhnf2cgab7fIjBo3NlaTVX3cO8HaRS2jIwM,3190
 tests/test_consensus.py,sha256=3dJvvPsPG7bHbw_FY4Pm647N_Gt_Ud9157OKYfPCUd4,9502
@@ -108,7 +108,7 @@ tests/test_network_net_create.py,sha256=VNFZTwQawAZQPDnVk_qFevgZErx5KyQZ24bMoZF4
 tests/test_network_net_propagation.py,sha256=9pKkUdduWejH4iKNCJXKFzAkdNpCfrMbiUWySgI_LH4,3244
 tests/test_network_ng_utils.py,sha256=CwDw4MKTPhVZXz2HA2XU2QjjBv8CXc1_yQ0drvkBkFw,724
 tests/test_network_paths.py,sha256=TWZnxY5bF3m6gahcxcYJGrBIawh2-_vUcec1LyPmXV8,1686
-tests/test_network_precompute.py,sha256=W1tuHM-dd90nk0vUUNP_xZ7EhCKSjigI5ndm8oq8l0c,8869
+tests/test_network_precompute.py,sha256=xMGmZI9DxcWhJxuP7GCZEqtmcOvDRNK2LSia0x94v0U,9018
 tests/test_ontologies_genodexito.py,sha256=hBlunyEPiKskqagjWKW5Z6DJwKvpueYHJLwbfyeeAdo,2256
 tests/test_ontologies_mygene.py,sha256=BuBLm8VatzpK39-Ew_fFTK9ueLE4eqmKIDS5UKE59n8,1541
 tests/test_ontologies_renaming.py,sha256=k7bQzP24zG7W3fpULwk1me2sOWEWlxylr4Mhx1_gJJY,3740
@@ -116,8 +116,8 @@ tests/test_pathwayannot.py,sha256=bceosccNy9tgxQei_7j7ATBSSvBSxOngJvK-mAzR_K0,33
 tests/test_rpy2_callr.py,sha256=UVzXMvYN3wcc-ikDIjH2sA4BqkbwiNbMm561BcbnbD4,2936
 tests/test_rpy2_init.py,sha256=APrNt9GEQV9va3vU5k250TxFplAoWFc-FJRFhM2GcDk,5927
 tests/test_sbml.py,sha256=f25zj1NogYrmLluvBDboLameTuCiQ309433Qn3iPvhg,1483
-tests/test_sbml_dfs_core.py,sha256=z2dYl5-3ZvIsEeK_sHxm8VtWSdL81Eljz_9aeedlM6U,16806
-tests/test_sbml_dfs_utils.py,sha256=onFWdhrTix30XR1-CMrMXld37BYxEGi6TZrweugLDzI,505
+tests/test_sbml_dfs_core.py,sha256=tFaLMMuVjTLuhL-wimvcBbodEp59dhyHvXZ-IlUGGeU,19222
+tests/test_sbml_dfs_utils.py,sha256=5lNzZ1NLOnFb_sZ0YWTgLzXy28yGNCtS_H8Q-W-T6Bw,2022
 tests/test_sbo.py,sha256=x_PENFaXYsrZIzOZu9cj_Wrej7i7SNGxgBYYvcigLs0,308
 tests/test_scverse_loading.py,sha256=bnU1lQSYYWhOAs0IIBoi4ZohqPokDQJ0n_rtkAfEyMU,29948
 tests/test_set_coverage.py,sha256=J-6m6LuOjcQa9pxRuWglSfJk4Ltm7kt_eOrn_Q-7P6Q,1604
@@ -126,8 +126,8 @@ tests/test_uncompartmentalize.py,sha256=nAk5kfAVLU9a2VWe2x2HYVcKqj-EnwmwddERIPRa
 tests/test_utils.py,sha256=JRJFmjDNZpjG59a-73JkTyGqa_a7Z8d0fE2cZt0CRII,22580
 tests/utils.py,sha256=SoWQ_5roJteFGcMaOeEiQ5ucwq3Z2Fa3AAs9iXHTsJY,749
 tests/test_data/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-napistu-0.3.3.dist-info/METADATA,sha256=Y5HCnBOuVO0Rvc1S-P3llVgWJSeBR1hes6UTt0cyhB4,3413
-napistu-0.3.3.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-napistu-0.3.3.dist-info/entry_points.txt,sha256=_QnaPOvJNA3IltxmZgWIiBoen-L1bPYX18YQfC7oJgQ,41
-napistu-0.3.3.dist-info/top_level.txt,sha256=Gpvk0a_PjrtqhYcQ9IDr3zR5LqpZ-uIHidQMIpjlvhY,14
-napistu-0.3.3.dist-info/RECORD,,
+napistu-0.3.4.dist-info/METADATA,sha256=u0M0PcjZJds7ds-cV2MYar8maae9_ld_9FO--0G3xwA,3414
+napistu-0.3.4.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+napistu-0.3.4.dist-info/entry_points.txt,sha256=_QnaPOvJNA3IltxmZgWIiBoen-L1bPYX18YQfC7oJgQ,41
+napistu-0.3.4.dist-info/top_level.txt,sha256=Gpvk0a_PjrtqhYcQ9IDr3zR5LqpZ-uIHidQMIpjlvhY,14
+napistu-0.3.4.dist-info/RECORD,,

tests/test_network_precompute.py

@@ -179,8 +179,11 @@ def test_precomputed_distances_neighborhoods():
                 right_on=join_key,
                 how="outer",
             )
-            .fillna(False)
         )
+        for col in ["in_precompute", "in_otf"]:
+            neighbor_comparison[col] = (
+                neighbor_comparison[col].astype("boolean").fillna(False)
+            )
         comparison_l.append(neighbor_comparison.assign(focal_sc_id=key))
 
     comparison_df = pd.concat(comparison_l)

tests/test_sbml_dfs_core.py

@@ -10,7 +10,14 @@ from napistu.ingestion import sbml
 from napistu.modify import pathwayannot
 
 from napistu import identifiers as napistu_identifiers
-from napistu.constants import SBML_DFS, SBOTERM_NAMES
+from napistu.constants import (
+    SBML_DFS,
+    SBOTERM_NAMES,
+    BQB_DEFINING_ATTRS,
+    BQB_DEFINING_ATTRS_LOOSE,
+    BQB,
+    IDENTIFIERS,
+)
 from napistu.sbml_dfs_core import SBML_dfs
 
 
@@ -493,3 +500,84 @@ def test_remove_entity_data_nonexistent(sbml_dfs_w_data, caplog):
 
     # Validate the model is still valid
     sbml_dfs_w_data.validate()
+
+
+def test_filter_to_characteristic_species_ids():
+
+    species_ids_dict = {
+        SBML_DFS.S_ID: ["large_complex"] * 6
+        + ["small_complex"] * 2
+        + ["proteinA", "proteinB"]
+        + ["proteinC"] * 3
+        + [
+            "promiscuous_complexA",
+            "promiscuous_complexB",
+            "promiscuous_complexC",
+            "promiscuous_complexD",
+            "promiscuous_complexE",
+        ],
+        IDENTIFIERS.ONTOLOGY: ["complexportal"]
+        + ["HGNC"] * 7
+        + ["GO"] * 2
+        + ["ENSG", "ENSP", "pubmed"]
+        + ["HGNC"] * 5,
+        IDENTIFIERS.IDENTIFIER: [
+            "CPX-BIG",
+            "mem1",
+            "mem2",
+            "mem3",
+            "mem4",
+            "mem5",
+            "part1",
+            "part2",
+            "GO:1",
+            "GO:2",
+            "dna_seq",
+            "protein_seq",
+            "my_cool_pub",
+        ]
+        + ["promiscuous_complex"] * 5,
+        IDENTIFIERS.BQB: [BQB.IS]
+        + [BQB.HAS_PART] * 7
+        + [BQB.IS] * 2
+        + [
+            # these are retained if BQB_DEFINING_ATTRS_LOOSE is used
+            BQB.ENCODES,
+            BQB.IS_ENCODED_BY,
+            # this should always be removed
+            BQB.IS_DESCRIBED_BY,
+        ]
+        + [BQB.HAS_PART] * 5,
+    }
+
+    species_ids = pd.DataFrame(species_ids_dict)
+
+    characteristic_ids_narrow = sbml_dfs_core.filter_to_characteristic_species_ids(
+        species_ids,
+        defining_biological_qualifiers=BQB_DEFINING_ATTRS,
+        max_complex_size=4,
+        max_promiscuity=4,
+    )
+
+    EXPECTED_IDS = ["CPX-BIG", "GO:1", "GO:2", "part1", "part2"]
+    assert characteristic_ids_narrow[IDENTIFIERS.IDENTIFIER].tolist() == EXPECTED_IDS
+
+    characteristic_ids_loose = sbml_dfs_core.filter_to_characteristic_species_ids(
+        species_ids,
+        # include encodes and is_encoded_by as equivalent to is
+        defining_biological_qualifiers=BQB_DEFINING_ATTRS_LOOSE,
+        max_complex_size=4,
+        # expand promiscuity to default value
+        max_promiscuity=20,
+    )
+
+    EXPECTED_IDS = [
+        "CPX-BIG",
+        "GO:1",
+        "GO:2",
+        "dna_seq",
+        "protein_seq",
+        "part1",
+        "part2",
+    ] + ["promiscuous_complex"] * 5
+    assert characteristic_ids_loose[IDENTIFIERS.IDENTIFIER].tolist() == EXPECTED_IDS

tests/test_sbml_dfs_utils.py

@@ -1,6 +1,9 @@
 from __future__ import annotations
 
+import pandas as pd
+
 from napistu import sbml_dfs_utils
+from napistu.constants import BQB, BQB_DEFINING_ATTRS, BQB_DEFINING_ATTRS_LOOSE
 
 
 def test_id_formatter():
@@ -14,9 +17,47 @@ def test_id_formatter():
     assert list(input_vals) == inv_ids
 
 
-################################################
-# __main__
-################################################
-
-if __name__ == "__main__":
-    test_id_formatter()
+def test_get_characteristic_species_ids():
+    """
+    Test get_characteristic_species_ids function with both dogmatic and non-dogmatic cases.
+    """
+    # Create mock species identifiers data
+    mock_species_ids = pd.DataFrame(
+        {
+            "s_id": ["s1", "s2", "s3", "s4", "s5"],
+            "identifier": ["P12345", "CHEBI:15377", "GO:12345", "P67890", "P67890"],
+            "ontology": ["uniprot", "chebi", "go", "uniprot", "chebi"],
+            "bqb": [
+                "BQB_IS",
+                "BQB_IS",
+                "BQB_HAS_PART",
+                "BQB_HAS_VERSION",
+                "BQB_ENCODES",
+            ],
+        }
+    )
+
+    # Create mock SBML_dfs object
+    class MockSBML_dfs:
+        def get_identifiers(self, entity_type):
+            return mock_species_ids
+
+    mock_sbml = MockSBML_dfs()
+
+    # Test dogmatic case (default)
+    expected_bqbs = BQB_DEFINING_ATTRS + [BQB.HAS_PART]  # noqa: F841
+    dogmatic_result = sbml_dfs_utils.get_characteristic_species_ids(mock_sbml)
+    expected_dogmatic = mock_species_ids.query("bqb in @expected_bqbs")
+
+    pd.testing.assert_frame_equal(dogmatic_result, expected_dogmatic, check_like=True)
+
+    # Test non-dogmatic case
+    expected_bqbs = BQB_DEFINING_ATTRS_LOOSE + [BQB.HAS_PART]  # noqa: F841
+    non_dogmatic_result = sbml_dfs_utils.get_characteristic_species_ids(
+        mock_sbml, dogmatic=False
+    )
+    expected_non_dogmatic = mock_species_ids.query("bqb in @expected_bqbs")
+
+    pd.testing.assert_frame_equal(
+        non_dogmatic_result, expected_non_dogmatic, check_like=True
+    )