napistu 0.3.4__py3-none-any.whl → 0.3.5__py3-none-any.whl

napistu/source.py

@@ -223,7 +223,7 @@ def greedy_set_coverge_of_sources(
     Greedy Set Coverage of Sources
 
     Apply the greedy set coverge algorithm to find the minimal set of
-      sources which cover all entries
+    sources which cover all entries
 
     Parameters:
     source_df: pd.DataFrame

{napistu-0.3.4.dist-info → napistu-0.3.5.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: napistu
-Version: 0.3.4
+Version: 0.3.5
 Summary: Connecting high-dimensional data to curated pathways
 Home-page: https://github.com/napistu/napistu-py
 Author: Sean Hackett

{napistu-0.3.4.dist-info → napistu-0.3.5.dist-info}/RECORD

@@ -1,12 +1,12 @@
 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=10SuKl19koWvCaeM2k-5GDQxvJpKY3GaGFY_4VZivXw,12356
+napistu/constants.py,sha256=XptXQa3OKmH5hPb6PK_3cLSNcETj6jqejJYY60GV9Zc,12384
 napistu/identifiers.py,sha256=wsVriQdvPllA5uvh5CiREklA2tYW2MIB14dV7CPaMVU,34003
 napistu/indices.py,sha256=E_djN1XWc6l1lrFw_QnQXfZTKYTaUv8-jFPP7cHkY5A,9780
-napistu/sbml_dfs_core.py,sha256=w4hoggMAXJ4Np45_2j-l92vOZg134eYa5Sg7SIdCaFo,91804
+napistu/sbml_dfs_core.py,sha256=us0Yz67ilav5dc2LY2TtXypaSdAQ7Kk55ZyGuyougzo,96605
 napistu/sbml_dfs_utils.py,sha256=LJo6WWTrmnE58ZLDuibeeHk88uCdfunWdja7XxdZpps,11525
-napistu/source.py,sha256=9uUJrkY4jHaKlzz5nNcQQ8wUAep2pfqhlHxHw1hmEkI,13648
+napistu/source.py,sha256=UGpN70bqbC9gnKmM0ivSdQYim9hfzgABeXoQKzRr9oU,13646
 napistu/utils.py,sha256=TcholWrFbRSu_sn9ODMA8y2YyAhekEKZjwf4S0WQNzI,33241
 napistu/context/__init__.py,sha256=LQBEqipcHKK0E5UlDEg1ct-ymCs93IlUrUaH8BCevf0,242
 napistu/context/discretize.py,sha256=Qq7zg46F_I-PvQIT2_pEDQV7YEtUQCxKoRvT5Gu9QsE,15052
@@ -60,14 +60,14 @@ napistu/modify/uncompartmentalize.py,sha256=U5X4Q7Z-YIkC8_711x3sU21vTVdv9rKfauwz
 napistu/network/__init__.py,sha256=dFXAhIqlTLJMwowS4BUDT08-Vy3Q0u1L0CMCErSZT1Y,239
 napistu/network/constants.py,sha256=fC1njZDu6in1JiaZ1-T1_fhmmkcc2HKSUUomDVyQ7Dw,5789
 napistu/network/data_handling.py,sha256=mxplWwyXNrjZRN-jjWWUI9IZOqX69k8qSMDIrL9h0Og,14736
-napistu/network/ig_utils.py,sha256=87vFuyLksYhfGoKBvjYeQt1yM_lg83m-14OaGbW64Wg,10478
+napistu/network/ig_utils.py,sha256=JSlf_sZtw3DiiSIiYJ2YqJFEP4hVJMwNRox2qYTA4zY,11470
 napistu/network/napistu_graph_core.py,sha256=2NbjiLcDcFWFyX1MuN17pobPDgoQFtcYWOwuPSFTT4g,10429
 napistu/network/neighborhoods.py,sha256=Q9HWUvf_J4a_4RQDKd7ywEy4cp3Wq2OPOfVsotDbEe0,56098
 napistu/network/net_create.py,sha256=2N5ocGmibdBxIUVtv3H36iFWwkbys9ECCERFRlByhLc,69407
 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=_TyztdHucczZg1JacWuXfNp5NGRKBFMGfp8Imx7OBMM,9118
+napistu/network/precompute.py,sha256=pIXCCE6Mf6HY8o-fiwUaOxvQ_9_mevK0vaC8fND4RZk,9141
 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-0.3.4.dist-info/licenses/LICENSE,sha256=kW8wVT__JWoHjl2BbbJDAZInWa9AxzJeR_uv6-i5x1g,1063
+napistu-0.3.5.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
@@ -102,7 +102,7 @@ tests/test_mcp_config.py,sha256=GTu9vywqAHTYkolywdYS_BEIW3gBzs4A4qcneMSPpRk,7007
 tests/test_mcp_documentation_utils.py,sha256=OW0N2N_2IOktbYTcCWhhWz4bANi8IB60l1q3DJi8Ra4,810
 tests/test_mcp_server.py,sha256=bP3PWVQsEfX6-lAgXKP32njdg__o65n2WuLvkxTTHkQ,11215
 tests/test_network_data_handling.py,sha256=oBSZuB3IRG9bwmD6n8FY-UZLe2UqGzXpNSxVtkHRSvE,12605
-tests/test_network_ig_utils.py,sha256=uojDLtL7oT9S9NJrXL8kBEHHFq5DB1GnJQT0v-gHEBE,632
+tests/test_network_ig_utils.py,sha256=Buoh570mNm5pcac3Hf6f3pevCjWfBwPfKuD8IkDLg58,2120
 tests/test_network_neighborhoods.py,sha256=8BV17m5X1OUd5FwasTTYUOkNYUHDPUkxOKH_VZCsyBE,631
 tests/test_network_net_create.py,sha256=VNFZTwQawAZQPDnVk_qFevgZErx5KyQZ24bMoZF4T4w,16462
 tests/test_network_net_propagation.py,sha256=9pKkUdduWejH4iKNCJXKFzAkdNpCfrMbiUWySgI_LH4,3244
@@ -116,7 +116,7 @@ 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=tFaLMMuVjTLuhL-wimvcBbodEp59dhyHvXZ-IlUGGeU,19222
+tests/test_sbml_dfs_core.py,sha256=MtmQp9EZD4OFmk-5tWUSb9hUjcGfRKTFbSBymiE_Qzo,23628
 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
@@ -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-0.3.4.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,,
+napistu-0.3.5.dist-info/METADATA,sha256=Dla6z2cQaQt3eR7HeUfSNOcqOn4uWY3vYtYp3gKEBl4,3414
+napistu-0.3.5.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+napistu-0.3.5.dist-info/entry_points.txt,sha256=_QnaPOvJNA3IltxmZgWIiBoen-L1bPYX18YQfC7oJgQ,41
+napistu-0.3.5.dist-info/top_level.txt,sha256=Gpvk0a_PjrtqhYcQ9IDr3zR5LqpZ-uIHidQMIpjlvhY,14
+napistu-0.3.5.dist-info/RECORD,,

tests/test_network_ig_utils.py

@@ -6,6 +6,15 @@ from napistu.network import ig_utils
 from napistu.network import net_create
 
 
+@pytest.fixture
+def multi_component_graph() -> ig_utils.ig.Graph:
+    """Creates a graph with multiple disconnected components of different sizes."""
+    g1 = ig_utils.ig.Graph.Ring(5)  # 5 vertices, 5 edges
+    g2 = ig_utils.ig.Graph.Tree(3, 2)  # 3 vertices, 2 edges
+    g3 = ig_utils.ig.Graph.Full(2)  # 2 vertices, 1 edge
+    return ig_utils.ig.disjoint_union([g1, g2, g3])
+
+
 def test_validate_graph_attributes(sbml_dfs):
 
     napistu_graph = net_create.process_napistu_graph(
@@ -21,3 +30,30 @@ def test_validate_graph_attributes(sbml_dfs):
     assert ig_utils.validate_vertex_attributes(napistu_graph, "node_type") is None
     with pytest.raises(ValueError):
         ig_utils.validate_vertex_attributes(napistu_graph, "baz")
+
+
+def test_filter_to_largest_subgraph(multi_component_graph):
+    """Tests that the function returns only the single largest component."""
+    largest = ig_utils.filter_to_largest_subgraph(multi_component_graph)
+    assert isinstance(largest, ig_utils.ig.Graph)
+    assert largest.vcount() == 5
+    assert largest.ecount() == 5
+
+
+def test_filter_to_largest_subgraphs(multi_component_graph):
+    """Tests that the function returns the top K largest components."""
+    # Test getting the top 2
+    top_2 = ig_utils.filter_to_largest_subgraphs(multi_component_graph, top_k=2)
+    assert isinstance(top_2, list)
+    assert len(top_2) == 2
+    assert all(isinstance(g, ig_utils.ig.Graph) for g in top_2)
+    assert [g.vcount() for g in top_2] == [5, 3]
+
+    # Test getting more than the total number of components
+    top_5 = ig_utils.filter_to_largest_subgraphs(multi_component_graph, top_k=5)
+    assert len(top_5) == 3
+    assert [g.vcount() for g in top_5] == [5, 3, 2]
+
+    # Test invalid top_k
+    with pytest.raises(ValueError):
+        ig_utils.filter_to_largest_subgraphs(multi_component_graph, top_k=0)

tests/test_sbml_dfs_core.py

@@ -6,8 +6,10 @@ import numpy as np
 import pandas as pd
 import pytest
 from napistu import sbml_dfs_core
+from napistu.source import Source
 from napistu.ingestion import sbml
 from napistu.modify import pathwayannot
+from napistu.sbml_dfs_utils import _stub_ids
 
 from napistu import identifiers as napistu_identifiers
 from napistu.constants import (
@@ -21,6 +23,66 @@ from napistu.constants import (
 from napistu.sbml_dfs_core import SBML_dfs
 
 
+@pytest.fixture
+def test_data():
+    """Create test data for SBML integration tests."""
+
+    # Test compartments
+    compartments_df = pd.DataFrame(
+        [
+            {"c_name": "nucleus", "c_Identifiers": _stub_ids([])},
+            {"c_name": "cytoplasm", "c_Identifiers": _stub_ids([])},
+        ]
+    )
+
+    # Test species with extra data
+    species_df = pd.DataFrame(
+        [
+            {
+                "s_name": "TP53",
+                "s_Identifiers": _stub_ids([]),
+                "gene_type": "tumor_suppressor",
+            },
+            {"s_name": "MDM2", "s_Identifiers": _stub_ids([]), "gene_type": "oncogene"},
+            {
+                "s_name": "CDKN1A",
+                "s_Identifiers": _stub_ids([]),
+                "gene_type": "cell_cycle",
+            },
+        ]
+    )
+
+    # Test interactions with extra data
+    interaction_edgelist = pd.DataFrame(
+        [
+            {
+                "upstream_name": "TP53",
+                "downstream_name": "CDKN1A",
+                "upstream_compartment": "nucleus",
+                "downstream_compartment": "nucleus",
+                "r_name": "TP53_activates_CDKN1A",
+                "sbo_term": "SBO:0000459",
+                "r_Identifiers": _stub_ids([]),
+                "r_isreversible": False,
+                "confidence": 0.95,
+            },
+            {
+                "upstream_name": "MDM2",
+                "downstream_name": "TP53",
+                "upstream_compartment": "cytoplasm",
+                "downstream_compartment": "nucleus",
+                "r_name": "MDM2_inhibits_TP53",
+                "sbo_term": "SBO:0000020",
+                "r_Identifiers": _stub_ids([]),
+                "r_isreversible": False,
+                "confidence": 0.87,
+            },
+        ]
+    )
+
+    return [interaction_edgelist, species_df, compartments_df, Source(init=True)]
+
+
 def test_drop_cofactors(sbml_dfs):
     starting_rscs = sbml_dfs.reaction_species.shape[0]
     reduced_dfs = pathwayannot.drop_cofactors(sbml_dfs)
@@ -581,3 +643,72 @@ def test_filter_to_characteristic_species_ids():
         "part2",
     ] + ["promiscuous_complex"] * 5
     assert characteristic_ids_loose[IDENTIFIERS.IDENTIFIER].tolist() == EXPECTED_IDS
+
+
+def test_sbml_basic_functionality(test_data):
+    """Test basic SBML_dfs creation from edgelist."""
+    interaction_edgelist, species_df, compartments_df, interaction_source = test_data
+
+    result = sbml_dfs_core.sbml_dfs_from_edgelist(
+        interaction_edgelist, species_df, compartments_df, interaction_source
+    )
+
+    assert isinstance(result, SBML_dfs)
+    assert len(result.species) == 3
+    assert len(result.compartments) == 2
+    assert len(result.reactions) == 2
+    assert (
+        len(result.compartmentalized_species) == 3
+    )  # TP53[nucleus], CDKN1A[nucleus], MDM2[cytoplasm]
+    assert len(result.reaction_species) == 4  # 2 reactions * 2 species each
+
+
+def test_sbml_extra_data_preservation(test_data):
+    """Test that extra columns are preserved when requested."""
+    interaction_edgelist, species_df, compartments_df, interaction_source = test_data
+
+    result = sbml_dfs_core.sbml_dfs_from_edgelist(
+        interaction_edgelist,
+        species_df,
+        compartments_df,
+        interaction_source,
+        keep_species_data=True,
+        keep_reactions_data="experiment",
+    )
+
+    assert hasattr(result, "species_data")
+    assert hasattr(result, "reactions_data")
+    assert "gene_type" in result.species_data["source"].columns
+    assert "confidence" in result.reactions_data["experiment"].columns
+
+
+def test_sbml_compartmentalized_naming(test_data):
+    """Test compartmentalized species naming convention."""
+    interaction_edgelist, species_df, compartments_df, interaction_source = test_data
+
+    result = sbml_dfs_core.sbml_dfs_from_edgelist(
+        interaction_edgelist, species_df, compartments_df, interaction_source
+    )
+
+    comp_names = result.compartmentalized_species["sc_name"].tolist()
+    assert "TP53 [nucleus]" in comp_names
+    assert "MDM2 [cytoplasm]" in comp_names
+    assert "CDKN1A [nucleus]" in comp_names
+
+
+def test_sbml_custom_stoichiometry(test_data):
+    """Test custom stoichiometry parameters."""
+    interaction_edgelist, species_df, compartments_df, interaction_source = test_data
+
+    result = sbml_dfs_core.sbml_dfs_from_edgelist(
+        interaction_edgelist,
+        species_df,
+        compartments_df,
+        interaction_source,
+        upstream_stoichiometry=2,
+        downstream_stoichiometry=3,
+    )
+
+    stoichiometries = result.reaction_species["stoichiometry"].unique()
+    assert 2 in stoichiometries  # upstream
+    assert 3 in stoichiometries  # downstream