napistu 0.3.6__py3-none-any.whl → 0.3.7__py3-none-any.whl

{napistu-0.3.6.dist-info → napistu-0.3.7.dist-info}/RECORD

@@ -1,13 +1,13 @@
 napistu/__init__.py,sha256=dFXAhIqlTLJMwowS4BUDT08-Vy3Q0u1L0CMCErSZT1Y,239
-napistu/__main__.py,sha256=JnPRdK9Revwpi0pouC7ZIZAMEunh9NIFuaq91RlPaR0,28648
-napistu/consensus.py,sha256=jsWpoXOzmNklFKasgOa5NEqbhoZvsgY0rLMFQddi6Vo,69945
-napistu/constants.py,sha256=IhjZZgP0Yb3pPn5mV5SeTWiimRSG2hH02UX_Y6c_aOo,12388
+napistu/__main__.py,sha256=cml91Be1r_eyWeel_KNSWC-42AbMXWsrKZGf4PVgkaE,28997
+napistu/consensus.py,sha256=xWXiqIM6ot-SSPJZXTrVpohbINSCkZXBtRi-5REfk_g,69897
+napistu/constants.py,sha256=dbofeN0HKdmjYluyKuj6nfiL88j69otPhuw2krEhHz8,13240
 napistu/identifiers.py,sha256=e2-nTVzr5AINa0y1ER9218bKXyF2kAeJ9At22S4Z00o,33914
-napistu/indices.py,sha256=E_djN1XWc6l1lrFw_QnQXfZTKYTaUv8-jFPP7cHkY5A,9780
-napistu/sbml_dfs_core.py,sha256=ntZfuKrjf42MV1EXhKUro298a1aSd6t6M-tt141x634,71129
-napistu/sbml_dfs_utils.py,sha256=aXbQIlx7Yv7TH_7YxSuHZLsf6w2UXd_iOzpALKzg608,43506
+napistu/indices.py,sha256=Zjg3gE0JQ3T879lCPazYg-WXVE6hvcAr713ZKpJ32rk,9830
+napistu/sbml_dfs_core.py,sha256=3Z2Kg-aVnZMGK9iK-_vztY2ORgNpta8BUMuWEZg80iE,73125
+napistu/sbml_dfs_utils.py,sha256=M0qNbxWkVnPCeUYTBZAD5i4PgV66qu6JE36Eb1dKaMw,43617
 napistu/source.py,sha256=UGpN70bqbC9gnKmM0ivSdQYim9hfzgABeXoQKzRr9oU,13646
-napistu/utils.py,sha256=TcholWrFbRSu_sn9ODMA8y2YyAhekEKZjwf4S0WQNzI,33241
+napistu/utils.py,sha256=ckYaIYjUOy22A3ojS7wSUabq_A1rJMMOk6QLrcbr3sU,33560
 napistu/context/__init__.py,sha256=LQBEqipcHKK0E5UlDEg1ct-ymCs93IlUrUaH8BCevf0,242
 napistu/context/discretize.py,sha256=Qq7zg46F_I-PvQIT2_pEDQV7YEtUQCxKoRvT5Gu9QsE,15052
 napistu/context/filtering.py,sha256=l1oq-43ysSGqU9VmhTOO_pYT4DSMf20yxvktPC1MI0I,13696
@@ -25,15 +25,15 @@ napistu/ingestion/napistu_edgelist.py,sha256=eVT9M7gmdBuGHcAYlvkD_zzvTtyzXufKWjw
 napistu/ingestion/obo.py,sha256=AQkIPWbjA464Lma0tx91JucWkIwLjC7Jgv5VHGRTDkE,9601
 napistu/ingestion/psi_mi.py,sha256=5eJjm7XWogL9oTyGqR52kntHClLwLsTePKqCvUGyi-w,10111
 napistu/ingestion/reactome.py,sha256=Hn9X-vDp4o_HK-OtaQvel3vJeZ8_TC1-4N2rruK9Oks,7099
-napistu/ingestion/sbml.py,sha256=N7neMwjTEF7OMhAcNvQJ29V_d3PqMLjLOZqvJTlK9q0,24743
-napistu/ingestion/string.py,sha256=eLboW-dkaaiypwW6DxM3P1mGVweM3wqGsJPYKyImMAI,11713
-napistu/ingestion/trrust.py,sha256=ccjZc_eF3PdxxurnukiEo_e0-aKc_3z22NYbaJBtHdY,9774
+napistu/ingestion/sbml.py,sha256=l8Z98yWuOIRGns8G4UNnoQz7v_xmukZb_IZ_5ye34Ko,25296
+napistu/ingestion/string.py,sha256=go1WGTkoLJejX7GQWf9bFeInFGAw4jNSpS2B_Zr5f_s,11364
+napistu/ingestion/trrust.py,sha256=_6hIS48O3tRpMxX-FdIC57ekhCcV7J4owUzoaYnRqZo,9204
 napistu/ingestion/yeast.py,sha256=7XwdkmgOnG1MYauKSk9nSK6fHemDrtXEPcS4ebs1_so,5268
 napistu/matching/__init__.py,sha256=dFXAhIqlTLJMwowS4BUDT08-Vy3Q0u1L0CMCErSZT1Y,239
 napistu/matching/constants.py,sha256=j4XSOE9Bpma9F6apVJ1LijKOUPgRk8Geo_u_rvNtpSU,610
 napistu/matching/interactions.py,sha256=XrzZvH1zgeaZLq3qhpsV0tx4BFgvNvkjM47l8ZUEOH4,18798
 napistu/matching/mount.py,sha256=8JEtiDIy7qdjWyDAs0vuVwEQkpwRf5ah4xMLZ4jKHag,19428
-napistu/matching/species.py,sha256=5-hmH8_UrvDmGfeJ1283trkCtPOC3BEmtYPcMHuZyNY,18893
+napistu/matching/species.py,sha256=U8OfzmDN9dMwemdnzQdV19bWfjY8MLJ9-wf83siK1bM,18888
 napistu/mcp/__init__.py,sha256=EmtcdtYyfhXdxxPB5cY_pshXnFv6XZ5CtRU0JMHn3aQ,2074
 napistu/mcp/__main__.py,sha256=o9C4J3YHkfh_pQi-K9OC5bwFmsNWHuK2l8GL7M90uFc,8057
 napistu/mcp/client.py,sha256=Zyy7unFFq9XPBDrr2Hl7dMVDTGoZbtj_YFuUH18QScs,6350
@@ -71,9 +71,9 @@ napistu/network/precompute.py,sha256=pIXCCE6Mf6HY8o-fiwUaOxvQ_9_mevK0vaC8fND4RZk
 napistu/ontologies/__init__.py,sha256=dFXAhIqlTLJMwowS4BUDT08-Vy3Q0u1L0CMCErSZT1Y,239
 napistu/ontologies/constants.py,sha256=GyOFvezSxDK1VigATcruTKtNhjcYaid1ggulEf_HEtQ,4345
 napistu/ontologies/dogma.py,sha256=VVj6NKBgNym4SdOSu8g22OohALj7cbObhIJmdY2Sfy0,8860
-napistu/ontologies/genodexito.py,sha256=5_gtdVtKHp5z-jtPXkHlZRiTsuHdZeA3TVI9u4SXqrQ,24725
+napistu/ontologies/genodexito.py,sha256=ZZmb7V38BmFjy9VOGdxbD3-BD5tKGl5izr0nwO_eEdA,24967
 napistu/ontologies/mygene.py,sha256=RMFQTWsLkeYxmsOPxxmeIya2phdcUMcF5V2abaS8MVg,11109
-napistu/ontologies/renaming.py,sha256=bL15T0CswjM81NFVIVp-3CEsa1kxIIk2xJ2kE5eTeeg,6817
+napistu/ontologies/renaming.py,sha256=aZR5oxjeZhse026fuvFyQiKM8PVzbBT915J8AfXGv1M,7006
 napistu/rpy2/__init__.py,sha256=8WzSK_tmdcbyMUtb17OmqdQqbisqIBl8OQrDsaFDeX4,8356
 napistu/rpy2/callr.py,sha256=yFCGobZTVgH1vJc5h0njAflvFr6zmCWIP-uuLWnZL-g,3701
 napistu/rpy2/constants.py,sha256=3thZa4UUfpDpXaUzGcqfDEyEIQaf4a_C01-O2pciZ7c,2760
@@ -81,15 +81,15 @@ 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-0.3.6.dist-info/licenses/LICENSE,sha256=kW8wVT__JWoHjl2BbbJDAZInWa9AxzJeR_uv6-i5x1g,1063
+napistu-0.3.7.dist-info/licenses/LICENSE,sha256=kW8wVT__JWoHjl2BbbJDAZInWa9AxzJeR_uv6-i5x1g,1063
 tests/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-tests/conftest.py,sha256=v8ZxJKqglEPlQ5ew3hM5eJQW2N0YhX9dOAaOQqdjyIc,4325
-tests/test_consensus.py,sha256=qnf6Ntc3q7oCji1aisH9Ziy6KbnQCf1REizinR8ier8,12454
+tests/conftest.py,sha256=Tdw9-uYpnV1ZvdO9k9oto-JDEqMOTF05fsVps-EpmCE,6240
+tests/test_consensus.py,sha256=Hzfrgp4SpkRDnEMVMD3f0UInSycndB8kKzC4wDDvRas,15076
 tests/test_constants.py,sha256=gJLDv7QMeeBiiupyMazj6mumk20KWvGMgm2myHMKKfc,531
 tests/test_context_discretize.py,sha256=5Mr9WqwHGYMO37M1TnMmSfC64UZ73mnoCiEM2IQHVDY,1667
 tests/test_context_filtering.py,sha256=5dwC2d-99CpLdnzzTf2NvEzsRuwiIj-YU8NFqwtWp0g,9485
 tests/test_curation.py,sha256=-Q2J0D7qs9PGjHZX-rM4NxRLLdwxoapytSo_98q9ItY,3864
-tests/test_gaps.py,sha256=mGGeyx1vUnmEOF__bsqfCYq9Y8a1P-9mefqna4Qgc_k,4062
+tests/test_gaps.py,sha256=GBRb0E0RUwhXz2PsnfTsGszKDsHHvH-E3x9hUZG1DhM,4550
 tests/test_gcs.py,sha256=p_uQWuY2TcGj3zV3qFC-GXBqj4St8YENR_XRpQ6UH5g,570
 tests/test_identifiers.py,sha256=9QlGCG27zposzEvazEuZqoMausNMLLuUwfA3FuYU1mc,8345
 tests/test_indices.py,sha256=e_8GSNzIT4JHGmelX9PseJzFXTxo-TQAus3r21AUt7I,4547
@@ -104,30 +104,30 @@ tests/test_mcp_server.py,sha256=bP3PWVQsEfX6-lAgXKP32njdg__o65n2WuLvkxTTHkQ,1121
 tests/test_network_data_handling.py,sha256=oBSZuB3IRG9bwmD6n8FY-UZLe2UqGzXpNSxVtkHRSvE,12605
 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_create.py,sha256=LDjkA9boX8kH4wCLOpa0ENwN6JZU2c29w3qpYlhQ6Rs,16456
 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=xMGmZI9DxcWhJxuP7GCZEqtmcOvDRNK2LSia0x94v0U,9018
+tests/test_network_precompute.py,sha256=8HqTSXdxdXuQqNewP3xxsps9UEtw6OVgPN_lUywXiNg,9012
 tests/test_ontologies_genodexito.py,sha256=6fINyUiubHZqu7qxye09DQfJXw28ZMAJc3clPb-cCoY,2298
 tests/test_ontologies_mygene.py,sha256=VkdRcKIWmcG6V-2dpfvsBiOJN5dO-j0RqZNxtJRcyBU,1583
-tests/test_ontologies_renaming.py,sha256=k7bQzP24zG7W3fpULwk1me2sOWEWlxylr4Mhx1_gJJY,3740
+tests/test_ontologies_renaming.py,sha256=pawp3pV1hxW8nskWc4f2YHwMUqTilEEBD2BtpcSay5Q,3839
 tests/test_pathwayannot.py,sha256=bceosccNy9tgxQei_7j7ATBSSvBSxOngJvK-mAzR_K0,3312
 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=Gef-wf0AI7adwS_CBUokiJCw7yyGzInwAUnAj7IRE-E,20311
+tests/test_sbml_dfs_core.py,sha256=CH5OXNSAozWTl6qBvbHfgTG0NcgdlKJ_WcG0lTYBm3k,26217
 tests/test_sbml_dfs_utils.py,sha256=-EAW6N_elEOSQdsdRhnEdDhnZQH_weCGpnVOd2Xaepc,6963
 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
 tests/test_source.py,sha256=hT0IlpexR5zP0OhWl5BBaho9d1aCYQlFZLwRIRRnw_Y,1969
 tests/test_uncompartmentalize.py,sha256=nAk5kfAVLU9a2VWe2x2HYVcKqj-EnwmwddERIPRax8c,1289
-tests/test_utils.py,sha256=JRJFmjDNZpjG59a-73JkTyGqa_a7Z8d0fE2cZt0CRII,22580
+tests/test_utils.py,sha256=ls0zETdSeupuWCsnycWbgBVwLs2aXLgrAO1jyEBrfao,23190
 tests/utils.py,sha256=SoWQ_5roJteFGcMaOeEiQ5ucwq3Z2Fa3AAs9iXHTsJY,749
 tests/test_data/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-napistu-0.3.6.dist-info/METADATA,sha256=vJqqDnZ9MU1mmU_qTFgGnBgaYx4zt-yqg26H6VDkqz0,3414
-napistu-0.3.6.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-napistu-0.3.6.dist-info/entry_points.txt,sha256=_QnaPOvJNA3IltxmZgWIiBoen-L1bPYX18YQfC7oJgQ,41
-napistu-0.3.6.dist-info/top_level.txt,sha256=Gpvk0a_PjrtqhYcQ9IDr3zR5LqpZ-uIHidQMIpjlvhY,14
-napistu-0.3.6.dist-info/RECORD,,
+napistu-0.3.7.dist-info/METADATA,sha256=59xinCTQICD-lrDm7UR5wdnScq6LHsXy553S6vCRk4Q,3414
+napistu-0.3.7.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+napistu-0.3.7.dist-info/entry_points.txt,sha256=_QnaPOvJNA3IltxmZgWIiBoen-L1bPYX18YQfC7oJgQ,41
+napistu-0.3.7.dist-info/top_level.txt,sha256=Gpvk0a_PjrtqhYcQ9IDr3zR5LqpZ-uIHidQMIpjlvhY,14
+napistu-0.3.7.dist-info/RECORD,,

tests/conftest.py

@@ -5,15 +5,19 @@ import os
 import sys
 import threading
 
+import pandas as pd
 import pytest
+from pytest import fixture
+from pytest import skip
 
 from napistu import consensus
 from napistu import indices
-from napistu import sbml_dfs_core
-from napistu.ingestion import sbml
-from napistu.network import net_create
-from pytest import fixture
-from pytest import skip
+from napistu.identifiers import Identifiers
+from napistu.sbml_dfs_core import SBML_dfs
+from napistu.source import Source
+from napistu.ingestion.sbml import SBML
+from napistu.network.net_create import process_napistu_graph
+from napistu.constants import SBML_DFS
 
 
 @fixture
@@ -28,13 +32,13 @@ def sbml_path():
 
 @fixture
 def sbml_model(sbml_path):
-    sbml_model = sbml.SBML(sbml_path)
+    sbml_model = SBML(sbml_path)
     return sbml_model
 
 
 @fixture
 def sbml_dfs(sbml_model):
-    sbml_dfs = sbml_dfs_core.SBML_dfs(sbml_model)
+    sbml_dfs = SBML_dfs(sbml_model)
     return sbml_dfs
 
 
@@ -56,20 +60,73 @@ def sbml_dfs_glucose_metabolism():
     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)
+    sbml_model = SBML(sbml_path)
+    sbml_dfs = SBML_dfs(sbml_model)
 
     return sbml_dfs
 
 
+@pytest.fixture
+def minimal_valid_sbml_dfs():
+    """Create a minimal valid SBML_dfs object for testing."""
+    blank_id = Identifiers([])
+    source = Source(init=True)
+
+    sbml_dict = {
+        SBML_DFS.COMPARTMENTS: pd.DataFrame(
+            {
+                SBML_DFS.C_NAME: ["cytosol"],
+                SBML_DFS.C_IDENTIFIERS: [blank_id],
+                SBML_DFS.C_SOURCE: [source],
+            },
+            index=pd.Index(["C00001"], name=SBML_DFS.C_ID),
+        ),
+        SBML_DFS.SPECIES: pd.DataFrame(
+            {
+                SBML_DFS.S_NAME: ["ATP"],
+                SBML_DFS.S_IDENTIFIERS: [blank_id],
+                SBML_DFS.S_SOURCE: [source],
+            },
+            index=pd.Index(["S00001"], name=SBML_DFS.S_ID),
+        ),
+        SBML_DFS.COMPARTMENTALIZED_SPECIES: pd.DataFrame(
+            {
+                SBML_DFS.SC_NAME: ["ATP [cytosol]"],
+                SBML_DFS.S_ID: ["S00001"],
+                SBML_DFS.C_ID: ["C00001"],
+                SBML_DFS.SC_SOURCE: [source],
+            },
+            index=pd.Index(["SC00001"], name=SBML_DFS.SC_ID),
+        ),
+        SBML_DFS.REACTIONS: pd.DataFrame(
+            {
+                SBML_DFS.R_NAME: ["test_reaction"],
+                SBML_DFS.R_IDENTIFIERS: [blank_id],
+                SBML_DFS.R_SOURCE: [source],
+                SBML_DFS.R_ISREVERSIBLE: [False],
+            },
+            index=pd.Index(["R00001"], name=SBML_DFS.R_ID),
+        ),
+        SBML_DFS.REACTION_SPECIES: pd.DataFrame(
+            {
+                SBML_DFS.R_ID: ["R00001"],
+                SBML_DFS.SC_ID: ["SC00001"],
+                SBML_DFS.STOICHIOMETRY: [1.0],
+                SBML_DFS.SBO_TERM: ["SBO:0000011"],
+            },
+            index=pd.Index(["RSC00001"], name=SBML_DFS.RSC_ID),
+        ),
+    }
+
+    return SBML_dfs(sbml_dict)
+
+
 @fixture
 def napistu_graph(sbml_dfs):
     """
     Pytest fixture to create a NapistuGraph from sbml_dfs with directed=True and topology weighting.
     """
-    return net_create.process_napistu_graph(
-        sbml_dfs, directed=True, weighting_strategy="topology"
-    )
+    return process_napistu_graph(sbml_dfs, directed=True, weighting_strategy="topology")
 
 
 @fixture
@@ -77,7 +134,7 @@ def napistu_graph_undirected(sbml_dfs):
     """
     Pytest fixture to create a NapistuGraph from sbml_dfs with directed=False and topology weighting.
     """
-    return net_create.process_napistu_graph(
+    return process_napistu_graph(
         sbml_dfs, directed=False, weighting_strategy="topology"
     )
 

tests/test_consensus.py

@@ -5,12 +5,13 @@ import os
 import pandas as pd
 import pytest
 from napistu import consensus
+from napistu import identifiers
 from napistu import indices
 from napistu import source
 from napistu import sbml_dfs_core
 from napistu.ingestion import sbml
 from napistu.modify import pathwayannot
-from napistu.constants import SBML_DFS, SBML_DFS_SCHEMA
+from napistu.constants import SBML_DFS, SBML_DFS_SCHEMA, SCHEMA_DEFS, IDENTIFIERS, BQB
 
 test_path = os.path.abspath(os.path.join(__file__, os.pardir))
 test_data = os.path.join(test_path, "test_data")
@@ -21,11 +22,16 @@ def test_reduce_to_consensus_ids():
 
     # 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"]
+    sbml_model = sbml.SBML(sbml_path)
+    comp_species_df = sbml_model._define_cspecies()
+    comp_species_df.index.names = [SBML_DFS.S_ID]
     consensus_species, species_lookup = consensus.reduce_to_consensus_ids(
-        comp_species_df, {"pk": "s_id", "id": "s_Identifiers"}
+        comp_species_df,
+        {
+            SCHEMA_DEFS.PK: SBML_DFS.S_ID,
+            SCHEMA_DEFS.ID: SBML_DFS.S_IDENTIFIERS,
+            SCHEMA_DEFS.TABLE: SBML_DFS.SPECIES,
+        },
     )
 
     assert isinstance(consensus_species, pd.DataFrame)
@@ -333,6 +339,68 @@ def test_report_consensus_merges_reactions(tmp_path):
     # No assertion: this is a smoke test to ensure the Series output is handled without error
 
 
+def test_build_consensus_identifiers_handles_merges_and_missing_ids():
+
+    # Three entities:
+    # - 'A' with identifier X
+    # - 'B' with no identifiers
+    # - 'C' with identifier X (should merge with 'A')
+    df = pd.DataFrame(
+        {
+            "s_id": ["A", "B", "C"],
+            "s_Identifiers": [
+                identifiers.Identifiers(
+                    [
+                        {
+                            IDENTIFIERS.ONTOLOGY: "test",
+                            IDENTIFIERS.IDENTIFIER: "X",
+                            IDENTIFIERS.BQB: BQB.IS,
+                        }
+                    ]
+                ),
+                identifiers.Identifiers([]),
+                identifiers.Identifiers(
+                    [
+                        {
+                            IDENTIFIERS.ONTOLOGY: "test",
+                            IDENTIFIERS.IDENTIFIER: "X",
+                            IDENTIFIERS.BQB: BQB.IS,
+                        }
+                    ]
+                ),
+            ],
+        }
+    ).set_index("s_id")
+
+    schema = SBML_DFS_SCHEMA.SCHEMA[SBML_DFS.SPECIES]
+
+    indexed_cluster, cluster_consensus_identifiers = (
+        consensus.build_consensus_identifiers(df, schema)
+    )
+
+    # All entities should be assigned to a cluster
+    assert set(indexed_cluster.index) == set(df.index)
+    assert not indexed_cluster.isnull().any()
+    # There should be a consensus identifier for each cluster
+    assert set(cluster_consensus_identifiers.index) == set(indexed_cluster.values)
+
+    # Entities 'A' and 'C' should be merged (same cluster)
+    assert indexed_cluster.loc["A"] == indexed_cluster.loc["C"]
+    # Entity 'B' should be in a different cluster
+    assert indexed_cluster.loc["B"] != indexed_cluster.loc["A"]
+
+    # The consensus identifier for the merged cluster should include identifier X
+    merged_cluster_id = indexed_cluster.loc["A"]
+    ids_obj = cluster_consensus_identifiers.loc[merged_cluster_id, schema["id"]]
+    assert any(i["identifier"] == "X" for i in getattr(ids_obj, "ids", []))
+
+    # The consensus identifier for the entity with no identifiers should be empty
+    noid_cluster_id = indexed_cluster.loc["B"]
+    ids_obj_noid = cluster_consensus_identifiers.loc[noid_cluster_id, schema["id"]]
+    assert hasattr(ids_obj_noid, "ids")
+    assert len(getattr(ids_obj_noid, "ids", [])) == 0
+
+
 ################################################
 # __main__
 ################################################
@@ -344,3 +412,4 @@ if __name__ == "__main__":
     test_passing_entity_data()
     test_consensus_ontology_check()
     test_report_consensus_merges_reactions()
+    test_build_consensus_identifiers_handles_merges_and_missing_ids()

tests/test_gaps.py

@@ -3,21 +3,32 @@ import numpy as np
 import warnings
 
 from napistu.sbml_dfs_core import SBML_dfs
-from napistu.constants import SBML_DFS
-from napistu.constants import MINI_SBO_FROM_NAME
 from napistu.identifiers import Identifiers
-
+from napistu.source import Source
 from napistu.modify import gaps
+from napistu.constants import BQB
+from napistu.constants import IDENTIFIERS
+from napistu.constants import ONTOLOGIES
+from napistu.constants import MINI_SBO_FROM_NAME
+from napistu.constants import SBML_DFS
+from napistu.ingestion.constants import EXCHANGE_COMPARTMENT, COMPARTMENTS
 
 
 # Minimal compartments table
 def _create_sbml_dfs_missing_transport_rxns():
 
+    blank_id = Identifiers([])
+    blank_source = Source(init=True)
+
     compartments = pd.DataFrame(
         {
-            SBML_DFS.C_NAME: ["mitochondria", "nucleus", "cytosol"],
-            SBML_DFS.C_IDENTIFIERS: [None],
-            SBML_DFS.C_SOURCE: [None],
+            SBML_DFS.C_NAME: [
+                COMPARTMENTS.MITOCHONDRIA,
+                COMPARTMENTS.NUCLEUS,
+                EXCHANGE_COMPARTMENT,
+            ],
+            SBML_DFS.C_IDENTIFIERS: [blank_id],
+            SBML_DFS.C_SOURCE: [blank_source],
         },
         index=["c_mito", "c_nucl", "c_cytosol"],
     ).rename_axis(SBML_DFS.C_ID)
@@ -30,15 +41,15 @@ def _create_sbml_dfs_missing_transport_rxns():
                 Identifiers(
                     [
                         {
-                            "ontology": "uniprot",
-                            "identifier": "PFAKE1",
-                            "bqb": "BQB_IS",
-                            "url": None,
+                            IDENTIFIERS.ONTOLOGY: ONTOLOGIES.UNIPROT,
+                            IDENTIFIERS.IDENTIFIER: "PFAKE1",
+                            IDENTIFIERS.BQB: BQB.IS,
+                            IDENTIFIERS.URL: None,
                         }
                     ]
                 )
             ],
-            SBML_DFS.S_SOURCE: [None],
+            SBML_DFS.S_SOURCE: [blank_source],
         },
         index=["s_A"],
     ).rename_axis(SBML_DFS.S_ID)
@@ -49,7 +60,7 @@ def _create_sbml_dfs_missing_transport_rxns():
             SBML_DFS.SC_NAME: ["A [mitochondria]", "A [nucleus]"],
             SBML_DFS.S_ID: ["s_A", "s_A"],
             SBML_DFS.C_ID: ["c_mito", "c_nucl"],
-            SBML_DFS.SC_SOURCE: [None],
+            SBML_DFS.SC_SOURCE: [blank_source],
         },
         index=["sc_A_mito", "sc_A_nucl"],
     ).rename_axis(SBML_DFS.SC_ID)
@@ -58,8 +69,8 @@ def _create_sbml_dfs_missing_transport_rxns():
     reactions = pd.DataFrame(
         {
             SBML_DFS.R_NAME: ["A [mito] -> A [mito]", "A [nucl] -> A [nucl]"],
-            SBML_DFS.R_IDENTIFIERS: [None],
-            SBML_DFS.R_SOURCE: [None],
+            SBML_DFS.R_IDENTIFIERS: [blank_id],
+            SBML_DFS.R_SOURCE: [blank_source],
             SBML_DFS.R_ISREVERSIBLE: [True, True],
         },
         index=["r_A_mito", "r_A_nucl"],
@@ -105,7 +116,7 @@ def test_add_transportation_reactions():
 
     sbml_dfs = _create_sbml_dfs_missing_transport_rxns()
     sbml_dfs_w_transport = gaps.update_sbml_df_with_exchange(
-        np.array(["s_A"]), sbml_dfs, exchange_compartment="cytosol"
+        np.array(["s_A"]), sbml_dfs, exchange_compartment=EXCHANGE_COMPARTMENT
     )
     assert sbml_dfs_w_transport.reactions.shape[0] == 4, "Should add 2 reactions"
     assert sbml_dfs_w_transport.reactions[

tests/test_network_net_create.py

@@ -20,7 +20,7 @@ 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, "R-HSA-1237044.sbml")
-sbml_model = sbml.SBML(sbml_path).model
+sbml_model = sbml.SBML(sbml_path)
 sbml_dfs = sbml_dfs_core.SBML_dfs(sbml_model)
 
 

tests/test_network_precompute.py

@@ -18,7 +18,7 @@ sbml_path = os.path.join(test_path, "test_data", "reactome_glucose_metabolism.sb
 if not os.path.isfile(sbml_path):
     raise ValueError(f"{sbml_path} not found")
 
-sbml_model = sbml.SBML(sbml_path).model
+sbml_model = sbml.SBML(sbml_path)
 sbml_dfs = sbml_dfs_core.SBML_dfs(sbml_model)
 sbml_dfs.validate()
 

tests/test_ontologies_renaming.py

@@ -1,14 +1,16 @@
 """Tests for the ontology aliases module."""
 
+from unittest.mock import patch
+
 import pytest
 import pandas as pd
 from napistu import identifiers
-from napistu.constants import IDENTIFIERS, SBML_DFS
+from napistu.constants import IDENTIFIERS, SBML_DFS, ONTOLOGIES
 from napistu.ontologies import renaming
 
 
 @pytest.fixture
-def mock_sbml_dfs():
+def mock_sbml_dfs(sbml_dfs):
     """Create a mock SBML_dfs object for testing."""
     # Create a simple species DataFrame with identifiers
     s1_ids = identifiers.Identifiers(
@@ -39,32 +41,27 @@ def mock_sbml_dfs():
         ]
     )
 
+    s3_ids = identifiers.Identifiers([])
+
     species_df = pd.DataFrame(
-        {"s_name": ["gene1", "gene2"], SBML_DFS.S_IDENTIFIERS: [s1_ids, s2_ids]}
+        {
+            SBML_DFS.S_NAME: ["gene1", "gene2", "gene3"],
+            SBML_DFS.S_IDENTIFIERS: [s1_ids, s2_ids, s3_ids],
+        }
     )
 
-    # Create mock SBML_dfs object
-    class MockSBMLDfs:
-        def __init__(self):
-            self.species = species_df
-            self.schema = {"species": {"pk": "s_id", "id": SBML_DFS.S_IDENTIFIERS}}
-
-        def get_identifiers(self, table_name):
-            if table_name == SBML_DFS.SPECIES:
-                all_ids = []
-                for idx, row in self.species.iterrows():
-                    for id_dict in row[SBML_DFS.S_IDENTIFIERS].ids:
-                        all_ids.append({"s_id": idx, **id_dict})
-                return pd.DataFrame(all_ids)
-            return pd.DataFrame()
-
-    return MockSBMLDfs()
+    # Patch the species attribute only for the duration of the test
+    with patch.object(sbml_dfs, "species", new=species_df):
+        yield sbml_dfs  # All methods are real, only .species is patched
 
 
 def test_rename_species_ontologies_basic(mock_sbml_dfs):
     """Test basic alias updating functionality."""
     # Define test aliases
-    test_aliases = {"ncbi_entrez_gene": {"ncbigene"}, "uniprot": {"uniprot_id"}}
+    test_aliases = {
+        ONTOLOGIES.NCBI_ENTREZ_GENE: {"ncbigene"},
+        ONTOLOGIES.UNIPROT: {"uniprot_id"},
+    }
 
     # Update aliases
     renaming.rename_species_ontologies(mock_sbml_dfs, test_aliases)
@@ -73,11 +70,18 @@ def test_rename_species_ontologies_basic(mock_sbml_dfs):
     updated_ids = mock_sbml_dfs.get_identifiers(SBML_DFS.SPECIES)
 
     # Check that ontologies were updated correctly
-    assert "ncbi_entrez_gene" in set(updated_ids[IDENTIFIERS.ONTOLOGY])
-    assert "uniprot" in set(updated_ids[IDENTIFIERS.ONTOLOGY])
+    assert ONTOLOGIES.NCBI_ENTREZ_GENE in set(updated_ids[IDENTIFIERS.ONTOLOGY])
+    assert ONTOLOGIES.UNIPROT in set(updated_ids[IDENTIFIERS.ONTOLOGY])
     assert "ncbigene" not in set(updated_ids[IDENTIFIERS.ONTOLOGY])
     assert "uniprot_id" not in set(updated_ids[IDENTIFIERS.ONTOLOGY])
 
+    # verify that all the species have Identifiers object
+    for row in mock_sbml_dfs.species.itertuples():
+        val = getattr(row, SBML_DFS.S_IDENTIFIERS)
+        assert val is not None and isinstance(
+            val, identifiers.Identifiers
+        ), f"Bad value: {val} in row {row}"
+
 
 def test_rename_species_ontologies_no_overlap(mock_sbml_dfs):
     """Test that error is raised when no aliases overlap with data."""
@@ -93,7 +97,7 @@ def test_rename_species_ontologies_partial_update(mock_sbml_dfs):
     """Test that partial updates work correctly."""
     # Define aliases that only update some ontologies
     test_aliases = {
-        "ncbi_entrez_gene": {"ncbigene"}
+        ONTOLOGIES.NCBI_ENTREZ_GENE: {"ncbigene"}
         # Don't include uniprot_id mapping
     }
 
@@ -104,7 +108,7 @@ def test_rename_species_ontologies_partial_update(mock_sbml_dfs):
     updated_ids = mock_sbml_dfs.get_identifiers(SBML_DFS.SPECIES)
 
     # Check that only ncbigene was updated
-    assert "ncbi_entrez_gene" in set(updated_ids[IDENTIFIERS.ONTOLOGY])
+    assert ONTOLOGIES.NCBI_ENTREZ_GENE in set(updated_ids[IDENTIFIERS.ONTOLOGY])
     assert "uniprot_id" in set(
         updated_ids[IDENTIFIERS.ONTOLOGY]
     )  # Should remain unchanged