napistu 0.3.5__py3-none-any.whl → 0.3.7__py3-none-any.whl

napistu/utils.py

@@ -810,50 +810,15 @@ def drop_extra_cols(
     return df_out.loc[:, ordered_cols]
 
 
-def _merge_and_log_overwrites(
-    left_df: pd.DataFrame, right_df: pd.DataFrame, merge_context: str, **merge_kwargs
-) -> pd.DataFrame:
+def update_pathological_names(names: pd.Series, prefix: str) -> pd.Series:
     """
-    Merge two DataFrames and log any column overwrites.
-
-    Parameters
-    ----------
-    left_df : pd.DataFrame
-        Left DataFrame for merge
-    right_df : pd.DataFrame
-        Right DataFrame for merge
-    merge_context : str
-        Description of the merge operation for logging
-    **merge_kwargs : dict
-        Additional keyword arguments passed to pd.merge
+    Update pathological names in a pandas Series.
 
-    Returns
-    -------
-    pd.DataFrame
-        Merged DataFrame with overwritten columns removed
+    Add a prefix to the names if they are all numeric.
     """
-    # Track original columns
-    original_cols = left_df.columns.tolist()
-
-    # Ensure we're using the correct suffixes
-    merge_kwargs["suffixes"] = ("_old", "")
-
-    # Perform merge
-    merged_df = pd.merge(left_df, right_df, **merge_kwargs)
-
-    # Check for and log any overwritten columns
-    new_cols = merged_df.columns.tolist()
-    overwritten_cols = [col for col in original_cols if col + "_old" in new_cols]
-    if overwritten_cols:
-        logger.warning(
-            f"The following columns were overwritten during {merge_context} merge and their original values "
-            f"have been suffixed with '_old': {', '.join(overwritten_cols)}"
-        )
-        # Drop the old columns
-        cols_to_drop = [col + "_old" for col in overwritten_cols]
-        merged_df = merged_df.drop(columns=cols_to_drop)
-
-    return merged_df
+    if names.apply(lambda x: x.isdigit()).all():
+        names = names.apply(lambda x: f"{prefix}{x}")
+    return names
 
 
 def format_identifiers_as_edgelist(
@@ -1108,3 +1073,49 @@ def _add_nameness_score(df, name_var):
 
     df.loc[:, "nameness_score"] = df[name_var].apply(score_nameness)
     return df
+
+
+def _merge_and_log_overwrites(
+    left_df: pd.DataFrame, right_df: pd.DataFrame, merge_context: str, **merge_kwargs
+) -> pd.DataFrame:
+    """
+    Merge two DataFrames and log any column overwrites.
+
+    Parameters
+    ----------
+    left_df : pd.DataFrame
+        Left DataFrame for merge
+    right_df : pd.DataFrame
+        Right DataFrame for merge
+    merge_context : str
+        Description of the merge operation for logging
+    **merge_kwargs : dict
+        Additional keyword arguments passed to pd.merge
+
+    Returns
+    -------
+    pd.DataFrame
+        Merged DataFrame with overwritten columns removed
+    """
+    # Track original columns
+    original_cols = left_df.columns.tolist()
+
+    # Ensure we're using the correct suffixes
+    merge_kwargs["suffixes"] = ("_old", "")
+
+    # Perform merge
+    merged_df = pd.merge(left_df, right_df, **merge_kwargs)
+
+    # Check for and log any overwritten columns
+    new_cols = merged_df.columns.tolist()
+    overwritten_cols = [col for col in original_cols if col + "_old" in new_cols]
+    if overwritten_cols:
+        logger.warning(
+            f"The following columns were overwritten during {merge_context} merge and their original values "
+            f"have been suffixed with '_old': {', '.join(overwritten_cols)}"
+        )
+        # Drop the old columns
+        cols_to_drop = [col + "_old" for col in overwritten_cols]
+        merged_df = merged_df.drop(columns=cols_to_drop)
+
+    return merged_df

{napistu-0.3.5.dist-info → napistu-0.3.7.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: napistu
-Version: 0.3.5
+Version: 0.3.7
 Summary: Connecting high-dimensional data to curated pathways
 Home-page: https://github.com/napistu/napistu-py
 Author: Sean Hackett
@@ -43,7 +43,7 @@ Requires-Dist: pytest-cov; extra == "dev"
 Requires-Dist: ruff; extra == "dev"
 Requires-Dist: testcontainers; extra == "dev"
 Provides-Extra: mcp
-Requires-Dist: fastmcp<3.0.0,>=2.0.0; extra == "mcp"
+Requires-Dist: fastmcp<2.9.0,>=2.0.0; extra == "mcp"
 Requires-Dist: mcp<2.0.0,>=1.0.0; extra == "mcp"
 Requires-Dist: httpx>=0.24.0; extra == "mcp"
 Requires-Dist: beautifulsoup4<5.0.0,>=4.11.0; extra == "mcp"

{napistu-0.3.5.dist-info → napistu-0.3.7.dist-info}/RECORD

@@ -1,22 +1,22 @@
 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=XptXQa3OKmH5hPb6PK_3cLSNcETj6jqejJYY60GV9Zc,12384
-napistu/identifiers.py,sha256=wsVriQdvPllA5uvh5CiREklA2tYW2MIB14dV7CPaMVU,34003
-napistu/indices.py,sha256=E_djN1XWc6l1lrFw_QnQXfZTKYTaUv8-jFPP7cHkY5A,9780
-napistu/sbml_dfs_core.py,sha256=us0Yz67ilav5dc2LY2TtXypaSdAQ7Kk55ZyGuyougzo,96605
-napistu/sbml_dfs_utils.py,sha256=LJo6WWTrmnE58ZLDuibeeHk88uCdfunWdja7XxdZpps,11525
+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=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=oH1uNsf-_qSWRFtoxR8gDvCfZOzO3Ps40YO0qGAGXXs,13660
+napistu/context/filtering.py,sha256=l1oq-43ysSGqU9VmhTOO_pYT4DSMf20yxvktPC1MI0I,13696
 napistu/gcs/__init__.py,sha256=dFXAhIqlTLJMwowS4BUDT08-Vy3Q0u1L0CMCErSZT1Y,239
 napistu/gcs/constants.py,sha256=g6PaU99GY5XvaRHx4BGmWHUpcJ36-Zh_GzeNVOeHviM,2856
 napistu/gcs/downloads.py,sha256=SvGv9WYr_Vt3guzyz1QiAuBndeKPTBtWSFLj1-QbLf4,6348
 napistu/gcs/utils.py,sha256=eLSsvewWJdCguyj2k0ozUGP5BTemaE1PZg41Z3aY5kM,571
 napistu/ingestion/__init__.py,sha256=dFXAhIqlTLJMwowS4BUDT08-Vy3Q0u1L0CMCErSZT1Y,239
-napistu/ingestion/bigg.py,sha256=q0HeVSO6pFftbrxxVfFGUtMvCoak9Wi9ngMggRfjFjo,4364
+napistu/ingestion/bigg.py,sha256=f65--8ARe248eYCUJpFMF284Wz53sLyFyBuwelxHmJA,4340
 napistu/ingestion/constants.py,sha256=9UP47VImZ11q0kz17N3EJg2155USqLewwNWyKpA-cbA,8089
 napistu/ingestion/gtex.py,sha256=X0hSC1yrpf4xSJWFhpeNcnHwJzKDII2MvjfUqYA0JN8,3720
 napistu/ingestion/hpa.py,sha256=R27ExrryKQ4Crxv9ATXmBJCa-yd01TMOrDjkeBhIQac,5054
@@ -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=YSWqaKm3I8bOixzvSA8fU4yfR2izddPYs4qJiqwjbxk,11678
-napistu/ingestion/trrust.py,sha256=ccjZc_eF3PdxxurnukiEo_e0-aKc_3z22NYbaJBtHdY,9774
-napistu/ingestion/yeast.py,sha256=bwFBNxRq-dLDaddgBL1hpfZj0eQ56nBXyR_9n0NZT9Y,5233
+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=5GQCOFVvPPS7tCJodcSy51Fzh4c-biaP1dbbhgc8VLs,18818
+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
@@ -56,24 +56,24 @@ napistu/modify/constants.py,sha256=H6K6twzPlxt0yp6QLAxIx0Tp8YzYhtKKXPdmXi5V_QQ,3
 napistu/modify/curation.py,sha256=sQeSO53ZLdn14ww2GSKkoP0vJnDpAoSWb-YDjUf5hDQ,21743
 napistu/modify/gaps.py,sha256=qprylC2BbSk_vPWayYPVT8lwURXDMOlW5zNLV_wMFZ4,26755
 napistu/modify/pathwayannot.py,sha256=xuBSMDFWbg_d6-Gzv0Td3Q5nnFTa-Qzic48g1b1AZtQ,48081
-napistu/modify/uncompartmentalize.py,sha256=U5X4Q7Z-YIkC8_711x3sU21vTVdv9rKfauwz4JNzl6c,9690
+napistu/modify/uncompartmentalize.py,sha256=y5LkXn5x6u80dB_McfAIh88BxZGIAVFLujkP7sPNRh0,9690
 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=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_create.py,sha256=aAw6kfHREpkMEcwQFgwU5CHg--b8YLO559surQLRXZI,69408
 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/paths.py,sha256=-dxRtaBRDYwuMw9DByGSn5OXFC3umDeO2zvVvD0TdWE,17452
 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
-napistu/ontologies/genodexito.py,sha256=5_gtdVtKHp5z-jtPXkHlZRiTsuHdZeA3TVI9u4SXqrQ,24725
+napistu/ontologies/dogma.py,sha256=VVj6NKBgNym4SdOSu8g22OohALj7cbObhIJmdY2Sfy0,8860
+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-0.3.5.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=XVkd0tQywhnf2cgab7fIjBo3NlaTVX3cO8HaRS2jIwM,3190
-tests/test_consensus.py,sha256=3dJvvPsPG7bHbw_FY4Pm647N_Gt_Ud9157OKYfPCUd4,9502
+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=0CWbmxKxerraJJgUqXiYHSYCfmRyOFvFRMG1u6mLbwI,9483
+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_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
+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=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=MtmQp9EZD4OFmk-5tWUSb9hUjcGfRKTFbSBymiE_Qzo,23628
-tests/test_sbml_dfs_utils.py,sha256=5lNzZ1NLOnFb_sZ0YWTgLzXy28yGNCtS_H8Q-W-T6Bw,2022
+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-0.3.5.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,,
+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

@@ -1,16 +1,23 @@
 from __future__ import annotations
 
+import functools
 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
@@ -25,13 +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
 
 
@@ -53,20 +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
@@ -74,7 +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"
     )
 
@@ -109,3 +169,43 @@ def pytest_runtest_setup(item):
     # 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")
+
+
+def skip_on_timeout(timeout_seconds):
+    """Cross-platform decorator that skips a test if it takes longer than timeout_seconds"""
+
+    def decorator(func):
+        @functools.wraps(func)
+        def wrapper(*args, **kwargs):
+            result = [None]
+            exception = [None]
+            finished = [False]
+
+            def target():
+                try:
+                    result[0] = func(*args, **kwargs)
+                    finished[0] = True
+                except Exception as e:
+                    exception[0] = e
+                    finished[0] = True
+
+            thread = threading.Thread(target=target)
+            thread.daemon = True
+            thread.start()
+            thread.join(timeout_seconds)
+
+            if not finished[0]:
+                # Thread is still running, timeout occurred
+                pytest.skip(f"Test skipped due to timeout ({timeout_seconds}s)")
+
+            if exception[0]:
+                raise exception[0]
+
+            return result[0]
+
+        return wrapper
+
+    return decorator
+
+
+pytest.skip_on_timeout = skip_on_timeout

tests/test_consensus.py

@@ -5,10 +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, SCHEMA_DEFS, IDENTIFIERS, BQB
 
 test_path = os.path.abspath(os.path.join(__file__, os.pardir))
 test_data = os.path.join(test_path, "test_data")
@@ -19,11 +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)
@@ -246,6 +254,153 @@ def test_consensus_ontology_check():
     assert post_shared_onto_sp_set == {"chebi", "reactome", "uniprot"}
 
 
+def test_report_consensus_merges_reactions(tmp_path):
+    # Create two minimal SBML_dfs objects with a single reaction each, same r_id
+    r_id = "R00000001"
+    reactions = pd.DataFrame(
+        {
+            SBML_DFS.R_NAME: ["rxn1"],
+            SBML_DFS.R_IDENTIFIERS: [None],
+            SBML_DFS.R_SOURCE: [None],
+            SBML_DFS.R_ISREVERSIBLE: [False],
+        },
+        index=[r_id],
+    )
+    reactions.index.name = SBML_DFS.R_ID
+    reaction_species = pd.DataFrame(
+        {
+            SBML_DFS.R_ID: [r_id],
+            SBML_DFS.SC_ID: ["SC0001"],
+            SBML_DFS.STOICHIOMETRY: [1],
+            SBML_DFS.SBO_TERM: ["SBO:0000459"],
+        },
+        index=["RSC0001"],
+    )
+    reaction_species.index.name = SBML_DFS.RSC_ID
+    compartmentalized_species = pd.DataFrame(
+        {
+            SBML_DFS.SC_NAME: ["A [cytosol]"],
+            SBML_DFS.S_ID: ["S0001"],
+            SBML_DFS.C_ID: ["C0001"],
+            SBML_DFS.SC_SOURCE: [None],
+        },
+        index=["SC0001"],
+    )
+    compartmentalized_species.index.name = SBML_DFS.SC_ID
+    species = pd.DataFrame(
+        {
+            SBML_DFS.S_NAME: ["A"],
+            SBML_DFS.S_IDENTIFIERS: [None],
+            SBML_DFS.S_SOURCE: [None],
+        },
+        index=["S0001"],
+    )
+    species.index.name = SBML_DFS.S_ID
+    compartments = pd.DataFrame(
+        {
+            SBML_DFS.C_NAME: ["cytosol"],
+            SBML_DFS.C_IDENTIFIERS: [None],
+            SBML_DFS.C_SOURCE: [None],
+        },
+        index=["C0001"],
+    )
+    compartments.index.name = SBML_DFS.C_ID
+    sbml_dict = {
+        SBML_DFS.COMPARTMENTS: compartments,
+        SBML_DFS.SPECIES: species,
+        SBML_DFS.COMPARTMENTALIZED_SPECIES: compartmentalized_species,
+        SBML_DFS.REACTIONS: reactions,
+        SBML_DFS.REACTION_SPECIES: reaction_species,
+    }
+    sbml1 = sbml_dfs_core.SBML_dfs(sbml_dict, validate=False, resolve=False)
+    sbml2 = sbml_dfs_core.SBML_dfs(sbml_dict, validate=False, resolve=False)
+    sbml_dfs_dict = {"mod1": sbml1, "mod2": sbml2}
+
+    # Create a lookup_table that merges both reactions into a new_id
+    lookup_table = pd.DataFrame(
+        {
+            "model": ["mod1", "mod2"],
+            "r_id": [r_id, r_id],
+            "new_id": ["merged_rid", "merged_rid"],
+        }
+    )
+    # Use the reactions schema
+    table_schema = SBML_DFS_SCHEMA.SCHEMA[SBML_DFS.REACTIONS]
+
+    # Call the function and check that it runs and the merge_labels are as expected
+    consensus.report_consensus_merges(
+        lookup_table.set_index(["model", "r_id"])[
+            "new_id"
+        ],  # this is a Series with name 'new_id'
+        table_schema,
+        sbml_dfs_dict=sbml_dfs_dict,
+        n_example_merges=1,
+    )
+    # 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__
 ################################################
@@ -256,3 +411,5 @@ if __name__ == "__main__":
     test_source_tracking()
     test_passing_entity_data()
     test_consensus_ontology_check()
+    test_report_consensus_merges_reactions()
+    test_build_consensus_identifiers_handles_merges_and_missing_ids()

tests/test_context_filtering.py

@@ -3,7 +3,7 @@ from __future__ import annotations
 import copy
 import pytest
 import pandas as pd
-from napistu import sbml_dfs_core
+from napistu import sbml_dfs_utils
 from napistu.constants import SBML_DFS
 from napistu.context.filtering import (
     filter_species_by_attribute,
@@ -208,7 +208,7 @@ def test_filter_reactions_with_disconnected_cspecies(sbml_dfs):
     first_reactions = list(sbml_dfs.reactions.index[:5])
 
     # 2. Find defining species in these reactions
-    reaction_species = sbml_dfs_core.add_sbo_role(sbml_dfs.reaction_species)
+    reaction_species = sbml_dfs_utils.add_sbo_role(sbml_dfs.reaction_species)
     defining_species = (
         reaction_species[reaction_species[SBML_DFS.R_ID].isin(first_reactions)]
         .query("sbo_role == 'DEFINING'")