update expected files with new genes and cluster

ppanggolin/cluster/cluster.py

@@ -475,8 +475,11 @@ def read_clustering_file(families_tsv_path: Path) -> Tuple[pd.DataFrame, bool]:
     families_df["representative"] = families_df["representative"].astype(str)
 
     # Check for duplicate gene IDs
-    if families_df["gene"].duplicated().any():
-        raise Exception("It seems that there is duplicated gene id in your clustering.")
+    duplicates = families_df[families_df["gene"].duplicated()]["gene"].unique()
+
+    if len(duplicates) > 0:
+        raise ValueError(f"Duplicate gene IDs found in your clustering: {', '.join(duplicates)}")
+
 
     return families_df[["family", "representative", "gene", "is_frag"]], families_df["is_frag"].any()
 

testingDataset/expected_info_files/checksum.txt

@@ -1,5 +1,5 @@
 9d6219523e890b08c467c936590b37436e915840a797ea161c9707041c3b821c  mybasicpangenome/gene_families.tsv
 9d6219523e890b08c467c936590b37436e915840a797ea161c9707041c3b821c  stepbystep/gene_families.tsv
-bd71918de23737aec5a262c883c1154a507ae616bdc47a152db0e76319e7484d  readclusterpang/gene_families.tsv
-b893343f249102dff23a9542752f83cdee93efd34bc951b48a0c986fcb5d26a4  myannopang/gene_families.tsv
+5cb88afbc1a49e7d21531d36d5ee3471a87834f4bb82578347dc92231ba0a452  readclusterpang/gene_families.tsv
+5cb88afbc1a49e7d21531d36d5ee3471a87834f4bb82578347dc92231ba0a452  myannopang/gene_families.tsv
 41511d7c482c0c400a504d5c564605427081917e54aee1e5f37ffda220d2cdb9  test_config/gene_families.tsv

testingDataset/expected_info_files/myannopang_info.yaml

@@ -11,10 +11,10 @@ Status:
     PPanGGOLiN_Version: 2.1.2
 
 Content:
-    Genes: 47961
+    Genes: 47986
     Genomes: 53
-    Families: 1084
-    Edges: 1318
+    Families: 1086
+    Edges: 1315
     Persistent:
         Family_count: 871
         min_genomes_frequency: 0.89
@@ -28,7 +28,7 @@ Content:
         sd_genomes_frequency: 0.18
         mean_genomes_frequency: 0.52
     Cloud:
-        Family_count: 157
+        Family_count: 159
         min_genomes_frequency: 0.02
         max_genomes_frequency: 0.23
         sd_genomes_frequency: 0.04