fix: resolve aliases when inserting to or querying lineage indexes again

GenSpectrum · Oct 4, 2024 · 561327d · 561327d
1 parent ca84ae2
commit 561327d
Show file tree

Hide file tree

Showing 18 changed files with 825 additions and 480 deletions.
diff --git a/endToEndTests/test/queries/aaMutDistribution_all.json b/endToEndTests/test/queries/aaMutDistribution_all.json
diff --git a/endToEndTests/test/queries/fasta_allTestSequences.json b/endToEndTests/test/queries/fasta_allTestSequences.json
@@ -3,115 +3,113 @@
   "query": {
     "action": {
       "type": "Fasta",
-      "sequenceName": "testSecondSequence"
+      "sequenceName": "testSecondSequence",
+      "orderByFields": [ "gisaid_epi_isl" ]
     },
     "filterExpression": {
       "type": "True"
     }
   },
   "expectedQueryResult": [
-    { "gisaid_epi_isl": "EPI_ISL_3086369", "testSecondSequence": "ACGT" },
-    { "gisaid_epi_isl": "EPI_ISL_3247294", "testSecondSequence": null },
-    {
-      "gisaid_epi_isl": "EPI_ISL_3259931",
-      "testSecondSequence": "JRZFHVKQIQGIVPUNJZCDKLOPDFTWZWXEXKZIHLGFWZNIGUAAPJBXPQCJBFUYHHIOPNDMTMHAFPHMZRCNUGIBRZCNKAJZMWXMBMPQRTZQUHTIFSOBXAQWMESDRWVJQWRE"
-    },
-    { "gisaid_epi_isl": "EPI_ISL_3267832", "testSecondSequence": "ACGT" },
-    { "gisaid_epi_isl": "EPI_ISL_3465556", "testSecondSequence": "ACGT" },
-    { "gisaid_epi_isl": "EPI_ISL_3465732", "testSecondSequence": "ACGT" },
-    { "gisaid_epi_isl": "EPI_ISL_1119584", "testSecondSequence": "ACGN" },
-    { "gisaid_epi_isl": "EPI_ISL_1750868", "testSecondSequence": "ACGT" },
-    { "gisaid_epi_isl": "EPI_ISL_2359636", "testSecondSequence": "ACGT" },
-    { "gisaid_epi_isl": "EPI_ISL_737604", "testSecondSequence": "ACGT" },
-    { "gisaid_epi_isl": "EPI_ISL_931279", "testSecondSequence": "ACGT" },
-    { "gisaid_epi_isl": "EPI_ISL_1003849", "testSecondSequence": "ACGT" },
-    { "gisaid_epi_isl": "EPI_ISL_1131102", "testSecondSequence": "ACGT" },
-    { "gisaid_epi_isl": "EPI_ISL_1260480", "testSecondSequence": "ACGT" },
-    { "gisaid_epi_isl": "EPI_ISL_1273715", "testSecondSequence": "ACGT" },
-    { "gisaid_epi_isl": "EPI_ISL_581968", "testSecondSequence": "ACGT" },
-    { "gisaid_epi_isl": "EPI_ISL_721941", "testSecondSequence": "ACGT" },
-    { "gisaid_epi_isl": "EPI_ISL_737860", "testSecondSequence": "ACGT" },
-    { "gisaid_epi_isl": "EPI_ISL_1001920", "testSecondSequence": "ACGT" },
-    { "gisaid_epi_isl": "EPI_ISL_1003036", "testSecondSequence": "ACGT" },
-    { "gisaid_epi_isl": "EPI_ISL_1003373", "testSecondSequence": "ACGT" },
-    { "gisaid_epi_isl": "EPI_ISL_1003425", "testSecondSequence": "ACGT" },
-    { "gisaid_epi_isl": "EPI_ISL_1003519", "testSecondSequence": "ACGT" },
-    { "gisaid_epi_isl": "EPI_ISL_737715", "testSecondSequence": "ACGT" },
-    { "gisaid_epi_isl": "EPI_ISL_830864", "testSecondSequence": "ACGT" },
-    { "gisaid_epi_isl": "EPI_ISL_899725", "testSecondSequence": "ACGT" },
-    { "gisaid_epi_isl": "EPI_ISL_899762", "testSecondSequence": "ACGT" },
-    { "gisaid_epi_isl": "EPI_ISL_931031", "testSecondSequence": "ACGT" },
-    { "gisaid_epi_isl": "EPI_ISL_1003010", "testSecondSequence": "ACGT" },
-    { "gisaid_epi_isl": "EPI_ISL_1036103", "testSecondSequence": "ACGT" },
-    { "gisaid_epi_isl": "EPI_ISL_1130868", "testSecondSequence": "ACGT" },
-    { "gisaid_epi_isl": "EPI_ISL_1750503", "testSecondSequence": "ACGT" },
-    { "gisaid_epi_isl": "EPI_ISL_1840634", "testSecondSequence": "ACGN" },
-    { "gisaid_epi_isl": "EPI_ISL_2213804", "testSecondSequence": "ACGT" },
-    { "gisaid_epi_isl": "EPI_ISL_2360326", "testSecondSequence": "ACGT" },
-    { "gisaid_epi_isl": "EPI_ISL_3578231", "testSecondSequence": "ACGT" },
-    { "gisaid_epi_isl": "EPI_ISL_1003629", "testSecondSequence": "ACGT" },
-    { "gisaid_epi_isl": "EPI_ISL_1080536", "testSecondSequence": "ATGT" },
-    { "gisaid_epi_isl": "EPI_ISL_1119315", "testSecondSequence": "ACGT" },
-    { "gisaid_epi_isl": "EPI_ISL_1129663", "testSecondSequence": "ACGT" },
-    { "gisaid_epi_isl": "EPI_ISL_1195052", "testSecondSequence": "ACGT" },
-    { "gisaid_epi_isl": "EPI_ISL_1273458", "testSecondSequence": "ANGT" },
-    { "gisaid_epi_isl": "EPI_ISL_1360935", "testSecondSequence": "ACGT" },
-    { "gisaid_epi_isl": "EPI_ISL_1361468", "testSecondSequence": "ACGT" },
-    { "gisaid_epi_isl": "EPI_ISL_1407962", "testSecondSequence": "ACGT" },
-    { "gisaid_epi_isl": "EPI_ISL_1408062", "testSecondSequence": "ACGT" },
-    { "gisaid_epi_isl": "EPI_ISL_1408408", "testSecondSequence": "ACGT" },
-    { "gisaid_epi_isl": "EPI_ISL_1597890", "testSecondSequence": "ACGT" },
-    { "gisaid_epi_isl": "EPI_ISL_1597932", "testSecondSequence": "ACGT" },
-    { "gisaid_epi_isl": "EPI_ISL_1599113", "testSecondSequence": "ACGT" },
-    { "gisaid_epi_isl": "EPI_ISL_1747752", "testSecondSequence": "ACGT" },
-    { "gisaid_epi_isl": "EPI_ISL_1747885", "testSecondSequence": "ACGT" },
-    { "gisaid_epi_isl": "EPI_ISL_1748215", "testSecondSequence": "ACGT" },
-    { "gisaid_epi_isl": "EPI_ISL_1748243", "testSecondSequence": "ACGT" },
-    { "gisaid_epi_isl": "EPI_ISL_1748395", "testSecondSequence": "ACGT" },
-    { "gisaid_epi_isl": "EPI_ISL_1749892", "testSecondSequence": "ACGT" },
-    { "gisaid_epi_isl": "EPI_ISL_1749899", "testSecondSequence": "AAGN" },
-    { "gisaid_epi_isl": "EPI_ISL_1749960", "testSecondSequence": "ACGT" },
-    { "gisaid_epi_isl": "EPI_ISL_1760534", "testSecondSequence": "ACGT" },
-    { "gisaid_epi_isl": "EPI_ISL_2016901", "testSecondSequence": "ACGT" },
-    { "gisaid_epi_isl": "EPI_ISL_2017036", "testSecondSequence": "ANGT" },
-    { "gisaid_epi_isl": "EPI_ISL_2019235", "testSecondSequence": "ACGT" },
-    { "gisaid_epi_isl": "EPI_ISL_2019350", "testSecondSequence": "ACGT" },
-    { "gisaid_epi_isl": "EPI_ISL_2180023", "testSecondSequence": "ACGT" },
-    { "gisaid_epi_isl": "EPI_ISL_2180995", "testSecondSequence": "ACGT" },
-    { "gisaid_epi_isl": "EPI_ISL_2181005", "testSecondSequence": "ACGT" },
-    { "gisaid_epi_isl": "EPI_ISL_2213934", "testSecondSequence": "ACGT" },
-    { "gisaid_epi_isl": "EPI_ISL_2213984", "testSecondSequence": "ACGT" },
-    { "gisaid_epi_isl": "EPI_ISL_2214128", "testSecondSequence": "ACGT" },
-    { "gisaid_epi_isl": "EPI_ISL_2270139", "testSecondSequence": null },
-    { "gisaid_epi_isl": "EPI_ISL_2307766", "testSecondSequence": "ACGT" },
-    { "gisaid_epi_isl": "EPI_ISL_2307888", "testSecondSequence": "ACGT" },
-    { "gisaid_epi_isl": "EPI_ISL_2308054", "testSecondSequence": null },
-    { "gisaid_epi_isl": "EPI_ISL_2374969", "testSecondSequence": "ACGT" },
-    { "gisaid_epi_isl": "EPI_ISL_2375097", "testSecondSequence": "ACGT" },
-    { "gisaid_epi_isl": "EPI_ISL_2375165", "testSecondSequence": "ACGT" },
-    { "gisaid_epi_isl": "EPI_ISL_2375247", "testSecondSequence": "ACGT" },
-    { "gisaid_epi_isl": "EPI_ISL_2375490", "testSecondSequence": "ACGT" },
-    { "gisaid_epi_isl": "EPI_ISL_2379651", "testSecondSequence": "ACGT" },
-    { "gisaid_epi_isl": "EPI_ISL_2405276", "testSecondSequence": "ACGT" },
-    { "gisaid_epi_isl": "EPI_ISL_2408472", "testSecondSequence": "AAGT" },
-    { "gisaid_epi_isl": "EPI_ISL_2544226", "testSecondSequence": "ACGT" },
-    { "gisaid_epi_isl": "EPI_ISL_2544332", "testSecondSequence": "ACGT" },
-    { "gisaid_epi_isl": "EPI_ISL_2544452", "testSecondSequence": "ACGT" },
-    { "gisaid_epi_isl": "EPI_ISL_2574088", "testSecondSequence": "ACGT" },
-    { "gisaid_epi_isl": "EPI_ISL_3016465", "testSecondSequence": "ACGT" },
-    { "gisaid_epi_isl": "EPI_ISL_1001493", "testSecondSequence": "ACGT" },
-    { "gisaid_epi_isl": "EPI_ISL_1002156", "testSecondSequence": "ACGN" },
-    { "gisaid_epi_isl": "EPI_ISL_1004495", "testSecondSequence": "ACGT" },
-    { "gisaid_epi_isl": "EPI_ISL_1005148", "testSecondSequence": "ACGT" },
-    { "gisaid_epi_isl": "EPI_ISL_1408805", "testSecondSequence": "ACGT" },
-    { "gisaid_epi_isl": "EPI_ISL_2086867", "testSecondSequence": "ACGT" },
-    { "gisaid_epi_isl": "EPI_ISL_3128796", "testSecondSequence": "ACGT" },
-    { "gisaid_epi_isl": "EPI_ISL_3128811", "testSecondSequence": "ACGTACGT" },
-    { "gisaid_epi_isl": "EPI_ISL_768148", "testSecondSequence": "ACGT" },
-    { "gisaid_epi_isl": "EPI_ISL_1002052", "testSecondSequence": "ACGT" },
-    { "gisaid_epi_isl": "EPI_ISL_2367431", "testSecondSequence": "NCGT" },
-    { "gisaid_epi_isl": "EPI_ISL_3128737", "testSecondSequence": "ACGT" },
-    { "gisaid_epi_isl": "EPI_ISL_466942", "testSecondSequence": "ACGT" },
-    { "gisaid_epi_isl": "EPI_ISL_1682849", "testSecondSequence": "ACGT" }
+    {"gisaid_epi_isl":"EPI_ISL_1001493","testSecondSequence":"ACGT"},
+    {"gisaid_epi_isl":"EPI_ISL_1001920","testSecondSequence":"ACGT"},
+    {"gisaid_epi_isl":"EPI_ISL_1002052","testSecondSequence":"ACGT"},
+    {"gisaid_epi_isl":"EPI_ISL_1002156","testSecondSequence":"ACGN"},
+    {"gisaid_epi_isl":"EPI_ISL_1003010","testSecondSequence":"ACGT"},
+    {"gisaid_epi_isl":"EPI_ISL_1003036","testSecondSequence":"ACGT"},
+    {"gisaid_epi_isl":"EPI_ISL_1003373","testSecondSequence":"ACGT"},
+    {"gisaid_epi_isl":"EPI_ISL_1003425","testSecondSequence":"ACGT"},
+    {"gisaid_epi_isl":"EPI_ISL_1003519","testSecondSequence":"ACGT"},
+    {"gisaid_epi_isl":"EPI_ISL_1003629","testSecondSequence":"ACGT"},
+    {"gisaid_epi_isl":"EPI_ISL_1003849","testSecondSequence":"ACGT"},
+    {"gisaid_epi_isl":"EPI_ISL_1004495","testSecondSequence":"ACGT"},
+    {"gisaid_epi_isl":"EPI_ISL_1005148","testSecondSequence":"ACGT"},
+    {"gisaid_epi_isl":"EPI_ISL_1036103","testSecondSequence":"ACGT"},
+    {"gisaid_epi_isl":"EPI_ISL_1080536","testSecondSequence":"ATGT"},
+    {"gisaid_epi_isl":"EPI_ISL_1119315","testSecondSequence":"ACGT"},
+    {"gisaid_epi_isl":"EPI_ISL_1119584","testSecondSequence":"ACGN"},
+    {"gisaid_epi_isl":"EPI_ISL_1129663","testSecondSequence":"ACGT"},
+    {"gisaid_epi_isl":"EPI_ISL_1130868","testSecondSequence":"ACGT"},
+    {"gisaid_epi_isl":"EPI_ISL_1131102","testSecondSequence":"ACGT"},
+    {"gisaid_epi_isl":"EPI_ISL_1195052","testSecondSequence":"ACGT"},
+    {"gisaid_epi_isl":"EPI_ISL_1260480","testSecondSequence":"ACGT"},
+    {"gisaid_epi_isl":"EPI_ISL_1273458","testSecondSequence":"ANGT"},
+    {"gisaid_epi_isl":"EPI_ISL_1273715","testSecondSequence":"ACGT"},
+    {"gisaid_epi_isl":"EPI_ISL_1360935","testSecondSequence":"ACGT"},
+    {"gisaid_epi_isl":"EPI_ISL_1361468","testSecondSequence":"ACGT"},
+    {"gisaid_epi_isl":"EPI_ISL_1407962","testSecondSequence":"ACGT"},
+    {"gisaid_epi_isl":"EPI_ISL_1408062","testSecondSequence":"ACGT"},
+    {"gisaid_epi_isl":"EPI_ISL_1408408","testSecondSequence":"ACGT"},
+    {"gisaid_epi_isl":"EPI_ISL_1408805","testSecondSequence":"ACGT"},
+    {"gisaid_epi_isl":"EPI_ISL_1597890","testSecondSequence":"ACGT"},
+    {"gisaid_epi_isl":"EPI_ISL_1597932","testSecondSequence":"ACGT"},
+    {"gisaid_epi_isl":"EPI_ISL_1599113","testSecondSequence":"ACGT"},
+    {"gisaid_epi_isl":"EPI_ISL_1682849","testSecondSequence":"ACGT"},
+    {"gisaid_epi_isl":"EPI_ISL_1747752","testSecondSequence":"ACGT"},
+    {"gisaid_epi_isl":"EPI_ISL_1747885","testSecondSequence":"ACGT"},
+    {"gisaid_epi_isl":"EPI_ISL_1748215","testSecondSequence":"ACGT"},
+    {"gisaid_epi_isl":"EPI_ISL_1748243","testSecondSequence":"ACGT"},
+    {"gisaid_epi_isl":"EPI_ISL_1748395","testSecondSequence":"ACGT"},
+    {"gisaid_epi_isl":"EPI_ISL_1749892","testSecondSequence":"ACGT"},
+    {"gisaid_epi_isl":"EPI_ISL_1749899","testSecondSequence":"AAGN"},
+    {"gisaid_epi_isl":"EPI_ISL_1749960","testSecondSequence":"ACGT"},
+    {"gisaid_epi_isl":"EPI_ISL_1750503","testSecondSequence":"ACGT"},
+    {"gisaid_epi_isl":"EPI_ISL_1750868","testSecondSequence":"ACGT"},
+    {"gisaid_epi_isl":"EPI_ISL_1760534","testSecondSequence":"ACGT"},
+    {"gisaid_epi_isl":"EPI_ISL_1840634","testSecondSequence":"ACGN"},
+    {"gisaid_epi_isl":"EPI_ISL_2016901","testSecondSequence":"ACGT"},
+    {"gisaid_epi_isl":"EPI_ISL_2017036","testSecondSequence":"ANGT"},
+    {"gisaid_epi_isl":"EPI_ISL_2019235","testSecondSequence":"ACGT"},
+    {"gisaid_epi_isl":"EPI_ISL_2019350","testSecondSequence":"ACGT"},
+    {"gisaid_epi_isl":"EPI_ISL_2086867","testSecondSequence":"ACGT"},
+    {"gisaid_epi_isl":"EPI_ISL_2180023","testSecondSequence":"ACGT"},
+    {"gisaid_epi_isl":"EPI_ISL_2180995","testSecondSequence":"ACGT"},
+    {"gisaid_epi_isl":"EPI_ISL_2181005","testSecondSequence":"ACGT"},
+    {"gisaid_epi_isl":"EPI_ISL_2213804","testSecondSequence":"ACGT"},
+    {"gisaid_epi_isl":"EPI_ISL_2213934","testSecondSequence":"ACGT"},
+    {"gisaid_epi_isl":"EPI_ISL_2213984","testSecondSequence":"ACGT"},
+    {"gisaid_epi_isl":"EPI_ISL_2214128","testSecondSequence":"ACGT"},
+    {"gisaid_epi_isl":"EPI_ISL_2270139","testSecondSequence":null},
+    {"gisaid_epi_isl":"EPI_ISL_2307766","testSecondSequence":"ACGT"},
+    {"gisaid_epi_isl":"EPI_ISL_2307888","testSecondSequence":"ACGT"},
+    {"gisaid_epi_isl":"EPI_ISL_2308054","testSecondSequence":null},
+    {"gisaid_epi_isl":"EPI_ISL_2359636","testSecondSequence":"ACGT"},
+    {"gisaid_epi_isl":"EPI_ISL_2360326","testSecondSequence":"ACGT"},
+    {"gisaid_epi_isl":"EPI_ISL_2367431","testSecondSequence":"NCGT"},
+    {"gisaid_epi_isl":"EPI_ISL_2374969","testSecondSequence":"ACGT"},
+    {"gisaid_epi_isl":"EPI_ISL_2375097","testSecondSequence":"ACGT"},
+    {"gisaid_epi_isl":"EPI_ISL_2375165","testSecondSequence":"ACGT"},
+    {"gisaid_epi_isl":"EPI_ISL_2375247","testSecondSequence":"ACGT"},
+    {"gisaid_epi_isl":"EPI_ISL_2375490","testSecondSequence":"ACGT"},
+    {"gisaid_epi_isl":"EPI_ISL_2379651","testSecondSequence":"ACGT"},
+    {"gisaid_epi_isl":"EPI_ISL_2405276","testSecondSequence":"ACGT"},
+    {"gisaid_epi_isl":"EPI_ISL_2408472","testSecondSequence":"AAGT"},
+    {"gisaid_epi_isl":"EPI_ISL_2544226","testSecondSequence":"ACGT"},
+    {"gisaid_epi_isl":"EPI_ISL_2544332","testSecondSequence":"ACGT"},
+    {"gisaid_epi_isl":"EPI_ISL_2544452","testSecondSequence":"ACGT"},
+    {"gisaid_epi_isl":"EPI_ISL_2574088","testSecondSequence":"ACGT"},
+    {"gisaid_epi_isl":"EPI_ISL_3016465","testSecondSequence":"ACGT"},
+    {"gisaid_epi_isl":"EPI_ISL_3086369","testSecondSequence":"ACGT"},
+    {"gisaid_epi_isl":"EPI_ISL_3128737","testSecondSequence":"ACGT"},
+    {"gisaid_epi_isl":"EPI_ISL_3128796","testSecondSequence":"ACGT"},
+    {"gisaid_epi_isl":"EPI_ISL_3128811","testSecondSequence":"ACGTACGT"},
+    {"gisaid_epi_isl":"EPI_ISL_3247294","testSecondSequence":null},
+    {"gisaid_epi_isl":"EPI_ISL_3259931","testSecondSequence":"JRZFHVKQIQGIVPUNJZCDKLOPDFTWZWXEXKZIHLGFWZNIGUAAPJBXPQCJBFUYHHIOPNDMTMHAFPHMZRCNUGIBRZCNKAJZMWXMBMPQRTZQUHTIFSOBXAQWMESDRWVJQWRE"},
+    {"gisaid_epi_isl":"EPI_ISL_3267832","testSecondSequence":"ACGT"},
+    {"gisaid_epi_isl":"EPI_ISL_3465556","testSecondSequence":"ACGT"},
+    {"gisaid_epi_isl":"EPI_ISL_3465732","testSecondSequence":"ACGT"},
+    {"gisaid_epi_isl":"EPI_ISL_3578231","testSecondSequence":"ACGT"},
+    {"gisaid_epi_isl":"EPI_ISL_466942","testSecondSequence":"ACGT"},
+    {"gisaid_epi_isl":"EPI_ISL_581968","testSecondSequence":"ACGT"},
+    {"gisaid_epi_isl":"EPI_ISL_721941","testSecondSequence":"ACGT"},
+    {"gisaid_epi_isl":"EPI_ISL_737604","testSecondSequence":"ACGT"},
+    {"gisaid_epi_isl":"EPI_ISL_737715","testSecondSequence":"ACGT"},
+    {"gisaid_epi_isl":"EPI_ISL_737860","testSecondSequence":"ACGT"},
+    {"gisaid_epi_isl":"EPI_ISL_768148","testSecondSequence":"ACGT"},
+    {"gisaid_epi_isl":"EPI_ISL_830864","testSecondSequence":"ACGT"},
+    {"gisaid_epi_isl":"EPI_ISL_899725","testSecondSequence":"ACGT"},
+    {"gisaid_epi_isl":"EPI_ISL_899762","testSecondSequence":"ACGT"},
+    {"gisaid_epi_isl":"EPI_ISL_931031","testSecondSequence":"ACGT"},
+    {"gisaid_epi_isl":"EPI_ISL_931279","testSecondSequence":"ACGT"}
   ]
 }
diff --git a/endToEndTests/test/queries/recombinantLineageWithAlias.json b/endToEndTests/test/queries/recombinantLineageWithAlias.json
@@ -13,7 +13,7 @@
   },
   "expectedQueryResult": [
     {
-      "count": 1
+      "count": 10
     }
   ]
 }
diff --git a/include/silo/common/bidirectional_map.h b/include/silo/common/bidirectional_map.h
@@ -33,6 +33,10 @@ class BidirectionalMap {
        : id_to_value(),
          value_to_id() {}
 
+   BidirectionalMap(std::vector<V>&& id_to_value, std::unordered_map<V, Idx>&& value_to_id)
+       : id_to_value(id_to_value),
+         value_to_id(value_to_id) {}
+
    BidirectionalMap(BidirectionalMap&& map) = default;
    BidirectionalMap& operator=(BidirectionalMap&& map) = default;
 

diff --git a/include/silo/common/lineage_tree.h b/include/silo/common/lineage_tree.h
@@ -1,18 +1,22 @@
 #pragma once
 
+#include <string>
+#include <unordered_map>
 #include <vector>
 
 #include <boost/serialization/access.hpp>
 
 #include "silo/common/bidirectional_map.h"
+#include "silo/common/lineage_name.h"
+#include "silo/common/types.h"
 #include "silo/preprocessing/lineage_definition_file.h"
 
 namespace silo::common {
 
 // The tree is allowed to be disconnected
 class LineageTree {
    friend class boost::serialization::access;
-   std::vector<std::optional<Idx>> parent_relation;
+   std::vector<std::vector<Idx>> parent_relation;
 
    template <class Archive>
    [[maybe_unused]] void serialize(Archive& archive, const uint32_t /* version */) {
@@ -30,7 +34,8 @@ class LineageTree {
 
    static LineageTree fromEdgeList(
       size_t n_vertices,
-      const std::vector<std::pair<Idx, Idx>>& edge_list
+      const std::vector<std::pair<Idx, Idx>>& edge_list,
+      const BidirectionalMap<std::string>& lookup
    );
 
    std::optional<Idx> getParent(Idx value);
@@ -43,12 +48,14 @@ class LineageTreeAndIdMap {
       // clang-format off
       archive & lineage_tree;
       archive & lineage_id_lookup_map;
+      archive & alias_mapping;
       // clang-format on
    }
 
   public:
    LineageTree lineage_tree;
    BidirectionalMap<std::string> lineage_id_lookup_map;
+   std::unordered_map<Idx, Idx> alias_mapping;
 
    LineageTreeAndIdMap() = default;
    LineageTreeAndIdMap(LineageTreeAndIdMap&& other) = default;
@@ -65,10 +72,14 @@ class LineageTreeAndIdMap {
   private:
    LineageTreeAndIdMap(
       LineageTree&& lineage_tree,
-      BidirectionalMap<std::string>&& lineage_id_lookup_map
+      BidirectionalMap<std::string>&& lineage_id_lookup_map,
+      std::unordered_map<Idx, Idx>&& alias_mapping
    );
 };
 
-bool containsCycle(int n, const std::vector<std::pair<Idx, Idx>>& edges);
+std::optional<std::vector<Idx>> containsCycle(
+   size_t number_of_vertices,
+   const std::vector<std::pair<Idx, Idx>>& edges
+);
 
 }  // namespace silo::common
diff --git a/include/silo/preprocessing/lineage_definition_file.h b/include/silo/preprocessing/lineage_definition_file.h
@@ -5,18 +5,15 @@
 
 #include <yaml-cpp/yaml.h>
 
-namespace silo::preprocessing {
-
-class LineageName {
-  public:
-   std::string string;
+#include "silo/common/lineage_name.h"
 
-   bool operator==(const LineageName& other) const;
-};
+namespace silo::preprocessing {
+using silo::common::LineageName;
 
 class LineageDefinition {
   public:
    LineageName lineage_name;
+   std::vector<LineageName> aliases;
    std::vector<LineageName> parents;
 };
 

diff --git a/include/silo/storage/column/indexed_string_column.h b/include/silo/storage/column/indexed_string_column.h
@@ -30,17 +30,19 @@ class IndexedStringColumnPartition {
       // clang-format off
       archive & value_ids;
       archive & indexed_values;
-      archive & lineage_index;
       // clang-format on
    }
 
    std::vector<Idx> value_ids;
    std::unordered_map<Idx, roaring::Roaring> indexed_values;
-   common::BidirectionalMap<std::string>& lookup;
-   std::optional<LineageIndex> lineage_index;
+   common::BidirectionalMap<std::string>* lookup;
+   std::optional<LineageIndex>* lineage_index;
 
   public:
-   explicit IndexedStringColumnPartition(common::BidirectionalMap<std::string>& lookup);
+   explicit IndexedStringColumnPartition(
+      common::BidirectionalMap<std::string>* lookup,
+      std::optional<LineageIndex>* lineage_index
+   );
 
    [[nodiscard]] std::optional<const roaring::Roaring*> filter(silo::Idx value_id) const;
 
@@ -54,7 +56,7 @@ class IndexedStringColumnPartition {
 
    [[nodiscard]] const std::vector<silo::Idx>& getValues() const;
 
-   [[nodiscard]] inline std::string lookupValue(Idx id) const { return lookup.getValue(id); }
+   [[nodiscard]] inline std::string lookupValue(Idx id) const { return lookup->getValue(id); }
 
    [[nodiscard]] std::optional<silo::Idx> getValueId(const std::string& value) const;
 
@@ -67,19 +69,21 @@ class IndexedStringColumn {
    template <class Archive>
    [[maybe_unused]] void serialize(Archive& archive, const uint32_t /* version */) {
       // clang-format off
-      archive & *lookup;
+      archive & lookup;
+      archive & lineage_index;
       // clang-format on
    }
 
-   std::unique_ptr<common::BidirectionalMap<std::string>> lookup;
+   common::BidirectionalMap<std::string> lookup;
+   std::optional<LineageIndex> lineage_index;
    std::deque<IndexedStringColumnPartition> partitions;
 
   public:
    IndexedStringColumn();
 
-   IndexedStringColumnPartition& createPartition();
+   IndexedStringColumn(const common::LineageTreeAndIdMap& lineage_tree);
 
-   void generateLineageIndex(const common::LineageTreeAndIdMap& lineage_tree);
+   IndexedStringColumnPartition& createPartition();
 };
 
 }  // namespace silo::storage::column