feat: add prefer-deletion-insertion option to coding-dna

chrovis · Feb 6, 2025 · 5a82362 · 5a82362
1 parent 4847fa7
commit 5a82362
Show file tree

Hide file tree

Showing 4 changed files with 24 additions and 2 deletions.
diff --git a/src/varity/hgvs.clj b/src/varity/hgvs.clj
@@ -10,6 +10,8 @@
    {:prefer-deletion? true}
    {:prefer-insertion? false}
    {:prefer-insertion? true}
+   {:prefer-deletion-insertion? false}
+   {:prefer-deletion-insertion? true}
    {:prefer-extension-for-initial-codon-alt? false}
    {:prefer-extension-for-initial-codon-alt? true}])
 

diff --git a/src/varity/vcf_to_hgvs.clj b/src/varity/vcf_to_hgvs.clj
@@ -69,6 +69,7 @@
 (def ^:private default-options
   {:prefer-deletion? false
    :prefer-insertion? false
+   :prefer-deletion-insertion? false
    :prefer-extension-for-initial-codon-alt? false
    :tx-margin 5000
    :verbose? false})
@@ -91,6 +92,10 @@
     :prefer-insertion? Prefer insertion (e.g. \"c.9_10insAGG\") to repeated
                        sequences (e.g. \"c.4_6[3]\"), default false.
 
+    :prefer-deletion-insertion? Prefer indel (e.g. \"c.18_20delATCinsGAT\")
+                                to inversion (e.g. \"c.18_20inv\"),
+                                default false.
+
     :tx-margin         The length of transcription margin, up to a maximum of
                        10000, default 5000.
 
@@ -234,6 +239,10 @@
     :prefer-insertion? Prefer insertion (e.g. \"c.9_10insAGG\") to repeated
                        sequences (e.g. \"c.4_6[3]\"), default false.
 
+    :prefer-deletion-insertion? Prefer indel (e.g. \"c.18_20delATCinsGAT\")
+                                to inversion (e.g. \"c.18_20inv\"),
+                                default false.
+
     :prefer-extension-for-initial-codon-alt? Prefer extension to protein unknown variant
                                              that affects initial codon, default false.
 

diff --git a/src/varity/vcf_to_hgvs/coding_dna.clj b/src/varity/vcf_to_hgvs/coding_dna.clj
@@ -68,7 +68,7 @@
       :reverse (repeat-info-backward seq-rdr rg pos alt type))))
 
 (defn- mutation-type
-  [seq-rdr rg pos ref alt {:keys [prefer-deletion? prefer-insertion?]}]
+  [seq-rdr rg pos ref alt {:keys [prefer-deletion? prefer-insertion? prefer-deletion-insertion?]}]
   (if (re-matches #"[acgntACGNT]*" alt)
     (let [[ref-only alt-only offset _] (diff-bases ref alt)
           nrefo (count ref-only)
@@ -79,7 +79,9 @@
         (or (= nrefo nalto 0) (= nrefo nalto 1)) :substitution
         (and prefer-deletion? (pos? nrefo) (zero? nalto)) :deletion
         (and prefer-insertion? (zero? nrefo) (pos? nalto)) :insertion
-        (= ref-only (util-seq/revcomp alt-only)) :inversion
+        (= ref-only (util-seq/revcomp alt-only)) (if (and prefer-deletion-insertion? (pos? nrefo) (pos? nalto))
+                                                   :indel
+                                                   :inversion)
         (and (some? unit) (= ref-repeat 1) (= alt-repeat 2)) :duplication
         (and (some? unit) (pos? alt-repeat)
              ;; In the protein coding region, repeat descriptions are used only

diff --git a/test/varity/vcf_to_hgvs_test.clj b/test/varity/vcf_to_hgvs_test.clj
@@ -166,6 +166,15 @@
         "chr3" 126492636 "C" "CCTCT" {:prefer-insertion? true} '("NM_001165974:c.1690-121_1690-120insAGAG"
                                                                  "NM_144639:c.1510-121_1510-120insAGAG")
 
+        ;; prefer-deletion-inserion?
+        ;; inversion cf. rs267608133 (+)
+        "chr2" 47806747 "AAAACTTTTTTTTTTTTTTTTTTAA" "ATTAAAAAAAAAAAAAAAAAAGTTT" {:prefer-deletion-insertion? true} '("NM_000179:c.4002-31_4002-8delAAACTTTTTTTTTTTTTTTTTTAAinsTTAAAAAAAAAAAAAAAAAAGTTT"
+                                                                                                                     "NM_001281492:c.3612-31_3612-8delAAACTTTTTTTTTTTTTTTTTTAAinsTTAAAAAAAAAAAAAAAAAAGTTT"
+                                                                                                                     "NM_001281493:c.3096-31_3096-8delAAACTTTTTTTTTTTTTTTTTTAAinsTTAAAAAAAAAAAAAAAAAAGTTT"
+                                                                                                                     "NM_001281494:c.3096-31_3096-8delAAACTTTTTTTTTTTTTTTTTTAAinsTTAAAAAAAAAAAAAAAAAAGTTT"
+                                                                                                                     "NM_025133:c.*1347_*1370delTTAAAAAAAAAAAAAAAAAAGTTTinsAAACTTTTTTTTTTTTTTTTTTAA"
+                                                                                                                     "NM_001190274:c.*1347_*1370delTTAAAAAAAAAAAAAAAAAAGTTTinsAAACTTTTTTTTTTTTTTTTTTAA")
+
         ;; tx-margin
         "chr5" 1295113 "G" "A" {:tx-margin 5000} '("NM_001193376:c.-124C>T"
                                                    "NM_198253:c.-124C>T")