Chain_qc adaptation (isotypically included B cells)

CHANGELOG.md

@@ -8,6 +8,12 @@ and this project adheres to [Semantic Versioning][].
 [keep a changelog]: https://keepachangelog.com/en/1.0.0/
 [semantic versioning]: https://semver.org/spec/v2.0.0.html
 
+## [Unreleased]
+
+### Addition
+
+-   Isotypically included B cells are now labelled as `receptor_subtype="IGH+IGK/L"` instead of `ambiguous` in `tl.chain_qc`. ([#537](https://github.com/scverse/scirpy/pull/537))
+
 ## v0.17.2
 
 ### Fixes

src/scirpy/tests/test_tools.py

@@ -30,6 +30,7 @@ def test_chain_qc():
             [False, "IGK", "IGH", "nan", "nan"],
             [False, "IGL", "IGH", "IGL", "IGH"],
             [False, "IGL", "IGH", "IGK", "IGH"],
+            [False, "IGK", "IGH", "IGL", "IGH"],
             [False, "nan", "IGH", "nan", "IGH"],
             [False, "TRA", "TRB", "TRG", "TRB"],
             [False, "IGK", "TRB", "nan", "nan"],
@@ -69,6 +70,7 @@ def test_chain_qc():
                 "BCR",
                 "BCR",
                 "BCR",
+                "BCR",
                 "TCR",
                 "ambiguous",
                 "TCR",
@@ -91,7 +93,8 @@ def test_chain_qc():
                 "TRA+TRB",
                 "IGH+IGK",
                 "IGH+IGL",
-                "ambiguous",
+                "IGH+IGK/L",
+                "IGH+IGK/L",
                 "IGH",
                 "ambiguous",
                 "ambiguous",

src/scirpy/tl/_chain_qc.py

@@ -42,9 +42,10 @@ def chain_qc(
         * `IGH` (all cells that have only IGH chains, but no IGL or IGK)
         * `IGH+IGL` (all cells that have only IGH and IGL chains)
         * `IGH+IGK` (all cells that have only IGH and IGK chains)
+        * `IGH+IGK/L` (isotypically included B cell i.e. IGH+IGK as the primary and
+          IGH+IGL as the secondary receptor or vice versa)
         * `multichain` (all cells with more than two VJ or more than two VDJ chains)
-        * `ambiguous` (all cells that are none of the above, e.g. TRA+TRD, TRA+IGH or,
-          IGH+IGK as the primary and IGH+IGL as the secondary receptor)
+        * `ambiguous` (all cells that are none of the above, e.g. TRA+TRD, TRA+IGH)
         * `no IR` (all cells without any detected immune receptor)
 
     `chain_pairing` can be one of the following
@@ -109,6 +110,7 @@ def chain_qc(
     subtype_is_tgd = (has_trg | has_trd) & ~(has_tra | has_trb | has_ig)
     subtype_is_ighk = (has_igk) & ~(has_tr | has_igl)
     subtype_is_ighl = (has_igl) & ~(has_tr | has_igk)
+    subtype_is_ighkl = (has_igl) & (has_igk) & ~(has_tr) & (has_igh)
     # orphan IGH
     subtype_is_igh = (has_igh) & ~(has_igk | has_igl | has_tr)
 
@@ -127,6 +129,7 @@ def chain_qc(
     res_receptor_subtype[subtype_is_igh] = "IGH"
     res_receptor_subtype[subtype_is_ighl] = "IGH+IGL"
     res_receptor_subtype[subtype_is_ighk] = "IGH+IGK"
+    res_receptor_subtype[subtype_is_ighkl] = "IGH+IGK/L"
     res_receptor_subtype[mask_multichain] = "multichain"
 
     res_chain_pairing = _chain_pairing(params, res_receptor_subtype == "ambiguous", mask_has_ir, mask_multichain)