biopipen 0.31.1__py3-none-any.whl → 0.31.3__py3-none-any.whl

biopipen/__init__.py

@@ -1 +1 @@
-__version__ = "0.31.1"
+__version__ = "0.31.3"

biopipen/scripts/tcr/CDR3AAPhyschem.R

@@ -169,7 +169,12 @@ immdata = readRDS(immdatafile)
 
 merge_data = function(sam) {
     # Merge the data for one sample from immdata and metadata
-    out = immdata$data[[sam]] %>%
+    out = immdata$data[[sam]]
+    if ("chain" %in% colnames(out)) {
+        out = out %>% separate_rows(chain, CDR3.aa, V.name, J.name, sep = ";") %>%
+            filter(chain == "TRB")
+    }
+    out = out %>%
         mutate(
             Sample = sam,
             locus = "TCRB",

biopipen/scripts/tcr/TCRClustering.R

@@ -34,9 +34,16 @@ if (is.null(prefix)) { prefix = immdata$prefix }
 if (is.null(prefix)) { prefix = "" }
 
 get_cdr3aa_df = function() {
-    expand_immdata(immdata, cell_id = "Barcode") %>%
-        mutate(Barcode = glue(paste0(prefix, "{Barcode}"))) %>%
-        select(Barcode, CDR3.aa)
+    out = expand_immdata(immdata, cell_id = "Barcode") %>%
+        mutate(Barcode = glue(paste0(prefix, "{Barcode}")))
+
+    if (on_multi) {
+        out$CDR3.aa = sub(";", "", out$CDR3.aa)
+    } else if ("chain" %in% colnames(out)) {
+        out = out %>% separate_rows(chain, CDR3.aa, sep = ";") %>%
+            filter(chain == "TRB")
+    }
+    out %>% select(Barcode, CDR3.aa)
 }
 cdr3aa_df = get_cdr3aa_df()
 
@@ -159,12 +166,14 @@ prepare_input = function() {
     # cdr3col = if (!on_multi) "cdr3" else "CDR3.aa"
     cdr3col = "CDR3.aa"
     for (sample in names(seqdata)) {
-        # cdr3 = bind_rows(cdr3, seqdata[[sample]] %>%
-        #     transmute(aminoAcid=CDR3.aa, vMaxResolved=paste0(V.name, "*01"), Sample=sample))
-        cdr3 = union(
-            cdr3,
-            seqdata[[sample]] %>% pull(cdr3col) %>% unique()
-        )
+        sdata = seqdata[[sample]]
+        if (on_multi) {
+            sdata[[cdr3col]] = sub(";", "", sdata[[cdr3col]])
+        } else if ("chain" %in% colnames(sdata)) {
+            sdata = sdata %>% separate_rows(chain, cdr3col, sep = ";") %>%
+                filter(chain == "TRB")
+        }
+        cdr3 = union(cdr3, unique(sdata[[cdr3col]]))
     }
     cdr3 = unique(cdr3)
 

{biopipen-0.31.1.dist-info → biopipen-0.31.3.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: biopipen
-Version: 0.31.1
+Version: 0.31.3
 Summary: Bioinformatics processes/pipelines that can be run from `pipen run`
 License: MIT
 Author: pwwang

{biopipen-0.31.1.dist-info → biopipen-0.31.3.dist-info}/RECORD

@@ -1,4 +1,4 @@
-biopipen/__init__.py,sha256=PB3hjnlSwoWLBLl2ge7lsrSRubKXRdIanr_Hg2t3ViA,23
+biopipen/__init__.py,sha256=KeJnUdf2sotD3eMjgcCRocii5SSlhH5-B6DNBS_0gO8,23
 biopipen/core/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 biopipen/core/config.py,sha256=edK5xnDhM8j27srDzsxubi934NMrglLoKrdcC8qsEPk,1069
 biopipen/core/config.toml,sha256=7IXvviRicZ2D1h6x3BVgbLJ96nsh-ikvZ0sVlQepqFE,1944
@@ -202,7 +202,7 @@ biopipen/scripts/tcgamaf/Maf2Vcf.py,sha256=Cxh7fiSNCxWDTfIJqZDOOnaSrw-85S_fH2U-P
 biopipen/scripts/tcgamaf/MafAddChr.py,sha256=V10HMisl12O3ZfXuRmFNdy5p-3mr43WCvy0GHxSpwfA,494
 biopipen/scripts/tcgamaf/maf2vcf.pl,sha256=hJKcH-NbgWK6fmK7f3qex7ozJJl-PqCNPXqpwfcHwJg,22707
 biopipen/scripts/tcr/Attach2Seurat.R,sha256=0KZaBkuPvqOBXq4ZG3pzIIua5HL-161K5dVXRoCysy4,1366
-biopipen/scripts/tcr/CDR3AAPhyschem.R,sha256=3fWmoTwxVHM3CNnwxdKxy6-7Jul1UltoN4ic39aGTH0,16649
+biopipen/scripts/tcr/CDR3AAPhyschem.R,sha256=ZxHyn4vJF-1PDbnbozovOipET_QZKqeFrKUibRpLgzw,16825
 biopipen/scripts/tcr/CloneResidency.R,sha256=KAcFB39vTYsk8IEj44s8oSFVhKjpAdJ8hkpKxtdWzRA,21540
 biopipen/scripts/tcr/CloneSizeQQPlot.R,sha256=hds1C80Q_W40Ikp-BrFfvh_aBf_V61lz-1YAvkDESyk,4569
 biopipen/scripts/tcr/GIANA/GIANA.py,sha256=0qLhgCWxT8K-4JvORA03CzBPTT5pd4Di5B_DgrHXbFA,47198
@@ -225,7 +225,7 @@ biopipen/scripts/tcr/ImmunarchLoading.R,sha256=Vw2oIza3mDJzg9kuo-w5jvwdivk4AtDA6
 biopipen/scripts/tcr/ImmunarchSplitIdents.R,sha256=FGCeGV0uSmFU91lKkldUAeV4A2m3hHw5X4GNi8ffGzI,1873
 biopipen/scripts/tcr/SampleDiversity.R,sha256=oipN4-2nQZe8bYjI0lZ0SvZ7T8GZ_FWkpkobi1cwmWE,2664
 biopipen/scripts/tcr/TCRClusterStats.R,sha256=QhXgfKSh27VHO901hDizyGYTXMYFJxW22StchQUq3uE,12906
-biopipen/scripts/tcr/TCRClustering.R,sha256=LOdq6NjKcRydGSSoYehILgH4vPCeHIbVpSEYev05578,9278
+biopipen/scripts/tcr/TCRClustering.R,sha256=MRCaFbgMhhW9uimVBrE1Q5VqqxQpnKv5W2ILWmHdkU8,9593
 biopipen/scripts/tcr/TCRDock.py,sha256=jjzxMWp-hs0LDtA1mVbiWDvUieSO7X-F9yeKGy1LSTM,3026
 biopipen/scripts/tcr/TESSA.R,sha256=XFC2P_e_Gm83jG5EjzVIW6KcyG5IieAaK7sXDA3_oZ0,6864
 biopipen/scripts/tcr/TESSA_source/Atchley_factors.csv,sha256=SumqDOqP67P54uM7Cuc5_O_rySTWcGo7eX3psMSPX9s,763
@@ -279,7 +279,7 @@ biopipen/utils/reference.py,sha256=oi5evicLwHxF0KAIPNZohBeHJLJQNWFJH0cr2y5pgcg,5
 biopipen/utils/rnaseq.R,sha256=Ro2B2dG-Z2oVaT5tkwp9RHBz4dp_RF-JcizlM5GYXFs,1298
 biopipen/utils/single_cell.R,sha256=pJjYP8bIZpNAtTQ32rOXhZxaM1Y-6D-xUcK3pql9tbk,4316
 biopipen/utils/vcf.py,sha256=ajXs0M_QghEctlvUlSRjWQIABVF02wPdYd-0LP4mIsU,9377
-biopipen-0.31.1.dist-info/METADATA,sha256=uPOVUaGxNgT5ZJwJWBDXqmnxaBUxaMvyErjqFCRsV60,882
-biopipen-0.31.1.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
-biopipen-0.31.1.dist-info/entry_points.txt,sha256=69SbeMaF47Z2DS40yo-qDyoBKmMmumrNnsjEZMOioCE,625
-biopipen-0.31.1.dist-info/RECORD,,
+biopipen-0.31.3.dist-info/METADATA,sha256=8EHJ3ymJf16BFc_fq11-5SnzC3XwuJw67fXEpe2vYlM,882
+biopipen-0.31.3.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
+biopipen-0.31.3.dist-info/entry_points.txt,sha256=69SbeMaF47Z2DS40yo-qDyoBKmMmumrNnsjEZMOioCE,625
+biopipen-0.31.3.dist-info/RECORD,,