#368: quick fix

antigenomics · May 30, 2024 · 159abf5 · 159abf5
1 parent 6ba149f
commit 159abf5
Show file tree

Hide file tree

Showing 2 changed files with 30 additions and 27 deletions.
diff --git a/patches/antigen_epitope_species_gene.dict b/patches/antigen_epitope_species_gene.dict
@@ -202,11 +202,11 @@ STPESANL	SIV	Tat
 CLLGTYTQDV	StreptomycesKanamyceticus	KanJ
 SIYRYYGL	Synthetic	Synthetic
 WIYVYRPMGCGGS	Synthetic	Synthetic
-SGEGSFQPSQENP	TriticumAestivum	NA
-APQPELPYPQPGS	TriticumAestivum	NA
-APQPELPYPQPG	TriticumAestivum	NA
-QPFPQPELPYP	TriticumAestivum	NA
-PSGEGSFQPSQENPQ	TriticumAestivum	NA
+SGEGSFQPSQENP	TriticumAestivum	Gliadin
+APQPELPYPQPGS	TriticumAestivum	Gliadin
+APQPELPYPQPG	TriticumAestivum	Gliadin
+QPFPQPELPYP	TriticumAestivum	Gliadin
+PSGEGSFQPSQENPQ	TriticumAestivum	Gliadin
 RGYVYQGL	VSV	N
 RGYVYKGL	VSV	N
 RGYVYEGL	VSV	N
@@ -217,19 +217,19 @@ LLWNGPMAV	YFV	NS4B
 RPGGKKHYM	HIV-1	Nef
 RMYSPVSI	HIV-1	Gag
 RMYSPVSIL	HIV-1	Gag
-ALHGGWTTK	PIK3CA	HomoSapiens
-HMTEVVRHC	p53	HomoSapiens
-LQPFPQPELPYGSGGS	DQ2-GLIA-OMEGA1	HomoSapiens
-QPFPQPEQPFP	DQ2-GLIA-OMEGA1	HomoSapiens
-HMTEVVRHC	p53	HomoSapiens
-PGVLLKEFTVSGNIL	NY-ESO-1	HomoSapiens
-APRGPHGGAASGL	NY-ESO-1	HomoSapiens
-TSTLQEQIGW	Gag	HIV-1
-HTQGYFPD	Nef	HIV-1
-RPGGKKHYM	Nef	HIV-1
-KRKGGIGGY	Pol	HIV-1
-IVLPEDKSW	RT	HIV-1
-ALTPVVVTL	UNC-CDK4-1	HomoSapiens
-VEELYLVAGEEGCGGGGSL	Insulin HomoSapiens
-TTDPSFLGRY ORF1ab	SARS-CoV-2
-YLEPGPVTV	PMEL	HomoSapiens
+ALHGGWTTK	HomoSapiens	PIK3CA
+HMTEVVRHC	HomoSapiens	p53
+LQPFPQPELPYGSGGS	TriticumAestivum	Gliadin
+QPFPQPEQPFP	TriticumAestivum	Gliadin
+HMTEVVRHC	HomoSapiens	p53
+PGVLLKEFTVSGNIL	HomoSapiens	NY-ESO-1
+APRGPHGGAASGL	HomoSapiens	NY-ESO-1
+TSTLQEQIGW	HIV-1	Gag
+HTQGYFPD	HIV-1	Nef
+RPGGKKHYM	HIV-1	Nef
+KRKGGIGGY	HIV-1	Pol
+IVLPEDKSW	HIV-1	RT
+ALTPVVVTL	HomoSapiens	UNC-CDK4-1
+VEELYLVAGEEGCGGGGSL	HomoSapiens	Insulin
+TTDPSFLGRY SARS-CoV-2	ORF1ab
+YLEPGPVTV	HomoSapiens	PMEL
diff --git a/summary/vdjdb_summary.Rmd b/summary/vdjdb_summary.Rmd
@@ -396,16 +396,19 @@ Representative data for Homo Sapiens. The spectratype is colored by epitope.
 ```{r message=FALSE, warning=FALSE}
 df.spe = subset(df, species=="HomoSapiens")
 
-ggplot(df.spe, 
-       aes(x=nchar(as.character(cdr3)))) + 
-  geom_histogram(aes(fill = antigen.epitope), 
-                 bins = 21, 
+ggplot(df.spe %>% mutate(
+  epi_len = nchar(antigen.epitope),
+  antigen.epitope = as.factor(antigen.epitope)), 
+  aes(x=nchar(as.character(cdr3)))) + 
+  geom_histogram(aes(fill = antigen.epitope %>% fct_reorder(epi_len) %>% as.integer(), 
+                     group = antigen.epitope), #), 
+                 bins = 21, size = 0,
                  binwidth = 1, alpha = 0.9, color = NA) + 
   geom_density(aes(y=..count..), adjust = 4, linetype = "dotted") +
   scale_x_continuous(limits = c(5,25), breaks = seq(5,25,5)) + 
   facet_wrap(~gene) + 
-  #scale_fill_distiller(palette = "Spectral", guide=F, "") +
-  scale_fill_viridis_d(guide=F, direction = -1) +
+  scale_fill_distiller(palette = "Spectral", guide=F, "") +
+  #scale_fill_viridis_d(guide=F, direction = -1) +
   xlab("CDR3 length") + ylab("Records") +
   theme_classic() +
   theme(axis.line = element_line(size = 0.3),