diff --git a/article/.RData b/article/.RData
index 8d8946a10c93df29096639fa1dd7d3ddc1517b26..d0cb02c81f66f20f0e5e408879fa136f4acdae00 100644
Binary files a/article/.RData and b/article/.RData differ
diff --git a/article/.RDataTmp1 b/article/.RDataTmp1
deleted file mode 100644
index d23c4208a969b4a3126b84ec16d8327603163176..0000000000000000000000000000000000000000
Binary files a/article/.RDataTmp1 and /dev/null differ
diff --git a/article/article_figures.Rmd b/article/article_figures.Rmd
index 72b21cb9636131194449735823279fc40769c39e..3dc06022829b9e490f30f502bae6a19e0367753c 100644
--- a/article/article_figures.Rmd
+++ b/article/article_figures.Rmd
@@ -178,65 +178,6 @@ ggsave("figures/fig2.pdf",grid,width=5,height=8)
rm(na_plot,prop_plot)
```
-## Table alleles different between parental strains and F2s
-
-```{r allele}
-#investigation of the role of mark_allele function
-#prove that some marker with non corresponding alleles between parents and F2
-
-#keep only markers that are exlcuded with mark_allele
-allele <- tab2%>%
- filter(exclude_allele==1&exclude_poly==0&exclude_prop==0)
-strains_allele <- strns_ref %>% filter(marker %in% allele$marker)
-
-#join with strains genotypes to have parental strains
-allele <- left_join(allele,strains_allele,by=c("marker"="marker"))
-
-
-#most of markers excluded with mark_allele that were not excluded with other functions have N/H as genotype for parents
-#keep only those with non missing/heterozygous genotypes
-allele %<>% filter(parent1 != "N" & parent2 != "N")
-allele %<>% select(marker,parent1,parent2,allele_1,allele_2)
-
-#number of markers in such situation
-count(tab2%>%
- filter(exclude_allele==1))
-
-#keep only beggining of the table
-allele <- allele[1:6,]
-
-print(allele)
-
-print(xtable::xtable(allele, type = "latex"), file = "tables/tab_alleles.tex",include.rownames=FALSE)
-rm(allele,strains_allele)
-```
-
-## Graph number of markers kept after each function
-
-```{r barplot}
-none <- tab2 %>% nrow()
-match <- tab2 %>% filter(exclude_match==0) %>% nrow()
-allele <- tab2 %>% filter(exclude_match==0&exclude_allele==0) %>% nrow()
-naf <- tab2 %>% filter(exclude_match==0&exclude_allele==0&exclude_na==0) %>% nrow()
-poly <- tab2 %>% filter(exclude_match==0&exclude_allele==0&exclude_na==0&exclude_poly==0) %>% nrow()
-prop <- tab2 %>% filter(exclude_match==0&exclude_allele==0&exclude_na==0&exclude_poly==0&exclude_prop==0) %>% nrow()
-
-
-functions_plot <- functions_df %>% ggplot(aes(x=markers,y=fct)) +
- geom_bar(stat="identity",width=0.6) +
- geom_text(aes(label=markers), hjust=1.3, color="white", size=3.5) +
- scale_y_discrete(limits=c("prop","poly", "na", "allele","match","none")) +
- theme(aspect.ratio=0.7) +
- labs(title="Number of markers kept after each step",
- x="Number of markers",
- y="Function used") +
- theme_classic() +
- theme(plot.title = element_text(hjust = 0.4,face="bold",size=14))
-
-functions_plot
-rm(none,allele,match,poly,prop,barplot_df)
-```
-
## Graph before after
### Before: creation of Rqtl csv file
@@ -431,11 +372,71 @@ dif <- full_join(strains,strns_ref,by=c("marker","chr","cM_cox")) %>%
dif %>% filter(dif==1) %>% count()
```
+## Table alleles different between parental strains and F2s
+
+```{r allele}
+#investigation of the role of mark_allele function
+#prove that some marker with non corresponding alleles between parents and F2
+
+#keep only markers that are exlcuded with mark_allele
+allele <- tab2%>%
+ filter(exclude_allele==1&exclude_poly==0&exclude_prop==0&exclude_na==0&exclude_estmap==0)
+strains_allele <- strains %>% filter(marker %in% allele$marker)
+
+#number of markers not excluded by other functoins
+tab2 %>%
+ filter(exclude_poly==0&exclude_prop==0&exclude_na==0&exclude_estmap==0) %>% nrow()
+
+#join with strains genotypes to have parental strains
+allele <- left_join(allele,strains_allele,by=c("marker"="marker"))
+
+
+#most of markers excluded with mark_allele that were not excluded with other functions have N/H as genotype for parents
+#keep only those with non missing/heterozygous genotypes
+allele %<>% filter(parent1 != "N" & parent2 != "N")
+allele %<>% select(marker,parent1,parent2,allele_1,allele_2)
+
+
+print(allele)
+
+print(xtable::xtable(allele, type = "latex"), file = "tables/tab_alleles.tex",include.rownames=FALSE)
+rm(allele,strains_allele)
+```
+
```{r dif_table}
table_dif <- dif %>% filter(dif==1) %>% select(marker,parent1_ref=parent1.y,parent1_geno=parent1.x,parent2_ref=parent2.y,parent2_geno=parent2.x) %>% head()
knitr::kable(table_dif)
```
+## Number of markers kept after each function
+
+```{r barplot}
+none <- tab2 %>% nrow()
+match <- tab2 %>% filter(exclude_match==0) %>% nrow()
+allele <- tab2 %>% filter(exclude_match==0&exclude_allele==0) %>% nrow()
+naf <- tab2 %>% filter(exclude_match==0&exclude_allele==0&exclude_na==0) %>% nrow()
+poly <- tab2 %>% filter(exclude_match==0&exclude_allele==0&exclude_na==0&exclude_poly==0) %>% nrow()
+prop <- tab2 %>% filter(exclude_match==0&exclude_allele==0&exclude_na==0&exclude_poly==0&exclude_prop==0) %>% nrow()
+estmap <- tab2 %>% filter(exclude_match==0&exclude_allele==0&exclude_na==0&exclude_poly==0&exclude_prop==0&exclude_estmap==0) %>% nrow()
+
+functions_df <- tibble(fct=c("none","match","allele","na","poly","prop","estmap"),
+ markers=c(none,match,allele,naf,poly,prop,estmap))
+
+functions_plot <- functions_df %>% ggplot(aes(x=markers,y=fct)) +
+ geom_bar(stat="identity",width=0.6) +
+ geom_text(aes(label=markers), hjust=1.3, color="white", size=3.5) +
+ scale_y_discrete(limits=c("estmap","prop","poly", "na", "allele","match","none")) +
+ theme(aspect.ratio=0.7) +
+ labs(title="Number of markers kept after each step",
+ x="Number of markers",
+ y="Function used") +
+ theme_classic() +
+ theme(plot.title = element_text(hjust = 0.4,face="bold",size=14))
+
+functions_plot
+rm(none,allele,match,poly,prop,barplot_df)
+```
+
# Pheno data format
```{r pheno}
format_pheno <- phenos[1:6,]
diff --git a/article/tables/tab_alleles.tex b/article/tables/tab_alleles.tex
new file mode 100644
index 0000000000000000000000000000000000000000..a3b393a4572c90e815405f68c25c7e22d1c8e0b7
--- /dev/null
+++ b/article/tables/tab_alleles.tex
@@ -0,0 +1,17 @@
+% latex table generated in R 4.0.4 by xtable 1.8-4 package
+% Tue Feb 15 09:50:40 2022
+\begin{table}[ht]
+\centering
+\begin{tabular}{lllll}
+ \hline
+marker & parent1 & parent2 & allele\_1 & allele\_2 \\
+ \hline
+S6J017555686 & C & C & T & C \\
+ S6J113080150 & G & G & A & G \\
+ gJAX00038569 & C & C & T & C \\
+ mUNC21540855 & C & C & A & C \\
+ gUNC21555204 & T & T & T & C \\
+ gUNC21596600 & A & A & A & G \\
+ \hline
+\end{tabular}
+\end{table}