refined LOESS section, added background on normalization

graphics_bioinf.R

@@ -36,7 +36,7 @@ library("vsn")
 library("matrixStats")
 library("pheatmap")
 library("tidyverse")
-
+#library("printr")
 
 theme_set(theme_gray(base_size = 18))
 
@@ -94,13 +94,21 @@ load(file.path(data_dir, "mtec_cell_anno.RData"))
 load(file.path(data_dir, "mtec_gene_anno.RData"))
 load(file.path(data_dir, "tras.RData"))
 
-## ----mtec_count_table----------------------------------------------------
+## ----mtec_count_table, results="asis"------------------------------------
 mtec_counts
 
+## ----mtec_cell_anno, results="asis"--------------------------------------
+mtec_cell_anno
+
+## ----trasENSEMBL, results="asis"-----------------------------------------
+tras
+mtec_gene_anno
+
 ## ----tidy_count----------------------------------------------------------
 mtec_counts_tidy <- gather(mtec_counts, key = "cell_id", value = "count",
                            -ensembl_id) %>%
-                           dplyr::mutate(is_tra = ensembl_id %in% tras$gene.ids,
+                           dplyr::mutate(
+                                  is_tra = ensembl_id %in% tras$gene.ids,
                                   is_detected = count > 0) %>%
                            left_join(mtec_cell_anno, 
                                     by = c("cell_id" = "cellID"))
@@ -128,7 +136,7 @@ scatter_tra
 scatter_tra + 
   geom_rug(alpha = I(0.2))
 
-## ----ex_geom-------------------------------------------------------------
+## ----ex_geom, echo=FALSE-------------------------------------------------
 ggplot(tra_detected, aes(x = total_detected, y = tra))
 
 scatter_tra +
@@ -140,33 +148,46 @@ lm_tra <- lm(tra ~ total_detected, data = tra_detected)
 lm_tra
 
 ## ----loessExampleLinFit, dependson="fit_model"---------------------------
+sim_data <- tibble(x = seq(from=1, to=10, length.out=100),
+                   y = x^3 +x^2  + rnorm(100,mean=0, sd=60))
 
-# create_data
-y <- seq(from=1, to=10, length.out=100)
-a <- y^3 +y^2  + rnorm(100,mean=0, sd=30)
-dataL <- data.frame(a=a, y=y)
-qplot(y, a, data = dataL)
+ggplot(aes(x, y), data = sim_data) +
+  geom_point() +
+  geom_smooth(method = "lm")
 
-# linear fit
-linreg <- lm(a~y, data = dataL)
 
+## ----loessExampleFit, dependson="loessExampleLinFit"---------------------
 
-(qplot(y, a, data = dataL) +
-  geom_abline(slope = tidy(linreg, quick = TRUE)[2,2], 
-              intercept = tidy(linreg, quick = TRUE)[1,2]))
-tidy(linreg)
+sim_data$locFit  <- predict(locfit(y~lp(x, nn=0.5, deg=1), data=sim_data),
+                         newdata = sim_data$x)
 
-dataL$LinReg <- predict(linreg)
+ggplot(aes(x, y), data = sim_data) +
+  geom_point() +
+  geom_smooth(method = "lm") +
+  ggtitle("Linear vs. local regression") +
+  geom_line(aes(x = x, y = locFit), color = "coral3")
 
-## ----loessExampleFit, dependson="loessExampleLinFit"---------------------
 
-dataL$locFit  <- predict(locfit(y~lp(a, nn=0.5, deg=1), data=dataL),
-                         newdata = dataL$a)
+## ----loessExercise, dependson="loessExampleLinFit", echo=FALSE-----------
+
+sim_data$locFit  <- predict(locfit(y~lp(x, nn=0.1, deg=1), data=sim_data),
+                         newdata = sim_data$x)
+
+ggplot(aes(x, y), data = sim_data) +
+  geom_point() +
+  geom_smooth() +
+  ggtitle("Linear vs. local regression") +
+  geom_line(aes(x = x, y = locFit), color = "coral3")
+
 
+## ----compCells-----------------------------------------------------------
 
- (qplot(a, y, data = dataL, main = "Linear vs. local regression")
- +  geom_line(aes(x = a, y = locFit), color = "dodgerblue3")
- +  geom_line(aes(x = a, y = LinReg), color = "coral3"))
+ggplot(aes(x = cell_id, y = log(count)), 
+           data = filter(mtec_counts_tidy, 
+                         cell_id %in% c("cell77", "cell6S35"),
+                         is_detected == TRUE)) +
+                         
+      geom_boxplot()
 
 
 ## ----import_crc----------------------------------------------------------