Processing data

All RNA-Seq data

When we download/collect all data for a particular data type from Bgee you are working with processed data.

From this processed data you can plot for each sample, referent to each experiment, the distribution of relative expression values. In the graphic bellow we plot the boxplot for all libraries that are present in Bgee for RNA-Seq data in Drosophila melanogaster.

principalInfo <- c()
for (i in dataBgee_DM) {
  
  collect <- i[c(1,2,4,5,7,9, 10,12)]
  principalInfo <- rbind(principalInfo, collect)
}

ggplot(principalInfo, aes(x = Experiment.ID, y = log2(TPM))) +
        geom_boxplot(aes(color = Library.ID), show.legend = FALSE) + xlab("Experiments") + ylab("Log2(TPM)") +
        ggtitle("Libraries per experiments from RNA-Seq data")+
  scale_color_viridis_d() +
        theme(axis.text.x = element_text(angle = 45, hjust = 1))

Past versions of all-rnaseq-data-fig-1.png

You can also group the data by corresponding anatomical entities. Note that here a violin_plot can represent multiple samples if the libraries in same experiment belongs to same the anatomical entity.

ggplot(principalInfo, aes(x = Experiment.ID, y = log2(TPM), fill = Anatomical.entity.ID)) +
        geom_violin() + xlab("Experiments") + ylab("Log2(TPM)") +
        ggtitle("Experiments per anatomical entity")+
  scale_color_viridis_d() +
        theme(axis.text.x = element_text(angle = 45, hjust = 1))+ guides(colour = guide_legend(override.aes = list(size=1)))

Past versions of all-rnaseq-data-anntEnt-1.png

Per experiment

Using as an example in the course, we will focus on the experiment retrieved in the section Extract Information, this means the experimentId SRP002072.

By plotting the data (just to visualize) you should be able to find the samples that belongs to the same anatomical entity and developmental stage for this experiment.

experiment_SRP002072 <- dplyr::filter(principalInfo, Experiment.ID == "SRP002072")

## remove useless columns in this case Experiment.ID = SRP002072 and Strain = NA
experiment_SRP002072[1] <- NULL
experiment_SRP002072[6] <- NULL

ggplot(experiment_SRP002072, aes(x = Library.ID, y = log2(TPM))) +
        geom_violin(aes(fill = Anatomical.entity.ID, col = Stage.ID)) + xlab("Libraries") + ylab("Log2(TPM)") +
        ggtitle("Experiment SRP002072")+
  scale_color_viridis_d() +
        theme(axis.text.x = element_text(angle = 45, hjust = 1))+ guides(colour = guide_legend(override.aes = list(size=1)))

Past versions of process-one-experiment-1.png

From this experiment we can collect samples from the same anatomical entity and same developmental stage. Now we will search which samples from this experiment differ by sex.

sexInfo <- c("male", "female")
libInfo <- dplyr::filter(experiment_SRP002072, Sex %in% sexInfo)
print(unique(libInfo$Library.ID))

From our analysis we know that the samples retrieved as unique have the same anatomical entity and same developmental stage but they differ in sex. Just verify how they correlate in overall (relative expression - TPM).

## extract just fundamental columns to make a reformated data.frame
libInfo <- libInfo[c(1,2,6)]

## reformat the data
reshapeTable <- reshape(libInfo, direction='wide',idvar='Library.ID', timevar='Gene.ID')
reshapeTable <- t(reshapeTable)[-c(1),]
finalTable <- data.frame(as.numeric(reshapeTable[,1]), as.numeric(reshapeTable[,2]))
colnames(finalTable) <- c("SRX019652", "SRX019653")
finalTable <- log(finalTable)
finalTable <- as.matrix(finalTable)

finalTable <- finalTable[!rowSums(!is.finite(finalTable)),]
finalTable <- as.data.frame(finalTable)

ggstatsplot::ggscatterstats(
  data = finalTable,
  x = SRX019652,
  y = SRX019653,
  xlab = "SRX019652 (F)",
  ylab = "SRX019653 (M)",
  title = "Correlation between samples from same experiment",
  messages = FALSE
)

Past versions of libraries-correlation-1.png

Protein coding (All samples)

In the aforementioned graph, we just plotted the 2 samples from our narrow analysis.

In order to get an overview of the % of protein coding genes for all samples from Drosophila melanogaster we should make a general plot.

ggplot(annotation_DrosMelRNASeq$sample.annotation, aes(x = Experiment.ID, y = Protein.coding.genes.percent.present)) +
        geom_point(aes(color = Anatomical.entity.name ), show.legend = TRUE) + xlab("Experiments") + ylab("% Protein coding") +
        ggtitle("Percentage of protein coding per library")+
        theme(axis.text.x = element_text(angle = 45, hjust = 1))

Past versions of all-data-PC-1.png

Session information

sessionInfo()