library(ggplot2)
library(plotly)

# Create some random data
set.seed(123)
x <- rnorm(100)
y <- rnorm(100)
z <- rnorm(100)

# Perform PCA
data <- data.frame(x, y, z)
pca <- prcomp(data, scale = TRUE)
scores <- as.data.frame(pca$x)

# Create 3D scatterplot using ggplot2 and plotly
ggplot(scores, aes(x = PC1, y = PC2, z = PC3)) +
  geom_point(size = 3, color = "blue") +
  labs(x = "PC1", y = "PC2", z = "PC3") +
  theme_bw() +
  theme(panel.grid.major = element_blank(),
        panel.grid.minor = element_blank(),
        axis.line = element_line(colour = "black", size = 0.5),
        panel.border = element_blank()) +
  scale_x_continuous(limits = c(-4, 4), expand = c(0, 0)) +
  scale_y_continuous(limits = c(-4, 4), expand = c(0, 0)) +
  scale_z_continuous(limits = c(-4, 4), expand = c(0, 0)) +
  coord_cartesian(xlim = c(-4, 4), ylim = c(-4, 4), zlim = c(-4, 4)) +
  ggtitle("3D Scatterplot using PCA") +
  theme(plot.title = element_text(size = 12, face = "bold"))

This code creates a 3D scatterplot using ggplot2 and the plotly package. It first generates some random data and performs principal component analysis (PCA) on it. The resulting PCA scores are then plotted in a 3D scatterplot. The labs() function is used to set the axis labels, and the ggtitle() function is used to set the plot title. The scale_x_continuous(), scale_y_continuous(), and scale_z_continuous() functions are used to set the axis limits, and the coord_cartesian() function is used to ensure that the plot is displayed with the specified limits. The theme() function is used to adjust the appearance of the plot.