MicrobTiSDA (version 0.1.0)

Classify.vis: Visualize Microbial Feature Classification Results Using NMDS

Description

This function generates a non-metric multidimensional scaling (NMDS) plot to visualize OTU/ASV classification results. It combines an OTU/ASV table with predicted group labels to produce a scatter plot in NMDS space, where each sample is colored according to its predicted group.

Usage

Classify.vis(
  classified_results,
  dist_method = "bray",
  fig_title = "NMDS visualization",
  legd_title = "Predicted Groups",
  points_size = 1,
  legend_title_size = 8,
  legend_text_size = 6,
  axis_title_size = 6,
  axis_text_size = 6
)

Value

A ggplot2 object displaying the NMDS plot with samples colored by their predicted group and convex hulls outlining each group.

Arguments

classified_results

A list object of Data.rf.classifier output.

dist_method

Dissimilarity index, defaults to bray. For other options, including manhattan, euclidean, canberra etc., see vegdist.

fig_title

A character string specifying the title of the NMDS plot. Default is 'NMDS visualization'.

legd_title

A character string for the legend title representing the predicted groups. Default is 'Predicted Groups'.

points_size

A numeric value specifying the size of the points in the plot. Default is 1.

legend_title_size

A numeric value specifying the font size of the legend title. Default is 8.

legend_text_size

A numeric value specifying the font size of the legend text. Default is 6.

axis_title_size

A numeric value specifying the font size of the axis titles. Default is 6.

axis_text_size

A numeric value specifying the font size of the axis text. Default is 6.

Author

Shijia Li

Details

The function expects as input the results of output of the function Data.rf.classifier. It conputes NMDS coordinates based on the OTU/ASV data using the specified distance method (defaulting to Bray-Curtis) and then maps the predicted group labels onto the NMDS coordinates. The visualization is produced using ggplot2, with polygons delineating the convex hull of each predicted group.

Examples

# \donttest{
# Example OTU count data (20 OTUs x 10 samples)
set.seed(123)
otu_data <- matrix(sample(0:100, 200, replace = TRUE), nrow = 20)
colnames(otu_data) <- paste0("Sample", 1:10)
rownames(otu_data) <- paste0("OTU", 1:20)

# Example metadata with group labels
metadata <- data.frame(Group = rep(c("Control", "Treatment"), each = 5))

# Run the classifier
rf_result <- Data.rf.classifier(raw_data = otu_data,
                             metadata = metadata,
                             train_p = 0.7,
                             Group = "Group",
                             OTU_counts_filter_value = 50)
# If you wish to select the top 5 features:
result <- Rf.biomarkers(rf = rf_result, feature_select_num = 5)

nm_plot <- Classify.vis(classified_results = result,
                        dist_method = 'bray',
                        fig_title = 'NMDS Plot',
                        legd_title = 'Predicted Groups',
                        points_size = 1.5)
# }