The 'group1' or 'group2' column in the 'daa_results_df' data frame contains more than one group. Please filter each to contain only one group.

[saassli21]

Hello @cafferychen777 , I have 2 datasets , I tested the script that is in #65 on the first and it worked nicely because when I print this command (daa_sub_method_results_df1 <- daa_results_df %>% filter(p_adjust < 0.05) %>% slice(1:29) ) I only have one group in group1 (P1) and group2 (CONTROL) . However when I tested the same script on my second dataset:

metadata <- read_delim("metadata_exp3.txt", delim = "\t", escape_double = FALSE, trim_ws = TRUE , comment = "#")

kegg_abundance <- ko2kegg_abundance("pred_metagenome_unstrat_exp3.tsv")

daa_results_df <- pathway_daa(abundance = kegg_abundance, metadata = metadata, group = "STATUS", daa_method = "LinDA", select = NULL, p.adjust = "BH" , reference = "T1")

daa_sub_method_results_df1 <- daa_results_df %>% filter(p_adjust < 0.05) %>% slice(1:29)

max(daa_sub_method_results_df1$p_adjust)

daa_annotated_sub_method_results_df1 <- pathway_annotation(pathway = "KO", daa_results_df = daa_sub_method_results_df1, ko_to_kegg = TRUE)

p <- pathway_errorbar(abundance = kegg_abundance, daa_results_df = daa_annotated_sub_method_results_df1, Group = metadata$STATUS, p_values_threshold = 0.05, order = "pathway_class", select = NULL, ko_to_kegg = TRUE, p_value_bar = TRUE, colors = NULL, x_lab = "pathway_name")

but I have this error : The 'group1' or 'group2' column in the 'daa_results_df' data frame contains more than one group. Please filter each to contain only one group.

Error in levels<-(*tmp*, value = as.character(levels)) : factor level [5] is duplicated

this error is due to the presence of multiple group in group1

I did this. does it correct ?

metadata <- read_delim("metadata_exp3.txt", delim = "\t", escape_double = FALSE, trim_ws = TRUE, comment = "#")

kegg_abundance <- ko2kegg_abundance("pred_metagenome_unstrat_exp3.tsv")

daa_results_df <- pathway_daa(abundance = kegg_abundance, metadata = metadata, group = "STATUS", daa_method = "LinDA", select = NULL, p.adjust = "BH", reference = "T1")

Get unique groups in 'group1'

unique_groups_group1 <- unique(daa_results_df$group1)

Initialize an empty list to store results

results_list <- list()

Iterate over each unique group

for (selected_group in unique_groups_group1) {

Filter the data for the current group

current_group_results <- daa_results_df %>% filter(group1 == selected_group)

Filter based on p_adjust and slice

filtered_slice <- current_group_results %>% filter(p_adjust < 0.05) %>% slice(1:29)

Annotate pathway results using KO to KEGG conversion

daa_annotated_results_df <- pathway_annotation(pathway = "KO", daa_results_df = filtered_slice, ko_to_kegg = TRUE)

Generate pathway error bar plot

p <- pathway_errorbar(abundance = kegg_abundance, daa_results_df = daa_annotated_results_df, Group = metadata$STATUS, p_values_threshold = 0.05, order = "pathway_class", select = NULL, ko_to_kegg = TRUE, p_value_bar = TRUE, colors = NULL, x_lab = "pathway_name")

Generate PCA plot

p1 <- pathway_pca(kegg_abundance, metadata, "STATUS")

Generate pathway heatmap

p2 <- pathway_heatmap(kegg_abundance %>% rownames_to_column("feature") %>% filter(feature %in% daa_annotated_results_df$feature) %>% column_to_rownames("feature"), metadata, "STATUS")

Save the plots to PNG files

ggsave(paste0("pathway_errorbar_", selected_group, ".png"), p, width = 30, height = 20, units = "in", dpi = 300) ggsave(paste0("pathway_pca_", selected_group, ".png"), p1, width = 30, height = 20, units = "in", dpi = 300) ggsave(paste0("pathway_heatmap_", selected_group, ".png"), p2, width = 30, height = 20, units = "in", dpi = 300)

Save the results in the list

results_list[[selected_group]] <- list(daa_annotated_results_df = daa_annotated_results_df, p = p, p1 = p1, p2 = p2) }