#' <% visualizations.ShotGun.print_qc_intro_caption(len(dna_samples), dna_columns[2:]) %>
#' ## DNA Samples Quality Control
#' ### DNA Samples Tables of Filtered Reads
#+ echo=False
# create a table of the paired counts
document.write_table(["# Sample"] + dna_columns, dna_samples, dna_data,
files.ShotGunVis.path("qc_counts", document.data_folder))
table_message = visualizations.show_table_max_rows(
document,
dna_data,
dna_samples,
dna_columns,
"DNA reads",
files.ShotGunVis.path("qc_counts"),
format_data_comma=True)
#' <%= table_message %>
#+ echo=False
# compute and plot the microbial reads ratios
# compute ratios for each database used for qc
dna_microbial_reads, dna_microbial_labels = utilities.microbial_read_proportion_multiple_databases(
dna_data, dna_columns)
# create a table of the microbial reads
document.write_table(["# Sample"] + dna_microbial_labels, dna_samples,
dna_microbial_reads,
all_taxa_counts = [[
a, b, c, d
] for a, b, c, d in zip(species_counts, species_counts_after_filter,
genera_counts, genera_counts_after_filter)]
# create a table of the data in the output folder
taxa_counts_column_names = [
"# Sample", "Species", "Species filtered", "Genera", "Genera filtered"
]
document.write_table(
taxa_counts_column_names, samples, all_taxa_counts,
files.ShotGunVis.path("taxa_counts", document.data_folder))
# show the table, reducing the rows if there are lots of samples
table_message = visualizations.show_table_max_rows(
document, all_taxa_counts, samples, taxa_counts_column_names[1:],
"Total taxa per sample", files.ShotGunVis.path("taxa_counts"))
#' <%= table_message %>
#' ## Ordination
#' ### Species
#+ echo=False
# get the top species by average abundance
top_taxonomy, top_data = utilities.top_rows(species_taxonomy,
species_data,
max_sets_heatmap,
function="average")
#' <%= visualizations.ShotGun.format_caption("pathway_abundance_heatmap",norm="z-score") %>
#' <% if pdf_format: print("\clearpage") %>
#+ echo=False
# write a table of the pathways average and variance
pathway_file_name = "top_average_pathways_names.tsv"
average_abundance_variance = visualizations.write_pathway_average_variance_table(
document, pathway_file_name, dna_top_average_data,
top_names_and_descriptions)
table_message = visualizations.show_table_max_rows(
document,
average_abundance_variance,
top_names_and_descriptions, [" Average ", " Variance "],
"Top " + str(max_sets) + " pathways by average abundance",
pathway_file_name,
font=7)
#' <%= table_message %>
#' <% visualizations.print_pathways_urls(dna_top_average_pathways,top_names_and_descriptions,3) %>
#+ echo=False
# check for then rna/dna norm files
show_norm_ratio = False
if vars["genefamilies_norm_ratio"] and vars["ecs_norm_ratio"] and vars[
"paths_norm_ratio"]:
show_norm_ratio = True
#+ echo=False
#' ## DNA Samples Quality Control
#' ### DNA Samples Tables of Filtered Reads
#+ echo=False
document.write_table(["# Sample"] + dna_paired_columns, dna_samples,
dna_paired_data,
files.ShotGunVis.path("qc_counts_paired",
document.data_folder))
table_message = visualizations.show_table_max_rows(
document,
dna_paired_data,
dna_samples,
dna_paired_columns,
"DNA Paired end reads",
files.ShotGunVis.path("qc_counts_paired"),
format_data_comma=True)
#' <%= table_message %>
#+ echo=False
document.write_table(["# Sample"] + dna_orphan_columns, dna_samples,
dna_orphan_data,
files.ShotGunVis.path("qc_counts_orphan",
document.data_folder))
table_message = visualizations.show_table_max_rows(
document,
dna_orphan_data,