From 4421e3246f88ccc02c680e64237ad405139684d2 Mon Sep 17 00:00:00 2001 From: Adam Dinan Date: Mon, 22 Jan 2024 15:48:01 -0600 Subject: [PATCH] Remove check for ref ann file as now optional --- bin/merge_kallisto_counts.py | 2 +- bin/normalise_counts.R | 2 +- bin/pca.R | 9 --------- 3 files changed, 2 insertions(+), 11 deletions(-) diff --git a/bin/merge_kallisto_counts.py b/bin/merge_kallisto_counts.py index 7bbe35b..151decc 100755 --- a/bin/merge_kallisto_counts.py +++ b/bin/merge_kallisto_counts.py @@ -41,7 +41,7 @@ def merge_counts( gene_lengths = gene_lengths.rename(columns={"feature_id": "locus_tag"}) quant_merged = quant_merged[["feature_id"] + metadata["sample"].tolist()] # export merged counts - outf1 = os.path.join(out_dir, "gene_counts.tsv") + outf1 = os.path.join(out_dir, "gene_counts1.tsv") quant_merged.to_csv(outf1, index=False, sep="\t") # # gene annotation df for extracting protein-coding genes # annot_dat = (gffpd.read_gff3(gff_f)).df diff --git a/bin/normalise_counts.R b/bin/normalise_counts.R index f6ddf8e..daa10a4 100755 --- a/bin/normalise_counts.R +++ b/bin/normalise_counts.R @@ -36,7 +36,7 @@ outdir <- opt$outdir # stringsAsFactors = FALSE # ) -counts_tab <- read_tsv("gene_counts_pc1.tsv") +counts_tab <- read_tsv("gene_counts_pc.tsv") ref_gene_tab <- read_tsv("ref_gene_df.tsv") gene_names <- counts_tab[["feature_id"]] diff --git a/bin/pca.R b/bin/pca.R index 40ab845..8e65f14 100755 --- a/bin/pca.R +++ b/bin/pca.R @@ -57,8 +57,6 @@ meta_tab$group <- as.factor(as.character(meta_tab$group)) ## order rows to match counts columns meta_tab <- meta_tab[match(colnames(norm_counts), meta_tab$sample), ] -cat(colnames(norm_counts), file = stderr()) -cat(dim(norm_counts), file = stderr()) ## ------------------------------------------------------------------------------ @@ -66,16 +64,9 @@ cat(dim(norm_counts), file = stderr()) ## ------------------------------------------------------------------------------ pca_counts <- prcomp(t(norm_counts), center = TRUE, scale = FALSE) -cat(colnames(pca_counts), file = stderr()) -cat(dim(pca_counts), file = stderr()) - pca_coords <- data.frame(pca_counts$x) pca_coords$sample <- rownames(pca_coords) -cat(colnames(pca_coords), file = stderr()) -cat(dim(pca_coords), file = stderr()) - - # move sample to first column pca_coords <- pca_coords[c( "sample", colnames(pca_coords)[1:ncol(pca_coords) - 1]