Dataset from: https://portal.gdc.cancer.gov/projects/TCGA-LIHC
+
library(reneeTools)
-#> Warning: replacing previous import 'S4Arrays::makeNindexFromArrayViewport' by
-#> 'DelayedArray::makeNindexFromArrayViewport' when loading 'SummarizedExperiment'
library(dplyr)
#>
#> Attaching package: 'dplyr'
@@ -77,14 +76,22 @@ intro
#> filter, lag
#> The following objects are masked from 'package:base':
#>
-#> intersect, setdiff, setequal, union
-# replace this line with actual path to your gene counts
-gene_counts_tsv <- system.file("extdata", "RSEM.genes.expected_count.all_samples.txt", package = "reneeTools")
-metadata_tsv <- system.file("extdata", "sample_metadata.tsv", package = "reneeTools")
+#> intersect, setdiff, setequal, union
+# replace these lines with the actual paths to your files
+gene_counts_tsv <- system.file("extdata",
+ "RSEM.genes.expected_count.all_samples.txt.gz",
+ package = "reneeTools"
+)
+metadata_tsv <- system.file("extdata", "sample_metadata.tsv.gz",
+ package = "reneeTools"
+)
# create reneeDataSet object
-renee_ds <- create_reneeDataSet_from_files(gene_counts_tsv, metadata_tsv) %>%
- run_deseq2(design = ~condition)
+renee_ds <- create_reneeDataSet_from_files(
+ sample_meta_filepath = metadata_tsv,
+ gene_counts_filepath = gene_counts_tsv
+)
#> Rows: 58929 Columns: 6
#> ── Column specification ────────────────────────────────────────────────────────
#> Delimiter: "\t"
@@ -100,38 +107,24 @@ intro
#>
#> ℹ Use `spec()` to retrieve the full column specification for this data.
#> ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
-#> Warning in DESeqDataSet(se, design = design, ignoreRank): some variables in
-#> design formula are characters, converting to factors
-#> estimating size factors
-#> estimating dispersions
-#> gene-wise dispersion estimates
-#> mean-dispersion relationship
-#> -- note: fitType='parametric', but the dispersion trend was not well captured by the
-#> function: y = a/x + b, and a local regression fit was automatically substituted.
-#> specify fitType='local' or 'mean' to avoid this message next time.
-#> final dispersion estimates
-#> fitting model and testing
-renee_ds@analyses$deseq2_results %>% head()
-#> log2 fold change (MLE): condition wildtype vs knockout
-#> Wald test p-value: condition wildtype vs knockout
-#> DataFrame with 6 rows and 6 columns
-#> baseMean log2FoldChange lfcSE stat pvalue
-#> <numeric> <numeric> <numeric> <numeric> <numeric>
-#> ENSG00000160179.18 4.23262 0.0527888 1.242584 0.0424831 9.66114e-01
-#> ENSG00000154734.15 20.38470 7.3430111 1.475316 4.9772452 6.44956e-07
-#> ENSG00000154736.6 10.72677 6.4048010 1.566426 4.0887980 4.33614e-05
-#> ENSG00000197381.16 5.36075 0.6802331 0.966972 0.7034673 4.81765e-01
-#> ENSG00000235609.7 2.82178 -0.5985472 1.168387 -0.5122848 6.08452e-01
-#> ENSG00000160216.19 8.84505 -0.4807875 0.769604 -0.6247206 5.32154e-01
-#> padj
-#> <numeric>
-#> ENSG00000160179.18 9.66114e-01
-#> ENSG00000154734.15 9.39793e-06
-#> ENSG00000154736.6 3.68572e-04
-#> ENSG00000197381.16 6.46821e-01
-#> ENSG00000235609.7 7.30142e-01
-#> ENSG00000160216.19 6.53973e-01Dataset from: https://portal.gdc.cancer.gov/projects/TCGA-LIHC
+