
library(testthat)

source("user_code.R")
test_that("function returns a list with correct names", {
  expect_true(exists("result"), info = "Result object should exist.")
  expect_true(is.list(result), info = "Result should be a list.")
  expect_true(all(c("subset_matrix", "avg_expression") %in% names(result)), info = "List should contain 'subset_matrix' and 'avg_expression'.")
})

test_that("subset_matrix contains correct genes and samples", {
  expected_genes <- c("GeneA", "GeneC")
  expected_samples <- c("Sample1", "Sample3")
  sm <- result$subset_matrix
  expect_true(is.matrix(sm), info = "subset_matrix should be a matrix.")
  expect_equal(rownames(sm), expected_genes, info = "Rows should match selected genes.")
  expect_equal(colnames(sm), expected_samples, info = "Columns should match selected samples.")
})

test_that("avg_expression is named numeric vector with correct values", {
  expected_genes <- c("GeneA", "GeneC")
  sm <- result$subset_matrix
  expected_avg <- rowMeans(sm)
  avg <- result$avg_expression
  expect_true(is.numeric(avg), info = "avg_expression should be numeric.")
  expect_equal(names(avg), expected_genes, info = "avg_expression should be named by gene.")
  expect_equal(as.numeric(avg), as.numeric(expected_avg), tolerance = 1e-8, info = "Averages should be correct.")
})

test_that("works with single gene selection", {
  single_gene <- c("GeneB")
  sg_result <- subset_gene_expression(expr_matrix, single_gene, sample_names)
  expect_equal(rownames(sg_result$subset_matrix), single_gene, info = "Single gene row name should match.")
  expect_equal(length(sg_result$avg_expression), 1, info = "Should return one average value for single gene.")
})

test_that("works with single sample selection", {
  single_sample <- c("Sample2")
  ss_result <- subset_gene_expression(expr_matrix, gene_names, single_sample)
  expect_equal(colnames(ss_result$subset_matrix), single_sample, info = "Single sample col name should match.")
  expect_equal(length(ss_result$avg_expression), 2, info = "Should return average for each gene (2 genes).")
  expect_equal(as.numeric(ss_result$avg_expression), as.numeric(ss_result$subset_matrix[,1]), tolerance = 1e-8, info = "Average should equal value for single sample.")
})

test_main.R

Eine praxisorientierte Einführung in die R-Programmierung, zugeschnitten auf Biologen und Bioinformatiker. Analyse, Visualisierung und Interpretation biologischer Daten mit R anhand von praxisnahen Beispielen aus Genomik, Ökologie und experimenteller Biologie.

Erlernen Sie die Grundlagen der R-Programmierung mit Schwerpunkt auf biologischen Daten, einschließlich Variablen, Datentypen und grundlegender Datenmanipulation.

Vertiefung in statistische Methoden zur Analyse biologischer Daten, einschließlich zusammenfassender Statistiken, Hypothesentests und Interpretation von Ergebnissen.

Beherrschen Sie die Kunst der Visualisierung biologischer Daten mit R, von einfachen Diagrammen bis hin zu fortgeschrittenen Visualisierungen, die für Experimente relevant sind.

Erlernen Sie den Umgang mit genomischen Daten und die Entwicklung reproduzierbarer Workflows für wissenschaftliche Forschung in R.

Challenge: Manipulating Genomic Data

Lösung