Omada包：无监督机器学习助你穿越基因表达谱的聚类迷宫！

if (!require("BiocManager", quietly = TRUE))  install.packages("BiocManager")BiocManager::install("omada")library(omada)

# Selecting dimensions and number of clustersnew.dataset.analysis <- feasibilityAnalysis(classes = 4, samples = 50, features = 15)

# Basing the simulation on an existing dataset and selecting the number of clustersexisting.dataset.analysis <- feasibilityAnalysisDataBased(data = toy_genes, classes = 3)

# Extract results of either functionaverage.sts.k <- get_average_stabilities_per_k(new.dataset.analysis) #maximum.st <- get_max_stability(new.dataset.analysis)average.st <- get_average_stability(new.dataset.analysis)generated.ds <- get_generated_dataset(new.dataset.analysis)

# Running the whole cascade of tools inputting an expression dataset# and the upper k (number of clusters) to be investigatedomada.analysis <- omada(toy_genes, method.upper.k = 6)

# Extract resultspa.scores <- get_partition_agreement_scores(omada.analysis)fs.scores <- get_feature_selection_scores(omada.analysis)fs.optimal.features <- get_feature_selection_optimal_features(omada.analysis)fs.optimal.number.of.features<-get_feature_selection_optimal_number_of_features(omada.analysis)           cv.scores <- get_cluster_voting_scores(omada.analysis)cv.memberships <- get_cluster_voting_memberships(omada.analysis)cv.metrics.votes <- get_cluster_voting_metric_votes(omada.analysis)cv.k.votes <- get_cluster_voting_k_votes(omada.analysis)sample.memberships <- get_sample_memberships(omada.analysis)

# Plot resultsplot_partition_agreement(omada.analysis)   

plot_feature_selection(omada.analysis)

plot_cluster_voting(omada.analysis)

# Selecting the upper k limit and number of comparisonsmethod.results <- clusteringMethodSelection(toy_genes, method.upper.k = 3, number.of.comparisons = 2)           # Extract resultspa.scores <- get_partition_agreement_scores(method.results)           # Plot resultsplot_partition_agreement(method.results)

# Selecting algorithms, measures and number of clustersagreement.results <- partitionAgreement(toy_genes, algorithm.1 = "spectral", measure.1 = "rbfdot", algorithm.2 = "kmeans",measure.2 = "Lloyd", number.of.clusters = 3)           # Extract resultspa.scores <- get_agreement_scores(agreement.results)

# Selecting minimum and maximum number of clusters and feature stepfeature.selection.results <-  featureSelection(toy_genes, min.k = 3, max.k = 6, step = 3)

# Extract resultsfeature.selection.scores <- get_average_feature_k_stabilities(feature.selection.results)optimal.number.of.features <- get_optimal_number_of_featuresoptimal.features <- get_optimal_features(feature.selection.results)

# Plot resultsplot_average_stabilities(feature.selection.results)

# Selecting minimum and maximum number of clusters and algorithm to be usedcluster.voting.results <- clusterVoting(toy_genes, 4,8,"sc")

# Extract resultsinternal.metric.scores <- get_internal_metric_scores(cluster.voting.results)cluster.memberships.k <- get_cluster_memberships_k(cluster.voting.results)metric.votes.k <- get_metric_votes_k(cluster.voting.results)vote.frequencies.k <- get_vote_frequencies_k(cluster.voting.results)

# Plot resultsplot_vote_frequencies(cluster.voting.results)

# Running the clustering with specific number of clusters(k) and algorithmsample.memberships <- optimalClustering(toy_genes, 4, "spectral")           # Extract resultsmemberships <- get_optimal_memberships(sample.memberships)optimal.stability <- get_optimal_stability_score(sample.memberships)    optimal.parameter <- get_optimal_parameter_used(sample.memberships)