cdsknn: CDSKNN clustering

In renjun0324/KKLClustering: Large-scale single-cell clustering algorithm based on optimal KNN graph structure

CDSKNN clustering

Description

This function is a wrapper that executes all steps of CDSKNN clustering analysis in one go.

Usage

cdsknn(
  dat = NULL,
  partition_count = 300,
  batch_size = 500,
  outlier_det = TRUE,
  outlier_methods = "md",
  outlier_q = 0.2,
  min_n = 200,
  num_init = 10,
  max_iters = 1000,
  cluster_method = "louvain",
  resolution = 1,
  knn_range = c(3:10),
  iter = 20,
  is_weight = TRUE,
  assess_index = "Calinski_Harabasz",
  res_range = seq(0.2, 3, 0.2),
  new_cluster_method = "louvain",
  python_path = "/usr/bin/python3",
  seed = 723
)

Arguments

dat	expression matrix, row is cell, col is feature
partition_count	the number of partitions
batch_size	the number of threads
outlier_det	whether running outlier detection
outlier_methods	outlier detection methods, md or ed. "md" utilizes the Mahalanobis distance for detection, while "ed" treats points that are far from the center proportionally as outliers.
outlier_q	the proportion of outliers you want to filter. When outlier_methods is ed, this parameter takes effect.
min_n	the minimum number of data points for outlier detection.
num_init	the proportion of outliers that need to be removed
max_iters	the maximum iterations for kmeans
cluster_method	louvain or leiden in resampling
resolution	clustering parameters settings in resampling
knn_range	the range of the number of neighbors in the KNN graph structure
iter	the number of iterations in resampling
is_weight	Whether to use distance weights when constructing the KNN graph
assess_index	evaluation index used to select the optimal KNN graph structure
res_range	resolution range in clustering
new_cluster_method	louvain or leiden
python_path	python path to be used
seed	random seed

renjun0324/KKLClustering documentation built on Oct. 8, 2024, 7:39 p.m.