wrappers/tools/tsne

Description

Compute a t-SNE embedding, running either the GPU (rapids-singlecell) or the
CPU (scanpy) variant of tsne, selected with --device_type.

Inputs

Name	Type & Properties	Description
--input	file required	Input h5mu file.
--modality	string	Which modality from the input MuData file to process.
--obsm_input	string	The `.obsm` slot to use as the representation to embed.
--n_pcs	integer	The number of dimensions of the representation to use. If not set, all dimensions of `--obsm_input` are used.

Name

Type & Properties

--input

file

required

--modality

string

--obsm_input

string

--n_pcs

integer

Compute

Name	Type & Properties	Description
--device_type	string	Which implementation to run: the GPU (rapids-singlecell) variant or the CPU (scanpy/squidpy) variant of the component. Selecting `gpu` requires a CUDA-capable GPU; the component errors out if none is available (there is no automatic fallback to CPU).

Name

Type & Properties

--device_type

string

Outputs

Name	Type & Properties	Description
--output	file required output	Output h5mu file.
--obsm_output	string	In which .obsm slot to store the resulting t-SNE embedding.
--output_compression	string	Compression format to use for the output AnnData and/or Mudata objects. By default no compression is applied.

Name

Type & Properties

--output

file

required

output

--obsm_output

string

--output_compression

string

Options

Name	Type & Properties	Description
--perplexity	integer	The perplexity is related to the number of nearest neighbors that is used in other manifold learning algorithms. Larger datasets usually require a larger perplexity.
--early_exaggeration	double	Controls how tight natural clusters in the original space are in the embedded space and how much space will be between them.
--learning_rate	double	The learning rate for the optimization. If the learning rate is too high, the data may look like a 'ball' with any point approximately equidistant from its nearest neighbours. If it is too low, most points may look compressed in a dense cloud with few outliers.
--metric	string	The metric to use when computing distances in the representation.

Name

Type & Properties

--perplexity

integer

--early_exaggeration

double

--learning_rate

double

--metric

string

rapids-singlecell options

Name	Type & Properties	Description
--overwrite	boolean	Allow overwriting the .obsm output slot if it already exists.
--method	string	The t-SNE method to use.

Name

Type & Properties

--overwrite

boolean

--method

string

Scanpy options

Name	Type & Properties	Description
--min_dist	double	The effective minimum distance between embedded points. Smaller values result in a more clustered embedding, larger values in a more even dispersal of points.
--random_state	integer	The random seed to use for the t-SNE computation.

Name

Type & Properties

--min_dist

double

--random_state

integer

Run this component

Run the following command to execute this component with Nextflow:

cat > params.yaml <<'EOM'  
modality: [ "rna" ]  
obsm_input: [ "X_pca" ]  
device_type: [ "gpu" ]  
output: "$id.$key.output.h5mu"  
obsm_output: [ "X_tsne" ]  
perplexity: [ 30 ]  
early_exaggeration: [ 12 ]  
learning_rate: [ 200 ]  
metric: [ "euclidean" ]  
overwrite: [ false ]  
method: [ "barnes_hut" ]  
min_dist: [ 0.5 ]  
random_state: [ 0 ]  
id: "run"  
publish_dir: "output/"  
EOM

nextflow run https://packages.viash-hub.com/vsh/openpipeline_rapids.git \  
  -revision v0.1.3 \  
  -main-script target/nextflow/wrappers/tools/tsne/main.nf \  
  -params-file params.yaml

wrappers/tools/tsne

Inputs

Compute

Outputs

Options

rapids-singlecell options

Scanpy options

Run this component

Relationships

Used by

Uses