Mercurial > repos > iuc > scanpy_cluster_reduce_dimension

comparison cluster_reduce_dimension.xml @ 11:edec35114f72 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/scanpy/ commit aba2a85f5da6e1094f382d1f0d94c4b8f2544a7d
author iuc
date Wed, 08 Nov 2023 14:46:29 +0000
parents aaa5da8e73a9
children 6acb08931836
comparison
equal deleted inserted replaced
10:aaa5da8e73a9 11:edec35114f72
1 <tool id="scanpy_cluster_reduce_dimension" name="Cluster, infer trajectories and embed" version="@galaxy_version@" profile="@profile@"> 1 <tool id="scanpy_cluster_reduce_dimension" name="Cluster, infer trajectories and embed" version="@galaxy_version@" profile="@profile@">
2 <description>with scanpy</description> 2 <description>with scanpy</description>
3 <expand macro="bio_tools"/>
4 <macros> 3 <macros>
5 <import>macros.xml</import> 4 <import>macros.xml</import>
6 <xml name="pca_inputs"> 5 <xml name="pca_inputs">
7 <param argument="n_comps" type="integer" min="0" value="50" label="Number of principal components to compute" help="If the value is larger than the number of observations the number of observations is used instead"/> 6 <param argument="n_comps" type="integer" min="0" value="50" label="Number of principal components to compute" help="If the value is larger than the number of observations the number of observations is used instead"/>
8 <param argument="dtype" type="text" value="float32" label="Numpy data type string to which to convert the result" help=""> 7 <param argument="dtype" type="text" value="float32" label="Numpy data type string to which to convert the result" help="">
18 </when> 17 </when>
19 <when value="False"> 18 <when value="False">
20 <param argument="zero_center" type="boolean" truevalue="True" falsevalue="False" checked="true" 19 <param argument="zero_center" type="boolean" truevalue="True" falsevalue="False" checked="true"
21 label="Compute standard PCA from covariance matrix?" 20 label="Compute standard PCA from covariance matrix?"
22 help="If not, it omits zero-centering variables (uses *TruncatedSVD* from scikit-learn), which allows to handle sparse input efficiently."/> 21 help="If not, it omits zero-centering variables (uses *TruncatedSVD* from scikit-learn), which allows to handle sparse input efficiently."/>
23 <expand macro="svd_solver"/> 22 <expand macro="svd_solver"/>
24 <param argument="random_state" type="integer" value="0" label="Initial states for the optimization" help=""/> 23 <param argument="random_state" type="integer" value="0" label="Initial states for the optimization" help=""/>
25 </when> 24 </when>
26 </conditional> 25 </conditional>
27 <param argument="use_highly_variable" type="boolean" truevalue="True" falsevalue="False" checked="false" label="Use highly variable genes only?" help="They should be use if they have been determined beforehand."/> 26 <param argument="use_highly_variable" type="boolean" truevalue="True" falsevalue="False" checked="false" label="Use highly variable genes only?" help="They should be use if they have been determined beforehand."/>
28 </xml> 27 </xml>
59 random_state=$method.pca.random_state, 58 random_state=$method.pca.random_state,
60 #end if 59 #end if
61 use_highly_variable=$method.use_highly_variable 60 use_highly_variable=$method.use_highly_variable
62 ]]></token> 61 ]]></token>
63 </macros> 62 </macros>
63 <expand macro="bio_tools"/>
64 <expand macro="requirements"> 64 <expand macro="requirements">
65 <requirement type="package" version="0.7.0">louvain</requirement>
66 </expand> 65 </expand>
67 <expand macro="version_command"/> 66 <expand macro="version_command"/>
68 <command detect_errors="exit_code"><![CDATA[ 67 <command detect_errors="exit_code"><![CDATA[
69 @CMD@ 68 @CMD@
70 ]]></command> 69 ]]></command>
177 n_dcs=$method.n_dcs, 176 n_dcs=$method.n_dcs,
178 n_branchings=$method.n_branchings, 177 n_branchings=$method.n_branchings,
179 min_group_size=$method.min_group_size, 178 min_group_size=$method.min_group_size,
180 allow_kendall_tau_shift=$method.allow_kendall_tau_shift, 179 allow_kendall_tau_shift=$method.allow_kendall_tau_shift,
181 copy=False) 180 copy=False)
181
182 #else if $method.method == "tl.embedding_density"
183 sc.tl.embedding_density(
184 adata=adata,
185 basis='$method.basis',
186 #if str($method.groupby) != ''
187 groupby='$method.groupby',
188 #end if
189 #if str($method.key_added) != ''
190 key_added='$method.key_added',
191 #end if
192 )
193
182 #end if 194 #end if
183 195
184 @CMD_anndata_write_outputs@ 196 @CMD_anndata_write_outputs@
185 ]]></configfile> 197 ]]></configfile>
186 </configfiles> 198 </configfiles>
196 <option value="tl.tsne">t-distributed stochastic neighborhood embedding (tSNE), using 'tl.tsne'</option> 208 <option value="tl.tsne">t-distributed stochastic neighborhood embedding (tSNE), using 'tl.tsne'</option>
197 <option value="tl.umap">Embed the neighborhood graph using UMAP, using 'tl.umap'</option> 209 <option value="tl.umap">Embed the neighborhood graph using UMAP, using 'tl.umap'</option>
198 <option value="tl.draw_graph">Force-directed graph drawing, using 'tl.draw_graph'</option> 210 <option value="tl.draw_graph">Force-directed graph drawing, using 'tl.draw_graph'</option>
199 <option value="tl.dpt">Infer progression of cells through geodesic distance along the graph, using 'tl.dpt'</option> 211 <option value="tl.dpt">Infer progression of cells through geodesic distance along the graph, using 'tl.dpt'</option>
200 <option value="tl.paga">Generate cellular maps of differentiation manifolds with complex topologies, using 'tl.paga'</option> 212 <option value="tl.paga">Generate cellular maps of differentiation manifolds with complex topologies, using 'tl.paga'</option>
213 <option value="tl.embedding_density">Calculate the density of cells in an embedding (per condition)</option>
201 </param> 214 </param>
202 <when value="tl.louvain"> 215 <when value="tl.louvain">
203 <conditional name="flavor"> 216 <conditional name="flavor">
204 <param argument="flavor" type="select" label="Flavor for the clustering" help=""> 217 <param argument="flavor" type="select" label="Flavor for the clustering" help="">
205 <option value="vtraag">vtraag (much more powerful)</option> 218 <option value="vtraag">vtraag (much more powerful)</option>
286 <param argument="model" type="select" label="PAGA connectivity model" help=""> 299 <param argument="model" type="select" label="PAGA connectivity model" help="">
287 <option value="v1.2">v1.2</option> 300 <option value="v1.2">v1.2</option>
288 <option value="v1.0">v1.0</option> 301 <option value="v1.0">v1.0</option>
289 </param> 302 </param>
290 </when> 303 </when>
291 </conditional> 304 <when value="tl.embedding_density">
305 <param argument="basis" type="text" value="umap" label="The embedding over which the density will be calculated." help="This embedded representation should be found in adata.obsm['X_[basis]']">
306 <expand macro="sanitize_query" />
307 </param>
308 <param argument="groupby" type="text" optional="true" value="" label="Key for categorical observation/cell annotation for which densities are calculated per category." >
309 <expand macro="sanitize_query" />
310 </param>
311 <param argument="key_added" type="text" optional="true" value="" label="Name of the .obs covariate that will be added with the density estimates.">
312 <expand macro="sanitize_query" />
313 </param>
314 </when>
315 </conditional>
292 <expand macro="inputs_common_advanced"/> 316 <expand macro="inputs_common_advanced"/>
293 </inputs> 317 </inputs>
294 <outputs> 318 <outputs>
295 <expand macro="anndata_outputs"/> 319 <expand macro="anndata_outputs"/>
296 </outputs> 320 </outputs>
297 <tests> 321 <tests>
298 <test> 322 <test expect_num_outputs="2">
299 <!-- test 0 --> 323 <!-- test 1 -->
300 <param name="adata" value="pp.neighbors_gauss_braycurtis.recipe_weinreb17.paul15_subsample.h5ad" /> 324 <param name="adata" value="pp.neighbors_gauss_braycurtis.recipe_weinreb17.paul15_subsample.h5ad" />
301 <conditional name="method"> 325 <conditional name="method">
302 <param name="method" value="tl.louvain"/> 326 <param name="method" value="tl.louvain"/>
303 <conditional name="flavor"> 327 <conditional name="flavor">
304 <param name="flavor" value="vtraag"/> 328 <param name="flavor" value="vtraag"/>
324 <has_text_matching expression="use_weights=False"/> 348 <has_text_matching expression="use_weights=False"/>
325 </assert_contents> 349 </assert_contents>
326 </output> 350 </output>
327 <output name="anndata_out" file="tl.louvain.neighbors_gauss_braycurtis.recipe_weinreb17.paul15_subsample.h5ad" ftype="h5ad" compare="sim_size"/> 351 <output name="anndata_out" file="tl.louvain.neighbors_gauss_braycurtis.recipe_weinreb17.paul15_subsample.h5ad" ftype="h5ad" compare="sim_size"/>
328 </test> 352 </test>
329 <test> 353 <test expect_num_outputs="2">
330 <!-- test 1 --> 354 <!-- test 2 -->
331 <param name="adata" value="pp.neighbors_gauss_braycurtis.recipe_weinreb17.paul15_subsample.h5ad" /> 355 <param name="adata" value="pp.neighbors_gauss_braycurtis.recipe_weinreb17.paul15_subsample.h5ad" />
332 <conditional name="method"> 356 <conditional name="method">
333 <param name="method" value="tl.leiden"/> 357 <param name="method" value="tl.leiden"/>
334 <param name="random_state" value="1"/> 358 <param name="random_state" value="1"/>
335 <param name="random_state" value="10"/> 359 <param name="random_state" value="10"/>
350 <has_text_matching expression="n_iterations=-1"/> 374 <has_text_matching expression="n_iterations=-1"/>
351 </assert_contents> 375 </assert_contents>
352 </output> 376 </output>
353 <output name="anndata_out" file="tl.leiden.neighbors_gauss_braycurtis.recipe_weinreb17.paul15_subsample.h5ad" ftype="h5ad" compare="sim_size"/> 377 <output name="anndata_out" file="tl.leiden.neighbors_gauss_braycurtis.recipe_weinreb17.paul15_subsample.h5ad" ftype="h5ad" compare="sim_size"/>
354 </test> 378 </test>
355 <test> 379 <test expect_num_outputs="2">
356 <!-- test 1 --> 380 <!-- test 3 -->
357 <param name="adata" value="krumsiek11.h5ad" /> 381 <param name="adata" value="krumsiek11.h5ad" />
358 <conditional name="method"> 382 <conditional name="method">
359 <param name="method" value="pp.pca"/> 383 <param name="method" value="pp.pca"/>
360 <param name="n_comps" value="50"/> 384 <param name="n_comps" value="50"/>
361 <param name="dtype" value="float32"/> 385 <param name="dtype" value="float32"/>
382 <has_text_matching expression="use_highly_variable=False"/> 406 <has_text_matching expression="use_highly_variable=False"/>
383 </assert_contents> 407 </assert_contents>
384 </output> 408 </output>
385 <output name="anndata_out" file="pp.pca.krumsiek11.h5ad" ftype="h5ad" compare="sim_size" delta="100000" delta_frac="0.15"/> 409 <output name="anndata_out" file="pp.pca.krumsiek11.h5ad" ftype="h5ad" compare="sim_size" delta="100000" delta_frac="0.15"/>
386 </test> 410 </test>
387 <!--<test> 411 <test expect_num_outputs="2">
388 < test 3 > 412 <!-- test 4 -->
389 <param name="adata" value="krumsiek11.h5ad" /> 413 <param name="adata" value="krumsiek11.h5ad" />
390 <conditional name="method"> 414 <conditional name="method">
391 <param name="method" value="pp.pca"/> 415 <param name="method" value="pp.pca"/>
392 <param name="n_comps" value="20"/> 416 <param name="n_comps" value="20"/>
393 <param name="dtype" value="float32"/> 417 <param name="dtype" value="float32"/>
395 <param name="chunked" value="True"/> 419 <param name="chunked" value="True"/>
396 <param name="chunk_size" value="50"/> 420 <param name="chunk_size" value="50"/>
397 </conditional> 421 </conditional>
398 <param name="use_highly_variable" value="false"/> 422 <param name="use_highly_variable" value="false"/>
399 </conditional> 423 </conditional>
400 <assert_stdout> 424 <section name="advanced_common">
401 <has_text_matching expression="sc.pp.pca"/> 425 <param name="show_log" value="true" />
402 <has_text_matching expression="data=adata"/> 426 </section>
403 <has_text_matching expression="n_comps=20"/> 427 <output name="hidden_output">
404 <has_text_matching expression="dtype='float32'"/> 428 <assert_contents>
405 <has_text_matching expression="copy=False"/> 429 <has_text_matching expression="sc.pp.pca"/>
406 <has_text_matching expression="chunked=True"/> 430 <has_text_matching expression="data=adata"/>
407 <has_text_matching expression="chunk_size=50"/> 431 <has_text_matching expression="dtype='float32'"/>
408 <has_text_matching expression="use_highly_variable=False"/> 432 <has_text_matching expression="copy=False"/>
409 </assert_stdout> 433 <has_text_matching expression="chunked=True"/>
434 <has_text_matching expression="chunk_size=50"/>
435 <has_text_matching expression="use_highly_variable=False"/>
436 </assert_contents>
437 </output>
410 <output name="anndata_out" file="pp.pca.krumsiek11_chunk.h5ad" ftype="h5ad" compare="sim_size"/> 438 <output name="anndata_out" file="pp.pca.krumsiek11_chunk.h5ad" ftype="h5ad" compare="sim_size"/>
411 </test> 439 </test>
412 --> 440 <test expect_num_outputs="2">
413 <test> 441 <!-- test 5 -->
414 <!-- test 2 -->
415 <param name="adata" value="krumsiek11.h5ad" /> 442 <param name="adata" value="krumsiek11.h5ad" />
416 <conditional name="method"> 443 <conditional name="method">
417 <param name="method" value="tl.pca"/> 444 <param name="method" value="tl.pca"/>
418 <param name="n_comps" value="50"/> 445 <param name="n_comps" value="50"/>
419 <param name="dtype" value="float32"/> 446 <param name="dtype" value="float32"/>
439 <has_text_matching expression="use_highly_variable=False"/> 466 <has_text_matching expression="use_highly_variable=False"/>
440 </assert_contents> 467 </assert_contents>
441 </output> 468 </output>
442 <output name="anndata_out" file="tl.pca.krumsiek11.h5ad" ftype="h5ad" compare="sim_size" delta="100000" delta_frac="0.15"/> 469 <output name="anndata_out" file="tl.pca.krumsiek11.h5ad" ftype="h5ad" compare="sim_size" delta="100000" delta_frac="0.15"/>
443 </test> 470 </test>
444 <test> 471 <test expect_num_outputs="2">
445 <!-- test 3 --> 472 <!-- test 6 -->
446 <param name="adata" value="pp.neighbors_gauss_braycurtis.recipe_weinreb17.paul15_subsample.h5ad" /> 473 <param name="adata" value="pp.neighbors_gauss_braycurtis.recipe_weinreb17.paul15_subsample.h5ad" />
447 <conditional name="method"> 474 <conditional name="method">
448 <param name="method" value="tl.diffmap"/> 475 <param name="method" value="tl.diffmap"/>
449 <param name="n_comps" value="15"/> 476 <param name="n_comps" value="15"/>
450 </conditional> 477 </conditional>
456 <has_text_matching expression="sc.tl.diffmap"/> 483 <has_text_matching expression="sc.tl.diffmap"/>
457 </assert_contents> 484 </assert_contents>
458 </output> 485 </output>
459 <output name="anndata_out" file="tl.diffmap.neighbors_gauss_braycurtis.recipe_weinreb17.paul15_subsample.h5ad" ftype="h5ad" compare="sim_size"/> 486 <output name="anndata_out" file="tl.diffmap.neighbors_gauss_braycurtis.recipe_weinreb17.paul15_subsample.h5ad" ftype="h5ad" compare="sim_size"/>
460 </test> 487 </test>
461 <test> 488 <test expect_num_outputs="2">
462 <!-- test 4 --> 489 <!-- test 7 -->
463 <param name="adata" value="krumsiek11.h5ad" /> 490 <param name="adata" value="krumsiek11.h5ad" />
464 <conditional name="method"> 491 <conditional name="method">
465 <param name="method" value="tl.tsne"/> 492 <param name="method" value="tl.tsne"/>
466 <param name="n_pcs" value="10"/> 493 <param name="n_pcs" value="10"/>
467 <param name="perplexity" value="30"/> 494 <param name="perplexity" value="30"/>
484 <has_text_matching expression="use_fast_tsne=True"/> 511 <has_text_matching expression="use_fast_tsne=True"/>
485 </assert_contents> 512 </assert_contents>
486 </output> 513 </output>
487 <output name="anndata_out" file="tl.tsne.krumsiek11.h5ad" ftype="h5ad" compare="sim_size"/> 514 <output name="anndata_out" file="tl.tsne.krumsiek11.h5ad" ftype="h5ad" compare="sim_size"/>
488 </test> 515 </test>
489 <test> 516 <test expect_num_outputs="2">
490 <!-- test 5 --> 517 <!-- test 8 -->
491 <param name="adata" value="pp.neighbors_umap_euclidean.recipe_weinreb17.paul15_subsample.h5ad" /> 518 <param name="adata" value="pp.neighbors_umap_euclidean.recipe_weinreb17.paul15_subsample.h5ad" />
492 <conditional name="method"> 519 <conditional name="method">
493 <param name="method" value="tl.umap"/> 520 <param name="method" value="tl.umap"/>
494 <param name="min_dist" value="0.5"/> 521 <param name="min_dist" value="0.5"/>
495 <param name="spread" value="1.0"/> 522 <param name="spread" value="1.0"/>
522 <assert_contents> 549 <assert_contents>
523 <has_h5_keys keys="X, obs, obsm, uns, var" /> 550 <has_h5_keys keys="X, obs, obsm, uns, var" />
524 </assert_contents> 551 </assert_contents>
525 </output> 552 </output>
526 </test> 553 </test>
527 <test> 554 <test expect_num_outputs="2">
528 <!-- test 6 --> 555 <!-- test 9 -->
529 <param name="adata" value="pp.neighbors_umap_euclidean.recipe_weinreb17.paul15_subsample.h5ad"/> 556 <param name="adata" value="pp.neighbors_umap_euclidean.recipe_weinreb17.paul15_subsample.h5ad"/>
530 <conditional name="method"> 557 <conditional name="method">
531 <param name="method" value="tl.draw_graph"/> 558 <param name="method" value="tl.draw_graph"/>
532 <param name="layout" value="fa"/> 559 <param name="layout" value="fa"/>
533 <param name="random_state" value="0"/> 560 <param name="random_state" value="0"/>
542 <has_text_matching expression="random_state=0"/> 569 <has_text_matching expression="random_state=0"/>
543 </assert_contents> 570 </assert_contents>
544 </output> 571 </output>
545 <output name="anndata_out" file="tl.draw_graph.pp.neighbors_umap_euclidean.recipe_weinreb17.paul15_subsample.h5ad" ftype="h5ad" compare="sim_size"/> 572 <output name="anndata_out" file="tl.draw_graph.pp.neighbors_umap_euclidean.recipe_weinreb17.paul15_subsample.h5ad" ftype="h5ad" compare="sim_size"/>
546 </test> 573 </test>
547 <test> 574 <test expect_num_outputs="2">
548 <!-- test 7 --> 575 <!-- test 10 -->
549 <param name="adata" value="pp.neighbors_gauss_braycurtis.recipe_weinreb17.paul15_subsample.h5ad"/> 576 <param name="adata" value="pp.neighbors_gauss_braycurtis.recipe_weinreb17.paul15_subsample.h5ad"/>
550 <conditional name="method"> 577 <conditional name="method">
551 <param name="method" value="tl.paga"/> 578 <param name="method" value="tl.paga"/>
552 <param name="groups" value="paul15_clusters"/> 579 <param name="groups" value="paul15_clusters"/>
553 <param name="use_rna_velocity" value="False"/> 580 <param name="use_rna_velocity" value="False"/>
564 <has_text_matching expression="model='v1.2'"/> 591 <has_text_matching expression="model='v1.2'"/>
565 </assert_contents> 592 </assert_contents>
566 </output> 593 </output>
567 <output name="anndata_out" file="tl.paga.neighbors_gauss_braycurtis.recipe_weinreb17.paul15_subsample.h5ad" ftype="h5ad" compare="sim_size"/> 594 <output name="anndata_out" file="tl.paga.neighbors_gauss_braycurtis.recipe_weinreb17.paul15_subsample.h5ad" ftype="h5ad" compare="sim_size"/>
568 </test> 595 </test>
569 <test> 596 <test expect_num_outputs="2">
570 <!-- test 8 --> 597 <!-- test 11 -->
571 <param name="adata" value="tl.diffmap.neighbors_gauss_braycurtis.recipe_weinreb17.paul15_subsample.h5ad" /> 598 <param name="adata" value="tl.diffmap.neighbors_gauss_braycurtis.recipe_weinreb17.paul15_subsample.h5ad" />
572 <conditional name="method"> 599 <conditional name="method">
573 <param name="method" value="tl.dpt"/> 600 <param name="method" value="tl.dpt"/>
574 <param name="n_dcs" value="15"/> 601 <param name="n_dcs" value="15"/>
575 <param name="n_branchings" value="1"/> 602 <param name="n_branchings" value="1"/>
588 <has_text_matching expression="allow_kendall_tau_shift=True"/> 615 <has_text_matching expression="allow_kendall_tau_shift=True"/>
589 </assert_contents> 616 </assert_contents>
590 </output> 617 </output>
591 <output name="anndata_out" file="tl.dpt.diffmap.neighbors_gauss_braycurtis.recipe_weinreb17.paul15_subsample.h5ad" ftype="h5ad" compare="sim_size"/> 618 <output name="anndata_out" file="tl.dpt.diffmap.neighbors_gauss_braycurtis.recipe_weinreb17.paul15_subsample.h5ad" ftype="h5ad" compare="sim_size"/>
592 </test> 619 </test>
620 <test expect_num_outputs="2">
621 <!-- test 12 -->
622 <param name="adata" value="tl.umap.neighbors_umap_euclidean.recipe_weinreb17.paul15_subsample.h5ad" />
623 <conditional name="method">
624 <param name="method" value="tl.embedding_density"/>
625 <param name="basis" value="umap"/>
626 <param name="key_added" value="umap_density"/>
627 </conditional>
628 <section name="advanced_common">
629 <param name="show_log" value="true" />
630 </section>
631 <output name="hidden_output">
632 <assert_contents>
633 <has_text_matching expression="sc.tl.embedding_density"/>
634 <has_text_matching expression="basis='umap'"/>
635 <has_text_matching expression="key_added='umap_density'"/>
636 </assert_contents>
637 </output>
638 <output name="anndata_out" file="tl.embedding_density.umap.neighbors_umap_euclidean.recipe_weinreb17.paul15_subsample.h5ad" ftype="h5ad" compare="sim_size"/>
639 </test>
593 </tests> 640 </tests>
594 <help><![CDATA[ 641 <help><![CDATA[
595 Cluster cells into subgroups (`tl.louvain`) 642 Cluster cells into subgroups (`tl.louvain`)
596 =========================================== 643 ===========================================
597 644
600 analysis by Levine et al, 2015. 647 analysis by Levine et al, 2015.
601 648
602 This requires to run `pp.neighbors`, first. 649 This requires to run `pp.neighbors`, first.
603 650
604 More details on the `tl.louvain scanpy documentation 651 More details on the `tl.louvain scanpy documentation
605 <https://icb-scanpy.readthedocs-hosted.com/en/@version@/api/scanpy.tl.louvain.html>`_ 652 <https://icb-scanpy.readthedocs-hosted.com/en/stable/api/scanpy.tl.louvain.html>`_
606 653
607 Cluster cells into subgroups (`tl.leiden`) 654 Cluster cells into subgroups (`tl.leiden`)
608 ========================================== 655 ==========================================
609 656
610 Cluster cells using the Leiden algorithm (Traag et al, 2018), an improved version of the Louvain algorithm (Blondel et al, 2008). 657 Cluster cells using the Leiden algorithm (Traag et al, 2018), an improved version of the Louvain algorithm (Blondel et al, 2008).
611 658
612 The Louvain algorithm has been proposed for single-cell analysis by Levine et al, 2015. 659 The Louvain algorithm has been proposed for single-cell analysis by Levine et al, 2015.
613 660
614 More details on the `tl.leiden scanpy documentation 661 More details on the `tl.leiden scanpy documentation
615 <https://icb-scanpy.readthedocs-hosted.com/en/@version@/api/scanpy.tl.leiden.html>`_ 662 <https://icb-scanpy.readthedocs-hosted.com/en/stable/api/scanpy.tl.leiden.html>`_
616 663
617 Computes PCA (principal component analysis) coordinates, loadings and variance decomposition, using `pp.pca` 664 Computes PCA (principal component analysis) coordinates, loadings and variance decomposition, using `pp.pca`
618 ============================================================================================================ 665 ============================================================================================================
619 666
620 @CMD_pca_outputs@ 667 @CMD_pca_outputs@
621 668
622 More details on the `pp.pca scanpy documentation 669 More details on the `pp.pca scanpy documentation
623 <https://icb-scanpy.readthedocs-hosted.com/en/@version@/api/scanpy.pp.pca.html>`__ 670 <https://icb-scanpy.readthedocs-hosted.com/en/stable/api/scanpy.pp.pca.html>`__
624 671
625 Computes PCA (principal component analysis) coordinates, loadings and variance decomposition, using `tl.pca` 672 Computes PCA (principal component analysis) coordinates, loadings and variance decomposition, using `tl.pca`
626 ============================================================================================================ 673 ============================================================================================================
627 674
628 @CMD_pca_outputs@ 675 @CMD_pca_outputs@
629 676
630 More details on the `tl.pca scanpy documentation 677 More details on the `tl.pca scanpy documentation
631 <https://icb-scanpy.readthedocs-hosted.com/en/@version@/api/scanpy.tl.pca.html>`__ 678 <https://icb-scanpy.readthedocs-hosted.com/en/stable/api/scanpy.tl.pca.html>`__
632 679
633 Diffusion Maps, using `tl.diffmap` 680 Diffusion Maps, using `tl.diffmap`
634 ================================== 681 ==================================
635 682
636 Diffusion maps (Coifman et al 2005) has been proposed for visualizing single-cell 683 Diffusion maps (Coifman et al 2005) has been proposed for visualizing single-cell
643 using a Gaussian kernel, use `method=='gauss'` in 690 using a Gaussian kernel, use `method=='gauss'` in
644 `pp.neighbors`. To use an exponential kernel, use the default 691 `pp.neighbors`. To use an exponential kernel, use the default
645 `method=='umap'`. Differences between these options shouldn't usually be 692 `method=='umap'`. Differences between these options shouldn't usually be
646 dramatic. 693 dramatic.
647 694
648 The diffusion map representation of data are added to the return AnnData in the multi-dimensional 695 The diffusion map representation of data are added to the return AnnData in the multi-dimensional
649 observations annotation (obsm). It is the right eigen basis of the transition matrix with eigenvectors 696 observations annotation (obsm). It is the right eigen basis of the transition matrix with eigenvectors
650 as colum. It can be accessed using the inspect tool for AnnData 697 as colum. It can be accessed using the inspect tool for AnnData
651 698
652 More details on the `tl.diffmap scanpy documentation 699 More details on the `tl.diffmap scanpy documentation
653 <https://icb-scanpy.readthedocs-hosted.com/en/@version@/api/scanpy.tl.diffmap.html>`__ 700 <https://icb-scanpy.readthedocs-hosted.com/en/stable/api/scanpy.tl.diffmap.html>`__
654 701
655 t-distributed stochastic neighborhood embedding (tSNE), using `tl.tsne` 702 t-distributed stochastic neighborhood embedding (tSNE), using `tl.tsne`
656 ======================================================================= 703 =======================================================================
657 704
658 t-distributed stochastic neighborhood embedding (tSNE) (Maaten et al, 2008) has been 705 t-distributed stochastic neighborhood embedding (tSNE) (Maaten et al, 2008) has been
659 proposed for visualizating single-cell data by (Amir et al, 2013). Here, by default, 706 proposed for visualizating single-cell data by (Amir et al, 2013). Here, by default,
660 we use the implementation of *scikit-learn* (Pedregosa et al, 2011). 707 we use the implementation of *scikit-learn* (Pedregosa et al, 2011).
661 708
662 It returns `X_tsne`, tSNE coordinates of data. 709 It returns `X_tsne`, tSNE coordinates of data.
663 710
664 More details on the `tl.tsne scanpy documentation 711 More details on the `tl.tsne scanpy documentation
665 <https://icb-scanpy.readthedocs-hosted.com/en/@version@/api/scanpy.tl.tsne.html>`__ 712 <https://icb-scanpy.readthedocs-hosted.com/en/stable/api/scanpy.tl.tsne.html>`__
666 713
667 Embed the neighborhood graph using UMAP, using `tl.umap` 714 Embed the neighborhood graph using UMAP, using `tl.umap`
668 ======================================================== 715 ========================================================
669 716
670 UMAP (Uniform Manifold Approximation and Projection) is a manifold learning 717 UMAP (Uniform Manifold Approximation and Projection) is a manifold learning
676 distribution of distances in the high-dimensional space. We use the 723 distribution of distances in the high-dimensional space. We use the
677 implementation of `umap-learn <https://github.com/lmcinnes/umap>`__ 724 implementation of `umap-learn <https://github.com/lmcinnes/umap>`__
678 (McInnes et al, 2018). For a few comparisons of UMAP with tSNE, see this `preprint 725 (McInnes et al, 2018). For a few comparisons of UMAP with tSNE, see this `preprint
679 <https://doi.org/10.1101/298430>`__. 726 <https://doi.org/10.1101/298430>`__.
680 727
681 The UMAP coordinates of data are added to the return AnnData in the multi-dimensional 728 The UMAP coordinates of data are added to the return AnnData in the multi-dimensional
682 observations annotation (obsm). This data is accessible using the inspect tool for AnnData 729 observations annotation (obsm). This data is accessible using the inspect tool for AnnData
683 730
684 More details on the `tl.umap scanpy documentation 731 More details on the `tl.umap scanpy documentation
685 <https://icb-scanpy.readthedocs-hosted.com/en/@version@/api/scanpy.tl.umap.html>`__ 732 <https://icb-scanpy.readthedocs-hosted.com/en/stable/api/scanpy.tl.umap.html>`__
686 733
687 Force-directed graph drawing, using `tl.draw_graph` 734 Force-directed graph drawing, using `tl.draw_graph`
688 =================================================== 735 ===================================================
689 736
690 Force-directed graph drawing describes a class of long-established algorithms for visualizing graphs. 737 Force-directed graph drawing describes a class of long-established algorithms for visualizing graphs.
691 It has been suggested for visualizing single-cell data by Islam et al, 11. 738 It has been suggested for visualizing single-cell data by Islam et al, 11.
692 Many other layouts as implemented in igraph are available. Similar approaches have been used by 739 Many other layouts as implemented in igraph are available. Similar approaches have been used by
693 Zunder et al, 2015 or Weinreb et al, 2016. 740 Zunder et al, 2015 or Weinreb et al, 2016.
694 741
695 This is an alternative to tSNE that often preserves the topology of the data better. 742 This is an alternative to tSNE that often preserves the topology of the data better.
696 This requires to run `pp.neighbors`, first. 743 This requires to run `pp.neighbors`, first.
697 744
698 The default layout (ForceAtlas2) uses the package fa2. 745 The default layout (ForceAtlas2) uses the package fa2.
699 746
700 The coordinates of graph layout are added to the return AnnData in the multi-dimensional 747 The coordinates of graph layout are added to the return AnnData in the multi-dimensional
701 observations annotation (obsm). This data is accessible using the inspect tool for AnnData. 748 observations annotation (obsm). This data is accessible using the inspect tool for AnnData.
702 749
703 More details on the `tl.draw_graph scanpy documentation 750 More details on the `tl.draw_graph scanpy documentation
704 <https://icb-scanpy.readthedocs-hosted.com/en/@version@/api/scanpy.tl.draw_graph.html>`__ 751 <https://icb-scanpy.readthedocs-hosted.com/en/stable/api/scanpy.tl.draw_graph.html>`__
705 752
706 Infer progression of cells through geodesic distance along the graph (`tl.dpt`) 753 Infer progression of cells through geodesic distance along the graph (`tl.dpt`)
707 =============================================================================== 754 ===============================================================================
708 755
709 Reconstruct the progression of a biological process from snapshot 756 Reconstruct the progression of a biological process from snapshot
712 version, which is able to deal with disconnected graphs (Wolf et al, 2017) and can 759 version, which is able to deal with disconnected graphs (Wolf et al, 2017) and can
713 be run in a `hierarchical` mode by setting the parameter 760 be run in a `hierarchical` mode by setting the parameter
714 `n_branchings>1`. We recommend, however, to only use 761 `n_branchings>1`. We recommend, however, to only use
715 `tl.dpt` for computing pseudotime (`n_branchings=0`) and 762 `tl.dpt` for computing pseudotime (`n_branchings=0`) and
716 to detect branchings via `paga`. For pseudotime, you need 763 to detect branchings via `paga`. For pseudotime, you need
717 to annotate your data with a root cell. 764 to annotate your data with a root cell.
718 765
719 This requires to run `pp.neighbors`, first. In order to 766 This requires to run `pp.neighbors`, first. In order to
720 reproduce the original implementation of DPT, use `method=='gauss'` in 767 reproduce the original implementation of DPT, use `method=='gauss'` in
721 this. Using the default `method=='umap'` only leads to minor quantitative 768 this. Using the default `method=='umap'` only leads to minor quantitative
722 differences, though. 769 differences, though.
728 - dpt_groups : Array of dim (number of samples) that stores the subgroup id ('0','1', ...) for each cell. The groups typically correspond to 'progenitor cells', 'undecided cells' or 'branches' of a process. 775 - dpt_groups : Array of dim (number of samples) that stores the subgroup id ('0','1', ...) for each cell. The groups typically correspond to 'progenitor cells', 'undecided cells' or 'branches' of a process.
729 776
730 The tool is similar to the R package `destiny` of Angerer et al (2016). 777 The tool is similar to the R package `destiny` of Angerer et al (2016).
731 778
732 More details on the `tl.dpt scanpy documentation 779 More details on the `tl.dpt scanpy documentation
733 <https://icb-scanpy.readthedocs-hosted.com/en/@version@/api/scanpy.tl.dpt.html>`_ 780 <https://icb-scanpy.readthedocs-hosted.com/en/stable/api/scanpy.tl.dpt.html>`_
734 781
735 782
736 Generate cellular maps of differentiation manifolds with complex topologies (`tl.paga`) 783 Generate cellular maps of differentiation manifolds with complex topologies (`tl.paga`)
737 ======================================================================================= 784 =======================================================================================
738 785
759 - Adjacency matrix of the tree-like subgraph that best explains the topology (connectivities_tree) 806 - Adjacency matrix of the tree-like subgraph that best explains the topology (connectivities_tree)
760 807
761 These datasets are stored in the unstructured annotation (uns) and can be accessed using the inspect tool for AnnData objects 808 These datasets are stored in the unstructured annotation (uns) and can be accessed using the inspect tool for AnnData objects
762 809
763 More details on the `tl.paga scanpy documentation 810 More details on the `tl.paga scanpy documentation
764 <https://icb-scanpy.readthedocs-hosted.com/en/@version@/api/scanpy.tl.paga.html>`_ 811 <https://icb-scanpy.readthedocs-hosted.com/en/stable/api/scanpy.tl.paga.html>`_
765 ]]></help> 812 ]]></help>
766 <expand macro="citations"/> 813 <expand macro="citations"/>
767 </tool> 814 </tool>