61 |
62 | 
66 |
67 |
68 |
--------------------------------------------------------------------------------
/pyproject.toml:
--------------------------------------------------------------------------------
1 | [build-system]
2 | build-backend = "hatchling.build"
3 | requires = [ "hatchling" ]
4 |
5 | [project]
6 | name = "scverse-tutorials"
7 | version = "0.0.1"
8 | description = "Tutorials for single-cell analysis with scverse packages"
9 | readme = "README.md"
10 | license = "BSD-3-Clause"
11 | maintainers = [ { name = "scverse team", email = "core-team@scverse.org" } ]
12 | authors = [ { name = "scverse team" } ]
13 | requires-python = ">=3.13"
14 | classifiers = [
15 | "Private :: Do Not Upload", # Prevent uploading to PyPI
16 | "Programming Language :: Python :: 3 :: Only",
17 | "Programming Language :: Python :: 3.13",
18 | "Programming Language :: Python :: 3.14",
19 | ]
20 | optional-dependencies.dev = [ "pre-commit" ]
21 | optional-dependencies.docs = [
22 | # For notebooks
23 | "ipykernel",
24 | "ipython",
25 | "myst-nb>=1.1",
26 | "sphinx>=7",
27 | "sphinx-autodoc-typehints",
28 | "sphinx-book-theme>=1.1",
29 | "sphinx-copybutton",
30 | "sphinx-issues>=5.0.1",
31 | "sphinx-tabs",
32 | "sphinxcontrib-bibtex>=1",
33 | "sphinxext-opengraph",
34 | ]
35 | optional-dependencies.registry = [ "httpx", "jsonschema", "pillow", "pyyaml" ]
36 | urls.Documentation = "https://scverse.org/scverse-tutorials"
37 | urls.Home-page = "https://github.com/scverse/scverse-tutorials"
38 | urls.Source = "https://github.com/scverse/scverse-tutorials"
39 |
40 | [tool.hatch.envs.default]
41 | installer = "uv"
42 | features = [ "dev" ]
43 |
44 | [tool.hatch.envs.registry]
45 | features = [ "registry" ]
46 | scripts.validate = "python tutorial-registry/validate.py {args}"
47 |
48 | [tool.hatch.envs.docs]
49 | features = [ "docs" ]
50 | extra-dependencies = [
51 | "setuptools", # undeclared dependency in pybtex
52 | # fix from here: https://github.com/executablebooks/MyST-NB/pull/597
53 | "myst-nb @ git+https://github.com/flying-sheep/MyST-NB.git@eval-metadata",
54 | ]
55 | scripts.build = "sphinx-build -M html docs docs/_build {args}"
56 | scripts.open = "python3 -m webbrowser -t docs/_build/html/index.html"
57 | scripts.clean = "git clean -fdX -- {args:docs}"
58 |
59 | [tool.hatch.build.targets.wheel]
60 | bypass-selection = true # This is not a package
61 |
62 | [tool.ruff]
63 | line-length = 120
64 | src = [ "src" ]
65 | extend-include = [ "*.ipynb" ]
66 |
67 | format.docstring-code-format = true
68 |
69 | lint.select = [
70 | "B", # flake8-bugbear
71 | "BLE", # flake8-blind-except
72 | "C4", # flake8-comprehensions
73 | "D", # pydocstyle
74 | "E", # Error detected by Pycodestyle
75 | "F", # Errors detected by Pyflakes
76 | "I", # isort
77 | "RUF100", # Report unused noqa directives
78 | "TID", # flake8-tidy-imports
79 | "UP", # pyupgrade
80 | "W", # Warning detected by Pycodestyle
81 | ]
82 | lint.ignore = [
83 | "B008", # Errors from function calls in argument defaults. These are fine when the result is immutable.
84 | "C408", # dict() is nice for some use cases
85 | "D100", # Missing docstring in public module
86 | "D104", # Missing docstring in public package
87 | "D105", # __magic__ methods are often self-explanatory, allow missing docstrings
88 | "D107", # Missing docstring in __init__
89 | # Disable one in each pair of mutually incompatible rules
90 | "D203", # We don’t want a blank line before a class docstring
91 | "D213", # <> We want docstrings to start immediately after the opening triple quote
92 | "D400", # first line should end with a period [Bug: doesn’t work with single-line docstrings]
93 | "D401", # First line should be in imperative mood; try rephrasing
94 | "E501", # line too long -> we accept long comment lines; formatter gets rid of long code lines
95 | "E731", # Do not assign a lambda expression, use a def -> lambda expression assignments are convenient
96 | "E741", # allow I, O, l as variable names -> I is the identity matrix
97 | ]
98 | lint.per-file-ignores."docs/**" = [
99 | "B018", # Trailing expressions in notebooks are not “useless”
100 | "D103", # No need for docstrings in functions, we use literate programming
101 | "E402", # Imports in non-top cells are fine
102 | ]
103 | lint.pydocstyle.convention = "numpy"
104 |
105 | [tool.cruft]
106 | skip = [
107 | ".github/ISSUE_TEMPLATE",
108 | "environment.yml",
109 | "*.md",
110 | "src",
111 | "docs/*.md",
112 | "docs/notebooks",
113 | "docs/references.bib",
114 | "tests",
115 | "tutorial-registry",
116 | ]
117 |
--------------------------------------------------------------------------------
/docs/conf.py:
--------------------------------------------------------------------------------
1 | # Configuration file for the Sphinx documentation builder.
2 |
3 | # This file only contains a selection of the most common options. For a full
4 | # list see the documentation:
5 | # https://www.sphinx-doc.org/en/master/usage/configuration.html
6 |
7 | # -- Path setup --------------------------------------------------------------
8 | import sys
9 | from datetime import datetime
10 | from importlib.metadata import metadata
11 | from pathlib import Path
12 |
13 | HERE = Path(__file__).parent
14 | sys.path.insert(0, str(HERE / "extensions"))
15 |
16 |
17 | # -- Project information -----------------------------------------------------
18 |
19 | # NOTE: If you installed your project in editable mode, this might be stale.
20 | # If this is the case, reinstall it to refresh the metadata
21 | info = metadata("scverse-tutorials")
22 | project_name = info["Name"]
23 | author = info["Author"]
24 | copyright = f"{datetime.now():%Y}, {author}."
25 | version = info["Version"]
26 | urls = dict(pu.split(", ") for pu in info.get_all("Project-URL"))
27 | repository_url = urls["Source"]
28 |
29 | # The full version, including alpha/beta/rc tags
30 | release = info["Version"]
31 |
32 | bibtex_bibfiles = ["references.bib"]
33 | templates_path = ["_templates"]
34 | nitpicky = True # Warn about broken links
35 | needs_sphinx = "4.0"
36 |
37 | html_context = {
38 | "display_github": True, # Integrate GitHub
39 | "github_user": "scverse",
40 | "github_repo": project_name,
41 | "github_version": "main",
42 | "conf_py_path": "/docs/",
43 | }
44 |
45 | # -- General configuration ---------------------------------------------------
46 |
47 | # Add any Sphinx extension module names here, as strings.
48 | # They can be extensions coming with Sphinx (named 'sphinx.ext.*') or your custom ones.
49 | extensions = [
50 | "myst_nb",
51 | "sphinx_copybutton",
52 | "sphinx.ext.autodoc",
53 | "sphinx.ext.intersphinx",
54 | "sphinx.ext.autosummary",
55 | "sphinx.ext.napoleon",
56 | "sphinx_issues",
57 | "sphinxcontrib.bibtex",
58 | "sphinx_autodoc_typehints",
59 | "sphinx_tabs.tabs",
60 | "sphinx.ext.mathjax",
61 | "IPython.sphinxext.ipython_console_highlighting",
62 | "sphinxext.opengraph",
63 | *[p.stem for p in (HERE / "extensions").glob("*.py")],
64 | ]
65 |
66 | autosummary_generate = True
67 | autodoc_member_order = "groupwise"
68 | default_role = "literal"
69 | napoleon_google_docstring = False
70 | napoleon_numpy_docstring = True
71 | napoleon_include_init_with_doc = False
72 | napoleon_use_rtype = True # having a separate entry generally helps readability
73 | napoleon_use_param = True
74 | myst_heading_anchors = 6 # create anchors for h1-h6
75 | myst_enable_extensions = [
76 | "amsmath",
77 | "colon_fence",
78 | "deflist",
79 | "dollarmath",
80 | "html_image",
81 | "html_admonition",
82 | ]
83 | myst_url_schemes = ("http", "https", "mailto")
84 | nb_output_stderr = "remove"
85 | nb_execution_mode = "off"
86 | nb_merge_streams = True
87 | typehints_defaults = "braces"
88 |
89 | source_suffix = {
90 | ".rst": "restructuredtext",
91 | ".ipynb": "myst-nb",
92 | ".myst": "myst-nb",
93 | }
94 |
95 | intersphinx_mapping = {
96 | "python": ("https://docs.python.org/3", None),
97 | "anndata": ("https://anndata.readthedocs.io/en/latest/", None), # TODO: change back to stable after 0.12 release
98 | "numpy": ("https://numpy.org/doc/stable/", None),
99 | "scanpy": ("https://scanpy.readthedocs.io/en/stable/", None),
100 | "fast-array-utils": ("https://icb-fast-array-utils.readthedocs-hosted.com/en/stable", None),
101 | "dask": ("https://docs.dask.org/en/stable", None),
102 | "scipy": ("https://docs.scipy.org/doc/scipy", None),
103 | "rapids-singlecell": ("https://rapids-singlecell.readthedocs.io/en/stable/", None),
104 | }
105 |
106 | # List of patterns, relative to source directory, that match files and
107 | # directories to ignore when looking for source files.
108 | # This pattern also affects html_static_path and html_extra_path.
109 | exclude_patterns = ["_build", "Thumbs.db", ".DS_Store", "**.ipynb_checkpoints", ".jupyter_cache"]
110 |
111 |
112 | # -- Options for HTML output -------------------------------------------------
113 |
114 | # The theme to use for HTML and HTML Help pages. See the documentation for
115 | # a list of builtin themes.
116 | #
117 | html_theme = "sphinx_book_theme"
118 | html_static_path = ["_static"]
119 | html_css_files = ["css/custom.css"]
120 |
121 | html_title = project_name
122 |
123 | html_theme_options = {
124 | "repository_url": repository_url,
125 | "use_repository_button": True,
126 | "path_to_docs": "docs/",
127 | "navigation_with_keys": False,
128 | }
129 |
130 | pygments_style = "default"
131 |
132 | nitpick_ignore = [
133 | # If building the documentation fails because of a missing link that is outside your control,
134 | # you can add an exception to this list.
135 | # ("py:class", "igraph.Graph"),
136 | ]
137 |
--------------------------------------------------------------------------------
/docs/references.bib:
--------------------------------------------------------------------------------
1 | @article{Wolf2018,
2 | author = {Wolf, F. Alexander
3 | and Angerer, Philipp
4 | and Theis, Fabian J.},
5 | title = {SCANPY: large-scale single-cell gene expression data analysis},
6 | journal = {Genome Biology},
7 | year = {2018},
8 | month = {Feb},
9 | day = {06},
10 | volume = {19},
11 | number = {1},
12 | pages = {15},
13 | abstract = {Scanpy is a scalable toolkit for analyzing single-cell gene expression data. It includes methods for preprocessing, visualization, clustering, pseudotime and trajectory inference, differential expression testing, and simulation of gene regulatory networks. Its Python-based implementation efficiently deals with data sets of more than one million cells (https://github.com/theislab/Scanpy). Along with Scanpy, we present AnnData, a generic class for handling annotated data matrices (https://github.com/theislab/anndata).},
14 | issn = {1474-760X},
15 | doi = {10.1186/s13059-017-1382-0},
16 | url = {https://doi.org/10.1186/s13059-017-1382-0}
17 | }
18 | @inproceedings{luecken2021,
19 | author = {Luecken, Malte and Burkhardt, Daniel and Cannoodt, Robrecht and Lance, Christopher and Agrawal, Aditi and Aliee, Hananeh and Chen, Ann and Deconinck, Louise and Detweiler, Angela and Granados, Alejandro and Huynh, Shelly and Isacco, Laura and Kim, Yang and Klein, Dominik and DE KUMAR, BONY and Kuppasani, Sunil and Lickert, Heiko and McGeever, Aaron and Melgarejo, Joaquin and Mekonen, Honey and Morri, Maurizio and M\"{u}ller, Michaela and Neff, Norma and Paul, Sheryl and Rieck, Bastian and Schneider, Kaylie and Steelman, Scott and Sterr, Michael and Treacy, Daniel and Tong, Alexander and Villani, Alexandra-Chloe and Wang, Guilin and Yan, Jia and Zhang, Ce and Pisco, Angela and Krishnaswamy, Smita and Theis, Fabian and Bloom, Jonathan M},
20 | booktitle = {Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks},
21 | editor = {J. Vanschoren and S. Yeung},
22 | pages = {},
23 | publisher = {Curran},
24 | title = {A sandbox for prediction and integration of DNA, RNA, and proteins in single cells},
25 | url = {https://datasets-benchmarks-proceedings.neurips.cc/paper_files/paper/2021/file/158f3069a435b314a80bdcb024f8e422-Paper-round2.pdf},
26 | volume = {1},
27 | year = {2021}
28 | }
29 | @article{McCarthy2017,
30 | doi = {10.1093/bioinformatics/btw777},
31 | url = {https://doi.org/10.1093/bioinformatics/btw777},
32 | year = {2017},
33 | month = jan,
34 | publisher = {Oxford University Press ({OUP})},
35 | volume = {33},
36 | number = {8},
37 | pages = {1179--1186},
38 | author = {Davis J McCarthy and Kieran R Campbell and Aaron T L Lun and Quin F Wills},
39 | editor = {Ivo Hofacker},
40 | title = {Scater: pre-processing, quality control, normalization and visualization of single-cell {RNA}-seq data in R},
41 | journal = {Bioinformatics}
42 | }
43 | @article{Wolock2019,
44 | doi = {10.1016/j.cels.2018.11.005},
45 | url = {https://doi.org/10.1016/j.cels.2018.11.005},
46 | year = {2019},
47 | month = apr,
48 | publisher = {Elsevier {BV}},
49 | volume = {8},
50 | number = {4},
51 | pages = {281--291.e9},
52 | author = {Samuel L. Wolock and Romain Lopez and Allon M. Klein},
53 | title = {Scrublet: Computational Identification of Cell Doublets in Single-Cell Transcriptomic Data},
54 | journal = {Cell Systems}
55 | }
56 | @article{Satija2015,
57 | doi = {10.1038/nbt.3192},
58 | url = {https://doi.org/10.1038/nbt.3192},
59 | year = {2015},
60 | month = apr,
61 | publisher = {Springer Science and Business Media {LLC}},
62 | volume = {33},
63 | number = {5},
64 | pages = {495--502},
65 | author = {Rahul Satija and Jeffrey A Farrell and David Gennert and Alexander F Schier and Aviv Regev},
66 | title = {Spatial reconstruction of single-cell gene expression data},
67 | journal = {Nature Biotechnology}
68 | }
69 | @article{Zheng2017,
70 | doi = {10.1038/ncomms14049},
71 | url = {https://doi.org/10.1038/ncomms14049},
72 | year = {2017},
73 | month = jan,
74 | publisher = {Springer Science and Business Media {LLC}},
75 | volume = {8},
76 | number = {1},
77 | author = {Grace X. Y. Zheng and Jessica M. Terry and Phillip Belgrader and Paul Ryvkin and Zachary W. Bent and Ryan Wilson and Solongo B. Ziraldo and Tobias D. Wheeler and Geoff P. McDermott and Junjie Zhu and Mark T. Gregory and Joe Shuga and Luz Montesclaros and Jason G. Underwood and Donald A. Masquelier and Stefanie Y. Nishimura and Michael Schnall-Levin and Paul W. Wyatt and Christopher M. Hindson and Rajiv Bharadwaj and Alexander Wong and Kevin D. Ness and Lan W. Beppu and H. Joachim Deeg and Christopher McFarland and Keith R. Loeb and William J. Valente and Nolan G. Ericson and Emily A. Stevens and Jerald P. Radich and Tarjei S. Mikkelsen and Benjamin J. Hindson and Jason H. Bielas},
78 | title = {Massively parallel digital transcriptional profiling of single cells},
79 | journal = {Nature Communications}
80 | }
81 | @article{stuart2019comprehensive,
82 | title = {Comprehensive integration of single-cell data},
83 | author = {Stuart, Tim and Butler, Andrew and Hoffman, Paul and Hafemeister, Christoph and Papalexi, Efthymia and Mauck, William M and Hao, Yuhan and Stoeckius, Marlon and Smibert, Peter and Satija, Rahul},
84 | journal = {Cell},
85 | volume = {177},
86 | number = {7},
87 | pages = {1888--1902},
88 | year = {2019},
89 | publisher = {Elsevier}
90 | }
91 | @article{traag2019louvain,
92 | title = {From Louvain to Leiden: guaranteeing well-connected communities},
93 | author = {Traag, Vincent A and Waltman, Ludo and Van Eck, Nees Jan},
94 | journal = {Scientific reports},
95 | volume = {9},
96 | number = {1},
97 | pages = {5233},
98 | year = {2019},
99 | publisher = {Nature Publishing Group UK London}
100 | }
101 |
--------------------------------------------------------------------------------
/tutorial-registry/validate.py:
--------------------------------------------------------------------------------
1 | #!/usr/bin/env python
2 | """Validate tutorials' meta.yaml and generate an output directory with json/images to be uploaded on github pages."""
3 |
4 | from __future__ import annotations
5 |
6 | import argparse
7 | import json
8 | import logging
9 | import shutil
10 | import sys
11 | from pathlib import Path
12 | from textwrap import dedent
13 | from typing import TYPE_CHECKING, Any, Literal
14 |
15 | import httpx
16 | import jsonschema
17 | import yaml
18 | from PIL import Image
19 |
20 | logger = logging.getLogger(__name__)
21 |
22 | if TYPE_CHECKING:
23 | from collections.abc import Generator, Iterable, Mapping
24 |
25 | HERE = Path(__file__).absolute().parent
26 |
27 |
28 | def _check_url_exists(url: str) -> None:
29 | logger.info(f"Testing URL: {url}")
30 | response = httpx.head(url, follow_redirects=True)
31 | if response.status_code != 200:
32 | raise ValueError(f"URL {url} is not reachable (error {response.status_code}). ")
33 |
34 |
35 | def _check_image(img_path: Path) -> None:
36 | """Check that the image exists and that it is either SVG or fits into the 512x512 bounding box."""
37 | if not img_path.exists():
38 | raise ValueError(f"Image does not exist: {img_path}")
39 | if img_path.suffix == ".svg":
40 | return
41 | with Image.open(img_path) as img:
42 | width, height = img.size
43 | if not ((width == 512 and height <= 512) or (width <= 512 and height == 512)):
44 | raise ValueError(
45 | dedent(
46 | f"""\
47 | When validating {img_path}: Image must fit in a 512x512px bounding box and one dimension must be
48 | exactly 512 px. Actual dimensions (width, height): ({width}, ({height}))."
49 | """
50 | )
51 | )
52 |
53 |
54 | def validate_tutorials(schema_file: Path, tutorials_dir: Path) -> Generator[dict]:
55 | """Find all tutorial `meta.yaml` files in the tutorials dir and yield tutorial records."""
56 | schema = json.loads(schema_file.read_bytes())
57 | known_links = set()
58 | known_primary_to_orders: dict[str, set[int]] = {}
59 |
60 | for tmp_meta_file in tutorials_dir.rglob("meta.yaml"):
61 | tutorial_id = tmp_meta_file.parent.name
62 | with tmp_meta_file.open() as f:
63 | tmp_tutorial = yaml.load(f, yaml.SafeLoader)
64 |
65 | jsonschema.validate(tmp_tutorial, schema)
66 |
67 | link = tmp_tutorial["link"]
68 | if link in known_links:
69 | raise ValueError(f"When validating {tmp_meta_file}: Duplicate link: {link}")
70 | known_links.add(link)
71 |
72 | # Check for duplicate orders within the same primary category
73 | primary_category = tmp_tutorial.get("primary_category")
74 | order = tmp_tutorial.get("order")
75 |
76 | if primary_category and order is not None:
77 | if primary_category not in known_primary_to_orders:
78 | known_primary_to_orders[primary_category] = set()
79 |
80 | if order in known_primary_to_orders[primary_category]:
81 | raise ValueError(
82 | f"When validating {tmp_meta_file}: Duplicate order {order} "
83 | f"for primary category '{primary_category}'"
84 | )
85 |
86 | known_primary_to_orders[primary_category].add(order)
87 |
88 | _check_url_exists(link)
89 |
90 | # replace image path by absolute local path to image
91 | img_path = tutorials_dir / tutorial_id / tmp_tutorial["image"]
92 | _check_image(img_path)
93 | tmp_tutorial["image"] = str(img_path)
94 |
95 | yield tmp_tutorial
96 |
97 |
98 | def load_categories(categories_file: Path) -> dict[str, Any]:
99 | """Load the categories JSON."""
100 | with open(categories_file) as f:
101 | return yaml.load(f, yaml.SafeLoader)
102 |
103 |
104 | def make_output(
105 | categories: Iterable[Mapping[str, Mapping[Literal["description"], str]]],
106 | tutorials: Iterable[Mapping[str, str | Iterable[str]]],
107 | *,
108 | outdir: Path | None = None,
109 | ) -> None:
110 | """Create the output directory.
111 |
112 | Structure:
113 | outdir
114 | - tutorials.json # contains categories and tutorials
115 | - tutorialxxx/icon.svg # original icon filenames under a folder for each tutorial. The path of the icon is listed in the json.
116 | - tutorialyyy/icon.png
117 | """
118 | if outdir:
119 | outdir.mkdir(parents=True)
120 |
121 | tutorials_rel = []
122 | for tutorial in tutorials:
123 | img_srcpath = Path(tutorial["image"])
124 | img_localpath = Path(img_srcpath.parent.name) / img_srcpath.name
125 | tut_rel = dict(tutorial)
126 | tut_rel["image"] = str(img_localpath)
127 | tutorials_rel.append(tut_rel)
128 | if outdir:
129 | img_outpath = outdir / img_localpath
130 | img_outpath.parent.mkdir()
131 | shutil.copy(img_srcpath, img_outpath)
132 |
133 | result = {"categories": categories, "tutorials": tutorials_rel}
134 |
135 | if outdir:
136 | with (outdir / "tutorials.json").open("w") as f:
137 | json.dump(result, f)
138 | else:
139 | json.dump(result, sys.stdout, indent=2)
140 |
141 |
142 | def main(schema_file: Path, meta_dir: Path, categories_file: Path, *, outdir: Path | None = None):
143 | """Validate and create output directory."""
144 | tutorials = list(validate_tutorials(schema_file, meta_dir))
145 | categories = load_categories(categories_file)
146 | make_output(categories, tutorials, outdir=outdir)
147 |
148 |
149 | if __name__ == "__main__":
150 | logging.basicConfig(level=logging.INFO, format="%(message)s")
151 |
152 | parser = argparse.ArgumentParser(
153 | prog="validate.py",
154 | description="Validate tutorials' meta.yaml and generate an output directory with json/images to be uploaded on github pages.",
155 | )
156 | parser.add_argument("--outdir", type=Path, help="outdir that will contain the data to be uploaded on github pages")
157 | args = parser.parse_args()
158 |
159 | SCHEMA = HERE / "schema.json"
160 | META_DIR = HERE / "tutorials"
161 | CATEGORIES = HERE / "categories.yml"
162 |
163 | main(SCHEMA, META_DIR, CATEGORIES, outdir=args.outdir)
164 |
--------------------------------------------------------------------------------
/docs/how-to-dask.md:
--------------------------------------------------------------------------------
1 | # Dask Q&A
2 |
3 | Here we will go through some common questions and answers about `dask`, with a special focus on its integration with `scanpy` and `anndata`. For more comprehensive tutorials or other topics like {doc}`launching a cluster
66 |
67 | MuData object with n_obs × n_vars = 5247 × 33570\n", 145 | " var:\t'gene_ids', 'feature_types', 'genome', 'pattern', 'read', 'sequence'\n", 146 | " 2 modalities\n", 147 | " rna:\t5247 x 33538\n", 148 | " var:\t'gene_ids', 'feature_types', 'genome', 'pattern', 'read', 'sequence'\n", 149 | " prot:\t5247 x 32\n", 150 | " var:\t'gene_ids', 'feature_types', 'genome', 'pattern', 'read', 'sequence'" 151 | ], 152 | "text/plain": [ 153 | "MuData object with n_obs × n_vars = 5247 × 33570\n", 154 | " var:\t'gene_ids', 'feature_types', 'genome', 'pattern', 'read', 'sequence'\n", 155 | " 2 modalities\n", 156 | " rna:\t5247 x 33538\n", 157 | " var:\t'gene_ids', 'feature_types', 'genome', 'pattern', 'read', 'sequence'\n", 158 | " prot:\t5247 x 32\n", 159 | " var:\t'gene_ids', 'feature_types', 'genome', 'pattern', 'read', 'sequence'" 160 | ] 161 | }, 162 | "execution_count": 4, 163 | "metadata": {}, 164 | "output_type": "execute_result" 165 | } 166 | ], 167 | "source": [ 168 | "pbmc5k" 169 | ] 170 | }, 171 | { 172 | "attachments": {}, 173 | "cell_type": "markdown", 174 | "metadata": {}, 175 | "source": [ 176 | "We create 2 different subsamples of the same underlying data for both RNA and PROT modalities." 177 | ] 178 | }, 179 | { 180 | "cell_type": "code", 181 | "execution_count": 5, 182 | "metadata": {}, 183 | "outputs": [], 184 | "source": [ 185 | "rna = pbmc5k.mod[\"rna\"]\n", 186 | "prot = pbmc5k.mod[\"prot\"]" 187 | ] 188 | }, 189 | { 190 | "cell_type": "code", 191 | "execution_count": 6, 192 | "metadata": {}, 193 | "outputs": [], 194 | "source": [ 195 | "rna_a = rna[np.arange(300), np.sort(np.random.choice(np.arange(1000), 1000, replace=False))].copy()\n", 196 | "prot_a = prot[rna_a.obs_names,].copy()\n", 197 | "\n", 198 | "\n", 199 | "rna_b = rna[np.arange(500, 900), np.sort(np.random.choice(np.arange(3000), 1000, replace=False))].copy()\n", 200 | "prot_b = prot[rna_b.obs_names, np.arange(15)].copy()" 201 | ] 202 | }, 203 | { 204 | "attachments": {}, 205 | "cell_type": "markdown", 206 | "metadata": {}, 207 | "source": [ 208 | "And we create the respective `MuData` objects." 209 | ] 210 | }, 211 | { 212 | "cell_type": "code", 213 | "execution_count": 7, 214 | "metadata": {}, 215 | "outputs": [], 216 | "source": [ 217 | "mdata_a = MuData({\"prot\": prot_a, \"rna\": rna_a})\n", 218 | "mdata_b = MuData({\"prot\": prot_b, \"rna\": rna_b})" 219 | ] 220 | }, 221 | { 222 | "cell_type": "code", 223 | "execution_count": 8, 224 | "metadata": {}, 225 | "outputs": [ 226 | { 227 | "data": { 228 | "text/html": [ 229 | "
MuData object with n_obs × n_vars = 300 × 1032\n", 230 | " var:\t'gene_ids', 'feature_types', 'genome', 'pattern', 'read', 'sequence'\n", 231 | " 2 modalities\n", 232 | " prot:\t300 x 32\n", 233 | " var:\t'gene_ids', 'feature_types', 'genome', 'pattern', 'read', 'sequence'\n", 234 | " rna:\t300 x 1000\n", 235 | " var:\t'gene_ids', 'feature_types', 'genome', 'pattern', 'read', 'sequence'" 236 | ], 237 | "text/plain": [ 238 | "MuData object with n_obs × n_vars = 300 × 1032\n", 239 | " var:\t'gene_ids', 'feature_types', 'genome', 'pattern', 'read', 'sequence'\n", 240 | " 2 modalities\n", 241 | " prot:\t300 x 32\n", 242 | " var:\t'gene_ids', 'feature_types', 'genome', 'pattern', 'read', 'sequence'\n", 243 | " rna:\t300 x 1000\n", 244 | " var:\t'gene_ids', 'feature_types', 'genome', 'pattern', 'read', 'sequence'" 245 | ] 246 | }, 247 | "execution_count": 8, 248 | "metadata": {}, 249 | "output_type": "execute_result" 250 | } 251 | ], 252 | "source": [ 253 | "mdata_a" 254 | ] 255 | }, 256 | { 257 | "cell_type": "code", 258 | "execution_count": 9, 259 | "metadata": {}, 260 | "outputs": [ 261 | { 262 | "data": { 263 | "text/html": [ 264 | "
MuData object with n_obs × n_vars = 400 × 1015\n", 265 | " var:\t'gene_ids', 'feature_types', 'genome', 'pattern', 'read', 'sequence'\n", 266 | " 2 modalities\n", 267 | " prot:\t400 x 15\n", 268 | " var:\t'gene_ids', 'feature_types', 'genome', 'pattern', 'read', 'sequence'\n", 269 | " rna:\t400 x 1000\n", 270 | " var:\t'gene_ids', 'feature_types', 'genome', 'pattern', 'read', 'sequence'" 271 | ], 272 | "text/plain": [ 273 | "MuData object with n_obs × n_vars = 400 × 1015\n", 274 | " var:\t'gene_ids', 'feature_types', 'genome', 'pattern', 'read', 'sequence'\n", 275 | " 2 modalities\n", 276 | " prot:\t400 x 15\n", 277 | " var:\t'gene_ids', 'feature_types', 'genome', 'pattern', 'read', 'sequence'\n", 278 | " rna:\t400 x 1000\n", 279 | " var:\t'gene_ids', 'feature_types', 'genome', 'pattern', 'read', 'sequence'" 280 | ] 281 | }, 282 | "execution_count": 9, 283 | "metadata": {}, 284 | "output_type": "execute_result" 285 | } 286 | ], 287 | "source": [ 288 | "mdata_b" 289 | ] 290 | }, 291 | { 292 | "attachments": {}, 293 | "cell_type": "markdown", 294 | "metadata": {}, 295 | "source": [ 296 | "as you see, the 2 RNA subsamples don't share any cells, but they share some features. It's the same for the PROT assay." 297 | ] 298 | }, 299 | { 300 | "cell_type": "code", 301 | "execution_count": 10, 302 | "metadata": {}, 303 | "outputs": [ 304 | { 305 | "data": { 306 | "text/plain": [ 307 | "0" 308 | ] 309 | }, 310 | "execution_count": 10, 311 | "metadata": {}, 312 | "output_type": "execute_result" 313 | } 314 | ], 315 | "source": [ 316 | "len(list(set(rna_a.obs_names.tolist()) & set(rna_b.obs_names.tolist())))" 317 | ] 318 | }, 319 | { 320 | "cell_type": "code", 321 | "execution_count": 11, 322 | "metadata": {}, 323 | "outputs": [ 324 | { 325 | "data": { 326 | "text/plain": [ 327 | "345" 328 | ] 329 | }, 330 | "execution_count": 11, 331 | "metadata": {}, 332 | "output_type": "execute_result" 333 | } 334 | ], 335 | "source": [ 336 | "len(list(set(rna_a.var_names.tolist()) & set(rna_b.var_names.tolist())))" 337 | ] 338 | }, 339 | { 340 | "cell_type": "code", 341 | "execution_count": 12, 342 | "metadata": {}, 343 | "outputs": [ 344 | { 345 | "data": { 346 | "text/plain": [ 347 | "15" 348 | ] 349 | }, 350 | "execution_count": 12, 351 | "metadata": {}, 352 | "output_type": "execute_result" 353 | } 354 | ], 355 | "source": [ 356 | "len(list(set(prot_a.var_names.tolist()) & set(prot_b.var_names.tolist())))" 357 | ] 358 | }, 359 | { 360 | "cell_type": "markdown", 361 | "metadata": {}, 362 | "source": [ 363 | "## 1. Concatenate datasets, by modality" 364 | ] 365 | }, 366 | { 367 | "cell_type": "markdown", 368 | "metadata": {}, 369 | "source": [ 370 | "In the `AnnData` convention, we store observations (samples or cells) in rows (`axis=0`)and variables (genes, proteins, atac regions, etc ...) in columns (`axis=1`).\n", 371 | "Both the rows and columns of this matrix are indexed, which allows us to link between each other the structured layers of the AnnData object. \n", 372 | "\n", 373 | "When we interact with both axes of these matrices, we modify the same axes on all the linked layers.\n", 374 | "\n", 375 | "In scRNA-seq data, each row corresponds to a cell with a barcode, and each column corresponds to a gene with a gene id, but in the protein assay of a CITEseq experiment the cells are the same along the `axis=0` and the features are different. \n", 376 | "\n", 377 | "To collect all the cells and features from 2 datasets we first have to concatenate each anndata and then build a new mudata with these.\n", 378 | "\n", 379 | "By default, anndata concatenates on `axis=0` " 380 | ] 381 | }, 382 | { 383 | "cell_type": "code", 384 | "execution_count": 13, 385 | "metadata": {}, 386 | "outputs": [ 387 | { 388 | "data": { 389 | "text/plain": [ 390 | "AnnData object with n_obs × n_vars = 700 × 345" 391 | ] 392 | }, 393 | "execution_count": 13, 394 | "metadata": {}, 395 | "output_type": "execute_result" 396 | } 397 | ], 398 | "source": [ 399 | "ad.concat([rna_a, rna_b])" 400 | ] 401 | }, 402 | { 403 | "cell_type": "code", 404 | "execution_count": 14, 405 | "metadata": {}, 406 | "outputs": [ 407 | { 408 | "data": { 409 | "text/plain": [ 410 | "AnnData object with n_obs × n_vars = 700 × 345" 411 | ] 412 | }, 413 | "execution_count": 14, 414 | "metadata": {}, 415 | "output_type": "execute_result" 416 | } 417 | ], 418 | "source": [ 419 | "ad.concat([rna_a, rna_b], axis=0)" 420 | ] 421 | }, 422 | { 423 | "cell_type": "markdown", 424 | "metadata": {}, 425 | "source": [ 426 | "You may have noticed that anndata also defaults to create a concatenated version of the 2 RNA subsets with only the features that the 2 matrices have in common. This is the default scenario obtained by setting the parameter `join=\"inner\"`.\n", 427 | "\n", 428 | "There may be instances in which you don't want to lose the features that are missing from one of the 2 RNA, so let's try setting `join=\"outer\"`" 429 | ] 430 | }, 431 | { 432 | "cell_type": "code", 433 | "execution_count": 15, 434 | "metadata": {}, 435 | "outputs": [ 436 | { 437 | "data": { 438 | "text/plain": [ 439 | "AnnData object with n_obs × n_vars = 700 × 1655" 440 | ] 441 | }, 442 | "execution_count": 15, 443 | "metadata": {}, 444 | "output_type": "execute_result" 445 | } 446 | ], 447 | "source": [ 448 | "ad.concat([rna_a, rna_b], axis=0, join=\"outer\")" 449 | ] 450 | }, 451 | { 452 | "cell_type": "markdown", 453 | "metadata": {}, 454 | "source": [ 455 | "Anndata is also filling the variables that don't match with `0`, instead of `na` values.\n", 456 | "\n", 457 | "*NB since `axis=0` is the default behaviour, we will omit it in the future calls of the `concat` command for simplicity*" 458 | ] 459 | }, 460 | { 461 | "cell_type": "code", 462 | "execution_count": 16, 463 | "metadata": {}, 464 | "outputs": [ 465 | { 466 | "data": { 467 | "text/plain": [ 468 | "array([[0., 0., 0., ..., 0., 0., 0.],\n", 469 | " [0., 0., 0., ..., 0., 0., 0.],\n", 470 | " [0., 0., 0., ..., 0., 0., 0.],\n", 471 | " ...,\n", 472 | " [0., 0., 0., ..., 0., 0., 0.],\n", 473 | " [0., 0., 0., ..., 0., 0., 0.],\n", 474 | " [0., 0., 0., ..., 0., 0., 0.]], shape=(700, 1655), dtype=float32)" 475 | ] 476 | }, 477 | "execution_count": 16, 478 | "metadata": {}, 479 | "output_type": "execute_result" 480 | } 481 | ], 482 | "source": [ 483 | "ad.concat([rna_a, rna_b], join=\"outer\").X.toarray()" 484 | ] 485 | }, 486 | { 487 | "cell_type": "code", 488 | "execution_count": 17, 489 | "metadata": {}, 490 | "outputs": [ 491 | { 492 | "data": { 493 | "text/plain": [ 494 | "np.False_" 495 | ] 496 | }, 497 | "execution_count": 17, 498 | "metadata": {}, 499 | "output_type": "execute_result" 500 | } 501 | ], 502 | "source": [ 503 | "np.isnan(ad.concat([rna_a, rna_b], join=\"outer\").X.toarray()).any()" 504 | ] 505 | }, 506 | { 507 | "cell_type": "markdown", 508 | "metadata": {}, 509 | "source": [ 510 | "We can use the same convention to concatenate the two protein assays." 511 | ] 512 | }, 513 | { 514 | "cell_type": "code", 515 | "execution_count": 18, 516 | "metadata": {}, 517 | "outputs": [], 518 | "source": [ 519 | "rna_c = ad.concat([rna_a, rna_b], join=\"outer\")\n", 520 | "prot_c = ad.concat([prot_a, prot_b], join=\"outer\")" 521 | ] 522 | }, 523 | { 524 | "cell_type": "markdown", 525 | "metadata": {}, 526 | "source": [ 527 | "And now we create the new `MuData` object with the newly concatenated assays" 528 | ] 529 | }, 530 | { 531 | "cell_type": "code", 532 | "execution_count": 19, 533 | "metadata": {}, 534 | "outputs": [ 535 | { 536 | "data": { 537 | "text/html": [ 538 | "
MuData object with n_obs × n_vars = 700 × 1687\n", 539 | " 2 modalities\n", 540 | " rna:\t700 x 1655\n", 541 | " prot:\t700 x 32" 542 | ], 543 | "text/plain": [ 544 | "MuData object with n_obs × n_vars = 700 × 1687\n", 545 | " 2 modalities\n", 546 | " rna:\t700 x 1655\n", 547 | " prot:\t700 x 32" 548 | ] 549 | }, 550 | "execution_count": 19, 551 | "metadata": {}, 552 | "output_type": "execute_result" 553 | } 554 | ], 555 | "source": [ 556 | "full = MuData({\"rna\": rna_c, \"prot\": prot_c})\n", 557 | "full" 558 | ] 559 | }, 560 | { 561 | "cell_type": "markdown", 562 | "metadata": {}, 563 | "source": [ 564 | "## 2. Concatenating different modalities\n", 565 | "\n", 566 | "You may want to concatenate the RNA and the PROT modalities of the same cells. While we don't recommend using this type of concatenation, because we believe that every basic operation you would want to perform on a multimodal object is covered by creating a `MuData` object instead, we know that some of the tools that deal with multimodal data integration have not implemented MuData support yet.\n" 567 | ] 568 | }, 569 | { 570 | "cell_type": "code", 571 | "execution_count": 20, 572 | "metadata": {}, 573 | "outputs": [ 574 | { 575 | "data": { 576 | "text/plain": [ 577 | "AnnData object with n_obs × n_vars = 300 × 1000\n", 578 | " var: 'gene_ids', 'feature_types', 'genome', 'pattern', 'read', 'sequence'" 579 | ] 580 | }, 581 | "execution_count": 20, 582 | "metadata": {}, 583 | "output_type": "execute_result" 584 | } 585 | ], 586 | "source": [ 587 | "rna_a" 588 | ] 589 | }, 590 | { 591 | "cell_type": "code", 592 | "execution_count": 21, 593 | "metadata": {}, 594 | "outputs": [ 595 | { 596 | "data": { 597 | "text/plain": [ 598 | "AnnData object with n_obs × n_vars = 300 × 32\n", 599 | " var: 'gene_ids', 'feature_types', 'genome', 'pattern', 'read', 'sequence'" 600 | ] 601 | }, 602 | "execution_count": 21, 603 | "metadata": {}, 604 | "output_type": "execute_result" 605 | } 606 | ], 607 | "source": [ 608 | "prot_a" 609 | ] 610 | }, 611 | { 612 | "cell_type": "code", 613 | "execution_count": 22, 614 | "metadata": {}, 615 | "outputs": [ 616 | { 617 | "data": { 618 | "text/plain": [ 619 | "AnnData object with n_obs × n_vars = 300 × 1032\n", 620 | " var: 'gene_ids', 'feature_types', 'genome', 'pattern', 'read', 'sequence'" 621 | ] 622 | }, 623 | "execution_count": 22, 624 | "metadata": {}, 625 | "output_type": "execute_result" 626 | } 627 | ], 628 | "source": [ 629 | "adata_paired = ad.concat([rna_a, prot_a], axis=1)\n", 630 | "adata_paired" 631 | ] 632 | }, 633 | { 634 | "cell_type": "markdown", 635 | "metadata": {}, 636 | "source": [ 637 | "we now have a concatenated anndata, whith 1032 `.var` and 600 `.obs`. Let's take a look at the individual layers." 638 | ] 639 | }, 640 | { 641 | "cell_type": "code", 642 | "execution_count": 23, 643 | "metadata": {}, 644 | "outputs": [ 645 | { 646 | "data": { 647 | "text/html": [ 648 | "
\n",
649 | "\n",
662 | "\n",
663 | " \n",
664 | "
\n",
704 | "
"
706 | ],
707 | "text/plain": [
708 | "Empty DataFrame\n",
709 | "Columns: []\n",
710 | "Index: [AAACCCAAGAGACAAG-1, AAACCCAAGGCCTAGA-1, AAACCCAGTCGTGCCA-1, AAACCCATCGTGCATA-1, AAACGAAAGACAAGCC-1, AAACGAAAGAGTGACC-1, AAACGAACATGCCATA-1, AAACGAAGTAATGATG-1, AAACGAAGTTAAAGTG-1, AAACGAATCATACAGC-1, AAACGAATCGTGGAAG-1, AAACGCTAGGTTGGAC-1, AAACGCTCATGCACTA-1, AAACGCTGTACAAACA-1, AAAGAACAGGCCGCTT-1, AAAGAACGTGGATCAG-1, AAAGAACTCCTTATAC-1, AAAGGATAGAGGCCAT-1, AAAGGATCACACTTAG-1, AAAGGATGTGATTAGA-1, AAAGGATGTGGTTTGT-1, AAAGGATTCGAGAATA-1, AAAGGATTCTAAGAAG-1, AAAGGATTCTCTATAC-1, AAAGGGCAGCCGATCC-1, AAAGGGCCAGCCGGTT-1, AAAGGGCGTGACAGCA-1, AAAGGGCGTTCAAACC-1, AAAGGGCTCAGTCACA-1, AAAGGGCTCATTTGGG-1, AAAGGGCTCGAACCAT-1, AAAGGGCTCGGTGTAT-1, AAAGGGCTCTGCTTAT-1, AAAGGTAAGTGCTCGC-1, AAAGGTACATGAGAAT-1, AAAGGTAGTCGCGTCA-1, AAAGGTAGTGTAACGG-1, AAAGGTAGTTACGATC-1, AAAGGTATCCTTATGT-1, AAAGTCCAGCCAGAGT-1, AAAGTCCCAAATTAGG-1, AAAGTCCCAACCACAT-1, AAAGTCCCACAAGGTG-1, AAAGTCCGTAGCTTTG-1, AAAGTCCGTGTGTCGC-1, AAAGTGAAGCAGCGAT-1, AAAGTGAAGTGCAGCA-1, AAAGTGAAGTTCCGTA-1, AAAGTGACAGAGCTAG-1, AAAGTGAGTCGGCTAC-1, AAAGTGAGTTTGTTGG-1, AAATGGAAGATCGCTT-1, AAATGGAAGGCGCTCT-1, AAATGGAGTGGCAGAT-1, AAATGGAGTTAAGTCC-1, AAATGGATCCGGGACT-1, AAATGGATCGCATTGA-1, AACAAAGCAACAAGTA-1, AACAAAGGTCATGCAT-1, AACAAAGTCTTCGCTG-1, AACAACCAGGATGTTA-1, AACAACCCATGACTCA-1, AACAACCGTGCACATT-1, AACAACCTCGAGTGGA-1, AACAACCTCGGTCACG-1, AACAACCTCTAAGAAG-1, AACAAGAAGAAGCCAC-1, AACAAGAAGCCGTCGT-1, AACAAGAAGCGTACAG-1, AACAAGACAACTGCTA-1, AACAAGAGTCATAACC-1, AACAAGATCCCATAGA-1, AACAAGATCGCTCTAC-1, AACACACAGATGGCGT-1, AACACACAGGGCTGAT-1, AACACACCACGCTGCA-1, AACACACGTAACAGGC-1, AACACACGTACGTGTT-1, AACACACGTTGGGATG-1, AACACACTCTATCACT-1, AACAGGGAGATACATG-1, AACAGGGGTAACATAG-1, AACAGGGGTCAACATC-1, AACAGGGGTCAGTCCG-1, AACAGGGTCAATCGGT-1, AACCAACCACAGTATC-1, AACCAACGTAACATCC-1, AACCAACGTCACAGAG-1, AACCAACGTCAGGTAG-1, AACCATGAGATCGGTG-1, AACCATGAGGTCGTCC-1, AACCATGTCTAAGGAA-1, AACCCAAAGGGTGGGA-1, AACCCAACAGCGGTTC-1, AACCCAAGTATCGGTT-1, AACCTGAAGCTGGCTC-1, AACCTGAAGTGCAGGT-1, AACCTGAGTCGAACGA-1, AACCTGAGTCGAGCTC-1, AACCTGAGTCTCTCAC-1, ...]\n",
711 | "\n",
712 | "[300 rows x 0 columns]"
713 | ]
714 | },
715 | "execution_count": 23,
716 | "metadata": {},
717 | "output_type": "execute_result"
718 | }
719 | ],
720 | "source": [
721 | "adata_paired.obs"
722 | ]
723 | },
724 | {
725 | "cell_type": "code",
726 | "execution_count": 24,
727 | "metadata": {},
728 | "outputs": [
729 | {
730 | "data": {
731 | "text/html": [
732 | "| \n", 666 | " |
|---|
| AAACCCAAGAGACAAG-1 | \n", 671 | "
| AAACCCAAGGCCTAGA-1 | \n", 674 | "
| AAACCCAGTCGTGCCA-1 | \n", 677 | "
| AAACCCATCGTGCATA-1 | \n", 680 | "
| AAACGAAAGACAAGCC-1 | \n", 683 | "
| ... | \n", 686 | "
| ACACTGAAGTTCCGGC-1 | \n", 689 | "
| ACACTGAGTGCCCGTA-1 | \n", 692 | "
| ACACTGAGTTCGTTCC-1 | \n", 695 | "
| ACAGAAAAGGTACTGG-1 | \n", 698 | "
| ACAGAAACAAATGGAT-1 | \n", 701 | "
300 rows × 0 columns
\n", 705 | "\n",
733 | "\n",
746 | "\n",
747 | " \n",
748 | "
\n",
860 | "
"
862 | ],
863 | "text/plain": [
864 | " gene_ids feature_types genome \\\n",
865 | "MIR1302-2HG ENSG00000243485 Gene Expression GRCh38 \n",
866 | "FAM138A ENSG00000237613 Gene Expression GRCh38 \n",
867 | "OR4F5 ENSG00000186092 Gene Expression GRCh38 \n",
868 | "AL627309.1 ENSG00000238009 Gene Expression GRCh38 \n",
869 | "AL627309.3 ENSG00000239945 Gene Expression GRCh38 \n",
870 | "... ... ... ... \n",
871 | "HLA-DR_TotalSeqB HLA-DR Antibody Capture \n",
872 | "TIGIT_TotalSeqB TIGIT Antibody Capture \n",
873 | "IgG1_control_TotalSeqB IgG1 Antibody Capture \n",
874 | "IgG2a_control_TotalSeqB IgG2a Antibody Capture \n",
875 | "IgG2b_control_TotalSeqB IgG2b Antibody Capture \n",
876 | "\n",
877 | " pattern read sequence \n",
878 | "MIR1302-2HG \n",
879 | "FAM138A \n",
880 | "OR4F5 \n",
881 | "AL627309.1 \n",
882 | "AL627309.3 \n",
883 | "... ... ... ... \n",
884 | "HLA-DR_TotalSeqB ^NNNNNNNNNN(BC)NNNNNNNNN R2 AATAGCGAGCAAGTA \n",
885 | "TIGIT_TotalSeqB ^NNNNNNNNNN(BC)NNNNNNNNN R2 TTGCTTACCGCCAGA \n",
886 | "IgG1_control_TotalSeqB ^NNNNNNNNNN(BC)NNNNNNNNN R2 GCCGGACGACATTAA \n",
887 | "IgG2a_control_TotalSeqB ^NNNNNNNNNN(BC)NNNNNNNNN R2 CTCCTACCTAAACTG \n",
888 | "IgG2b_control_TotalSeqB ^NNNNNNNNNN(BC)NNNNNNNNN R2 ATATGTATCACGCGA \n",
889 | "\n",
890 | "[1032 rows x 6 columns]"
891 | ]
892 | },
893 | "execution_count": 24,
894 | "metadata": {},
895 | "output_type": "execute_result"
896 | }
897 | ],
898 | "source": [
899 | "adata_paired.var"
900 | ]
901 | },
902 | {
903 | "cell_type": "markdown",
904 | "metadata": {},
905 | "source": [
906 | "the `.obs` layer is empty now, and we need to repopulate it. "
907 | ]
908 | },
909 | {
910 | "cell_type": "code",
911 | "execution_count": 25,
912 | "metadata": {},
913 | "outputs": [],
914 | "source": [
915 | "rna_cols = rna_a.obs.columns\n",
916 | "prot_cols = prot_a.obs.columns\n",
917 | "\n",
918 | "rnaobs = rna_a.obs.copy()\n",
919 | "rnaobs.columns = [\"rna:\" + x for x in rna_cols]\n",
920 | "protobs = prot.obs.copy()\n",
921 | "protobs.columns = [\"prot:\" + x for x in prot_cols]\n",
922 | "adata_paired.obs = pd.merge(rnaobs, protobs, left_index=True, right_index=True)"
923 | ]
924 | },
925 | {
926 | "cell_type": "markdown",
927 | "metadata": {},
928 | "source": [
929 | "For more information on how anndata perform concatenation please check this [tutorial](https://anndata.readthedocs.io/en/latest/concatenation.html) \n",
930 | "\n",
931 | "\n"
932 | ]
933 | }
934 | ],
935 | "metadata": {
936 | "kernelspec": {
937 | "display_name": "Python 3 (ipykernel)",
938 | "language": "python",
939 | "name": "python3"
940 | },
941 | "language_info": {
942 | "codemirror_mode": {
943 | "name": "ipython",
944 | "version": 3
945 | },
946 | "file_extension": ".py",
947 | "mimetype": "text/x-python",
948 | "name": "python",
949 | "nbconvert_exporter": "python",
950 | "pygments_lexer": "ipython3",
951 | "version": "3.12.12"
952 | },
953 | "vscode": {
954 | "interpreter": {
955 | "hash": "9f2c2ed92b9244d41be0bdd21ae19cc7b57648bb6fdcd4cb66fc3fbd398bef96"
956 | }
957 | }
958 | },
959 | "nbformat": 4,
960 | "nbformat_minor": 2
961 | }
962 |
--------------------------------------------------------------------------------
/tutorial-registry/tutorials/anndata-mudata-axes/icon.svg:
--------------------------------------------------------------------------------
1 |
2 |
--------------------------------------------------------------------------------
| \n", 750 | " | gene_ids | \n", 751 | "feature_types | \n", 752 | "genome | \n", 753 | "pattern | \n", 754 | "read | \n", 755 | "sequence | \n", 756 | "
|---|---|---|---|---|---|---|
| MIR1302-2HG | \n", 761 | "ENSG00000243485 | \n", 762 | "Gene Expression | \n", 763 | "GRCh38 | \n", 764 | "\n", 765 | " | \n", 766 | " | \n", 767 | " |
| FAM138A | \n", 770 | "ENSG00000237613 | \n", 771 | "Gene Expression | \n", 772 | "GRCh38 | \n", 773 | "\n", 774 | " | \n", 775 | " | \n", 776 | " |
| OR4F5 | \n", 779 | "ENSG00000186092 | \n", 780 | "Gene Expression | \n", 781 | "GRCh38 | \n", 782 | "\n", 783 | " | \n", 784 | " | \n", 785 | " |
| AL627309.1 | \n", 788 | "ENSG00000238009 | \n", 789 | "Gene Expression | \n", 790 | "GRCh38 | \n", 791 | "\n", 792 | " | \n", 793 | " | \n", 794 | " |
| AL627309.3 | \n", 797 | "ENSG00000239945 | \n", 798 | "Gene Expression | \n", 799 | "GRCh38 | \n", 800 | "\n", 801 | " | \n", 802 | " | \n", 803 | " |
| ... | \n", 806 | "... | \n", 807 | "... | \n", 808 | "... | \n", 809 | "... | \n", 810 | "... | \n", 811 | "... | \n", 812 | "
| HLA-DR_TotalSeqB | \n", 815 | "HLA-DR | \n", 816 | "Antibody Capture | \n", 817 | "\n", 818 | " | ^NNNNNNNNNN(BC)NNNNNNNNN | \n", 819 | "R2 | \n", 820 | "AATAGCGAGCAAGTA | \n", 821 | "
| TIGIT_TotalSeqB | \n", 824 | "TIGIT | \n", 825 | "Antibody Capture | \n", 826 | "\n", 827 | " | ^NNNNNNNNNN(BC)NNNNNNNNN | \n", 828 | "R2 | \n", 829 | "TTGCTTACCGCCAGA | \n", 830 | "
| IgG1_control_TotalSeqB | \n", 833 | "IgG1 | \n", 834 | "Antibody Capture | \n", 835 | "\n", 836 | " | ^NNNNNNNNNN(BC)NNNNNNNNN | \n", 837 | "R2 | \n", 838 | "GCCGGACGACATTAA | \n", 839 | "
| IgG2a_control_TotalSeqB | \n", 842 | "IgG2a | \n", 843 | "Antibody Capture | \n", 844 | "\n", 845 | " | ^NNNNNNNNNN(BC)NNNNNNNNN | \n", 846 | "R2 | \n", 847 | "CTCCTACCTAAACTG | \n", 848 | "
| IgG2b_control_TotalSeqB | \n", 851 | "IgG2b | \n", 852 | "Antibody Capture | \n", 853 | "\n", 854 | " | ^NNNNNNNNNN(BC)NNNNNNNNN | \n", 855 | "R2 | \n", 856 | "ATATGTATCACGCGA | \n", 857 | "
1032 rows × 6 columns
\n", 861 | "