mirror of
https://github.com/chanzuckerberg/cellxgene.git
synced 2026-09-19 10:58:10 +08:00
94f95d6565
* Scanpy engine now required Without the --engine param we need to error if scanpy engine cannot be imported rather than waiting for all engines * CLI options and help matches proposal (but not all options hooked up yet) * Flesh out top level args * Move computation args to engine * CLI input file (#374) * Fix test command (tests still won't work) * Input is file instead of directory - also renamed example file * Csweaver/debug (#376) * Respect debug flag for logging flask calls * Add loading messages * max categories (#377) * Add max categories * Rename max_categories to category_selection_limit * ensure whole numbers
116 lines
4.1 KiB
Python
116 lines
4.1 KiB
Python
from abc import ABCMeta, abstractmethod
|
|
|
|
"""
|
|
Sort order for methods
|
|
1. Initialize
|
|
2. Helper
|
|
3. Filter
|
|
4. Data & Metadata
|
|
5. Computation
|
|
"""
|
|
|
|
|
|
class CXGDriver(metaclass=ABCMeta):
|
|
|
|
def __init__(self, data, layout_method=None, diffexp_method=None, category_selection_limit=100):
|
|
self.data = self._load_data(data)
|
|
self.layout_method = layout_method
|
|
self.diffexp_method = diffexp_method
|
|
self.category_selection_limit = category_selection_limit
|
|
self.cluster = None
|
|
|
|
@property
|
|
def features(self):
|
|
features = {
|
|
"cluster": {"available": False},
|
|
"layout": {
|
|
"obs": {"available": False},
|
|
"var": {"available": False},
|
|
},
|
|
"diffexp": {"available": False}
|
|
}
|
|
# TODO - Interactive limit should be generated from the actual available methods see GH issue #94
|
|
if self.layout_method:
|
|
# TODO handle "var" when gene layout becomes available
|
|
features["layout"]["obs"] = {"available": True, "interactiveLimit": 50000}
|
|
if self.diffexp_method:
|
|
features["diffexp"] = {"available": True, "interactiveLimit": 50000}
|
|
if self.cluster:
|
|
features["cluster"] = {"available": True, "interactiveLimit": 50000}
|
|
return features
|
|
|
|
@staticmethod
|
|
@abstractmethod
|
|
def _load_data(data):
|
|
pass
|
|
|
|
@abstractmethod
|
|
def cells(self):
|
|
pass
|
|
|
|
@abstractmethod
|
|
def genes(self):
|
|
pass
|
|
|
|
@abstractmethod
|
|
def filter_dataframe(self, filter):
|
|
"""
|
|
Filter cells from data and return a subset of the data. They can operate on both obs and var dimension with
|
|
indexing and filtering by annotation value. Filters are combined with the and operator.
|
|
See REST specs for info on filter format:
|
|
https://github.com/chanzuckerberg/cellxgene/blob/master/docs/REST_API.md
|
|
|
|
:param filter: dictionary with filter params
|
|
:return: View into scanpy object with cells/genes filtered
|
|
"""
|
|
pass
|
|
|
|
@abstractmethod
|
|
def annotation(self, filter, axis, fields=None):
|
|
"""
|
|
Gets annotation value for each observation
|
|
:param filter: filter: dictionary with filter params
|
|
:param axis: string obs or var
|
|
:param fields: list of keys for annotation to return, returns all annotation values if not set.
|
|
:return: dict: names - list of fields in order, data - list of lists or metadata
|
|
[observation ids, val1, val2...]
|
|
"""
|
|
pass
|
|
|
|
@abstractmethod
|
|
def data_frame(self, filter, axis):
|
|
"""
|
|
Retrieves data for each variable for observations in data frame
|
|
:param filter: filter: dictionary with filter params
|
|
:param axis: string obs or var
|
|
:return: {
|
|
"var": list of variable ids,
|
|
"obs": [cellid, var1 expression, var2 expression, ...],
|
|
}
|
|
"""
|
|
pass
|
|
|
|
@abstractmethod
|
|
def diffexp(self, filter1, filter2, top_n=None, interactive_limit=None):
|
|
"""
|
|
Computes the top differentially expressed variables between two observation sets. If dataframes
|
|
contain a subset of variables, then statistics for all variables will be returned, otherwise
|
|
only the top N vars will be returned.
|
|
:param filter1: filter: dictionary with filter params for first set of observations
|
|
:param filter2: filter: dictionary with filter params for second set of observations
|
|
:param top_n: Limit results to top N (Top var mode only)
|
|
:param interactive_limit: -- don't compute if total # genes in dataframes are larger than this
|
|
:return: top genes, stats and expression values for variables
|
|
"""
|
|
pass
|
|
|
|
@abstractmethod
|
|
def layout(self, filter, interactive_limit=None):
|
|
"""
|
|
Computes a n-d layout for cells through dimensionality reduction.
|
|
:param filter: filter: dictionary with filter params
|
|
:param interactive_limit: -- don't compute if total # genes in dataframes are larger than this
|
|
:return: [cellid, x, y, ...]
|
|
"""
|
|
pass
|