from archimedes.functions.dataflow import output_path, input_path, input_var
from archimedes.functions.scanpy import scanpy as sc
scdata = sc.read(input_path('pca_anndata.h5ad'))
# Neighborhood
max_pc = int(input_var('max_pc'))
n_neighbors = int(input_var('n_neighbors'))
sc.pp.neighbors(scdata, n_neighbors=n_neighbors, n_pcs=max_pc)
##### OUTPUT
scdata.write(output_path('nn_anndata.h5ad'))
from archimedes.functions.dataflow import output_path, input_path, input_var, json, input_json, buildTargetPath
from archimedes.functions.scanpy import scanpy as sc
from archimedes.functions.plotting import pio, scatter_plotly
from archimedes.functions.magma import connect, question
from archimedes.functions.list import flatten
from archimedes.functions.environment import project_name
from archimedes.functions.utils import pandas as pd
# Read inputs
scdata = sc.read(input_path('umap_anndata.h5ad'))
leiden = list(map(str, input_json('leiden.json')))
color_by = input_var('color_by')
px_args = {}
# Prep magma querying
magma = connect()
def get(ids, value):
ids = ids if type(ids) == list else ids.tolist()
values = dict(question(magma, [
'sc_seq',
[ '::identifier', '::in', ids ],
'::all',
*value
], strip_identifiers=False))
return [ values.get(id, None) for id in ids ]
pdat = input_json("project_data")[project_name]
from archimedes.functions.dataflow import input_path, output_json, input_json
from archimedes.functions.scanpy import scanpy as sc
from archimedes.functions.environment import project_name
scdata = sc.read(input_path('leiden_anndata.h5ad'))
pdat = input_json("project_data")[project_name]
color_options = {
'Gene': dict([[gene_id, None] for gene_id in scdata.raw.var_names]),
'Cluster': None,
'Manual Annotations': None,
'Tube': None
}
color_options.update([[label, None] for label in pdat['color_options'].keys()])
output_json(color_options, 'color_options')
from archimedes.functions.dataflow import output_path, input_path, input_bool
from archimedes.functions.scanpy import scanpy as sc
scdata = sc.read(input_path('normed_anndata.h5ad'))
regress_nCounts = input_bool('regress_counts')
regress_nFeatures = input_bool('regress_genes')
regress_pct_mito = input_bool('regress_pct_mito')
regress_pct_ribo = input_bool('regress_pct_ribo')
regress_tube_id = input_bool('regress_tube_id')
# Regress out and scale
if any([regress_nCounts, regress_nFeatures, regress_pct_mito, regress_pct_ribo, regress_tube_id]):
regress_on = []
if regress_nCounts:
regress_on.append('n_counts')
if regress_nFeatures:
regress_on.append('n_genes')
if regress_pct_mito:
regress_on.append('pct_counts_mt')
if regress_pct_ribo:
regress_on.append('pct_counts_rb')
if regress_tube_id:
regress_on.append('Record_ID')
sc.pp.regress_out(scdata, regress_on)
sc.pp.scale(scdata, max_value=10)
# pca
sc.tl.pca(scdata, svd_solver='arpack')
##### OUTPUT
from archimedes.functions.dataflow import output_path, input_path, input_var
from archimedes.functions.scanpy import scanpy as sc
scdata = sc.read(input_path('merged_anndata.h5ad'))
# Convert these too
min_nCounts = int(input_var('min_nCounts'))
max_nCounts = int(input_var('max_nCounts'))
min_nFeatures = int(input_var('min_nFeatures'))
max_per_mito = int(input_var('max_per_mito'))
max_per_ribo = int(input_var('max_per_ribo'))
# Calculate mito QC metrics
scdata.var['mt'] = scdata.var_names.str.startswith(
'Mt-') # annotate the group of mitochondrial genes as 'mt'
scdata.var['rb'] = scdata.var_names.str.startswith(
'Rps-|Rpl-'
) # annotate the group of ribosomal genes as 'rb' ## not sure if the syntax works.
sc.pp.calculate_qc_metrics(scdata,
qc_vars=['mt'],
percent_top=None,
log1p=False,
inplace=True)
sc.pp.calculate_qc_metrics(scdata,
qc_vars=['rb'],
percent_top=None,
log1p=False,
inplace=True)
# Perform all filtering
sc.pp.filter_cells(scdata, min_genes=min_nFeatures)
sc.pp.filter_cells(scdata, min_counts=min_nCounts)