def run(sample):
assay_names = []
for a in [sample.dna, sample.protein]:
if a is not None:
assay_names.append(a.name)
assay_type, clicked, assay_args = render(sample, assay_names)
first_pass_preprocess(sample, assay_args)
if assay_type == DNA_ASSAY:
preprocess_dna(sample, clicked, *assay_args)
elif assay_type == PROTEIN_ASSAY:
preprocess_protein(sample, clicked, *assay_args)
if clicked:
interface.rerun()
available_assays = []
for a in [sample.dna, sample.protein]:
if a is not None:
available_assays.append(a)
if a.name == assay_type:
current_assay = a
interface.subheader(
f'Analysing {assay_type} | {current_assay.shape[0]} cells | {current_assay.shape[1]} ids | {len(set(current_assay.get_labels()))} clusters'
)
return current_assay, available_assays
def run(sample, name, should_save):
for assay, og_assay in zip(
[sample.dna, sample.protein],
[sample._original_dna, sample._original_protein]):
if assay is not None:
for key in assay.metadata:
og_assay.add_metadata(key, assay.metadata[key])
for key in assay.row_attrs:
og_assay.add_row_attr(key, assay.row_attrs[key])
if should_save:
interface.status('Saving h5 file.')
if name == '':
interface.error('Please provide a name to save by.')
elif name[-3:] == '.h5':
name = name[:-3]
try:
os.remove(DFT.ROOT / f'h5/analyzed/{name}.h5')
except FileNotFoundError:
pass
samp = sample[:]
set_defaults(samp)
mio.save(samp, DFT.ROOT / f'h5/analyzed/{name}.h5')
interface.status('Saved.')
interface.rerun()
def customize_labels(assay, lab_map, pal):
old_labs = set(assay.get_labels())
old_pal = assay.get_palette()
assay.rename_labels(lab_map)
assay.set_palette(pal)
new_labs = set(assay.get_labels())
if new_labs != old_labs or old_pal != pal:
interface.rerun()
def run(assay, available_assays):
clicked, method, description, cluster_kwargs, info = render(assay)
first_pass_cluster(available_assays)
if clicked:
cluster(assay, method, description, **cluster_kwargs)
interface.rerun()
interface.info(
f'Currently clustered using {assay.metadata[DFT.CLUSTER_DESCRIPTION]}',
info)
def run(assay, available_assays):
clicked, scale_attribute, pca_attribute, umap_attribute, pca_comps, info = render(
assay)
first_pass_prepare(available_assays)
if clicked:
prepare(assay, scale_attribute, pca_attribute, umap_attribute,
pca_comps)
interface.rerun()
interface.info(
f'Current transformations are:<br>'
f'Scale on {assay.metadata[DFT.SCALE_ATTR]}<br>'
f'PCA on {assay.metadata[DFT.PCA_ATTR]}<br>'
f'UMAP on {assay.metadata[DFT.UMAP_ATTR]}', info)
def run(sample, name):
interface.status('Saving h5 file.')
if name == '':
interface.error('Please provide a name to save by.')
elif name[-3:] == '.h5':
name = name[:-3]
try:
os.remove(DFT.ROOT / f'h5/analyzed/{name}.h5')
except FileNotFoundError:
pass
samp = sample[:]
set_defaults(samp)
mio.save(samp, DFT.ROOT / f'h5/analyzed/{name}.h5')
interface.status('Saved.')
interface.rerun()
def render(sample, assay):
interface.status('Creating visuals.')
category, kind = assay.metadata[DFT.VISUAL_TYPE]
options = DFT.VISUALS[category][1]
column_sizes = DFT.VISUALS[category][0]
columns = st.beta_columns(column_sizes)
with columns[0]:
new_category = st.selectbox("", list(DFT.VISUALS.keys()))
if new_category != category:
assay.add_metadata(DFT.VISUAL_TYPE,
[new_category, DFT.VISUALS[new_category][1][0]])
interface.rerun()
for i in range(len(options)):
with columns[i + 1]:
st.markdown(f"<p style='margin-bottom:33px'></p>",
unsafe_allow_html=True)
clicked = st.button(options[i], key=f'visual-{options[i]}')
if clicked:
kind = options[i]
assay.add_metadata(DFT.VISUAL_TYPE, [category, kind])
if kind in DFT.LAYOUT:
columns = st.beta_columns(DFT.LAYOUT[kind])
args_conatiner = columns[0]
plot_columns = columns[1:]
else:
columns = st.beta_columns([0.75, 0.1, 2])
args_conatiner = columns[0]
plot_columns = columns[2]
with args_conatiner:
kwargs = {}
analyte_map = {'protein': 'Protein', 'dna': 'DNA'}
if kind == DFT.SIGNATURES:
kwargs['layer'] = st.selectbox('Layer', DFT.LAYERS[assay.name])
kwargs['attribute'] = st.selectbox(
'Signature', ['Median', 'Standard deviation', 'p-value'])
elif kind == DFT.HEATMAP:
kwargs['attribute'] = st.selectbox('Attribute',
DFT.LAYERS[assay.name],
key='Visualization Attribute')
kwargs['splitby'] = st.selectbox('Split by',
DFT.SPLITBY[assay.name])
kwargs['orderby'] = st.selectbox('Order by',
DFT.LAYERS[assay.name],
key='Visualization Orderby')
kwargs['cluster'] = st.checkbox('Cluster within labels', True)
kwargs['convolve'] = st.slider('Smoothing', 0, 100)
elif kind == DFT.SCATTERPLOT:
kwargs['attribute'] = st.selectbox('Attribute', DFT.ATTRS_2D)
kwargs['colorby'] = st.selectbox('Color by',
DFT.COLORBY[assay.name])
if kwargs['colorby'] not in DFT.SPLITBY[assay.name] + ['density']:
features = st.multiselect(
'Features', list(assay.ids()),
list(assay.ids())[:min(len(assay.ids()), 4)])
if len(features) != 0:
kwargs['features'] = features
elif kind == DFT.FEATURE_SCATTER:
kwargs['layer'] = st.selectbox('Layer', DFT.LAYERS[assay.name])
feature1 = st.selectbox('Feature 1', list(assay.ids()), index=0)
feature2 = st.selectbox('Feature 1', list(assay.ids()), index=2)
kwargs['ids'] = [feature1, feature2]
kwargs['colorby'] = st.selectbox('Color by',
DFT.COLORBY[assay.name])
elif kind == DFT.VIOLINPLOT:
kwargs['attribute'] = st.selectbox('Attribute',
DFT.LAYERS[assay.name])
kwargs['splitby'] = st.selectbox('Split by',
DFT.SPLITBY[assay.name])
kwargs['points'] = st.checkbox('Box and points', False)
features = st.multiselect(
'Features', list(assay.ids()),
list(assay.ids())[:min(len(assay.ids()), 4)])
if len(features) != 0:
kwargs['features'] = features
elif kind == DFT.RIDGEPLOT:
kwargs['attribute'] = st.selectbox('Attribute',
DFT.LAYERS[assay.name])
kwargs['splitby'] = st.selectbox('Split by',
DFT.SPLITBY[assay.name])
features = st.multiselect(
'Features', list(assay.ids()),
list(assay.ids())[:min(len(assay.ids()), 4)])
if len(features) != 0:
kwargs['features'] = features
elif kind == DFT.STRIPPLOT:
kwargs['attribute'] = st.selectbox('Attribute',
DFT.LAYERS[assay.name])
kwargs['colorby'] = st.selectbox('Colorby', DFT.LAYERS[assay.name])
features = st.multiselect(
'Features', list(assay.ids()),
list(assay.ids())[:min(len(assay.ids()), 4)])
if len(features) != 0:
kwargs['features'] = features
elif kind == DFT.DNA_PROTEIN_PLOT:
kwargs['analyte'] = st.selectbox(
'Analyte', ['protein'], format_func=lambda a: analyte_map[a])
kwargs['dna_features'] = st.multiselect('DNA features',
list(sample.dna.ids()),
sample.dna.ids()[:4])
kwargs['protein_features'] = st.multiselect(
'Protein features', list(sample.protein.ids()),
sample.protein.ids()[:4])
elif kind == DFT.DNA_PROTEIN_HEATMAP:
kwargs['clusterby'] = st.selectbox(
'Cluster by', ['dna', 'protein'],
format_func=lambda a: analyte_map[a])
kwargs['sortby'] = st.selectbox(
'Sort by', ['dna', 'protein'],
format_func=lambda a: analyte_map[a])
kwargs['dna_features'] = st.multiselect('DNA features',
list(sample.dna.ids()),
sample.dna.ids())
kwargs['protein_features'] = st.multiselect(
'Protein features', list(sample.protein.ids()),
sample.protein.ids())
elif kind == DFT.METRICS:
st.header('')
interface.info(
'<b>Some values might be missing in case the raw<br> files are not loaded.</b> These metrics can be<br> pasted into the metrics sheet as is.'
)
elif kind == DFT.READ_DEPTH:
if assay.name == PROTEIN_ASSAY:
kwargs['layer'] = st.selectbox('Layer', DFT.LAYERS[assay.name])
kwargs['colorby'] = st.selectbox('Color by', ['density', None])
kwargs['features'] = st.multiselect(
'Features', list(assay.ids()),
list(assay.ids())[:min(len(assay.ids()), 4)])
else:
st.header('')
interface.info('<b>Only applicable for the protein assay</b>')
elif kind == DFT.ASSAY_SCATTER:
kwargs['draw'] = sample.protein_raw is not None
if not kwargs['draw']:
interface.info('<b>Raw files needed for this plot.</b>')
elif kind == DFT.DOWNLOAD:
kwargs['item'] = st.selectbox('Object to Download',
DFT.DOWNLOAD_ITEMS)
kwargs['download'] = st.button('Download', key='download_button')
return plot_columns, kind, kwargs
def render():
with st.sidebar.beta_expander('Files', expanded=True):
interface.info('Load or download a file from s3')
info = st.empty()
col1, col2 = st.beta_columns([0.3, 1])
with col1:
st.markdown(f"<sup><p style='margin-bottom:22px'></p></sup>",
unsafe_allow_html=True)
load_raw = st.checkbox('Raw')
with col2:
st.markdown(f"<sup><p style='margin-bottom:22px'></p></sup>",
unsafe_allow_html=True)
apply_filter = st.checkbox('Filter', False)
link = st.text_input('Load from s3', value='')
if not os.path.exists(DFT.ROOT / 'h5'):
os.mkdir(DFT.ROOT / 'h5')
if not os.path.exists(DFT.ROOT / 'h5/downloads'):
os.mkdir(DFT.ROOT / 'h5/downloads/')
if not os.path.exists(DFT.ROOT / 'h5/analyzed'):
os.mkdir(DFT.ROOT / 'h5/analyzed/')
downloaded_files = np.array(os.listdir(DFT.ROOT / 'h5/downloads/'))
analyzed_files = np.array(os.listdir(DFT.ROOT / 'h5/analyzed/'))
filenames = list(analyzed_files[analyzed_files.argsort()]) + list(
downloaded_files[downloaded_files.argsort()])
filenames = [None] + [f for f in filenames if f[-3:] == '.h5']
def shownames(name):
nonlocal analyzed_files
if name in analyzed_files:
return '* ' + name
else:
return name
kind = None
selector = st.empty()
file = selector.selectbox('Load existing file',
filenames,
format_func=shownames)
if link != '':
kind = DFT.S3
file = link
elif file is not None:
if file in downloaded_files:
file = DFT.ROOT / f'h5/downloads/{file}'
else:
file = DFT.ROOT / f'h5/analyzed/{file}'
kind = DFT.LOCAL
typed_name = st.text_input('Save, download or delete the given file',
value='')
def _get_file_from_name(typed_name):
if typed_name[-3:] == '.h5':
typed_name = typed_name[:-3]
if typed_name + '.h5' in analyzed_files:
typed_name = DFT.ROOT / f'h5/analyzed/{typed_name}.h5'
elif typed_name + '.h5' in downloaded_files:
typed_name = DFT.ROOT / f'h5/downloads/{typed_name}.h5'
else:
interface.error(
f'Cannot find "{typed_name}" in the available files')
return typed_name
col1, col2, col3 = st.beta_columns([0.25, 0.4, 0.4])
with col1:
st.markdown('')
should_save = st.button('Save')
with col2:
st.markdown('')
if st.button('Download'):
download_path = _get_file_from_name(typed_name)
interface.download(download_path)
with col3:
st.markdown('')
if st.button('Delete'):
typed_name = _get_file_from_name(typed_name)
if file is not None and typed_name == file:
interface.error(
'Cannot delete the file used in the current analysis.')
os.remove(typed_name)
interface.rerun()
return file, load_raw, apply_filter, kind, should_save, typed_name, info