def render(assay):
with st.sidebar.beta_expander('Customizations'):
interface.info('Rename the labels.<br>Merge by giving the same name.')
lab_map = {}
keep_labs = []
pal = assay.get_palette()
lab_set = np.unique(assay.get_labels())
for lab in lab_set:
col1, col2, col3 = st.beta_columns([1, 0.1, 0.07])
with col1:
new_name = st.text_input(f'Give a new name to {lab}', lab)
with col2:
st.markdown(f"<p style='margin-bottom:34px'></p>",
unsafe_allow_html=True)
pal[lab] = st.color_picker('',
pal[lab],
key=f'colorpicker-{lab}')
with col3:
st.markdown(f"<p style='margin-bottom:42px'></p>",
unsafe_allow_html=True)
keep = st.checkbox('', True, key=f'keep-cells-{lab}-{lab_set}')
if keep:
keep_labs.append(lab)
if new_name != lab:
lab_map[lab] = new_name
pal[new_name] = pal[lab]
del pal[lab]
if len(keep_labs) == 0:
interface.error('At least one label must be selected.')
return lab_map, pal, keep_labs
def render(sample, assay_names):
with st.sidebar.beta_expander('Preprocessing'):
info = st.empty()
assay_name = {DNA_ASSAY: 'DNA', PROTEIN_ASSAY: 'Protein'}
assay_type = st.selectbox('Assay',
assay_names,
format_func=lambda x: assay_name[x])
if assay_type == DNA_ASSAY:
dp, gq, af, std = sample.dna.metadata[DFT.PREPROCESS_ARGS]
dp = st.slider('Minimum read depth (DP)',
min_value=0,
max_value=100,
value=int(dp))
gq = st.slider('Minimum genotype quality (GQ)',
min_value=0,
max_value=100,
value=int(gq))
af = st.slider('Minimum allele frequency (VAF)',
min_value=0,
max_value=100,
value=int(af))
std = st.slider('Minimum standard deviation of AF',
min_value=0,
max_value=100,
value=int(std))
ids = sample.dna.metadata[DFT.ALL_IDS]
ids = list(ids[ids.argsort()])
drop_vars = st.multiselect(
'Variants to discard',
ids,
default=sample.dna.metadata[DFT.DROP_IDS])
keep_vars = st.multiselect(
'Variants to keep',
ids,
default=sample.dna.metadata[DFT.KEEP_IDS])
if len(keep_vars) != 0 and len(drop_vars) != 0:
interface.error(
'Cannot keep and drop variants both. Choose only one of the options'
)
assay_args = [drop_vars, keep_vars, dp, gq, af, std]
elif assay_type == PROTEIN_ASSAY:
ids = sample.protein.metadata[DFT.ALL_IDS]
ids = list(ids[ids.argsort()])
drop_abs = st.multiselect(
'Antibodies to discard',
ids,
default=sample.protein.metadata[DFT.DROP_IDS])
assay_args = [drop_abs]
interface.info(f'{assay_type} currently loaded', info)
clicked = st.button('Process')
return assay_type, clicked, assay_args
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 _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
def run():
file, load_raw, apply_filter, kind, should_save, save_name, info = render()
if kind == DFT.S3:
file = download(file)
if file is None:
interface.error(
'Please use the options available in the sidebar to load a sample.<br>'
'New h5 files should be copied to the <i>/h5/downloads/</i> folder where the app is stored.'
)
sample = load(file, load_raw, apply_filter)
interface.info(f'Currently loaded {sample.name}', info)
return sample, should_save, save_name
def download(link):
interface.status('Downloading from s3.')
s3 = boto3.client('s3')
link = link.replace('s3://', '')
link = link.split('/')
bucket, file = link[0], '/'.join(link[1:])
filename = file.split('/')[-1]
filename = DFT.ROOT / f'h5/downloads/{filename}'
filename = str(filename)
try:
s3.download_file(bucket, file, filename)
except Exception as e:
interface.status('Done.')
interface.error(f'Could not find the given h5 file. {e}')
return filename
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 preprocess_dna(sample, clicked, drop_vars, keep_vars, dp, gq, af, std):
args_changed = (
list(sample.dna.metadata[DFT.PREPROCESS_ARGS]) != [dp, gq, af, std]
or set(sample.dna.metadata[DFT.DROP_IDS]) != set(drop_vars)
or set(sample.dna.metadata[DFT.KEEP_IDS]) != set(keep_vars))
if sample.dna.metadata[DFT.INITIALIZE] or (args_changed and clicked):
interface.status('Processing DNA assay.')
sample.reset('dna')
if len(keep_vars) == 0:
dna_vars = sample.dna.filter_variants(min_dp=dp,
min_gq=gq,
min_vaf=af,
min_std=std)
sample.dna.add_metadata(DFT.ALL_IDS, sample.dna.ids())
if len(drop_vars) > 0:
sample.dna = sample.dna.drop(drop_vars)
else:
dna_vars = keep_vars
if len(dna_vars) == 0:
interface.status('Done.')
interface.error(
'No variants found. Adjust the filters and process again. Make sure "Filter" is deselected in the Files section.'
)
sample.dna = sample.dna[:, dna_vars]
sample.dna.add_metadata(DFT.PREPROCESS_ARGS, [dp, gq, af, std])
sample.dna.add_metadata(DFT.DROP_IDS, drop_vars)
sample.dna.add_metadata(DFT.KEEP_IDS, keep_vars)
if not sample.dna.metadata[DFT.INITIALIZE]:
sample.dna.add_metadata(DFT.PREPPED, False)
sample.dna.add_metadata(DFT.CLUSTERED, False)
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