def upload_chunk(ch_i, storage):
chunk_sp_inds = chunks[ch_i]
# Get imzml_reader from COS because it's too big to include via Lithops captured vars
imzml_reader = read_cloud_object_with_retry(storage,
imzml_reader_cobject,
deserialise)
n_spectra = sum(imzml_reader.mzLengths[sp_i] for sp_i in chunk_sp_inds)
sp_mz_int_buf = np.zeros((n_spectra, 3),
dtype=imzml_reader.mzPrecision)
chunk_start = 0
for sp_i, mzs, ints in get_spectra(storage, ibd_cobject, imzml_reader,
chunk_sp_inds):
chunk_end = chunk_start + len(mzs)
sp_mz_int_buf[chunk_start:chunk_end, 0] = sp_id_to_idx[sp_i]
sp_mz_int_buf[chunk_start:chunk_end, 1] = mzs
sp_mz_int_buf[chunk_start:chunk_end, 2] = ints
chunk_start = chunk_end
by_mz = np.argsort(sp_mz_int_buf[:, 1])
sp_mz_int_buf = sp_mz_int_buf[by_mz]
del by_mz
chunk = serialise(sp_mz_int_buf)
size = sys.getsizeof(chunk) * (1 / 1024**2)
logger.info(f'Uploading spectra chunk {ch_i} - %.2f MB' % size)
chunk_cobject = storage.put_cloudobject(chunk)
logger.info(f'Spectra chunk {ch_i} finished')
return chunk_cobject
def _first_level_segment_upload(segm_i):
l = ds_segments_bounds[segm_i][0, 0]
r = ds_segments_bounds[segm_i][-1, 1]
segm_start, segm_end = np.searchsorted(
sp_mz_int_buf[:, 1], (l, r)) # mz expected to be in column 1
segm = sp_mz_int_buf[segm_start:segm_end]
return storage.put_cloudobject(serialise(segm))
def merge_spectra_chunk_segments(segm_cobjects, id, storage):
print(f'Merging segment {id} spectra chunks')
def _merge(ch_i):
segm_spectra_chunk = read_cloud_object_with_retry(
storage, segm_cobjects[ch_i], deserialise)
return segm_spectra_chunk
with ThreadPoolExecutor(max_workers=128) as pool:
segm = list(pool.map(_merge, range(len(segm_cobjects))))
segm = np.concatenate(segm)
# Alternative in-place sorting (slower) :
# segm.view(f'{ds_segm_dtype},{ds_segm_dtype},{ds_segm_dtype}').sort(order=['f1'], axis=0)
segm = segm[segm[:, 1].argsort()]
bounds_list = ds_segments_bounds[id]
segms_len = []
segms_cobjects = []
for segm_j in range(len(bounds_list)):
l, r = bounds_list[segm_j]
segm_start, segm_end = np.searchsorted(
segm[:, 1], (l, r)) # mz expected to be in column 1
sub_segm = segm[segm_start:segm_end]
segms_len.append(len(sub_segm))
base_id = sum([len(bounds) for bounds in ds_segments_bounds[:id]])
segm_i = base_id + segm_j
print(f'Storing dataset segment {segm_i}')
segms_cobjects.append(storage.put_cloudobject(serialise(sub_segm)))
return segms_len, segms_cobjects
def save_images(self):
if self.formula_images:
print(f'Saving {len(self.formula_images)} images')
cloud_obj = self._storage.put_cloudobject(
serialise(self.formula_images))
self.cloud_objs.append(cloud_obj)
self._partition += 1
else:
print(f'No images to save')
def build_ranking(group_i, ranking_i, database, modifier, adduct, id,
storage):
print("Building ranking...")
print(f'job_i: {id}')
print(f'ranking_i: {ranking_i}')
print(f'database: {database}')
print(f'modifier: {modifier}')
print(f'adduct: {adduct}')
# For every unmodified formula in `database`, look up the MSM score for the molecule
# that it would become after the modifier and adduct are applied
mols = read_cloud_object_with_retry(storage,
mol_db_path_to_cobj[database],
deserialise)
if adduct is not None:
# Target rankings use the same adduct for all molecules
mol_formulas = list(
map(safe_generate_ion_formula, mols, repeat(modifier),
repeat(adduct)))
else:
# Decoy rankings use a consistent random adduct for each molecule, chosen so that it doesn't overlap
# with other decoy rankings for this molecule
adducts = _get_random_adduct_set(len(mols), decoy_adducts,
ranking_i)
mol_formulas = list(
map(safe_generate_ion_formula, mols, repeat(modifier),
adducts))
formula_to_id = {}
for cobject in formula_to_id_cobjects:
formula_to_id_chunk = read_cloud_object_with_retry(
storage, cobject, deserialise)
for formula in mol_formulas:
if formula_to_id_chunk.get(formula) is not None:
formula_to_id[formula] = formula_to_id_chunk.get(formula)
formula_is = [
formula and formula_to_id.get(formula) for formula in mol_formulas
]
msm = [
formula_i and msm_lookup.get(formula_i) for formula_i in formula_is
]
if adduct is not None:
ranking_df = pd.DataFrame({
'mol': mols,
'msm': msm
},
index=formula_is)
ranking_df = ranking_df[~ranking_df.msm.isna()]
else:
# Specific molecules don't matter in the decoy rankings, only their msm distribution
ranking_df = pd.DataFrame({'msm': msm})
ranking_df = ranking_df[~ranking_df.msm.isna()]
return id, storage.put_cloudobject(serialise(ranking_df))
def _upload(segm_i):
segm = pd.concat([
deserialise_from_file(
ds_segments_path / f'ds_segm_{segm_i:04}_{chunk_i:04}')
for chunk_i in range(chunks_n)
],
ignore_index=True,
sort=False)
segm.sort_values('mz', inplace=True)
segm.reset_index(drop=True, inplace=True)
segm = serialise(segm)
logger.debug(
f'Uploading segment {segm_i}: {segm.getbuffer().nbytes} bytes')
return storage.put_cloudobject(segm)
def clip_centr_df_chunk(peaks_i, peaks_cobject, storage):
print(f'Clipping centroids dataframe chunk {peaks_i}')
centroids_df_chunk = deserialise(
storage.get_cloudobject(peaks_cobject,
stream=True)).sort_values('mz')
centroids_df_chunk = centroids_df_chunk[centroids_df_chunk.mz > 0]
ds_mz_range_unique_formulas = centroids_df_chunk[
(mz_min < centroids_df_chunk.mz)
& (centroids_df_chunk.mz < mz_max)].index.unique()
centr_df_chunk = centroids_df_chunk[centroids_df_chunk.index.isin(
ds_mz_range_unique_formulas)].reset_index()
clip_centr_chunk_cobject = storage.put_cloudobject(
serialise(centr_df_chunk))
return clip_centr_chunk_cobject, centr_df_chunk.shape[0]
def calculate_peaks_chunk(segm_i, segm_cobject, storage):
print(f'Calculating peaks from formulas chunk {segm_i}')
chunk_df = deserialise(
storage.get_cloudobject(segm_cobject, stream=True))
peaks = [
peak for formula_i, formula in chunk_df.items()
for peak in calculate_peaks_for_formula(formula_i, formula)
]
peaks_df = pd.DataFrame(peaks,
columns=['formula_i', 'peak_i', 'mz', 'int'])
peaks_df.set_index('formula_i', inplace=True)
print(f'Storing centroids chunk {id}')
peaks_cobject = storage.put_cloudobject(serialise(peaks_df))
return peaks_cobject, peaks_df.shape[0]
def store_formula_to_id_chunk(ch_i, input_cobjects, storage):
print(f'Storing formula_to_id dictionary chunk {ch_i}')
def _get(cobj):
formula_chunk = read_cloud_object_with_retry(
storage, cobj, deserialise)
formula_to_id_chunk = dict(
zip(formula_chunk.values, formula_chunk.index))
return formula_to_id_chunk
formula_to_id = {}
with ThreadPoolExecutor(max_workers=128) as pool:
for chunk_dict in pool.map(_get, input_cobjects):
formula_to_id.update(chunk_dict)
return storage.put_cloudobject(serialise(formula_to_id))
def _store(segm_i):
id = chunk_i * n_threads + segm_i
print(f'Storing formulas segment {id}')
return storage.put_cloudobject(serialise(segm_list[segm_i]))
def save(self, data, key):
self.storage.put_object(self.bucket, self.resolve_key(key),
serialise(data))
def _upload(path):
mol_sfs = sorted(set(pd.read_csv(path).sf))
return storage.put_cloudobject(serialise(mol_sfs))
def _second_level_upload(df):
return storage.put_cloudobject(serialise(df))
def _first_level_upload(args):
segm_i, df = args
del df['segm_i']
return segm_i, storage.put_cloudobject(serialise(df))
def _store(chunk_i):
return chunk_i, storage.put_cloudobject(
serialise(formulas_chunks[chunk_i]))
def get_portable_imzml_reader(storage):
imzml_stream = storage.get_cloudobject(imzml_cobject, stream=True)
parser = ImzMLParser(imzml_stream, ibd_file=None)
imzml_reader = parser.portable_spectrum_reader()
imzml_reader_cobject = storage.put_cloudobject(serialise(imzml_reader))
return imzml_reader, imzml_reader_cobject
def _store_db_data(db_data):
return storage.put_cloudobject(serialise(db_data))
def _store(segm):
return storage.put_cloudobject(serialise(segm))
