def main(args):
log = logging.getLogger('root')
hdlr = logging.StreamHandler(sys.stdout)
log.addHandler(hdlr)
log.setLevel(logging.getLevelName(args.loglevel.upper()))
# apix = args.apix = hdr["xlen"] / hdr["nx"]
for fn in args.input:
if not (fn.endswith(".star") or fn.endswith(".mrcs")
or fn.endswith(".mrc") or fn.endswith(".par")):
log.error("Only .star, .mrc, .mrcs, and .par files supported")
return 1
first_ptcl = 0
dfs = []
with mrc.ZSliceWriter(args.output) as writer:
for fn in args.input:
if fn.endswith(".star"):
df = star.parse_star(fn, keep_index=False)
star.augment_star_ucsf(df)
star.set_original_fields(df, inplace=True)
df = df.sort_values([
star.UCSF.IMAGE_ORIGINAL_PATH,
star.UCSF.IMAGE_ORIGINAL_INDEX
])
gb = df.groupby(star.UCSF.IMAGE_ORIGINAL_PATH)
for name, g in gb:
with mrc.ZSliceReader(name) as reader:
for i in g[star.UCSF.IMAGE_ORIGINAL_INDEX].values:
writer.write(reader.read(i))
elif fn.endswith(".par"):
if args.stack_path is None:
log.error(".par file input requires --stack-path")
return 1
df = metadata.par2star(metadata.parse_fx_par(fn),
data_path=args.stack_path)
# star.set_original_fields(df, inplace=True) # Redundant.
star.augment_star_ucsf(df)
elif fn.endswith(".csv"):
return 1
elif fn.endswith(".cs"):
return 1
else:
if fn.endswith(".mrcs"):
with mrc.ZSliceReader(fn) as reader:
for img in reader:
writer.write(img)
df = pd.DataFrame({
star.UCSF.IMAGE_ORIGINAL_INDEX:
np.arange(reader.nz)
})
df[star.UCSF.IMAGE_ORIGINAL_PATH] = fn
else:
print("Unrecognized input file type")
return 1
if args.star is not None:
df[star.UCSF.IMAGE_INDEX] = np.arange(first_ptcl,
first_ptcl + df.shape[0])
df[star.UCSF.IMAGE_PATH] = writer.path
df["index"] = df[star.UCSF.IMAGE_INDEX]
star.simplify_star_ucsf(df)
dfs.append(df)
first_ptcl += df.shape[0]
if args.star is not None:
df = pd.concat(dfs, join="inner")
# df = pd.concat(dfs)
# df = df.dropna(df, axis=1, how="any")
star.write_star(args.star, df, reindex=True)
return 0
def main(args):
if args.info:
args.input.append(args.output)
df = pd.concat(
(star.parse_star(inp, augment=args.augment) for inp in args.input),
join="inner")
dfaux = None
if args.cls is not None:
df = star.select_classes(df, args.cls)
if args.info:
if star.is_particle_star(df) and star.Relion.CLASS in df.columns:
c = df[star.Relion.CLASS].value_counts()
print("%s particles in %d classes" %
("{:,}".format(df.shape[0]), len(c)))
print(" ".join([
'%d: %s (%.2f %%)' % (i, "{:,}".format(s), 100. * s / c.sum())
for i, s in iteritems(c.sort_index())
]))
elif star.is_particle_star(df):
print("%s particles" % "{:,}".format(df.shape[0]))
if star.Relion.MICROGRAPH_NAME in df.columns:
mgraphcnt = df[star.Relion.MICROGRAPH_NAME].value_counts()
print(
"%s micrographs, %s +/- %s particles per micrograph" %
("{:,}".format(len(mgraphcnt)), "{:,.3f}".format(
np.mean(mgraphcnt)), "{:,.3f}".format(np.std(mgraphcnt))))
try:
print("%f A/px (%sX magnification)" %
(star.calculate_apix(df), "{:,.0f}".format(
df[star.Relion.MAGNIFICATION][0])))
except KeyError:
pass
if len(df.columns.intersection(star.Relion.ORIGINS3D)) > 0:
print("Largest shift is %f pixels" % np.max(
np.abs(df[df.columns.intersection(
star.Relion.ORIGINS3D)].values)))
return 0
if args.drop_angles:
df.drop(star.Relion.ANGLES, axis=1, inplace=True, errors="ignore")
if args.drop_containing is not None:
containing_fields = [
f for q in args.drop_containing for f in df.columns if q in f
]
if args.invert:
containing_fields = df.columns.difference(containing_fields)
df.drop(containing_fields, axis=1, inplace=True, errors="ignore")
if args.offset_group is not None:
df[star.Relion.GROUPNUMBER] += args.offset_group
if args.restack is not None:
if not args.augment:
star.augment_star_ucsf(df, inplace=True)
star.set_original_fields(df, inplace=True)
df[star.UCSF.IMAGE_PATH] = args.restack
df[star.UCSF.IMAGE_INDEX] = np.arange(df.shape[0])
if args.subsample_micrographs is not None:
if args.bootstrap is not None:
print("Only particle sampling allows bootstrapping")
return 1
mgraphs = df[star.Relion.MICROGRAPH_NAME].unique()
if args.subsample_micrographs < 1:
args.subsample_micrographs = np.int(
max(np.round(args.subsample_micrographs * len(mgraphs)), 1))
else:
args.subsample_micrographs = np.int(args.subsample_micrographs)
ind = np.random.choice(len(mgraphs),
size=args.subsample_micrographs,
replace=False)
mask = df[star.Relion.MICROGRAPH_NAME].isin(mgraphs[ind])
if args.auxout is not None:
dfaux = df.loc[~mask]
df = df.loc[mask]
if args.subsample is not None and args.suffix == "":
if args.subsample < 1:
args.subsample = np.int(
max(np.round(args.subsample * df.shape[0]), 1))
else:
args.subsample = np.int(args.subsample)
ind = np.random.choice(df.shape[0], size=args.subsample, replace=False)
mask = df.index.isin(ind)
if args.auxout is not None:
dfaux = df.loc[~mask]
df = df.loc[mask]
if args.copy_angles is not None:
angle_star = star.parse_star(args.copy_angles, augment=args.augment)
df = star.smart_merge(df,
angle_star,
fields=star.Relion.ANGLES,
key=args.merge_key)
if args.copy_alignments is not None:
align_star = star.parse_star(args.copy_alignments,
augment=args.augment)
df = star.smart_merge(df,
align_star,
fields=star.Relion.ALIGNMENTS,
key=args.merge_key)
if args.copy_reconstruct_images is not None:
recon_star = star.parse_star(args.copy_reconstruct_images,
augment=args.augment)
df[star.Relion.RECONSTRUCT_IMAGE_NAME] = recon_star[
star.Relion.IMAGE_NAME]
if args.transform is not None:
if args.transform.count(",") == 2:
r = geom.euler2rot(
*np.deg2rad([np.double(s) for s in args.transform.split(",")]))
else:
r = np.array(json.loads(args.transform))
df = star.transform_star(df, r, inplace=True)
if args.invert_hand:
df = star.invert_hand(df, inplace=True)
if args.copy_paths is not None:
path_star = star.parse_star(args.copy_paths)
star.set_original_fields(df, inplace=True)
df[star.Relion.IMAGE_NAME] = path_star[star.Relion.IMAGE_NAME]
if args.copy_ctf is not None:
ctf_star = pd.concat((star.parse_star(inp, augment=args.augment)
for inp in glob.glob(args.copy_ctf)),
join="inner")
df = star.smart_merge(df,
ctf_star,
star.Relion.CTF_PARAMS,
key=args.merge_key)
if args.copy_micrograph_coordinates is not None:
coord_star = pd.concat(
(star.parse_star(inp, augment=args.augment)
for inp in glob.glob(args.copy_micrograph_coordinates)),
join="inner")
df = star.smart_merge(df,
coord_star,
fields=star.Relion.MICROGRAPH_COORDS,
key=args.merge_key)
if args.scale is not None:
star.scale_coordinates(df, args.scale, inplace=True)
star.scale_origins(df, args.scale, inplace=True)
star.scale_magnification(df, args.scale, inplace=True)
if args.scale_particles is not None:
star.scale_origins(df, args.scale_particles, inplace=True)
star.scale_magnification(df, args.scale_particles, inplace=True)
if args.scale_coordinates is not None:
star.scale_coordinates(df, args.scale_coordinates, inplace=True)
if args.scale_origins is not None:
star.scale_origins(df, args.scale_origins, inplace=True)
if args.scale_magnification is not None:
star.scale_magnification(df, args.scale_magnification, inplace=True)
if args.scale_apix is not None:
star.scale_apix(df, args.scale_apix, inplace=True)
if args.recenter:
df = star.recenter(df, inplace=True)
if args.zero_origins:
df = star.zero_origins(df, inplace=True)
if args.pick:
df.drop(df.columns.difference(star.Relion.PICK_PARAMS),
axis=1,
inplace=True,
errors="ignore")
if args.subsample is not None and args.suffix != "":
if args.subsample < 1:
print("Specific integer sample size")
return 1
nsamplings = args.bootstrap if args.bootstrap is not None else df.shape[
0] / np.int(args.subsample)
inds = np.random.choice(df.shape[0],
size=(nsamplings, np.int(args.subsample)),
replace=args.bootstrap is not None)
for i, ind in enumerate(inds):
star.write_star(
os.path.join(
args.output,
os.path.basename(args.input[0])[:-5] + args.suffix +
"_%d" % (i + 1)), df.iloc[ind])
if args.to_micrographs:
df = star.to_micrographs(df)
if args.micrograph_range:
df.set_index(star.Relion.MICROGRAPH_NAME, inplace=True)
m, n = [int(tok) for tok in args.micrograph_range.split(",")]
mg = df.index.unique().sort_values()
outside = list(range(0, m)) + list(range(n, len(mg)))
dfaux = df.loc[mg[outside]].reset_index()
df = df.loc[mg[m:n]].reset_index()
if args.micrograph_path is not None:
df = star.replace_micrograph_path(df,
args.micrograph_path,
inplace=True)
if args.min_separation is not None:
gb = df.groupby(star.Relion.MICROGRAPH_NAME)
dupes = []
for n, g in gb:
nb = algo.query_connected(
g[star.Relion.COORDS].values - g[star.Relion.ORIGINS],
args.min_separation / star.calculate_apix(df))
dupes.extend(g.index[~np.isnan(nb)])
dfaux = df.loc[dupes]
df.drop(dupes, inplace=True)
if args.merge_source is not None:
if args.merge_fields is not None:
if "," in args.merge_fields:
args.merge_fields = args.merge_fields.split(",")
else:
args.merge_fields = [args.merge_fields]
else:
print("Merge fields must be specified using --merge-fields")
return 1
if args.merge_key is not None:
if "," in args.merge_key:
args.merge_key = args.merge_key.split(",")
if args.by_original:
args.by_original = star.original_field(args.merge_key)
else:
args.by_original = args.merge_key
merge_star = star.parse_star(args.merge_source, augment=args.augment)
df = star.smart_merge(df,
merge_star,
fields=args.merge_fields,
key=args.merge_key,
left_key=args.by_original)
if args.revert_original:
df = star.revert_original(df, inplace=True)
if args.set_optics is not None:
tok = args.set_optics.split(",")
df = star.set_optics_groups(df,
sep=tok[0],
idx=int(tok[1]),
inplace=True)
df.dropna(axis=0, how="any", inplace=True)
if args.drop_optics_group is not None:
idx = df[star.Relion.OPTICSGROUP].isin(args.drop_optics_group)
if not np.any(idx):
idx = df[star.Relion.OPTICSGROUPNAME].isin(args.drop_optics_group)
if not np.any(idx):
print("No group found to drop")
return 1
df = df.loc[~idx]
if args.split_micrographs:
dfs = star.split_micrographs(df)
for mg in dfs:
star.write_star(
os.path.join(args.output,
os.path.basename(mg)[:-4]) + args.suffix, dfs[mg])
return 0
if args.auxout is not None and dfaux is not None:
if not args.relion2:
df = star.remove_deprecated_relion2(dfaux, inplace=True)
star.write_star(args.output,
df,
resort_records=args.sort,
simplify=args.augment_output,
optics=True)
else:
df = star.remove_new_relion31(dfaux, inplace=True)
star.write_star(args.output,
df,
resort_records=args.sort,
simplify=args.augment_output,
optics=False)
if args.output is not None:
if not args.relion2: # Relion 3.1 style output.
df = star.remove_deprecated_relion2(df, inplace=True)
star.write_star(args.output,
df,
resort_records=args.sort,
simplify=args.augment_output,
optics=True)
else:
df = star.remove_new_relion31(df, inplace=True)
star.write_star(args.output,
df,
resort_records=args.sort,
simplify=args.augment_output,
optics=False)
return 0
def main(args):
log = logging.getLogger('root')
hdlr = logging.StreamHandler(sys.stdout)
log.addHandler(hdlr)
log.setLevel(logging.getLevelName(args.loglevel.upper()))
# apix = args.apix = hdr["xlen"] / hdr["nx"]
for fn in args.input:
if not (fn.endswith(".star") or fn.endswith(".mrcs") or
fn.endswith(".mrc") or fn.endswith(".par")):
log.error("Only .star, .mrc, .mrcs, and .par files supported")
return 1
first_ptcl = 0
dfs = []
with mrc.ZSliceWriter(args.output) as writer:
for fn in args.input:
if fn.endswith(".star"):
df = star.parse_star(fn, augment=True)
if args.cls is not None:
df = star.select_classes(df, args.cls)
star.set_original_fields(df, inplace=True)
if args.resort:
df = df.sort_values([star.UCSF.IMAGE_ORIGINAL_PATH,
star.UCSF.IMAGE_ORIGINAL_INDEX])
for idx, row in df.iterrows():
if args.stack_path is not None:
input_stack_path = os.path.join(args.stack_path, row[star.UCSF.IMAGE_ORIGINAL_PATH])
else:
input_stack_path = row[star.UCSF.IMAGE_ORIGINAL_PATH]
with mrc.ZSliceReader(input_stack_path) as reader:
i = row[star.UCSF.IMAGE_ORIGINAL_INDEX]
writer.write(reader.read(i))
elif fn.endswith(".par"):
if args.stack_path is None:
log.error(".par file input requires --stack-path")
return 1
df = metadata.par2star(metadata.parse_fx_par(fn), data_path=args.stack_path)
# star.set_original_fields(df, inplace=True) # Redundant.
star.augment_star_ucsf(df)
elif fn.endswith(".csv"):
return 1
elif fn.endswith(".cs"):
return 1
else:
if fn.endswith(".mrcs"):
with mrc.ZSliceReader(fn) as reader:
for img in reader:
writer.write(img)
df = pd.DataFrame(
{star.UCSF.IMAGE_ORIGINAL_INDEX: np.arange(reader.nz)})
df[star.UCSF.IMAGE_ORIGINAL_PATH] = fn
else:
print("Unrecognized input file type")
return 1
if args.star is not None:
df[star.UCSF.IMAGE_INDEX] = np.arange(first_ptcl,
first_ptcl + df.shape[0])
if args.abs_path:
df[star.UCSF.IMAGE_PATH] = writer.path
else:
df[star.UCSF.IMAGE_PATH] = os.path.relpath(writer.path, os.path.dirname(args.star))
df["index"] = df[star.UCSF.IMAGE_INDEX]
star.simplify_star_ucsf(df)
dfs.append(df)
first_ptcl += df.shape[0]
if args.star is not None:
df = pd.concat(dfs, join="inner")
# df = pd.concat(dfs)
# df = df.dropna(df, axis=1, how="any")
if not args.relion2: # Relion 3.1 style output.
df = star.remove_deprecated_relion2(df, inplace=True)
star.write_star(args.star, df, resort_records=False, optics=True)
else:
df = star.remove_new_relion31(df, inplace=True)
star.write_star(args.star, df, resort_records=False, optics=False)
return 0