def main(args):
fmt = args._from
# detect the input file formats
path = args.file
if fmt == 'auto':
try:
fmt = file_utils.detect_format(path)
except file_utils.UnknownFormatError as e:
print('Error: unrecognized input coordinates file extension (' +
e.ext + ')',
file=sys.stderr)
sys.exit(1)
_, ext = os.path.splitext(path)
suffix = args.suffix
t = args.threshold
base = args.output
if fmt == 'star':
with open(path, 'r') as f:
table = star.parse(f)
# apply score threshold
if star.SCORE_COLUMN_NAME in table.columns:
table = table.loc[table[star.SCORE_COLUMN_NAME] >= t]
# write per micrograph files
for image_name, group in table.groupby('MicrographName'):
image_name, _ = os.path.splitext(image_name)
path = base + '/' + image_name + suffix + ext
with open(path, 'w') as f:
star.write(group, f)
else: # format is coordinate table
table = pd.read_csv(path, sep='\t')
if 'score' in table.columns:
table = table.loc[table['score'] >= t]
# write per micrograph files
for image_name, group in table.groupby('image_name'):
path = base + '/' + image_name + suffix + ext
group.to_csv(path, sep='\t', index=False)
def read_coordinates(path, format='auto'):
if format == 'auto':
format = detect_format(path)
if format == 'star':
with open(path, 'r') as f:
table = star.parse(f)
# standardize the image name, x, y, and score column names
d = {
star.SCORE_COLUMN_NAME: 'score',
'MicrographName': 'image_name',
star.X_COLUMN_NAME: 'x_coord',
star.Y_COLUMN_NAME: 'y_coord',
star.VOLTAGE: 'voltage',
star.DETECTOR_PIXEL_SIZE: 'detector_pixel_size',
star.MAGNIFICATION: 'magnification',
star.AMPLITUDE_CONTRAST: 'amplitude_contrast',
}
for k, v in d.items():
if k in table.columns:
table[v] = table[k]
table = table.drop(k, axis=1)
# strip off image extension, but save this for later
table['image_name'] = table['image_name'].apply(strip_ext)
particles = table
elif format == 'box':
box = read_box(path)
image_name = os.path.basename(os.path.splitext(path)[0])
particles = boxes_to_coordinates(box, image_name=image_name)
elif format == 'csv':
# this is VIA CSV format
particles = read_via_csv(path)
else: # default to coordiantes table format
particles = pd.read_csv(path, sep='\t')
return particles
def main(args):
with open(args.file, 'r') as f:
table = star.parse(f)
if 'ParticleScore' in table.columns:
## columns of interest are 'MicrographName', 'CoordinateX', 'CoordinateY', and 'ParticleScore'
table = table[['MicrographName', 'CoordinateX', 'CoordinateY', 'ParticleScore']]
table.columns = ['image_name', 'x_coord', 'y_coord', 'score']
else:
## columns of interest are 'MicrographName', 'CoordinateX', and 'CoordinateY'
table = table[['MicrographName', 'CoordinateX', 'CoordinateY']]
table.columns = ['image_name', 'x_coord', 'y_coord']
## convert the coordinates to integers
table['x_coord'] = table['x_coord'].astype(float).astype(int)
table['y_coord'] = table['y_coord'].astype(float).astype(int)
## strip file extensions off the image names if present
table['image_name'] = table['image_name'].apply(strip_ext)
out = sys.stdout
if args.output is not None:
out = args.output
table.to_csv(out, sep='\t', index=False)
def main(args):
verbose = args.verbose
form = args._from
from_forms = [form for _ in range(len(args.files))]
# detect the input file formats
if form == 'auto':
try:
from_forms = [
file_utils.detect_format(path) for path in args.files
]
except file_utils.UnknownFormatError as e:
print('Error: unrecognized input coordinates file extension (' +
e.ext + ')',
file=sys.stderr)
sys.exit(1)
formats_detected = list(set(from_forms))
if verbose > 0:
print('# INPUT formats detected: ' + str(formats_detected),
file=sys.stderr)
# determine the output file format
output_path = args.output
output = None
to_form = args.to
if output_path is None:
output = sys.stdout
# if output is to stdout and form is not set
# then raise an error
if to_form == 'auto':
if len(formats_detected) == 1:
# write the same output format as input format
to_form = from_forms[0]
else:
print(
'Error: writing file to stdout and multiple input formats present with no output format (--to) set! Please tell me what format to write!'
)
sys.exit(1)
if to_form == 'box' or to_form == 'json':
print(
'Error: writing BOX or JSON output files requires a destination directory. Please set the --output parameter!'
)
sys.exit(1)
image_ext = args.image_ext
boxsize = args.boxsize
if to_form == 'auto':
# first check for directory
if output_path[-1] == '/':
# image-ext must be set for these file formats
if image_ext is None:
print(
'Error: writing BOX or JSON output files requires setting the image file extension!'
)
sys.exit(1)
# format is either json or box, check for boxsize to decide
if boxsize > 0:
# write boxes!
if verbose > 0:
print(
'# Detected output format is BOX, because OUTPUT is a directory and boxsize > 0.',
file=sys.stderr)
to_form = 'box'
else:
if verbose > 0:
print(
'# Detected output format is JSON, because OUTPUT is a directory and no boxsize set.',
file=sys.stderr)
to_form = 'json'
else:
try:
to_form = file_utils.detect_format(output_path)
except file_utils.UnkownFormatError as e:
print(
'Error: unrecognized output coordinates file extension (' +
e.ext + ')',
file=sys.stderr)
sys.exit(1)
if verbose > 0:
print('# OUTPUT format: ' + to_form)
suffix = args.suffix
t = args.threshold
down_scale = args.down_scale
up_scale = args.up_scale
scale = up_scale / down_scale
# special case when inputs and outputs are all star files
if len(formats_detected
) == 1 and formats_detected[0] == 'star' and to_form == 'star':
dfs = []
for path in args.files:
with open(path, 'r') as f:
table = star.parse(f)
dfs.append(table)
table = pd.concat(dfs, axis=0)
# convert score column to float and apply threshold
if star.SCORE_COLUMN_NAME in table.columns:
table = table.loc[table[star.SCORE_COLUMN_NAME] >= t]
# scale coordinates
if scale != 1:
x_coord = table[star.X_COLUMN_NAME].values
x_coord = np.round(scale * x_coord).astype(int)
table[star.X_COLUMN_NAME] = x_coord
y_coord = table[star.Y_COLUMN_NAME].values
y_coord = np.round(scale * y_coord).astype(int)
table[star.Y_COLUMN_NAME] = y_coord
# add metadata if specified
if args.voltage > 0:
table[star.VOLTAGE] = args.voltage
if args.detector_pixel_size > 0:
table[star.DETECTOR_PIXEL_SIZE] = args.detector_pixel_size
if args.magnification > 0:
table[star.MAGNIFICATION] = args.magnification
if args.amplitude_contrast > 0:
table[star.AMPLITUDE_CONTRAST] = args.amplitude_contrast
# write output file
if output is None:
with open(output_path, 'w') as f:
star.write(table, f)
else:
star.write(table, output)
else: # general case
# read the input files
dfs = []
for i in range(len(args.files)):
path = args.files[i]
coords = file_utils.read_coordinates(path, format=from_forms[i])
dfs.append(coords)
coords = pd.concat(dfs, axis=0)
# threshold particles by score (if there is a score)
if 'score' in coords.columns:
coords = coords.loc[coords['score'] >= t]
# scale coordinates
if scale != 1:
x_coord = coords['x_coord'].values
x_coord = np.round(scale * x_coord).astype(int)
coords['x_coord'] = x_coord
y_coord = coords['y_coord'].values
y_coord = np.round(scale * y_coord).astype(int)
coords['y_coord'] = y_coord
# add metadata if specified
if args.voltage > 0:
coords['voltage'] = args.voltage
if args.detector_pixel_size > 0:
coords['detector_pixel_size'] = args.detector_pixel_size
if args.magnification > 0:
coords['magnification'] = args.magnification
if args.amplitude_contrast > 0:
coords['amplitude_contrast'] = args.amplitude_contrast
# invert y-axis coordinates if specified
invert_y = args.invert_y
if invert_y:
if args.imagedir is None:
print(
'Error: --imagedir must specify the directory of images in order to mirror the y-axis coordinates',
file=sys.stderr)
sys.exit(1)
dfs = []
for image_name, group in coords.groupby('image_name'):
impath = os.path.join(args.imagedir,
image_name) + '.' + args.image_ext
# use glob incase image_ext is '*'
impath = glob.glob(impath)[0]
im = load_image(impath)
height = im.height
group = mirror_y_axis(group, height)
dfs.append(group)
coords = pd.concat(dfs, axis=0)
# output file format is decided and coordinates are processed, now write files
if output is None and to_form != 'box' and to_form != 'json':
output = open(output_path, 'w')
if to_form == 'box' or to_form == 'json':
output = output_path
file_utils.write_coordinates(output,
coords,
format=to_form,
boxsize=boxsize,
image_ext=image_ext,
suffix=suffix)