Ejemplo n.º 1
0
def main(args):
    log = logging.getLogger('root')
    hdlr = logging.StreamHandler(sys.stdout)
    log.addHandler(hdlr)
    log.setLevel(logging.getLevelName(args.loglevel.upper()))

    if args.input.endswith(".cs"):
        log.debug("Detected CryoSPARC 2+ .cs file")
        cs = np.load(args.input)
        try:
            df = metadata.parse_cryosparc_2_cs(cs,
                                               passthrough=args.passthrough,
                                               minphic=args.minphic)
        except (KeyError, ValueError) as e:
            log.error(e.message)
            log.error(
                "A passthrough file may be required (check inside the cryoSPARC 2+ job directory)"
            )
            log.debug(e, exc_info=True)
            return 1
    else:
        log.debug("Detected CryoSPARC 0.6.5 .csv file")
        meta = metadata.parse_cryosparc_065_csv(
            args.input)  # Read cryosparc metadata file.
        df = metadata.cryosparc_065_csv2star(meta, args.minphic)

    if args.cls is not None:
        df = star.select_classes(df, args.cls)

    if args.copy_micrograph_coordinates is not None:
        coord_star = pd.concat(
            (star.parse_star(inp, keep_index=False)
             for inp in glob(args.copy_micrograph_coordinates)),
            join="inner")
        star.augment_star_ucsf(coord_star)
        star.augment_star_ucsf(df)
        key = star.merge_key(df, coord_star)
        log.debug("Coordinates merge key: %s" % key)
        if args.cached or key == star.Relion.IMAGE_NAME:
            fields = star.Relion.MICROGRAPH_COORDS
        else:
            fields = star.Relion.MICROGRAPH_COORDS + [
                star.UCSF.IMAGE_INDEX, star.UCSF.IMAGE_PATH
            ]
        df = star.smart_merge(df, coord_star, fields=fields, key=key)
        star.simplify_star_ucsf(df)

    if args.micrograph_path is not None:
        df = star.replace_micrograph_path(df,
                                          args.micrograph_path,
                                          inplace=True)

    if args.transform is not None:
        r = np.array(json.loads(args.transform))
        df = star.transform_star(df, r, inplace=True)

    # Write Relion .star file with correct headers.
    star.write_star(args.output, df, reindex=True)
    log.info("Output fields: %s" % ", ".join(df.columns))
    return 0
Ejemplo n.º 2
0
def main(args):
    log = logging.getLogger('root')
    hdlr = logging.StreamHandler(sys.stdout)
    log.addHandler(hdlr)
    log.setLevel(logging.getLevelName(args.loglevel.upper()))

    if args.input[0].endswith(".cs"):
        log.debug("Detected CryoSPARC 2+ .cs file")
        cs = np.load(args.input[0])
        try:
            df = metadata.parse_cryosparc_2_cs(cs, passthroughs=args.input[1:], minphic=args.minphic,
                                               boxsize=args.boxsize, swapxy=args.swapxy,
                                               invertx=args.invertx, inverty=args.inverty)
        except (KeyError, ValueError) as e:
            log.error(e, exc_info=True)
            log.error("Required fields could not be mapped. Are you using the right input file(s)?")
            return 1
    else:
        log.debug("Detected CryoSPARC 0.6.5 .csv file")
        if len(args.input) > 1:
            log.error("Only one file at a time supported for CryoSPARC 0.6.5 .csv format")
            return 1
        meta = metadata.parse_cryosparc_065_csv(args.input[0])  # Read cryosparc metadata file.
        df = metadata.cryosparc_065_csv2star(meta, args.minphic)

    if args.cls is not None:
        df = star.select_classes(df, args.cls)

    if args.copy_micrograph_coordinates is not None:
        df = star.augment_star_ucsf(df, inplace=True)
        coord_star = pd.concat(
            (star.parse_star(inp, keep_index=False, augment=True) for inp in
             glob(args.copy_micrograph_coordinates)), join="inner")
        key = star.merge_key(df, coord_star)
        log.debug("Coordinates merge key: %s" % key)
        if args.cached or key == star.Relion.IMAGE_NAME:
            fields = star.Relion.MICROGRAPH_COORDS
        else:
            fields = star.Relion.MICROGRAPH_COORDS + [star.UCSF.IMAGE_INDEX, star.UCSF.IMAGE_PATH]
        df = star.smart_merge(df, coord_star, fields=fields, key=key)
        star.simplify_star_ucsf(df)

    if args.micrograph_path is not None:
        df = star.replace_micrograph_path(df, args.micrograph_path, inplace=True)

    if args.transform is not None:
        r = np.array(json.loads(args.transform))
        df = star.transform_star(df, r, inplace=True)

    df = star.check_defaults(df, inplace=True)

    if args.relion2:
        df = star.remove_new_relion31(df, inplace=True)
        star.write_star(args.output, df, resort_records=True, optics=False)
    else:
        df = star.remove_deprecated_relion2(df, inplace=True)
        star.write_star(args.output, df, resort_records=True, optics=True)

    log.info("Output fields: %s" % ", ".join(df.columns))
    return 0
Ejemplo n.º 3
0
def main(args):
    if args.input.endswith(".cs"):
        cs = np.load(args.input)
        if args.passthrough is None:
            if u"blob/path" not in cs.dtype.names:
                print(
                    "A passthrough file is required (found inside the cryoSPARC 2+ job directory)"
                )
                return 1
        df = metadata.parse_cryosparc_2_cs(cs,
                                           passthrough=args.passthrough,
                                           minphic=args.minphic)
    else:
        meta = metadata.parse_cryosparc_065_csv(
            args.input)  # Read cryosparc metadata file.
        df = metadata.cryosparc_065_csv2star(meta, args.minphic)

    if args.cls is not None:
        df = star.select_classes(df, args.cls)

    if args.copy_micrograph_coordinates is not None:
        coord_star = pd.concat(
            (star.parse_star(inp, keep_index=False)
             for inp in glob(args.copy_micrograph_coordinates)),
            join="inner")
        df = star.smart_merge(df,
                              coord_star,
                              fields=star.Relion.MICROGRAPH_COORDS)

    if args.transform is not None:
        r = np.array(json.loads(args.transform))
        df = star.transform_star(df, r, inplace=True)

    # Write Relion .star file with correct headers.
    star.write_star(args.output, df, reindex=True)
    return 0
Ejemplo n.º 4
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
Ejemplo n.º 5
0
def main(args):
    log = logging.getLogger('root')
    hdlr = logging.StreamHandler(sys.stdout)
    log.addHandler(hdlr)
    log.setLevel(logging.getLevelName(args.loglevel.upper()))

    dfs = [metadata.parse_fx_par(fn) for fn in args.input]
    n = dfs[0].shape[0]
    if not np.all(np.array([df.shape[0] for df in dfs]) == n):
        log.error("Input files are not aligned!")
        return 1
    df = pd.concat(dfs, axis=0, ignore_index=True)
    df["CLASS"] = np.repeat(np.arange(1, len(dfs) + 1), n)

    if args.min_occ:
        df = df[df["OCC"] >= args.min_occ]

    df = df.sort_values(by="OCC")
    df = df.drop_duplicates("C", keep="last")
    df = df.sort_values(by="C")
    df.reset_index(inplace=True)

    if args.min_score is not None:
        if args.min_score < 1:
            args.min_score = np.percentile(df["SCORE"],
                                           (1 - args.min_score) * 100)
        df = df.loc[df["SCORE"] >= args.min_score]

    if args.merge is not None:
        dfo = star.parse_star(args.merge)
        args.apix = star.calculate_apix(dfo)
        args.cs = dfo.iloc[0][star.Relion.CS]
        args.ac = dfo.iloc[0][star.Relion.AC]
        args.voltage = dfo.iloc[0][star.Relion.VOLTAGE]
        df = metadata.par2star(df,
                               data_path=args.stack,
                               apix=args.apix,
                               cs=args.cs,
                               ac=args.ac,
                               kv=args.voltage,
                               invert_eulers=args.invert_eulers)
        if args.stack is None:
            df[star.UCSF.IMAGE_INDEX] = dfo[star.UCSF.IMAGE_INDEX]
            df[star.UCSF.IMAGE_PATH] = dfo[star.UCSF.IMAGE_PATH]
        key = [star.UCSF.IMAGE_INDEX, star.UCSF.IMAGE_PATH]
        fields = star.Relion.MICROGRAPH_COORDS + [
            star.UCSF.IMAGE_ORIGINAL_INDEX, star.UCSF.IMAGE_ORIGINAL_PATH
        ] + [star.Relion.OPTICSGROUP
             ] + star.Relion.OPTICSGROUPTABLE + [star.Relion.RANDOMSUBSET]
        df = star.smart_merge(df, dfo, fields=fields, key=key)
        if args.revert_original:
            df = star.revert_original(df, inplace=True)
    else:
        df = metadata.par2star(df,
                               data_path=args.stack,
                               apix=args.apix,
                               cs=args.cs,
                               ac=args.ac,
                               kv=args.voltage,
                               invert_eulers=args.invert_eulers)

    if args.cls is not None:
        df = star.select_classes(df, args.cls)

    df = star.check_defaults(df, inplace=True)
    df = star.compatible(df, relion2=args.relion2, inplace=True)
    star.write_star(args.output, df, optics=(not args.relion2))
    return 0
Ejemplo n.º 6
0
Archivo: star.py Proyecto: dzyla/pyem
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 c.sort_index().iteritems()
            ]))
        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
        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.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)

    if args.transform is not None:
        if args.transform.count(",") == 2:
            r = star.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.Relion.ANGLEROT] = -df[star.Relion.ANGLEROT]
        df[star.Relion.ANGLETILT] = 180 - df[star.Relion.ANGLETILT]

    if args.copy_paths is not None:
        path_star = star.parse_star(args.copy_paths)
        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)

    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)

    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, inplace=True)
        star.scale_magnification(df, args.scale, 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_magnfication, 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:
        gb = df.groupby(star.Relion.MICROGRAPH_NAME)
        mu = gb.mean()
        df = mu[[
            c for c in star.Relion.CTF_PARAMS + star.Relion.MICROSCOPE_PARAMS +
            [star.Relion.MICROGRAPH_NAME] if c in mu
        ]].reset_index()

    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],
                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(",")
        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)

    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:
        star.write_star(args.auxout, dfaux, simplify=args.augment)

    if args.output is not None:
        star.write_star(args.output, df, simplify=args.augment)
    return 0
Ejemplo n.º 7
0
def main(args):
    meta = parse_metadata(args.input)  # Read cryosparc metadata file.
    meta["data_input_idx"] = [
        "%.6d" % (i + 1) for i in meta["data_input_idx"]
    ]  # Reformat particle idx for Relion.

    if "data_input_relpath" not in meta.columns:
        if args.data_path is None:
            print(
                "Data path missing, use --data-path to specify particle stack path"
            )
            return 1
        meta["data_input_relpath"] = args.data_path

    meta["data_input_relpath"] = meta["data_input_idx"].str.cat(
        meta["data_input_relpath"], sep="@")  # Construct rlnImageName field.
    # Take care of trivial mappings.
    rlnheaders = [
        general[h] for h in meta.columns
        if h in general and general[h] is not None
    ]
    df = meta[[
        h for h in meta.columns if h in general and general[h] is not None
    ]].copy()
    df.columns = rlnheaders

    if "rlnRandomSubset" in df.columns:
        df["rlnRandomSubset"] = df["rlnRandomSubset"].apply(
            lambda x: ord(x) - 64)

    if "rlnPhaseShift" in df.columns:
        df["rlnPhaseShift"] = np.rad2deg(df["rlnPhaseShift"])

    # Class assignments and other model parameters.
    phic = meta[[h for h in meta.columns if "phiC" in h
                 ]]  # Posterior probability over class assignments.
    if len(phic.columns) > 0:  # Check class assignments exist in input.
        # phic.columns = [int(h[21]) for h in meta.columns if "phiC" in h]
        phic.columns = range(len(phic.columns))
        cls = phic.idxmax(axis=1)
        for p in model:
            if model[p] is not None:
                pspec = p.split("model")[1]
                param = meta[[h for h in meta.columns if pspec in h]]
                if len(param.columns) > 0:
                    param.columns = phic.columns
                    df[model[p]] = param.lookup(param.index, cls)
        df["rlnClassNumber"] = cls + 1  # Add one for Relion indexing.
    else:
        for p in model:
            if model[p] is not None and p in meta.columns:
                df[model[p]] = meta[p]
        df["rlnClassNumber"] = 1

    if args.cls is not None:
        df = star.select_classes(df, args.cls)

    # Convert axis-angle representation to Euler angles (degrees).
    if df.columns.intersection(star.Relion.ANGLES).size == len(
            star.Relion.ANGLES):
        df[star.Relion.ANGLES] = np.rad2deg(df[star.Relion.ANGLES].apply(
            lambda x: rot2euler(expmap(x)), axis=1, raw=True, broadcast=True))

    if args.minphic is not None:
        mask = np.all(phic < args.minphic, axis=1)
        if args.keep_bad:
            df.loc[mask, "rlnClassNumber"] = 0
        else:
            df.drop(df[mask].index, inplace=True)

    if args.copy_micrograph_coordinates is not None:
        coord_star = pd.concat(
            (star.parse_star(inp, keep_index=False)
             for inp in glob(args.copy_micrograph_coordinates)),
            join="inner")
        df = star.smart_merge(df,
                              coord_star,
                              fields=star.Relion.MICROGRAPH_COORDS)

    if args.transform is not None:
        r = np.array(json.loads(args.transform))
        df = star.transform_star(df, r, inplace=True)

    # Write Relion .star file with correct headers.
    star.write_star(args.output, df, reindex=True)
    return 0