10x H5 Format Error about cellbender HOT 23 CLOSED

tables.copy_file(orig_h5, fixed_h5)
with tables.open_file(fixed_h5, "r+") as f:
    n = f.get_node("/matrix/features")
    n_genes = f.get_node("/matrix/shape")[0]
    if "genome" not in n:
        f.create_array(n, "genome", np.repeat("GRCh38", n_genes))

adata = readCellbenderH5('Day9_10x_cellbender_filtered.h5')

---------------------------------------------------------------------------
KeyError                                  Traceback (most recent call last)
<ipython-input-11-248abec2df25> in <module>
----> 1 adata = readCellbenderH5('Day9_10x_cellbender_filtered.h5')

<ipython-input-4-9b15cfa9372a> in readCellbenderH5(filename)
      6     mat=f['matrix']
      7     cols=['latent_cell_probability','latent_RT_efficiency',"latent_dirichlet_precision"]
----> 8     obsdict={x:mat[x] for x in cols}
      9     ad=sc.AnnData(X=scipy.sparse.csr_matrix((mat['data'][:], 
     10                                           mat['indices'][:],

<ipython-input-4-9b15cfa9372a> in <dictcomp>(.0)
      6     mat=f['matrix']
      7     cols=['latent_cell_probability','latent_RT_efficiency',"latent_dirichlet_precision"]
----> 8     obsdict={x:mat[x] for x in cols}
      9     ad=sc.AnnData(X=scipy.sparse.csr_matrix((mat['data'][:], 
     10                                           mat['indices'][:],

h5py/_objects.pyx in h5py._objects.with_phil.wrapper()

h5py/_objects.pyx in h5py._objects.with_phil.wrapper()

~/anaconda3/envs/scanpy/lib/python3.8/site-packages/h5py/_hl/group.py in __getitem__(self, name)
    262                 raise ValueError("Invalid HDF5 object reference")
    263         else:
--> 264             oid = h5o.open(self.id, self._e(name), lapl=self._lapl)
    265 
    266         otype = h5i.get_type(oid)

h5py/_objects.pyx in h5py._objects.with_phil.wrapper()

h5py/_objects.pyx in h5py._objects.with_phil.wrapper()

h5py/h5o.pyx in h5py.h5o.open()

KeyError: "Unable to open object (object 'latent_dirichlet_precision' doesn't exist)"

"""Functions for downstream work with outputs of remove-background."""

import tables
import numpy as np
import scipy.sparse as sp
from typing import Dict


def dict_from_h5(file: str) -> Dict[str, np.ndarray]:
    """Read in everything from an h5 file and put into a dictionary."""
    d = {}
    with tables.open_file(file) as f:
        # read in everything
        for array in f.walk_nodes("/", "Array"):
            d[array.name] = array.read()
    return d


def anndata_from_h5(file: str,
                    analyzed_barcodes_only: bool = True) -> 'anndata.AnnData':
    """Load an output h5 file into an AnnData object for downstream work.

    Args:
        file: The h5 file
        analyzed_barcodes_only: False to load all barcodes, so that the size of
            the AnnData object will match the size of the input raw count matrix.
            True to load a limited set of barcodes: only those analyzed by the
            algorithm. This allows relevant latent variables to be loaded
            properly into adata.obs and adata.obsm, rather than adata.uns.

    Returns:
        adata: The anndata object, populated with inferred latent variables
            and metadata.

    """

    try:
        import anndata
    except ImportError:
        raise ImportError('The anndata package must be installed to use the '
                          'function anndata_from_h5()')

    d = dict_from_h5(file)
    X = sp.csc_matrix((d.pop('data'), d.pop('indices'), d.pop('indptr')),
                      shape=d.pop('shape')).transpose().tocsr()

    if analyzed_barcodes_only:
        if 'barcodes_analyzed_inds' in d.keys():
            X = X[d['barcodes_analyzed_inds'], :]
            d['barcodes'] = d['barcodes'][d['barcodes_analyzed_inds']]
        elif 'barcode_indices_for_latents' in d.keys():
            X = X[d['barcode_indices_for_latents'], :]
            d['barcodes'] = d['barcodes'][d['barcode_indices_for_latents']]
        else:
            print('Warning: analyzed_barcodes_only=True, but the key '
                  '"barcodes_analyzed_inds" or "barcode_indices_for_latents" '
                  'is missing from the h5 file. '
                  'Will output all barcodes, and proceed as if '
                  'analyzed_barcodes_only=False')

    # Construct the count matrix.
    adata = anndata.AnnData(X=X,
                            obs={'barcode': d.pop('barcodes').astype(str)},
                            var={'gene_name': (d.pop('gene_names') if 'gene_names' in d.keys()
                                               else d.pop('name')).astype(str)})
    adata.obs.set_index('barcode', inplace=True)
    adata.var.set_index('gene_name', inplace=True)

    # Add other information to the adata object in the appropriate slot.
    for key, value in d.items():
        try:
            value = np.asarray(value)
            if len(value.shape) == 0:
                adata.uns[key] = value
            elif value.shape[0] == X.shape[0]:
                if (len(value.shape) < 2) or (value.shape[1] < 2):
                    adata.obs[key] = value
                else:
                    adata.obsm[key] = value
            elif value.shape[0] == X.shape[1]:
                if value.dtype.name.startswith('bytes'):
                    adata.var[key] = value.astype(str)
                else:
                    adata.var[key] = value
            else:
                adata.uns[key] = value
        except Exception:
            print('Unable to load data into AnnData: ', key, value, type(value))

    if analyzed_barcodes_only:
        for col in adata.obs.columns[adata.obs.columns.str.startswith('barcodes_analyzed')
                                     | adata.obs.columns.str.startswith('barcode_indices')]:
            try:
                del adata.obs[col]
            except Exception:
                pass

    return adata


def load_anndata_from_input_and_output(input_file: str,
                                       output_file: str,
                                       analyzed_barcodes_only: bool = True,
                                       input_layer_key: str = 'cellranger') -> 'anndata.AnnData':
    """Load remove-background output count matrix into an anndata object,
    together with remove-background metadata and the raw input counts.

    Args:
        input_file: Raw h5 file used as input for remove-background.
        output_file: Output h5 file created by remove-background (can be
            filtered or not).
        analyzed_barcodes_only: Argument passed to anndata_from_h5().
            False to load all barcodes, so that the size of
            the AnnData object will match the size of the input raw count matrix.
            True to load a limited set of barcodes: only those analyzed by the
            algorithm. This allows relevant latent variables to be loaded
            properly into adata.obs and adata.obsm, rather than adata.uns.
        input_layer_key: Key of the anndata.layer that is created for the raw
            input count matrix.

    Return:
        adata_out: AnnData object with counts before and after remove-background,
            as well as inferred latent variables from remove-background.

    """

    # Load input data.
    adata_raw = anndata_from_h5(input_file, analyzed_barcodes_only=False)

    # Load remove-background output data.
    adata_out = anndata_from_h5(output_file, analyzed_barcodes_only=analyzed_barcodes_only)

    # Subset the raw dataset to the relevant barcodes.
    adata_raw = adata_raw[adata_out.obs.index]

    # Put count matrices into 'layers' in anndata for clarity.
    adata_out.layers[input_layer_key] = adata_raw.X.copy()
    adata_out.layers['cellbender'] = adata_out.X.copy()

    # Pre-compute a bit of metadata.
    adata_out.var['n_cellranger'] = np.array(adata_out.layers['cellranger'].sum(axis=0)).squeeze()
    adata_out.var['n_cellbender'] = np.array(adata_out.layers['cellbender'].sum(axis=0)).squeeze()

    return adata_out