pyadata-cli 0.8.0__tar.gz → 0.10.0__tar.gz

{pyadata_cli-0.8.0 → pyadata_cli-0.10.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: pyadata-cli
-Version: 0.8.0
+Version: 0.10.0
 Summary: Streaming CLI for exploring and editing large AnnData .h5ad and .zarr stores
 Keywords: anndata,h5ad,zarr,bioinformatics,single-cell,cli
 Author: Aljes Binkevich
@@ -48,7 +48,7 @@ A command-line tool for exploring huge AnnData stores (`.h5ad` and `.zarr`) with
 - Auto-detects `.h5ad` files vs `.zarr` directories
 - Chunked processing for dense and sparse matrices (CSR/CSC)
 - Reads every AnnData on-disk layout, from 0.7.x through the current spec, and always writes the current one
-- Converts between HDF5 and Zarr (v2 and v3) in either direction with `adata convert`, and to and from 10x Genomics HDF5 matrices and 10x / STARsolo MTX folders
+- Converts between HDF5 and Zarr (v2 and v3) in either direction with `adata convert`, and to and from 10x Genomics HDF5 matrices and 10x / STARsolo MTX folders, and from CellBender output
 - Rich terminal output with progress indicators, kept on stderr so results pipe cleanly
 
 **Documentation: [cellgeni.github.io/adata-cli](https://cellgeni.github.io/adata-cli/)**
@@ -96,7 +96,7 @@ Run help at any level (e.g. `adata --help`, `adata export --help`).
 - `subset` – stream and write a filtered copy, selected by obs/var name lists (`--obs`/`--var`) or by expression (`--obs-query`/`--var-query`).
 - `split` – write one store per distinct value of an annotation column, with a CSV manifest.
 - `concat` – concatenate stores along the obs axis, with `--join inner|outer` and merge strategies for var and uns.
-- `convert` – change a store's format: h5ad ↔ Zarr v2/v3, 10x Genomics HDF5 (Cell Ranger's `*_feature_bc_matrix.h5`) and 10x / STARsolo MTX folders in and out, streaming, with the output written beside its destination and moved into place only once complete.
+- `convert` – change a store's format: h5ad ↔ Zarr v2/v3, 10x Genomics HDF5 (Cell Ranger's `*_feature_bc_matrix.h5`) and 10x / STARsolo MTX folders in and out, CellBender output in, streaming, with the output written beside its destination and moved into place only once complete.
 - `recast` – change a matrix's dtype, layout (CSR/CSC/dense) or density, streaming; refuses a lossy cast or a large size increase unless forced. Called `convert` until 0.7.0.
 - `export` – extract data from a store; subcommands: `dataframe` (any dataframe group to CSV), `array` (dense to `.npy`), `sparse` (CSR/CSC to `.mtx`), `dict` (JSON), `image` (PNG). Results go to stdout when no `--output` is given.
 - `import` – write new data into a store at any path; subcommands: `dataframe` (CSV), `array` (`.npy`), `sparse` (`.mtx`), `dict` (JSON), `image` (PNG/JPEG/TIFF).
@@ -141,6 +141,7 @@ adata convert data.zarr -o data.h5ad --compression gzip
 adata convert filtered_feature_bc_matrix.h5 -o counts.h5ad --feature-type "Gene Expression"
 adata convert counts.h5ad -o for_cellbender.h5 --layer counts
 adata convert Solo.out/Velocyto/raw -o velocyto.h5ad
+adata convert splitpipe_out -o parse.h5ad --unfiltered
 ```
 
 ## Documentation

{pyadata_cli-0.8.0 → pyadata_cli-0.10.0}/README.md

@@ -8,7 +8,7 @@ A command-line tool for exploring huge AnnData stores (`.h5ad` and `.zarr`) with
 - Auto-detects `.h5ad` files vs `.zarr` directories
 - Chunked processing for dense and sparse matrices (CSR/CSC)
 - Reads every AnnData on-disk layout, from 0.7.x through the current spec, and always writes the current one
-- Converts between HDF5 and Zarr (v2 and v3) in either direction with `adata convert`, and to and from 10x Genomics HDF5 matrices and 10x / STARsolo MTX folders
+- Converts between HDF5 and Zarr (v2 and v3) in either direction with `adata convert`, and to and from 10x Genomics HDF5 matrices and 10x / STARsolo MTX folders, and from CellBender output
 - Rich terminal output with progress indicators, kept on stderr so results pipe cleanly
 
 **Documentation: [cellgeni.github.io/adata-cli](https://cellgeni.github.io/adata-cli/)**
@@ -56,7 +56,7 @@ Run help at any level (e.g. `adata --help`, `adata export --help`).
 - `subset` – stream and write a filtered copy, selected by obs/var name lists (`--obs`/`--var`) or by expression (`--obs-query`/`--var-query`).
 - `split` – write one store per distinct value of an annotation column, with a CSV manifest.
 - `concat` – concatenate stores along the obs axis, with `--join inner|outer` and merge strategies for var and uns.
-- `convert` – change a store's format: h5ad ↔ Zarr v2/v3, 10x Genomics HDF5 (Cell Ranger's `*_feature_bc_matrix.h5`) and 10x / STARsolo MTX folders in and out, streaming, with the output written beside its destination and moved into place only once complete.
+- `convert` – change a store's format: h5ad ↔ Zarr v2/v3, 10x Genomics HDF5 (Cell Ranger's `*_feature_bc_matrix.h5`) and 10x / STARsolo MTX folders in and out, CellBender output in, streaming, with the output written beside its destination and moved into place only once complete.
 - `recast` – change a matrix's dtype, layout (CSR/CSC/dense) or density, streaming; refuses a lossy cast or a large size increase unless forced. Called `convert` until 0.7.0.
 - `export` – extract data from a store; subcommands: `dataframe` (any dataframe group to CSV), `array` (dense to `.npy`), `sparse` (CSR/CSC to `.mtx`), `dict` (JSON), `image` (PNG). Results go to stdout when no `--output` is given.
 - `import` – write new data into a store at any path; subcommands: `dataframe` (CSV), `array` (`.npy`), `sparse` (`.mtx`), `dict` (JSON), `image` (PNG/JPEG/TIFF).
@@ -101,6 +101,7 @@ adata convert data.zarr -o data.h5ad --compression gzip
 adata convert filtered_feature_bc_matrix.h5 -o counts.h5ad --feature-type "Gene Expression"
 adata convert counts.h5ad -o for_cellbender.h5 --layer counts
 adata convert Solo.out/Velocyto/raw -o velocyto.h5ad
+adata convert splitpipe_out -o parse.h5ad --unfiltered
 ```
 
 ## Documentation

{pyadata_cli-0.8.0 → pyadata_cli-0.10.0}/pyproject.toml

@@ -3,7 +3,7 @@
 # so the distribution is published as `pyadata-cli`. The import package
 # and the command are both still `adata`.
 name = "pyadata-cli"
-version = "0.8.0"
+version = "0.10.0"
 description = "Streaming CLI for exploring and editing large AnnData .h5ad and .zarr stores"
 readme = "README.md"
 requires-python = ">=3.12"

{pyadata_cli-0.8.0 → pyadata_cli-0.10.0}/src/adata/cli.py

@@ -522,6 +522,11 @@ _CONVERT_FLAGS = {
     "gene_ids_column": "--gene-ids-column",
     "gene_names_column": "--gene-names-column",
     "feature_types_column": "--feature-types-column",
+    "raw": "--raw",
+    "min_cell_probability": "--min-cell-probability",
+    "sample": "--sample",
+    "all_samples": "--all-samples",
+    "unfiltered": "--unfiltered",
 }
 
 #: Flags that only make sense for format conversion; with recast's flags,
@@ -606,9 +611,10 @@ def convert(
         "Cell Ranger 2 matrix)",
     ),
     var_names: str = typer.Option(
-        "gene_symbols",
+        "gene_ids",
         "--var-names",
-        help="10x input: name features by gene_symbols or gene_ids",
+        help="10x input: name features by gene_ids (default; unique) or "
+        "gene_symbols (scanpy's default)",
     ),
     make_unique: bool = typer.Option(
         False,
@@ -645,6 +651,36 @@ def convert(
         "--feature-types-column",
         help="10x output: var column holding feature types (default feature_types)",
     ),
+    raw: Optional[Path] = typer.Option(
+        None,
+        "--raw",
+        help="CellBender input: the raw Cell Ranger .h5 it ran on, added as "
+        "layers['cellranger']",
+        exists=True,
+        dir_okay=False,
+        readable=True,
+    ),
+    min_cell_probability: Optional[float] = typer.Option(
+        None,
+        "--min-cell-probability",
+        help="CellBender input: keep droplets with cell_probability at least "
+        "this (CellBender's own cutoff is 0.5)",
+    ),
+    sample: Optional[str] = typer.Option(
+        None,
+        "--sample",
+        help="Parse input: the sample folder to read (default: all-sample)",
+    ),
+    all_samples: bool = typer.Option(
+        False,
+        "--all-samples",
+        help="Parse input: write one output per sample, OUT.<sample>.h5ad",
+    ),
+    unfiltered: bool = typer.Option(
+        False,
+        "--unfiltered",
+        help="Parse input: read DGE_unfiltered (every barcode) not DGE_filtered",
+    ),
     # Deprecated: recast's flags, so `convert` keeps working as it did until
     # 1.0.0. Hidden from --help; the old matrix paths arrive in ctx.args.
     inplace: bool = typer.Option(False, "--inplace", hidden=True),
@@ -662,10 +698,14 @@ def convert(
     Genomics matrix (Cell Ranger's *_feature_bc_matrix.h5); --to 10x-mtx
     writes a Matrix Market folder. Between h5ad and zarr every element is
     copied, streamed, keeping the source's chunking and compression where the
-    target can express them. A 10x matrix is read as scanpy's read_10x_h5 or
-    read_10x_mtx (gex_only=False) reads it, keeping integer counts, and
-    written as Cell Ranger writes it. MTX folders from Cell Ranger and
-    STARsolo, velocyto's included, are read in two streaming passes.
+    target can express them. CellBender output keeps its latent variables, as
+    CellBender's own loader names them. A 10x matrix is read as scanpy's
+    read_10x_h5 or read_10x_mtx (gex_only=False) reads it, keeping integer
+    counts, and written as Cell Ranger writes it. MTX folders from Cell
+    Ranger and STARsolo, velocyto's included, and Parse split-pipe output
+    are read in two streaming passes. Features are named by gene id, unique
+    but in probe-level (Flex) matrices; --var-names gene_symbols names them
+    as scanpy does.
 
     Nothing is written until every check has passed, and the output is moved
     into place only once complete: a failed conversion leaves nothing
@@ -684,6 +724,10 @@ def convert(
         adata convert Solo.out/Gene/filtered -o counts.h5ad
         adata convert Solo.out/Velocyto/raw -o velocyto.h5ad
         adata convert counts.h5ad -o counts_mtx --to 10x-mtx --layer counts
+        adata convert cellbender_output.h5 -o cb.h5ad --raw raw_feature_bc_matrix.h5
+        adata convert cellbender_output.h5 -o cells.h5ad --min-cell-probability 0.5
+        adata convert splitpipe_out -o parse.h5ad
+        adata convert splitpipe_out -o parse.h5ad --all-samples --unfiltered
     """
     entries = list(ctx.args)
     recast_flags = _given(ctx, _RECAST_FLAGS)
@@ -767,6 +811,11 @@ def convert(
                 gene_ids_column=gene_ids_column,
                 gene_names_column=gene_names_column,
                 feature_types_column=feature_types_column,
+                raw=raw,
+                min_cell_probability=min_cell_probability,
+                sample=sample,
+                all_samples=all_samples,
+                unfiltered=unfiltered,
             ),
         )
     except Exception as e:

{pyadata_cli-0.8.0 → pyadata_cli-0.10.0}/src/adata/conversion/__init__.py

@@ -17,7 +17,7 @@ from typing import Dict, FrozenSet, List, Optional
 
 import h5py
 
-from adata.conversion import mtx, tenx
+from adata.conversion import cellbender, mtx, parse, tenx
 from adata.conversion.anndata_copy import AnnDataCopy
 from adata.conversion.base import ConversionPlan, Converter, Format, Options
 from adata.storage import has_valid_anndata_root_attrs, is_zarr_path
@@ -66,6 +66,15 @@ FORMATS: Dict[str, Format] = {
         anndata=True,
         sniff=is_zarr_path,
     ),
+    # Before 10x-h5: a CellBender file is a 10x matrix too, and the first
+    # sniffer to match wins. `--from 10x-h5` still reads one as plain 10x.
+    "cellbender": Format(
+        name="cellbender",
+        description="CellBender remove-background output (0.2 and later)",
+        extensions=(".h5",),
+        sniff=cellbender.sniff,
+        importer=cellbender.CellbenderImport(),
+    ),
     "10x-h5": Format(
         name="10x-h5",
         description="10x Genomics feature-barcode matrix (Cell Ranger v2 or v3)",
@@ -83,6 +92,14 @@ FORMATS: Dict[str, Format] = {
         importer=mtx.MtxImport(),
         exporter=mtx.MtxExport(),
     ),
+    # A folder too; read only.
+    "parse": Format(
+        name="parse",
+        description="Parse Biosciences split-pipe output (a run, sample or DGE folder)",
+        extensions=(),
+        sniff=parse.sniff,
+        importer=parse.ParseImport(),
+    ),
 }
 
 _ANNDATA_COPY = AnnDataCopy()
@@ -136,10 +153,21 @@ def output_format(path: Path, requested: Optional[str] = None) -> str:
     path = Path(path)
     if requested is not None and requested not in FORMATS:
         raise ValueError(f"Unknown format {requested!r}; use one of: {_names()}.")
+    if requested is not None and not (
+        FORMATS[requested].anndata or FORMATS[requested].exporter is not None
+    ):
+        raise ValueError(f"{requested} can be read but not written.")
 
     suffix = path.suffix.lower()
+    # Only formats that can be written: `.h5` names CellBender output too,
+    # but an `.h5` output is a 10x matrix.
     by_extension = next(
-        (fmt.name for fmt in FORMATS.values() if suffix in fmt.extensions), None
+        (
+            fmt.name
+            for fmt in FORMATS.values()
+            if suffix in fmt.extensions and (fmt.anndata or fmt.exporter is not None)
+        ),
+        None,
     )
     if requested is None:
         if by_extension is None:

{pyadata_cli-0.8.0 → pyadata_cli-0.10.0}/src/adata/conversion/base.py

@@ -24,7 +24,7 @@ class Options:
 
     # Reading a 10x matrix.
     genome: Optional[str] = None
-    var_names: str = "gene_symbols"
+    var_names: str = "gene_ids"
     make_unique: bool = False
     feature_type: Optional[str] = None
     split_feature_types: bool = False
@@ -35,6 +35,15 @@ class Options:
     gene_names_column: Optional[str] = None
     feature_types_column: Optional[str] = None
 
+    # Reading CellBender output.
+    raw: Optional[Path] = None
+    min_cell_probability: Optional[float] = None
+
+    # Reading Parse split-pipe output.
+    sample: Optional[str] = None
+    all_samples: bool = False
+    unfiltered: bool = False
+
 
 @dataclass
 class ConversionPlan: