sclab 0.2.4__py3-none-any.whl → 0.3.0__py3-none-any.whl

sclab/tools/cellflow/utils/smoothen.py

@@ -0,0 +1,124 @@
+import logging
+from typing import Callable
+
+import numpy as np
+from numpy import bool_, floating, integer
+from numpy.typing import NDArray
+from tqdm.auto import tqdm
+
+logger = logging.getLogger(__name__)
+PIX2 = 2 * np.pi
+
+
+def count_empty_intervals(t: NDArray[floating], t_grid: NDArray[floating]) -> int:
+    n_data_in_intervals = count_data_in_intervals(t, t_grid)
+    empty_intervals_count = np.sum(n_data_in_intervals == 0)
+    return empty_intervals_count
+
+
+def count_data_in_intervals(
+    t: NDArray[floating], t_grid: NDArray[floating]
+) -> NDArray[integer]:
+    t = t.reshape(-1, 1)
+    return np.logical_and(t_grid[:-1] <= t, t <= t_grid[1:]).sum(axis=0)
+
+
+def choose_grid_size(t: NDArray[floating], t_range: tuple[float, float]) -> int:
+    grid_size = 2**10
+    for _ in range(10):
+        t_grid: NDArray[floating] = np.linspace(*t_range, grid_size + 1)
+        empty_intervals = count_empty_intervals(t, t_grid)
+        if empty_intervals == 0:
+            break
+        grid_size //= 2
+    else:
+        raise ValueError("Could not find a suitable grid size")
+
+    return grid_size
+
+
+def smoothen_data(
+    t: NDArray[floating],
+    X: NDArray[floating],
+    t_range: tuple[float, float] | None = None,
+    t_grid: NDArray[floating] | None = None,
+    fn: Callable[[NDArray[floating]], NDArray[floating]] = np.average,
+    window_width: float | None = None,
+    weights: NDArray[floating] | None = None,
+    zero_weight: float = 1,
+    periodic: bool = False,
+    quiet: bool = False,
+    progress: bool = False,
+) -> NDArray[floating]:
+    if t_grid is None:
+        # no grid provided. We will have one output point for each input point
+        t_grid = t
+        is_grid = False
+    else:
+        # grid is provided
+        is_grid = True
+        empty_intervals = count_empty_intervals(t, t_grid)
+        if empty_intervals > 0 and not quiet:
+            logger.warning(f"Provided grid has {empty_intervals} empty intervals")
+
+    if t_range is not None:
+        # we used a specific t values range
+        tmin, tmax = t_range
+    else:
+        tmin, tmax = t_grid.min(), t_grid.max()
+
+    # full time window size
+    tspan = tmax - tmin
+
+    if window_width is None and not is_grid:
+        window_width = tspan * 0.05
+    elif window_width is None and is_grid:
+        window_width = tspan / (t_grid.size - 1) * 2
+
+    # initialize the output matrix with NaNs
+    X_smooth: NDArray[floating] = np.full((t_grid.size,) + X.shape[1:], np.nan)
+
+    generator = enumerate(t_grid)
+    if progress:
+        generator = tqdm(
+            generator,
+            total=t_grid.size,
+            bar_format="{desc} {percentage:3.0f}%|{bar}|",
+            desc="Smoothing data",
+        )
+
+    X = X.astype(float)
+    eps = np.finfo(float).eps
+    for i, m in generator:
+        low = m - window_width / 2
+        hig = m + window_width / 2
+
+        mask: NDArray[bool_] = (t >= low) & (t <= hig)
+        if periodic:
+            # include points beyond the periodic boundaries
+            mask = (
+                mask
+                | (t >= low + tspan) & (t <= hig + tspan)
+                | (t >= low - tspan) & (t <= hig - tspan)
+            )
+
+        if mask.sum() == 0:
+            continue
+
+        x = X[mask] + eps
+        if fn == np.average and weights is not None:
+            w = weights[mask]
+            X_smooth[i] = np.average(x, axis=0, weights=w)
+
+        elif fn == np.average and zero_weight == 1:
+            X_smooth[i] = np.mean(x, axis=0)
+
+        elif fn == np.average and zero_weight != 1:
+            w = np.ones_like(x)
+            w[x == eps] = zero_weight + eps
+            X_smooth[i] = fn(x, axis=0, weights=w)
+
+        else:
+            X_smooth[i] = fn(x, axis=0)
+
+    return X_smooth - eps

sclab/tools/cellflow/utils/times.py

@@ -0,0 +1,55 @@
+import itertools
+
+import numpy as np
+from numpy import floating
+from numpy.typing import NDArray
+
+
+def guess_trange(
+    times: NDArray[floating], verbose: bool = False
+) -> tuple[float, float]:
+    tmin, tmax = times.min(), times.max()
+    tspan = tmax - tmin
+
+    scale = 10.0 ** np.ceil(np.log10(tspan)) / 100
+    tspan = np.ceil(tspan / scale) * scale
+
+    scale = 10.0 ** np.ceil(np.log10(tspan)) / 100
+    g_tmin = np.floor(tmin / scale) * scale
+    g_tmax = np.ceil(tmax / scale) * scale
+
+    g_tmin = 0.0 if g_tmin == -0.0 else g_tmin
+    g_tmax = 0.0 if g_tmax == -0.0 else g_tmax
+
+    if verbose:
+        print(
+            f"tspan: {tspan:10.4f}    min-max: {tmin:10.4f} - {tmax:10.4f} | {g_tmin:>8} - {g_tmax:>8}"
+        )
+
+    return g_tmin, g_tmax
+
+
+def test_guess_trange(N: int = 1000, verbose: bool = False) -> None:
+    def _test1(trange: tuple[float, float]) -> bool:
+        tmin, tmax = trange
+        tspan = tmax - tmin
+        g_tmin, g_tmax = guess_trange(np.random.uniform(*trange, N))
+        err_min = np.abs(g_tmin - tmin) / tspan
+        err_max = np.abs(g_tmax - tmax) / tspan
+        return err_min <= 0.01 and err_max <= 0.01
+
+    scales1 = [0.001, 0.01, 0.1, 1, 10, 100, 1000]
+    scales2 = [1, 2, 3, 5, 7]
+    for s1, s2 in itertools.product(scales1, scales2):
+        scale = s1 * s2
+        for lw, hg in [(-2, -1), (-1 / 2, 1 / 2), (1, 2)]:
+            trange = lw * scale, hg * scale
+            acc1 = np.mean([_test1(trange) for _ in range(500)])
+            if verbose:
+                print(
+                    f"scale: {scale: 9.3f} | lw-hg: {lw: 5.1f} - {hg: 5.1f} | {acc1: 8.2%}"
+                )
+            else:
+                assert acc1 > 0.95, (
+                    f"scale: {scale: 9.3f} | lw-hg: {lw: 5.1f} - {hg: 5.1f} | {acc1: 8.2%}"
+                )

sclab/tools/differential_expression/__init__.py

@@ -0,0 +1,5 @@
+from ._pseudobulk_edger import pseudobulk_edger
+
+__all__ = [
+    "pseudobulk_edger",
+]

sclab/tools/differential_expression/_pseudobulk_edger.py

@@ -0,0 +1,304 @@
+import pandas as pd
+from anndata import AnnData
+
+from ._pseudobulk_helpers import aggregate_and_filter
+
+
+def pseudobulk_edger(
+    adata_: AnnData,
+    group_key: str,
+    condition_group: str | list[str] | None = None,
+    reference_group: str | None = None,
+    cell_identity_key: str | None = None,
+    batch_key: str | None = None,
+    layer: str | None = None,
+    replicas_per_group: int = 10,
+    min_cells_per_group: int = 30,
+    bootstrap_sampling: bool = True,
+    use_cells: dict[str, list[str]] | None = None,
+    aggregate: bool = True,
+    verbosity: int = 0,
+) -> dict[str, pd.DataFrame]:
+    """
+    Fits a model using edgeR and computes top tags for a given condition vs
+    reference group.
+
+    Parameters
+    ----------
+    adata_ : AnnData
+        Annotated data matrix.
+    group_key : str
+        Key in AnnData object to use to group cells.
+    condition_group : str | list[str] | None, optional
+        Condition group to compare to reference group. If None, each group will be
+        contrasted to the corresponding reference group.
+    reference_group : str | None, optional
+        Reference group to compare condition group(s) to. If None, the condition group
+        is compared to the rest of the cells.
+    cell_identity_key : str | None, optional
+        If provided, separate contrasts will be computed for each identity. Defaults to None.
+    layer : str | None, optional
+        Layer in AnnData object to use. EdgeR requires raw counts. Defaults to None.
+    replicas_per_group : int, optional
+        Number of replicas to create for each group. Defaults to 10.
+    min_cells_per_group : int, optional
+        Minimum number of cells required for a group to be included. Defaults to 30.
+    bootstrap_sampling : bool, optional
+        Whether to use bootstrap sampling to create replicas. Defaults to True.
+    use_cells : dict[str, list[str]] | None, optional
+        If not None, only use the specified cells. Defaults to None. Dictionary key
+        is a categorical variable in the obs dataframe and the dictionary value is a
+        list of categories to include.
+    aggregate : bool, optional
+        Whether to aggregate cells before fitting the model. EdgeR requires a small
+        number of samples, so if adata_ is a single-cell experiment, the cells should
+        be aggregated. Defaults to True.
+    verbosity : int, optional
+        Verbosity level. Defaults to 0.
+
+    Returns
+    -------
+    dict[str, pd.DataFrame]
+        Dictionary of dataframes, one for each contrast, with the following columns:
+
+        * gene_ids : str
+            Gene IDs.
+        * logFC : float
+            Log2 fold change.
+        * logCPM : float
+            Log2 CPM.
+        * F: float
+            F-statistic.
+        * PValue : float
+            p-value.
+        * FDR : float
+            False discovery rate.
+        * pct_expr_cnd : float
+            Percentage of cells in condition group expressing the gene.
+        * pct_expr_ref : float
+            Percentage of cells in reference group expressing the gene.
+    """
+    _try_imports()
+    import anndata2ri  # noqa: F401
+    import rpy2.robjects as robjects
+    from rpy2.rinterface_lib.embedded import RRuntimeError  # noqa: F401
+    from rpy2.robjects import pandas2ri  # noqa: F401
+    from rpy2.robjects.conversion import localconverter  # noqa: F401
+
+    R = robjects.r
+
+    if aggregate:
+        aggr_adata = aggregate_and_filter(
+            adata_,
+            group_key,
+            cell_identity_key,
+            layer,
+            replicas_per_group,
+            min_cells_per_group,
+            bootstrap_sampling,
+            use_cells,
+        )
+    else:
+        aggr_adata = adata_.copy()
+
+    with localconverter(anndata2ri.converter):
+        R.assign("aggr_adata", aggr_adata)
+
+    # defines the R function for fitting the model with edgeR
+    R(_fit_model_r_script)
+
+    if condition_group is None:
+        condition_group_list = aggr_adata.obs[group_key].unique()
+    elif isinstance(condition_group, str):
+        condition_group_list = [condition_group]
+    else:
+        condition_group_list = condition_group
+
+    if cell_identity_key is not None:
+        cids = aggr_adata.obs[cell_identity_key].unique()
+    else:
+        cids = [""]
+
+    tt_dict = {}
+    for condition_group in condition_group_list:
+        if reference_group is not None and condition_group == reference_group:
+            continue
+
+        if verbosity > 0:
+            print(f"Fitting model for {condition_group}...")
+
+        if reference_group is not None:
+            gk = group_key
+        else:
+            gk = f"{group_key}_{condition_group}"
+
+        try:
+            R(f"""
+                outs <- fit_model(aggr_adata, "{gk}", "{cell_identity_key}", "{batch_key}", verbosity = {verbosity})
+                fit <- outs$fit
+                y <- outs$y
+            """)
+
+        except RRuntimeError as e:
+            print("Error fitting model for", condition_group)
+            print("Error:", e)
+            print("Skipping...", flush=True)
+            continue
+
+        if reference_group is None:
+            new_contrasts_tuples = [
+                (
+                    condition_group,  # common prefix
+                    "",  # condition group
+                    "not",  # reference group
+                    cid,  # cell identity
+                )
+                for cid in cids
+            ]
+
+        else:
+            new_contrasts_tuples = [
+                (
+                    "",  # common prefix
+                    condition_group,  # condition group
+                    reference_group,  # reference group
+                    cid,  # cell identity
+                )
+                for cid in cids
+            ]
+
+        new_contrasts = [
+            f"group{cnd}{prefix}_{cid}".strip("_")
+            + "-"
+            + f"group{ref}{prefix}_{cid}".strip("_")
+            for prefix, cnd, ref, cid in new_contrasts_tuples
+        ]
+
+        for contrast, contrast_tuple in zip(new_contrasts, new_contrasts_tuples):
+            prefix, cnd, ref, cid = contrast_tuple
+
+            if ref == "not":
+                cnd, ref = "", "rest"
+
+            contrast_key = f"{prefix}{cnd}_vs_{ref}"
+            if cid:
+                contrast_key = f"{cell_identity_key}:{cid}|{contrast_key}"
+
+            if verbosity > 0:
+                print(f"Computing contrast: {contrast_key}... ({contrast})")
+
+            R(f"myContrast <- makeContrasts('{contrast}', levels = y$design)")
+            R("qlf <- glmQLFTest(fit, contrast=myContrast)")
+            R("tt <- topTags(qlf, n = Inf)$table")
+            tt: pd.DataFrame = pandas2ri.rpy2py(R("tt"))
+            tt.index.name = "gene_ids"
+
+            genes = tt.index
+            cnd, ref = [c[5:] for c in contrast.split("-")]
+            tt["pct_expr_cnd"] = aggr_adata.var[f"pct_expr_{cnd}"].loc[genes]
+            tt["pct_expr_ref"] = aggr_adata.var[f"pct_expr_{ref}"].loc[genes]
+            tt["num_expr_cnd"] = aggr_adata.var[f"num_expr_{cnd}"].loc[genes]
+            tt["num_expr_ref"] = aggr_adata.var[f"num_expr_{ref}"].loc[genes]
+            tt["tot_expr_cnd"] = aggr_adata.var[f"tot_expr_{cnd}"].loc[genes]
+            tt["tot_expr_ref"] = aggr_adata.var[f"tot_expr_{ref}"].loc[genes]
+            tt["mean_cnd"] = tt["tot_expr_cnd"] / tt["num_expr_cnd"]
+            tt["mean_ref"] = tt["tot_expr_ref"] / tt["num_expr_ref"]
+            tt_dict[contrast_key] = tt
+
+    return tt_dict
+
+
+_fit_model_r_script = """
+suppressPackageStartupMessages({
+    library(edgeR)
+    library(MAST)
+})
+
+fit_model <- function(adata_, group_key, cell_identity_key = "None", batch_key = "None", verbosity = 0){
+
+    if (verbosity > 0){
+        cat("Group key:", group_key, "\n")
+        cat("Cell identity key:", cell_identity_key, "\n")
+    }
+
+    # create an edgeR object with counts and grouping factor
+    y <- DGEList(assay(adata_, "X"), group = colData(adata_)[[group_key]])
+    # filter out genes with low counts
+    if (verbosity > 1){
+        cat("Dimensions before subsetting:", dim(y), "\n")
+    }
+    keep <- filterByExpr(y)
+    y <- y[keep, , keep.lib.sizes=FALSE]
+    if (verbosity > 1){
+        cat("Dimensions after subsetting:", dim(y), "\n")
+    }
+
+    # normalize
+    y <- calcNormFactors(y)
+    # create a vector that is concatentation of condition and cell type that we will later use with contrasts
+    if (cell_identity_key == "None"){
+        group <- colData(adata_)[[group_key]]
+    } else {
+        group <- paste0(colData(adata_)[[group_key]], "_", colData(adata_)[[cell_identity_key]])
+    }
+    if (verbosity > 1){
+        cat("Group(s):", group, "\n")
+    }
+
+    replica <- colData(adata_)$replica
+
+    # create a design matrix
+    if (batch_key == "None"){
+        design <- model.matrix(~ 0 + group + replica)
+    } else {
+        batch <- colData(adata_)[[batch_key]]
+        design <- model.matrix(~ 0 + group + replica + batch)
+    }
+
+    # estimate dispersion
+    y <- estimateDisp(y, design = design)
+    # fit the model
+    fit <- glmQLFit(y, design)
+    return(list("fit"=fit, "design"=design, "y"=y))
+}
+"""
+
+
+def _try_imports():
+    try:
+        import rpy2.robjects as robjects
+        from rpy2.robjects.packages import PackageNotInstalledError, importr
+
+        robjects.r("options(warn=-1)")
+        import anndata2ri  # noqa: F401
+        from rpy2.rinterface_lib.embedded import RRuntimeError  # noqa: F401
+        from rpy2.robjects import numpy2ri, pandas2ri  # noqa: F401
+        from rpy2.robjects.conversion import localconverter  # noqa: F401
+
+        importr("edgeR")
+        importr("MAST")
+        importr("SingleCellExperiment")
+
+    except ModuleNotFoundError:
+        message = (
+            "edger_pseudobulk requires rpy2 and anndata2ri to be installed.\n"
+            "or\n"
+            "$ pip install rpy2 sclab-tools[r]\n"
+            "or\n"
+            "$ pip install rpy2 anndata2ri\n"
+            "or\n"
+            "$ conda install -c conda-forge rpy2 anndata2ri\n"
+        )
+        print(message)
+        raise ModuleNotFoundError(message)
+
+    except PackageNotInstalledError:
+        message = (
+            "edger_pseudobulk requires the following R packages to be installed: edgeR, MAST, and SingleCellExperiment.\n"
+            "> \n"
+            "> if (!require('BiocManager', quietly = TRUE)) install.packages('BiocManager');\n"
+            "> BiocManager::install(c('edgeR', 'MAST', 'SingleCellExperiment'));\n"
+            "> \n"
+        )
+        print(message)
+        raise ImportError(message)