CardamomOT.tools.plot_results_kov ================================= .. py:module:: CardamomOT.tools.plot_results_kov .. autoapi-nested-parse:: Plotting and analysis utilities for KO/OV perturbation results. Functions --------- .. autoapisummary:: CardamomOT.tools.plot_results_kov.plot_results_sim_kov CardamomOT.tools.plot_results_kov.compare_cell_types Module Contents --------------- .. py:function:: plot_results_sim_kov(p, combo, stim=1.0, prior=1.0, project_on_full=False, normtransform=False, logtransform=True) Compare wild-type simulation to a KO/OV perturbation (UMAP). :param p: Path to the project directory (trailing slash included). :type p: str :param combo: Perturbation label, e.g. ``"KO_Gata6_OV_none"``. :type combo: str :param stim: Stimulus-edge penalisation value used during inference. :type stim: float :param prior: Prior-network weighting value used during inference. :type prior: float :param project_on_full: If True, fit UMAP on NB mixture and project others. :type project_on_full: bool :param normlog: Apply normalisation and log1p before UMAP. :type normlog: bool .. py:function:: compare_cell_types(p, combo_name, split='full', stim=1.0, prior=1.0, label_key='cell_type') Compare cell-type proportions between wild-type and a KO/OV perturbation. Trains a classifier on the observed data, predicts cell types on WT trajectories, WT simulation, and the perturbation simulation, then plots stacked bar proportions for all three. :param p: Path to the project directory (trailing slash included). :type p: str :param combo_name: Perturbation label, e.g. ``"KO_CHGA_OV_none"``. :type combo_name: str :param split: Data split used to load the reference data (``"full"`` or ``"train"``). :type split: str :param stim: Stimulus value used during inference. :type stim: float :param prior: Prior value used during inference. :type prior: float :param label_key: ``obs`` key used to store/read cell-type predictions. :type label_key: str