{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "cc669ef4-e158-4cf8-86a9-c20baadf8b89",
   "metadata": {},
   "source": [
    "# Getting Start"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "6ff81890-f861-4b70-8d97-c5a57920a0b4",
   "metadata": {},
   "source": [
    "Examples of PhyloVelo and steps are provided in Jupyter Notebook under notebooks folder. For start, please refer to records analyzing simulation, C.elegans and KPTracer datasets."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "335d702f-0540-40ae-9968-2a89263b80eb",
   "metadata": {},
   "source": [
    "## PhyloVelo on New Dataset"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "7bdc0ba4-e857-4e94-a856-4e237ed0bea7",
   "metadata": {},
   "source": [
    "PhyloVelo provides an integrated function for phylogenetic velocity analysis by default whilst specific configurations might need to be adjusted accordingly."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "42d2d9c7-3137-4bb1-ba45-f9d44b614f20",
   "metadata": {},
   "source": [
    "### 1. import pacakge"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "0fd06f38-24b5-4c85-a8e0-d65bc75e8a26",
   "metadata": {},
   "source": [
    "```import phylovelo as pv```"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "431f43bf-6b75-4e51-abc1-675f46432758",
   "metadata": {},
   "source": [
    "### 2. import data, filter, normalize and dimensionality reduction"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d71fb1c7-4bad-4c45-9320-a975d170fd01",
   "metadata": {},
   "source": [
    "```\n",
    "sd = pv.scData(count=xx, phylo_tree=xx)\n",
    "sd.drop_duplicate_genes()\n",
    "sd.normalize_filter(min_count=20)\n",
    "sd.dimensionality_reduction(target='x_normed', method='umap')\n",
    "```"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d4f8ab5c-eb42-411a-929c-5e1bbc5a0c11",
   "metadata": {},
   "source": [
    "### 3. Run model"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "115360eb-2df3-48c2-83c6-47188ebb78f0",
   "metadata": {},
   "source": [
    "```\n",
    "depths = [tree.get_depth(sd.phylo_tree.find_any(name=i)) for i in sd.x_normed.index]\n",
    "pv.velocity_inference(sd, depths, cutoff=0.95, target='x_normed')\n",
    "```"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "7c8cf7cb-6ce2-4463-9a0c-bf8484842df1",
   "metadata": {},
   "source": [
    "### 4. Porject velocity into embedding and visualization"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "0ce878fe-51fc-4a33-b929-bd6cfee7f044",
   "metadata": {},
   "source": [
    "```\n",
    "pv.velocity_embedding(sd, target='x_normed')\n",
    "fig, ax = plt.subplots()\n",
    "ax.scatter(sd.Xdr.iloc[:,0], sd.Xdr.iloc[:,1], c=depths, s=100, alpha=0.3)\n",
    "ax = pv.velocity_plot(sd.Xdr.to_numpy(), sd.velocity_embeded, ax, 'stream', radius=0.8, lw_coef=100, arrowsize=2)\n",
    "```"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "487cf0dd-e133-42e1-bd8d-7c86e03ac02d",
   "metadata": {},
   "source": [
    "### 5. PhyloVelo pseudotime analysis\n",
    "\n",
    "PhyloVelo supports two pseudotime estimators. The default graph-based method uses the projected velocity field in the embedding, while the MEG expression method directly scores cells from robustly oriented MEG expression. Both methods store a `[0, 1]` normalized result in `sd.phylo_pseudotime`."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "de8af8e5-d66d-4f67-b608-e047bd8453df",
   "metadata": {},
   "source": [
    "```\n",
    "# Graph-based pseudotime from the projected velocity field.\n",
    "pv.calc_phylo_pseudotime(sd, n_neighbors=100, r_sample=0.8, random_state=0)\n",
    "\n",
    "# Alternatively, estimate pseudotime directly from MEG expression.\n",
    "# pv.calc_meg_pseudotime(sd, target='x_normed')\n",
    "# pv.calc_phylo_pseudotime(sd, method='meg', target='x_normed')\n",
    "\n",
    "fig, ax = plt.subplots(figsize=(8,8))\n",
    "scatter = ax.scatter(sd.Xdr.iloc[:,0],sd.Xdr.iloc[:,1], c=sd.phylo_pseudotime,cmap='plasma', s=60)\n",
    "cbaxes = inset_axes(ax, width=\"3%\", height=\"30%\", loc='lower left') \n",
    "plt.colorbar(scatter, cax=cbaxes, orientation='vertical')\n",
    "```"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "bc2caa34-e679-43c6-b6da-f0554b5856b0",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.9.12"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}