📌 v0.2.1 release

Author: xiachenrui

.gitattributes

@@ -1,2 +1,4 @@
 # ignore the special file 
-**.ipynb linguist-vendored
+**.ipynb linguist-vendored
+**.R linguist-vendored
+** .Rprofile linguist-vendored

.github/workflows/build.yml

@@ -30,8 +30,8 @@ jobs:
           sudo apt install -y libxml2-utils pandoc
           curl -sSL https://install.python-poetry.org | python3 -
           pip install --upgrade pip
-          pip install -e ".[torch]"
-          pip install -e ".[pyg,docs,dev]"
+          pip install -e ".[docs, dev]"
+          pip install pyg_lib torch_scatter torch_sparse torch_cluster torch_spline_conv -f https://data.pyg.org/whl/torch-2.0.0+cpu.html
       
       - name: Build documentation
         run: |

.github/workflows/release.yml

@@ -21,8 +21,9 @@ jobs:
       run: |
         curl -sSL https://install.python-poetry.org | python3 -
         pip install --upgrade pip
-        pip install -e ".[torch]"
-        pip install -e ".[pyg,docs,dev]"
+        pip install -e ".[docs, dev]"
+        pip install pyg_lib torch_scatter torch_sparse torch_cluster torch_spline_conv -f https://data.pyg.org/whl/torch-2.0.0+cpu.html
+
     
     - name: Build package
       run: |

.gitignore

@@ -18,6 +18,9 @@
 *.arrow
 *Weights
 *.sqlite
+*.svg
+*.gz
+*.whl
 
 # folder
 **/conda/

README.md

@@ -46,36 +46,33 @@ docker pull huhansan666666/slat:latest
 > **Note**
 > Installing `scSLAT` within a new [conda environment](https://conda.io/projects/conda/en/latest/user-guide/tasks/manage-environments.html) is recommended.
 
-First, we create a clean environment and install `scSLAT` from PyPI. We need install dependency `torch` before install `pyg`.
+First, we create a clean environment and install `scSLAT` from PyPI. Then we also need install dependencies for `pyg` manually. We default install with CUDA 11.7. Please refer [here](https://pytorch-geometric.readthedocs.io/en/latest/install/installation.html#quick-start) for CPU version or different CUDA versions.
 
 > **Warning**
 > old NVIDIA driver may raise error, please update NVIDIA driver to the latest version.
 
 ```bash
 conda create -n scSLAT python=3.8 -y && conda activate scSLAT
-pip install "scSLAT[torch]"
-pip install "scSLAT[pyg]"
+pip install scSLAT
+pip install pyg_lib torch_scatter torch_sparse torch_cluster torch_spline_conv -f https://data.pyg.org/whl/torch-2.0.0+cu117.html
 ```
 
-> **Note**
-> Some dependencies such as `torch-scatter` need to compile from source, which may take a long time. Please refer our solution to accelerate the install [here](https://slat.readthedocs.io/en/latest/install.html)
-
 ### Development version
 For development purpose, clone this repo and install:
 
 ```bash
 git clone git@github.com:gao-lab/SLAT.git
 cd SLAT
-pip install -e ".[torch]"
-pip install -e ".[pyg,dev,doc]"
+pip install -e ".[dev,docs]"
+pip install pyg_lib torch_scatter torch_sparse torch_cluster torch_spline_conv -f https://data.pyg.org/whl/torch-2.0.0+cu117.html
 ```
 
 ### Conda (Ongoing)
 We plan to provide a conda package of `scSLAT` in the near future.
 
 
 ## Reproduce manuscript results
-1. Please follow the [`env/README.md`](env/README.md) to install all dependencies. Please checkout the repository to v0.2.0 before install `scSLAT`:
-2. Download and pre-process data follow the [`data/README.md`](data/README.md)
+1. Please follow the [`env/README.md`](env/README.md) to install all dependencies. Please checkout the repository to v0.2.1 before install `scSLAT`.
+2. Download and pre-process data follow the [`data/README.md`](data/README.md).
 3. Whole benchmark and evaluation procedure can be found in [`/benchmark`](benchmark/README.md) and [`/evaluation`](evaluation/README.md), respectively.
 4. Every case study is recorded in the [`/case`](case/README.md) directory in the form of jupyter notebook.

benchmark/.gitignore

@@ -4,4 +4,5 @@ results*/
 split/
 multi/
 results_bak/
-figures/
+figures/
+hetero/

benchmark/analysis/3d_analysis.ipynb

@@ -79,8 +79,19 @@
    "language": "python",
    "name": "stagate_pyg"
   },
-  "orig_nbformat": 4
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.8.13"
+  }
  },
  "nbformat": 4,
- "nbformat_minor": 2
+ "nbformat_minor": 4
 }

benchmark/analysis/benchmark_analysis.ipynb

@@ -0,0 +1,230 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "7eef7d2f-cc7f-4ab7-bd03-c242ea7ad280",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Loading required package: ggplot2\n",
+      "\n",
+      "Loading required package: ggrepel\n",
+      "\n",
+      "Registered S3 methods overwritten by 'ggalt':\n",
+      "  method                  from   \n",
+      "  grid.draw.absoluteGrob  ggplot2\n",
+      "  grobHeight.absoluteGrob ggplot2\n",
+      "  grobWidth.absoluteGrob  ggplot2\n",
+      "  grobX.absoluteGrob      ggplot2\n",
+      "  grobY.absoluteGrob      ggplot2\n",
+      "\n",
+      "── \u001b[1mAttaching packages\u001b[22m ─────────────────────────────────────────────────────────────────────────────── tidyverse 1.3.2 ──\n",
+      "\u001b[32m✔\u001b[39m \u001b[34mtibble \u001b[39m 3.1.8      \u001b[32m✔\u001b[39m \u001b[34mdplyr  \u001b[39m 1.0.10\n",
+      "\u001b[32m✔\u001b[39m \u001b[34mtidyr  \u001b[39m 1.2.1      \u001b[32m✔\u001b[39m \u001b[34mstringr\u001b[39m 1.5.0 \n",
+      "\u001b[32m✔\u001b[39m \u001b[34mreadr  \u001b[39m 2.1.3      \u001b[32m✔\u001b[39m \u001b[34mforcats\u001b[39m 0.5.2 \n",
+      "\u001b[32m✔\u001b[39m \u001b[34mpurrr  \u001b[39m 1.0.0      \n",
+      "── \u001b[1mConflicts\u001b[22m ────────────────────────────────────────────────────────────────────────────────── tidyverse_conflicts() ──\n",
+      "\u001b[31m✖\u001b[39m \u001b[34mdplyr\u001b[39m::\u001b[32mfilter()\u001b[39m masks \u001b[34mstats\u001b[39m::filter()\n",
+      "\u001b[31m✖\u001b[39m \u001b[34mdplyr\u001b[39m::\u001b[32mlag()\u001b[39m    masks \u001b[34mstats\u001b[39m::lag()\n"
+     ]
+    }
+   ],
+   "source": [
+    "setwd('../../')\n",
+    "source('.Rprofile')\n",
+    "setwd('./case/visium_xenium')\n",
+    "\n",
+    "library(EnhancedVolcano)\n",
+    "library(tidyverse)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "e2d0b05f-f1bf-49d0-bd83-3d5d1df4b600",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\u001b[1m\u001b[22mNew names:\n",
+      "\u001b[36m•\u001b[39m `` -> `...1`\n",
+      "\u001b[1mRows: \u001b[22m\u001b[34m18056\u001b[39m \u001b[1mColumns: \u001b[22m\u001b[34m9\u001b[39m\n",
+      "\u001b[36m──\u001b[39m \u001b[1mColumn specification\u001b[22m \u001b[36m────────────────────────────────────────────────────────────────────────────────────────────────\u001b[39m\n",
+      "\u001b[1mDelimiter:\u001b[22m \",\"\n",
+      "\u001b[31mchr\u001b[39m (2): No_name, Yes_name\n",
+      "\u001b[32mdbl\u001b[39m (7): ...1, No_pval, No_logf, No_scor, Yes_pval, Yes_logf, Yes_scor\n",
+      "\n",
+      "\u001b[36mℹ\u001b[39m Use `spec()` to retrieve the full column specification for this data.\n",
+      "\u001b[36mℹ\u001b[39m Specify the column types or set `show_col_types = FALSE` to quiet this message.\n",
+      "Warning message:\n",
+      "“Setting row names on a tibble is deprecated.”\n"
+     ]
+    }
+   ],
+   "source": [
+    "hvg <- read_csv('../../data/visium/breast/hvg_align.csv')\n",
+    "hvg <- hvg[,c('Yes_name','Yes_pval','Yes_logf','Yes_scor')]\n",
+    "rownames(hvg) <- hvg[['Yes_name']]\n",
+    "colnames(hvg) <- c('Name','adj.Pval','logFC2','Score')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "d6f16112-c341-4bb3-8145-61cc9b83f946",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# top 25\n",
+    "top25 <- hvg %>% filter(logFC2 > 1.5 & adj.Pval < 0.05) %>% arrange(-Score) %>% head(25) \n",
+    "top25 <- as.vector(top25$Name)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "760219ac-3db1-4e5b-a8c9-4df9c57df114",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<style>\n",
+       ".list-inline {list-style: none; margin:0; padding: 0}\n",
+       ".list-inline>li {display: inline-block}\n",
+       ".list-inline>li:not(:last-child)::after {content: \"\\00b7\"; padding: 0 .5ex}\n",
+       "</style>\n",
+       "<ol class=list-inline><li>'STC2'</li><li>'TRH'</li><li>'CACNG4'</li><li>'TMEM47'</li><li>'MUCL1'</li><li>'RIMS4'</li><li>'AFF3'</li><li>'CPB1'</li><li>'MAGED2'</li><li>'STARD10'</li><li>'NOS1AP'</li><li>'NEK10'</li><li>'LDLRAD3'</li><li>'PHGR1'</li><li>'MAPT'</li><li>'EREG'</li><li>'IFI27'</li><li>'LAMA3'</li><li>'SULT2B1'</li><li>'TBC1D9'</li><li>'ADCY1'</li><li>'KIAA1324'</li><li>'AUTS2'</li><li>'FAM3B'</li><li>'MCCC2'</li></ol>\n"
+      ],
+      "text/latex": [
+       "\\begin{enumerate*}\n",
+       "\\item 'STC2'\n",
+       "\\item 'TRH'\n",
+       "\\item 'CACNG4'\n",
+       "\\item 'TMEM47'\n",
+       "\\item 'MUCL1'\n",
+       "\\item 'RIMS4'\n",
+       "\\item 'AFF3'\n",
+       "\\item 'CPB1'\n",
+       "\\item 'MAGED2'\n",
+       "\\item 'STARD10'\n",
+       "\\item 'NOS1AP'\n",
+       "\\item 'NEK10'\n",
+       "\\item 'LDLRAD3'\n",
+       "\\item 'PHGR1'\n",
+       "\\item 'MAPT'\n",
+       "\\item 'EREG'\n",
+       "\\item 'IFI27'\n",
+       "\\item 'LAMA3'\n",
+       "\\item 'SULT2B1'\n",
+       "\\item 'TBC1D9'\n",
+       "\\item 'ADCY1'\n",
+       "\\item 'KIAA1324'\n",
+       "\\item 'AUTS2'\n",
+       "\\item 'FAM3B'\n",
+       "\\item 'MCCC2'\n",
+       "\\end{enumerate*}\n"
+      ],
+      "text/markdown": [
+       "1. 'STC2'\n",
+       "2. 'TRH'\n",
+       "3. 'CACNG4'\n",
+       "4. 'TMEM47'\n",
+       "5. 'MUCL1'\n",
+       "6. 'RIMS4'\n",
+       "7. 'AFF3'\n",
+       "8. 'CPB1'\n",
+       "9. 'MAGED2'\n",
+       "10. 'STARD10'\n",
+       "11. 'NOS1AP'\n",
+       "12. 'NEK10'\n",
+       "13. 'LDLRAD3'\n",
+       "14. 'PHGR1'\n",
+       "15. 'MAPT'\n",
+       "16. 'EREG'\n",
+       "17. 'IFI27'\n",
+       "18. 'LAMA3'\n",
+       "19. 'SULT2B1'\n",
+       "20. 'TBC1D9'\n",
+       "21. 'ADCY1'\n",
+       "22. 'KIAA1324'\n",
+       "23. 'AUTS2'\n",
+       "24. 'FAM3B'\n",
+       "25. 'MCCC2'\n",
+       "\n",
+       "\n"
+      ],
+      "text/plain": [
+       " [1] \"STC2\"     \"TRH\"      \"CACNG4\"   \"TMEM47\"   \"MUCL1\"    \"RIMS4\"   \n",
+       " [7] \"AFF3\"     \"CPB1\"     \"MAGED2\"   \"STARD10\"  \"NOS1AP\"   \"NEK10\"   \n",
+       "[13] \"LDLRAD3\"  \"PHGR1\"    \"MAPT\"     \"EREG\"     \"IFI27\"    \"LAMA3\"   \n",
+       "[19] \"SULT2B1\"  \"TBC1D9\"   \"ADCY1\"    \"KIAA1324\" \"AUTS2\"    \"FAM3B\"   \n",
+       "[25] \"MCCC2\"   "
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "top25"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "id": "af31222e-4ef7-4b41-a7e3-da4db650aa06",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "options(repr.plot.width=13, repr.plot.height=12)\n",
+    "p1 <- EnhancedVolcano(hvg, lab = rownames(hvg), x = 'logFC2', y= 'adj.Pval', xlim = c(-6,6), ylim = c(0,6), FCcutoff = 1.5, pCutoff = 0.05, labSize =7,axisLabSize =24,\n",
+    "                colAlpha = 1,\n",
+    "                xlab = 'log2 fold change', ylab = 'log10 adjust P.value',\n",
+    "                # selectLab = top25,\n",
+    "                # col = c(\"grey30\", \"grey30\", \"grey30\", \"red2\"),\n",
+    "                # drawConnectors = TRUE,\n",
+    "                title = '', subtitle ='',\n",
+    "                pointSize = c(ifelse((hvg$\"logFC2\">1.5 |hvg$\"logFC2\"< -1.5) & hvg$\"adj.Pval\"<0.05 , 2.5, 1.5)),\n",
+    "                legendLabels =c('NS','log2FC only','adj.P only','Significant'),\n",
+    "                legendPosition = 'right',\n",
+    "                legendLabSize = 22)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 24,
+   "id": "a0cd6eb7-9738-42a6-9cec-74a7efee1afb",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "ggsave('./volcano.svg',p1, width = 13, height = 12)"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "slat_r",
+   "language": "R",
+   "name": "slat_r"
+  },
+  "language_info": {
+   "codemirror_mode": "r",
+   "file_extension": ".r",
+   "mimetype": "text/x-r-source",
+   "name": "R",
+   "pygments_lexer": "r",
+   "version": "4.1.3"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}