diff --git a/README.md b/README.md index 114d5df1c63541912aa0a8342ffa69ae3d102cbf..a8f6acd400f92f9904846e2e0838acb795448409 100644 --- a/README.md +++ b/README.md @@ -20,3 +20,5 @@ The only other file you need to install is `xlsx2csv` using `pip`: ``` pip install xlsx2csv ``` + +Additionally, I used `ripgrep` instead of `grep` for faster extraction of subset data from EggNOG. In case you rely on `grep` make edits accordingly in the notebooks (replace commands of `rg`) diff --git a/notebooks/01-01_download_data.ipynb b/notebooks/01-01_download_data.ipynb index 265a7254d60b086f1526bb51770b814e93bc5431..9e6f784243ebbea1e3e2f7d9eb0aff7b9821b32b 100644 --- a/notebooks/01-01_download_data.ipynb +++ b/notebooks/01-01_download_data.ipynb @@ -9,8 +9,10 @@ ] }, { - "cell_type": "raw", + "cell_type": "code", + "execution_count": null, "metadata": {}, + "outputs": [], "source": [ "e6_url = \"http://eggnog6.embl.de/download/eggnog_6.0/\"\n", "all_trees_path = e6_url + \"e6.all_raw_trees_and_algs.tsv\"\n", @@ -38,12 +40,10 @@ ] }, { - "cell_type": "raw", - "metadata": { - "vscode": { - "languageId": "raw" - } - }, + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], "source": [ "%%bash -s \"$data_dir\" \"$all_trees_path\" \"$og2seqs_species_path\" \"$seq2ogs_path\" \"$gold_url\"\n", "pip install xlsx2csv\n",