diff --git a/.gitignore b/.gitignore
new file mode 100644
index 0000000000000000000000000000000000000000..bc52824899a07e433d9b6a7e42b86e2fb866b514
--- /dev/null
+++ b/.gitignore
@@ -0,0 +1,33 @@
+MANIFEST
+build
+dist
+_build
+docs/man/*.gz
+docs/source/api/generated
+docs/source/config/options
+docs/source/config/shortcuts/*.csv
+docs/source/savefig
+docs/source/interactive/magics-generated.txt
+docs/gh-pages
+jupyter_notebook/notebook/static/mathjax
+jupyter_notebook/static/style/*.map
+*.py[co]
+__pycache__
+*.egg-info
+*~
+*.bak
+.ipynb_checkpoints
+.tox
+.DS_Store
+\#*#
+.#*
+.cache
+.coverage
+*.swp
+.vscode
+.pytest_cache
+.python-version
+venv*/
+.idea/
+.mypy_cache/
+
diff --git a/analysis/.ipynb_checkpoints/Untitled-checkpoint.ipynb b/analysis/.ipynb_checkpoints/Untitled-checkpoint.ipynb
deleted file mode 100644
index 363fcab7ed6e9634e198cf5555ceb88932c9a245..0000000000000000000000000000000000000000
--- a/analysis/.ipynb_checkpoints/Untitled-checkpoint.ipynb
+++ /dev/null
@@ -1,6 +0,0 @@
-{
- "cells": [],
- "metadata": {},
- "nbformat": 4,
- "nbformat_minor": 5
-}
diff --git a/analysis/Untitled.ipynb b/analysis/Untitled.ipynb
deleted file mode 100644
index 7e71573309dec622d2f063c48548c99efdccf190..0000000000000000000000000000000000000000
--- a/analysis/Untitled.ipynb
+++ /dev/null
@@ -1,44 +0,0 @@
-{
- "cells": [
- {
- "cell_type": "code",
- "execution_count": 2,
- "id": "b713a10d",
- "metadata": {},
- "outputs": [],
- "source": [
- "import numpy as np\n",
- "import pandas as pd"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "id": "e8e14aad",
- "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": "3.8.6"
- }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}
diff --git a/analysis/batch1.ipynb b/analysis/batch1.ipynb
new file mode 100644
index 0000000000000000000000000000000000000000..7b957b4c10ffc9c3de14902805ae9a8da165bd15
--- /dev/null
+++ b/analysis/batch1.ipynb
@@ -0,0 +1,673 @@
+{
+ "cells": [
+ {
+ "cell_type": "code",
+ "execution_count": 1,
+ "id": "b713a10d",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "import json\n",
+ "import os\n",
+ "\n",
+ "from tqdm import tqdm\n",
+ "\n",
+ "import numpy as np\n",
+ "import pandas as pd\n",
+ "\n",
+ "import matplotlib.pyplot as plt"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 2,
+ "id": "e8e14aad",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# MSA location\n",
+ "msas = \"/scratch/npapadop/msas/batch1/\"\n",
+ "# FOLDSEEK scores\n",
+ "fs_pdb = \"/scratch/npapadop/foldseek_results/pdb_score.tsv\"\n",
+ "fs_afdb = \"/scratch/npapadop/foldseek_results/afdb_score.tsv\"\n",
+ "fs_swp = \"/scratch/npapadop/foldseek_results/swissprot_score.tsv\"\n",
+ "# AlphaFold predictions\n",
+ "structure_list = \"/scratch/npapadop/spongilla_best_model/\"\n",
+ "metadata = \"/scratch/npapadop/spongilla_structures/\""
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 3,
+ "id": "41ea0950-5ac1-4ea3-b7c1-f593579ace0b",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "100%|██████████| 1335/1335 [00:14<00:00, 93.70it/s] \n"
+ ]
+ }
+ ],
+ "source": [
+ "N = len(os.listdir(structure_list))\n",
+ "proteins = [\"\"] * N\n",
+ "scores = [0.] * N\n",
+ "\n",
+ "for i, protein in enumerate(tqdm(os.listdir(structure_list))):\n",
+ " full_name = protein.split(\".\")[0]\n",
+ " metadata_loc = metadata + full_name + \"_scores.json\"\n",
+ " with open(metadata_loc, \"r\") as f:\n",
+ " score = json.load(f)\n",
+ " name = full_name.split(\"_\")[0]\n",
+ " proteins[i] = name\n",
+ " scores[i] = np.mean(score[\"plddt\"])"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 4,
+ "id": "8a94071c-b22b-46d0-9925-7476bbf3e02a",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "alphafold = pd.DataFrame({\"query\": proteins, \"plddt\": scores})\n",
+ "alphafold.set_index(\"query\", inplace=True)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 5,
+ "id": "f42188be-0436-47bc-aa59-890192ef00a4",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "def read_foldseek(result_path):\n",
+ " df = pd.read_csv(result_path, sep=\"\\s+\", header=None)\n",
+ " df.columns = [\"query\", \"target\", \"seq. id.\", \"alignment length\", \"no. mismatches\",\n",
+ " \"no. gap open\", \"query start\", \"target start\", \"query end\", \"target end\",\n",
+ " \"e value\", \"bit score\"]\n",
+ " df[\"query\"] = df[\"query\"].str.split(\"_\").str[0]\n",
+ " if \"pdb\" in result_path:\n",
+ " df[\"target\"] = df[\"target\"].str.split(\".\").str[0]\n",
+ " else:\n",
+ " df[\"target\"] = df[\"target\"].str.split(\"-\").str[:3].str.join(\"-\")\n",
+ " return df"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 6,
+ "id": "2ad95435-9023-4d97-a0ce-cd7612e57a66",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "pdb = read_foldseek(fs_pdb)\n",
+ "afdb = read_foldseek(fs_afdb)\n",
+ "swp = read_foldseek(fs_swp)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 7,
+ "id": "7ef2393f-3125-4108-b21a-6729f1c536a0",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "def keep_best_match(df, prefix):\n",
+ " df = df.sort_values('bit score', ascending=False).drop_duplicates(['query'])\n",
+ " df.set_index(\"query\", inplace=True)\n",
+ " df.columns = prefix + \" \" + df.columns\n",
+ " return df"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 8,
+ "id": "f1d9ef06-d55b-48bb-a966-5d4d8e9b6fba",
+ "metadata": {
+ "tags": []
+ },
+ "outputs": [],
+ "source": [
+ "pdb = keep_best_match(pdb, \"pdb\")\n",
+ "afdb = keep_best_match(afdb, \"afdb\")\n",
+ "swp = keep_best_match(swp, \"swp\")"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 9,
+ "id": "f07f22f8-bf4b-474a-a0c1-4c7e184b0b4b",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "foldseek = pdb.join(afdb, how=\"outer\").join(swp, how=\"outer\").join(alphafold)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 10,
+ "id": "91aaabea-24d9-4915-aa09-66035c86dbb9",
+ "metadata": {
+ "collapsed": true,
+ "jupyter": {
+ "outputs_hidden": true
+ },
+ "tags": []
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style scoped>\n",
+ " .dataframe tbody tr th:only-of-type {\n",
+ " vertical-align: middle;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>pdb target</th>\n",
+ " <th>pdb seq. id.</th>\n",
+ " <th>pdb alignment length</th>\n",
+ " <th>pdb no. mismatches</th>\n",
+ " <th>pdb no. gap open</th>\n",
+ " <th>pdb query start</th>\n",
+ " <th>pdb target start</th>\n",
+ " <th>pdb query end</th>\n",
+ " <th>pdb target end</th>\n",
+ " <th>pdb e value</th>\n",
+ " <th>...</th>\n",
+ " <th>swp alignment length</th>\n",
+ " <th>swp no. mismatches</th>\n",
+ " <th>swp no. gap open</th>\n",
+ " <th>swp query start</th>\n",
+ " <th>swp target start</th>\n",
+ " <th>swp query end</th>\n",
+ " <th>swp target end</th>\n",
+ " <th>swp e value</th>\n",
+ " <th>swp bit score</th>\n",
+ " <th>plddt</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>query</th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>10001</th>\n",
+ " <td>4x92</td>\n",
+ " <td>0.236</td>\n",
+ " <td>199.0</td>\n",
+ " <td>139.0</td>\n",
+ " <td>5.0</td>\n",
+ " <td>1.0</td>\n",
+ " <td>197.0</td>\n",
+ " <td>186.0</td>\n",
+ " <td>373.0</td>\n",
+ " <td>9.148000e-15</td>\n",
+ " <td>...</td>\n",
+ " <td>207.0</td>\n",
+ " <td>132.0</td>\n",
+ " <td>5.0</td>\n",
+ " <td>2.0</td>\n",
+ " <td>201.0</td>\n",
+ " <td>229.0</td>\n",
+ " <td>421.0</td>\n",
+ " <td>1.621000e-15</td>\n",
+ " <td>630.0</td>\n",
+ " <td>88.311832</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>10038</th>\n",
+ " <td>1uf1</td>\n",
+ " <td>0.475</td>\n",
+ " <td>124.0</td>\n",
+ " <td>60.0</td>\n",
+ " <td>3.0</td>\n",
+ " <td>57.0</td>\n",
+ " <td>180.0</td>\n",
+ " <td>10.0</td>\n",
+ " <td>128.0</td>\n",
+ " <td>2.325000e-11</td>\n",
+ " <td>...</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>66.247545</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>10121</th>\n",
+ " <td>3zk4</td>\n",
+ " <td>0.342</td>\n",
+ " <td>146.0</td>\n",
+ " <td>85.0</td>\n",
+ " <td>3.0</td>\n",
+ " <td>6.0</td>\n",
+ " <td>140.0</td>\n",
+ " <td>405.0</td>\n",
+ " <td>550.0</td>\n",
+ " <td>2.610000e-12</td>\n",
+ " <td>...</td>\n",
+ " <td>146.0</td>\n",
+ " <td>86.0</td>\n",
+ " <td>3.0</td>\n",
+ " <td>6.0</td>\n",
+ " <td>140.0</td>\n",
+ " <td>202.0</td>\n",
+ " <td>347.0</td>\n",
+ " <td>4.720000e-13</td>\n",
+ " <td>546.0</td>\n",
+ " <td>91.322817</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>10166</th>\n",
+ " <td>6r84</td>\n",
+ " <td>0.421</td>\n",
+ " <td>95.0</td>\n",
+ " <td>52.0</td>\n",
+ " <td>2.0</td>\n",
+ " <td>9.0</td>\n",
+ " <td>100.0</td>\n",
+ " <td>229.0</td>\n",
+ " <td>323.0</td>\n",
+ " <td>4.067000e-06</td>\n",
+ " <td>...</td>\n",
+ " <td>87.0</td>\n",
+ " <td>36.0</td>\n",
+ " <td>1.0</td>\n",
+ " <td>15.0</td>\n",
+ " <td>100.0</td>\n",
+ " <td>586.0</td>\n",
+ " <td>672.0</td>\n",
+ " <td>1.309000e-06</td>\n",
+ " <td>298.0</td>\n",
+ " <td>83.675347</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>10209</th>\n",
+ " <td>7k5b</td>\n",
+ " <td>0.324</td>\n",
+ " <td>410.0</td>\n",
+ " <td>262.0</td>\n",
+ " <td>9.0</td>\n",
+ " <td>1.0</td>\n",
+ " <td>401.0</td>\n",
+ " <td>1865.0</td>\n",
+ " <td>2268.0</td>\n",
+ " <td>3.414000e-31</td>\n",
+ " <td>...</td>\n",
+ " <td>302.0</td>\n",
+ " <td>202.0</td>\n",
+ " <td>17.0</td>\n",
+ " <td>1.0</td>\n",
+ " <td>285.0</td>\n",
+ " <td>4.0</td>\n",
+ " <td>262.0</td>\n",
+ " <td>3.768000e-11</td>\n",
+ " <td>540.0</td>\n",
+ " <td>93.212818</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>...</th>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>9754</th>\n",
+ " <td>7obq</td>\n",
+ " <td>0.389</td>\n",
+ " <td>444.0</td>\n",
+ " <td>247.0</td>\n",
+ " <td>11.0</td>\n",
+ " <td>49.0</td>\n",
+ " <td>486.0</td>\n",
+ " <td>2.0</td>\n",
+ " <td>427.0</td>\n",
+ " <td>2.292000e-21</td>\n",
+ " <td>...</td>\n",
+ " <td>629.0</td>\n",
+ " <td>361.0</td>\n",
+ " <td>14.0</td>\n",
+ " <td>2.0</td>\n",
+ " <td>609.0</td>\n",
+ " <td>1.0</td>\n",
+ " <td>617.0</td>\n",
+ " <td>1.823000e-32</td>\n",
+ " <td>1849.0</td>\n",
+ " <td>79.526873</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>9809</th>\n",
+ " <td>7lht</td>\n",
+ " <td>0.326</td>\n",
+ " <td>147.0</td>\n",
+ " <td>81.0</td>\n",
+ " <td>4.0</td>\n",
+ " <td>15.0</td>\n",
+ " <td>152.0</td>\n",
+ " <td>632.0</td>\n",
+ " <td>769.0</td>\n",
+ " <td>2.676000e-08</td>\n",
+ " <td>...</td>\n",
+ " <td>150.0</td>\n",
+ " <td>96.0</td>\n",
+ " <td>7.0</td>\n",
+ " <td>17.0</td>\n",
+ " <td>153.0</td>\n",
+ " <td>9.0</td>\n",
+ " <td>156.0</td>\n",
+ " <td>3.172000e-08</td>\n",
+ " <td>361.0</td>\n",
+ " <td>82.121069</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>982</th>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>...</td>\n",
+ " <td>529.0</td>\n",
+ " <td>299.0</td>\n",
+ " <td>14.0</td>\n",
+ " <td>1.0</td>\n",
+ " <td>493.0</td>\n",
+ " <td>20.0</td>\n",
+ " <td>476.0</td>\n",
+ " <td>1.429000e-14</td>\n",
+ " <td>650.0</td>\n",
+ " <td>66.836215</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>9821</th>\n",
+ " <td>5ulm</td>\n",
+ " <td>0.465</td>\n",
+ " <td>234.0</td>\n",
+ " <td>120.0</td>\n",
+ " <td>3.0</td>\n",
+ " <td>180.0</td>\n",
+ " <td>411.0</td>\n",
+ " <td>3.0</td>\n",
+ " <td>233.0</td>\n",
+ " <td>1.048000e-14</td>\n",
+ " <td>...</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>87.248447</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>9978</th>\n",
+ " <td>4c8a</td>\n",
+ " <td>0.138</td>\n",
+ " <td>159.0</td>\n",
+ " <td>110.0</td>\n",
+ " <td>9.0</td>\n",
+ " <td>26.0</td>\n",
+ " <td>164.0</td>\n",
+ " <td>2.0</td>\n",
+ " <td>153.0</td>\n",
+ " <td>3.096000e-08</td>\n",
+ " <td>...</td>\n",
+ " <td>322.0</td>\n",
+ " <td>221.0</td>\n",
+ " <td>14.0</td>\n",
+ " <td>1.0</td>\n",
+ " <td>302.0</td>\n",
+ " <td>11.0</td>\n",
+ " <td>324.0</td>\n",
+ " <td>1.106000e-19</td>\n",
+ " <td>810.0</td>\n",
+ " <td>74.847840</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "<p>696 rows × 34 columns</p>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " pdb target pdb seq. id. pdb alignment length pdb no. mismatches \\\n",
+ "query \n",
+ "10001 4x92 0.236 199.0 139.0 \n",
+ "10038 1uf1 0.475 124.0 60.0 \n",
+ "10121 3zk4 0.342 146.0 85.0 \n",
+ "10166 6r84 0.421 95.0 52.0 \n",
+ "10209 7k5b 0.324 410.0 262.0 \n",
+ "... ... ... ... ... \n",
+ "9754 7obq 0.389 444.0 247.0 \n",
+ "9809 7lht 0.326 147.0 81.0 \n",
+ "982 NaN NaN NaN NaN \n",
+ "9821 5ulm 0.465 234.0 120.0 \n",
+ "9978 4c8a 0.138 159.0 110.0 \n",
+ "\n",
+ " pdb no. gap open pdb query start pdb target start pdb query end \\\n",
+ "query \n",
+ "10001 5.0 1.0 197.0 186.0 \n",
+ "10038 3.0 57.0 180.0 10.0 \n",
+ "10121 3.0 6.0 140.0 405.0 \n",
+ "10166 2.0 9.0 100.0 229.0 \n",
+ "10209 9.0 1.0 401.0 1865.0 \n",
+ "... ... ... ... ... \n",
+ "9754 11.0 49.0 486.0 2.0 \n",
+ "9809 4.0 15.0 152.0 632.0 \n",
+ "982 NaN NaN NaN NaN \n",
+ "9821 3.0 180.0 411.0 3.0 \n",
+ "9978 9.0 26.0 164.0 2.0 \n",
+ "\n",
+ " pdb target end pdb e value ... swp alignment length \\\n",
+ "query ... \n",
+ "10001 373.0 9.148000e-15 ... 207.0 \n",
+ "10038 128.0 2.325000e-11 ... NaN \n",
+ "10121 550.0 2.610000e-12 ... 146.0 \n",
+ "10166 323.0 4.067000e-06 ... 87.0 \n",
+ "10209 2268.0 3.414000e-31 ... 302.0 \n",
+ "... ... ... ... ... \n",
+ "9754 427.0 2.292000e-21 ... 629.0 \n",
+ "9809 769.0 2.676000e-08 ... 150.0 \n",
+ "982 NaN NaN ... 529.0 \n",
+ "9821 233.0 1.048000e-14 ... NaN \n",
+ "9978 153.0 3.096000e-08 ... 322.0 \n",
+ "\n",
+ " swp no. mismatches swp no. gap open swp query start swp target start \\\n",
+ "query \n",
+ "10001 132.0 5.0 2.0 201.0 \n",
+ "10038 NaN NaN NaN NaN \n",
+ "10121 86.0 3.0 6.0 140.0 \n",
+ "10166 36.0 1.0 15.0 100.0 \n",
+ "10209 202.0 17.0 1.0 285.0 \n",
+ "... ... ... ... ... \n",
+ "9754 361.0 14.0 2.0 609.0 \n",
+ "9809 96.0 7.0 17.0 153.0 \n",
+ "982 299.0 14.0 1.0 493.0 \n",
+ "9821 NaN NaN NaN NaN \n",
+ "9978 221.0 14.0 1.0 302.0 \n",
+ "\n",
+ " swp query end swp target end swp e value swp bit score plddt \n",
+ "query \n",
+ "10001 229.0 421.0 1.621000e-15 630.0 88.311832 \n",
+ "10038 NaN NaN NaN NaN 66.247545 \n",
+ "10121 202.0 347.0 4.720000e-13 546.0 91.322817 \n",
+ "10166 586.0 672.0 1.309000e-06 298.0 83.675347 \n",
+ "10209 4.0 262.0 3.768000e-11 540.0 93.212818 \n",
+ "... ... ... ... ... ... \n",
+ "9754 1.0 617.0 1.823000e-32 1849.0 79.526873 \n",
+ "9809 9.0 156.0 3.172000e-08 361.0 82.121069 \n",
+ "982 20.0 476.0 1.429000e-14 650.0 66.836215 \n",
+ "9821 NaN NaN NaN NaN 87.248447 \n",
+ "9978 11.0 324.0 1.106000e-19 810.0 74.847840 \n",
+ "\n",
+ "[696 rows x 34 columns]"
+ ]
+ },
+ "execution_count": 10,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "foldseek"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 15,
+ "id": "c53c1eb6-81de-409f-82aa-4db231b51fe3",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "/opt/conda/lib/python3.9/site-packages/pandas/core/arraylike.py:364: RuntimeWarning: divide by zero encountered in log\n",
+ " result = getattr(ufunc, method)(*inputs, **kwargs)\n"
+ ]
+ },
+ {
+ "data": {
+ "text/plain": [
+ "<matplotlib.collections.PathCollection at 0x7fa5c9a4c850>"
+ ]
+ },
+ "execution_count": 15,
+ "metadata": {},
+ "output_type": "execute_result"
+ },
+ {
+ "data": {
+ "image/png": "iVBORw0KGgoAAAANSUhEUgAAAXcAAAD4CAYAAAAXUaZHAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjQuMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8rg+JYAAAACXBIWXMAAAsTAAALEwEAmpwYAAAjbklEQVR4nO3df5Bc1ZUf8O9Rq4V7ZIcRi3BJY2TJLiyCwiKZKUxKWZfBG2SwMYNZ86O8KapChaSKrSwsmfIoTiE5McnsKl5tqjbZDRtTZmPWSBgsy0UlrNcicYVa2R55RhYyKMZGyGopINuM8UoDmhmd/NHvjbp77n3vvn6/X38/VSrNvOnpvvN65rz7zj33XlFVEBFRtSzJuwFERJQ8BnciogpicCciqiAGdyKiCmJwJyKqoKV5NwAALr74Yl27dm3ezSAiKpUDBw78XFVXmr5WiOC+du1aTExM5N0MIqJSEZFXbV9jWoaIqIIY3ImIKojBnYioghjciYgqiMGdiKiCClEtQ0TUb/ZMNrHj2SM4MT2D1YMNjG5Zj5FNQ4k9P4M7EVHG9kw2sfXpQ5iZnQcANKdnsPXpQwCQWIBnWoaIKGM7nj2yENh9M7Pz2PHskcReg8GdiChjJ6ZnIh3vBYM7EVHGVg82Ih3vBYM7EVHGRresR6Ne6zjWqNcwumV9Yq/BAVUiooz5g6asliEiqpiRTUOJBvNuTMsQEVUQgzsRUQUxuBMRVRCDOxFRBTG4ExFVEIM7EVEFMbgTEVUQgzsRUQUxuBMRVRCDOxFRBTG4ExFVEIM7EVEFMbgTEVUQgzsRUQVxyV+iitkz2Ux1nXAqBwZ3ogrZM9nE1qcPLWy+3JyewdanDwEAA3yfYVqGqEJ2PHtkIbD7ZmbnsePZIzm1iPLC4E5UISemZyIdp+picCeqkNWDjUjHqboY3IkqZHTLejTqtY5jjXoNo1vW59QiygsHVIkqxB80ZbUMMbgTVczIpiEGcwpPy4jIpSLynIi8KCKHReT3veMXici3ROTH3v8r2r5nq4i8LCJHRGRLmj8AEREt5pJznwPwoKr+fQDXArhPRK4AMAbg26p6GYBve5/D+9qdADYA+BiA/yIiNeMzExFRKkKDu6qeVNUfeB//GsCLAIYA3ALgMe9hjwEY8T6+BcATqvq2qr4C4GUA1yTcbiIiChAp5y4iawFsAvBdAO9W1ZNA6wIgIpd4DxsCsL/t2457x7qf614A9wLAmjVrIjeciKqPSyn0zrkUUkTeCeApAPer6ptBDzUc00UHVB9R1WFVHV65cqVrM4ioT/hLKTSnZ6A4v5TCnslm3k0rBafgLiJ1tAL746r6tHf4NRFZ5X19FYDXvePHAVza9u3vAXAimeYSUb/gUgrxuFTLCIAvAXhRVf+47Ut7AdztfXw3gG+0Hb9TRC4QkXUALgPwveSaTET9gEspxOOSc98M4J8AOCQiU96xfw1gHMBuEbkHwDEAnwYAVT0sIrsB/AitSpv7VHV+0bMSEQVYPdhA0xDIuZSCm9Dgrqr/B+Y8OgB81PI9DwN4OEa7iKjPjW5Z37F8McClFKLgDFUiKiQupRAPgzuVDsvj+geXUugdgzuVCncaInLDJX+pVFgeR+SGPXcqFZbHRcMUVv9iz51KhTsNueMMz/7G4E6lwp2G3DGF1d+YlqFSYXmcO6aw+huDO5UOy+PccIZnf2NahqiiqpLC2jPZxObxfVg39gw2j+/jmIEj9tyJKqoKKSzOa+gdgztRhZU9hRU0KFzmnysLTMsQUWFxULh3DO5EVFic19A7BnciKqyqDArngTl3oj6W5/IELq9dhUHhvDC4E/WpPCtRorx22QeF88LgTtSnwpYnSLO3zCqY9DG4E/UpW8WJ34tOs0fPKpj0cUCVKEVFnl1pqzipiaS+4BirYNLH4E6FU+SAGEXRl9y1VaLMqxofn2SvmlUw6WNwp0IpekBsF3YRKvqSuyObhvAfPnUlhgYbEABDg42Fz02S7FXbXpv59uQw506FUpaBNpdqjzLklW2VKO0/G5BOr5pVMOliz50KxbRELVCsgAi49crLmldmr7oa2HOnwtgz2YQAMGV8ixYQXXrlo1vWZ9IDTgN71eXHnjsVxo5njxgDuwCFC4guvXL2gClP7LlTYdh6w4rird3t2iuP0wPOc2kAKj8GdyoM27ZwtuqNPKW95gk3qaC4GNypMMqWo04zL12WqiEqLgZ3KoyqrwAYJc1ShjJKKjYGdyqUqlZpRE2z2FJURasaouJitQxRBqLOVuX0fIqLPfc+wcqLfEVNs1Q9RUXpY3DvA6y8yF8vaZaqpqgoG6FpGRF5VEReF5EX2o5tF5GmiEx5/25q+9pWEXlZRI6IyJa0Gk7uir6AVT9gmoWy5tJz/zKAPwXwl13Hd6rqf2w/ICJXALgTwAYAqwH8jYh8QFXnQblh5UX+skyzMAVHgENwV9XviMhax+e7BcATqvo2gFdE5GUA1wD4296bSHGx8qIYskizMAVHvjjVMr8nIj/00jYrvGNDAH7W9pjj3rFFROReEZkQkYlTp07FaAaFue7ylZGOU3kxBUe+XoP7nwF4P4CNAE4C+KJ3XAyPNW7roqqPqOqwqg6vXMkg0yuXXYuee8l88bQdp/JiCo58PQV3VX1NVedV9RyAv0Ar9QK0euqXtj30PQBOxGsi2bjuWsQ/+P5R1jXkKXk9BXcRWdX26a0A/EqavQDuFJELRGQdgMsAfC9eE8nG9Racf/D5irInbNz9Y1mVQ77QAVUR+SqAjwC4WESOA9gG4CMishGtlMtRAP8cAFT1sIjsBvAjAHMA7mOlTHpce+RlW5CrSqIMcCYxGMrJT+RzqZa5y3D4SwGPfxjAw3EaRW5cq2D4B5+fKKs7JrUSJCc/EcAZqqUWpUfOP/h8RBnv4NgIJYnBvcTS6pFzEkxyoswx4HwEShKDe8kl3SMv4ySYIl+MotxdcWyEksQlf6lD2SbBuJaD5iXKJtncUJuSxJ47dShb3rcM29FFubvi2AglhcGdOrjkfYuUBinbxYgoK0zLUIewSTBFS4NwghaRGYM7dQjL+xYtJ88ZmURmTMvQIkF536KlQThBi8iMwZ0iKWItdlUGIYs0lkHlx7QMRcI0SDqKNpZB5ceeOy1w6TkyDZKOMpR0UrkwuKMct8NptzHKzNSypUFM5w4o1gWqaGMZVH59H9zLMN0+iTaGXRyq2nM0nbvRJw8CAszO68KxvN5z/30xblcGlnRS7/o+51600j6TuG10yefm3XOMu0mFjenczZ7ThcDuy+M9b39fTDiWQXH0fc8976DmIm4bXXrleVbBpHn3FOV9tD02akrM9fGm98U3VIBUEZVb3/fcyzDDMW4bXS4OeVbBpHn3FOV9ND02ahVLlMfb3hcB8PzY9QzsFEvfB/cylPbFbaPLxcFlRcK0Uidp3j2Zzl19iaBek45jtvMZ9cIT5fGDA3Xjc9iOE0XR92mZMpT2xW2j6zrhQVUwaaZO0kwJ2c6d6Zjp54h64YlyXC2jqLbjRFH0fXAHylHaF6eNSVzA0qymSXqTClPO+/mx6xc9zqXdtgvPhY06No/vW3Q+o1yofjUza3xN23GiKBjcM5ZXTX3cC1jc1EnQz53k3VPSdximC099ieD02TlMe0G4/TVGt6zH6JMHMXtOOx5vulAVcSkHqg4G9wyVoabeJk4gcvm5k7p7SuIOo/tCdNvVQ3jupVMLn585O4c3znT2rv3XGN2yvjUi2q77cw+31aM0iRYgwTc8PKwTExN5NyN1m8f3GQPkYKOO5RcszS3n73I30R2ggVYgMm0D1/18p98+38ttNzTYwPNj1yd6N7Nu7BnjhCAB8Mr4x0O/3+XnDHoN20XQ/1lNr1fk8R4qNhE5oKrDpq+x596DXv8gbSmM6ZlZ4y1+Fn/krncTrqkT0/PZnJieSfxuJm6qI+6cgKjpqzKM91A5MbhHFBaMggK/LSh0y3Laf5Q0hksgCpqY0231YCOxgVr/vDenZyBAR886SqrDJThfd/lKPL7/mPE1/DZ0Yx6dssbgHlFYHXNQ4DflWG2ymiGbdI256/f5wfCBXVOxX7/7gtsedFcM1LHt5g3OF4qw6hjTxUMA3Hb1+Qsf8+hUBH0/iSmqoGAYFvhNE4VWWCasZNXTS3qGru37VgzUjROkknj9oLuFt2bPOT8PYJ/0dPrs3ELQ7863K4DnXjoFwG0yGFEW2HOPKG6+tTu1YRvAs/X0kh6AS7piw/Z8tt5zEq8f1MuPmuIxjS2YqmOC2sA8OhUBe+4RBS0FYOttLhGxTtWP0tNLY7eepHuaUZ8vidcP6+VHTTGNbBrC82PX45Xxj+P5sesxHRLYXdpAlDWWQvbA1ns29cJ9trLBKGyllLYyu34RdN6B4PPjcidkO+++JN5bol4ElUIyuCdsz2QTD+4+iHnDeXUJwkHBJm4Nd1XYdlb6/DcPL0qfNOq1RZOQgi7GpkBtepw/qMqleSlPQcGdaZmEjWwawjnLBTMsPRCWdinD8sRps50jAJh86Ab8yR0bO1I8t109hKcONI3n1HUFR1PqaOcdG3HUS9swsFMRcUA1Bb1OpAmr+e5l8LFqMyDDzlH3YObm8X3Gx9vurgDzRZiDpFQ27LmnoNf118OqbaIOPqYxAJu3KHX5eyab1ly5LbAD/XUnRNXFnnsKokzVb3/M4EDdWHLXvamGaw+yCpted5+jCxt14zo13QHZv7BFxQlHVBWhwV1EHgXwCQCvq+o/8I5dBGAXgLUAjgK4XVXf8L62FcA9AOYB/EtVfTaVlhdcWBA2LWPg7xDUvnlzlGDTHQhtvdYi7Q8bxHiOaoL6EulYUtd0jqIsg+Dj4ChViUvP/csA/hTAX7YdGwPwbVUdF5Ex7/PPisgVAO4EsAHAagB/IyIfUNVof2UlESefbQo+s+e05xUiTYGwe5q8rwxpB1vVkX/hq4lgXtUakKNewPq9nJSqJzS4q+p3RGRt1+FbAHzE+/gxAP8LwGe940+o6tsAXhGRlwFcA+BvE2qvs7QHEuOuZmgLPr+amcXUthsit8d0sVAg1iJaefHPbVBefF514WcxnW/XRdqAcpwToqh6HVB9t6qeBADv/0u840MAftb2uOPesUVE5F4RmRCRiVOnTvXYDLMsBhKjbpzcLemyRtvFwq/FLtM6J64plZnZedy/a8q4WbdpUNtXrwkGG/VSnROiqJIeUDXtOWPsfqnqIwAeAVqTmJJ48fZlX7slPZAYdzXFpNd0ibpJRFEFVbjY2HZ2ArDw+xCWxiGqml6D+2siskpVT4rIKgCve8ePA7i07XHvAXAiTgNdhU1BB5IdSIy7KUSS+4YC1diyrdcKF8B88WZtOvWzXtMyewHc7X18N4BvtB2/U0QuEJF1AC4D8L14TXTjciuf5ECirZb9ustXYvP4Pqwbe8aYLmjnL1C1846NAIAHLCkGF1VYajboPfSrZIKUpQqIKAsupZBfRWvw9GIROQ5gG4BxALtF5B4AxwB8GgBU9bCI7AbwIwBzAO7LqlIm7A87TkmhqUdt6nlfd/lKPHWgGWmQNclt5sreUw16D3f8zlWt/y1pN6AcVUBEWanMwmFBK/dFybOa0jv1mmD5sqX41cysMdgH5frbX990wSjLSo9ZLGPgei6ibNZNVGV9sUG2Lecc9Q/eWH8+r9YNrF1y/f73mHrnUafT57FOTNKbWNu4jhv4r7l97+GF9+Udda6kQdSuMn8RSeWcXfK27SWPLrn+moi1bNK1JDKPdWL2TDaxeXwf7t81ZWz/5795ONHXi/oevj13fgu9N87Mln7dHKIkVabnDiSTc3ad/OJfBFxy/bbgf2J6Bjvv2OjUW816nRiXO5I3zsxiz2Qz0dd3WbYhq3JXojKrTM+9m9/rdKlaaRc0+aWd37MOGsTze55DAb1z195q3Lr6qFwnErlO2nIR9p61373YsGKGqKVSPXdfnBxxdxXM4EAdf/fWnHWhKtdcf1Dv3NRb7XU1xKS4BsmkgqnLe5Z1uStRmVUyuEdNYXQH0usuX7nwtYFlS/Hx31xl3KYNcJuMFHXCUpzVEG3PF3Ug1jU95QfTuIO9Lu9ZkuWuRFVXyeAetQKlO5B+Zf+xha83p2fw1IFm4MCeS64/7jrss/OKFQN1DCxzXzFyz2Rz0b6irncxpjsS2+PCet2mi2f3xdLlPQu64HBZAaJOlQzuUZYGcLnVz3qgzhbops/MYvIhtxUjgwZEXX4e/2umTad9KwbqC7X6pl739r2HjReX7ovn1qcPOaWdkip3JeoHlQju3T3Dtb/RwAmvZNBnu2WPmls2pR+A5NaIAeKvW+O3J4l1dt6cmTMeFwDbbt4Q+FymYG0yMzuPd9SXLKos6n7Pkl6Ph6jKSh/cTSmB7sAoAG672pwWiZJbNr3W6JMHATm/iUQSE3ySWAQsLHiHXSjC1lT3j24e32de9jOi6TOz2HnHRqdlHxjMicKVPri7pFUUwHMvmdeMd8kt+4HVtntSt7hpnCR6qEEXLUHrIrR5fJ/1ecPO62Cj7pSTj9JeBm6i5JQ+uMct2bMtAGaqjnlg11Ti7bKJG+iCLlr+5aj9LgPoPAdhdzNvvjULw3UNQGtG7gVLBWdmz5kf0IVVLkTJK31wj1qyZ+IaSKNs3ZZ3vbXponXm7NyiwVF/GYG3Zs91pJvC2AI70NoC7+15LCrdBFo9/k9cZS8tJaJklD64R0mruAiq1x7dsh73O/Tei9IT7b5orRt7xvg4WzVMHPPnFO9YVsMlA8sYxIlyUPrgHiWtEiasXntk05C1NLAmgnOqqQaxuBOFotx5JOH02Xkc/rfFWbaYqJ+UPrgDyVVQ2GZJPrj74MLrbLt5Q2q11kHBO4lld21VOAJ1zo8TUTlUIrgntc65bRB0XtW4zkmS6Yaw4J3EqpC2tm/feziV4D7YqCf+nETkpvTBPcmNJILSFu2BNI2SvbDgndSqkKa2R6kCclVfItj+yQ2JPy8RuSn9kr9BQdHnuvxv2HK/LoE06lLD/uNtFxX/uOumHr1IurKnJoIdn76Kg6dEOSp9zz2sRxulZ+9//uDug8aZma6zOl3vIlw2xKiJAAietdprWqp94wsBEplpCgDnVBnYiXJW+p57WI/WpWffbmTTEL54+1WLevAu5Y1RX8tldq1/kbFt6gGgp+339kw2Mfq1gwt3Bkluk553jT8RVaDnHrYOSy+5atdB0+4esy21Ejdf3r5MQHcbbCsyhg20fv6bhxfWw4mju8dflBp/on5X+uAeFohtQXeJCNaNPdPzAlWmFIwttRF0d+FSd96cnsEDu6Yw8eov8YWRKzu+1uuFI+7EJQGw846NALhKI1ERlT64A8GB2DaD1U939FpdY0qpKKL1ZF1nvPrP/fj+Yxh+70Ud7bRdIBQwLgzm323EpTh/vhjMiYqnEsG9W3e65LarhxZmrC4RWTRYGpbGMA1Y2nrGilY+3KUnGzTj1fbc3e0MWn6hOT2D+3dN4cmJYzj6i5lEB05tm34TUTFULrib0iXt2+TZ1lexBWvT8z2wawoDy2o4fXZxQB0abOD5Mfcp99tu3uDceze1sz0tZUvxPP+TXy58nNTAafs+s0RUPKWvlukWVrESVl3TXae+fe9hY/rl9Nl51GvScbyXwcSRTUNYMeA+k9PU/pFNQ5EuKCZiONao16xts62PT0TFUPqee9SKlbB68e5eepClSwTnzrXy9zUR625PQe0d3bLeuF6Nie3iETePbkrVrBioY9vNG6yzV+OuV09E6Sp1cO+lYiWousZUVhhkpm09lnlVPHWguWjAM6y9D+yagqK1Dsvs/DnMWRZKHwoox4y7I5LpFQeWLV1Y0ybufq5ElL1SB/deK1Zs1TVxe6NhA7O29gLhm0n72/w9sGuq44LkMhGqFy53OkRUXKUO7nErVrpTJBc26sYgu3xZDWfOzjsNRgZdIOKspW5b1iCt9IjLnQ4RFVepg7stx+5SsWJKkdRrsmhruEa9hodvbU0c8gNcUJAPSlfUDGWYrmzrzA8O1BPfScn1ToeIiqvUwT3OYlqmdMbsvGLFQB0Dy5Yav8//37aKo3htsr12r4HdZl4Vf/fWXOznWb6shkFuh0dUKaUO7raUAWBPY/jfY0tnTJ+ZxeRDNywE6Ad2TWHHs0cW7aXafVERAJ+5dk3r6187uLBuS3N6BqNfa+3kNJTCNnez5zTSxKR6TTrWlKnXBA/fGn8XKSIqFtEYvUkROQrg1wDmAcyp6rCIXARgF4C1AI4CuF1V3wh6nuHhYZ2YmOi5Hd1sPWu/4iRowk9NBHd96FI8daAZuJVed+/c37fV9rx+aWHcyhYblwDf/vOzl05UfiJyQFWHjV9LILgPq+rP2479EYBfquq4iIwBWKGqnw16niSCe3uwDfqJGvVaaHC1BUpbLt+1HNHvucfJvdue97rLV+Lx/cesP3t9CTfQIKqaoOCexgzVWwA85n38GICRFF6jgx9cmyGBvSbi1Gu2PUdzesa4TrprOaLfq59XRaNewxLTtNAejG5Zjy+MXImdd2xcWPNF2p57sFFnYCfqM3F77q8AeAOtePhfVfUREZlW1cG2x7yhqisM33svgHsBYM2aNVe/+uqrPbcjaJs6n0uP3UWjXutYiMx12d60rBioY/KhG3J7fSLKT5o9982q+kEANwK4T0Q+7PqNqvqIqg6r6vDKlfEWoQoLrv6uRUmsZDgzO4/H9x/r2PkooQ54ZI16Ddtu5ibURLRYrGoZVT3h/f+6iHwdwDUAXhORVap6UkRWAXg9gXZahW0n150nT2JAs/tex3Tv4+fthwYbOP32nHFyVJzld/0BWqZaiMik5567iCwXkXf5HwO4AcALAPYCuNt72N0AvhG3kUG27z0c+PX2jbJdcuNJ9MJFWmWRR8c/jtEt6zvy3+3iDKm+1bauDRFRtzg993cD+Lq0ItdSAH+lqv9TRL4PYLeI3APgGIBPx2+mXdiaLKsHG5EW10qihkUV+Mr+Y/jK/mMJPJuZyz6pRNS/eg7uqvpTAFcZjv8CwEfjNCop/mzVJBfXWr6shrNz5zqWKMgLl90lIptSb9axZ7JpLScUwcKkoySD4Omz85hLeBmBXnHZXSKyKW1w91Mtpg50vSbYefvGhZRF0kGwCLGdy+4SUZDSri0TlGqZndeOnYlOv714ca3aEsEFNcGZEgxMDjbq+MRVqzpq67lsABEFKW1wD0u1LCzYpTDmx5cA+Pef+k0AwOe/eTjxZXOTYNt9iYgoTGnTMi6pltl5tQ58zp5TPLi7tVrj5EM3YPmymvFxQUsEpDl5qSaC58euZ2Anop6UNriPblkfO7jOq2Lr04ewZ7KJM2fNKZ6gopg0U+/zqtg8vi90khYRkUlpg/vIpqGF9dPj8OvFi1h54q9DzwBPRFGVNrgDwBdGrsTvXrsmdg/+xPRMIncCafAvPkREUZQ6uO+ZbOK5l07FTo+sHmxgZNNQqmkWmyVorRMTdGHhZCUiiqq01TJRlhQI05yewdqxZxJoVTSDjTq2f3JD6N6sRUwZEVGxlbbnnuSSAnlo1GsdgR1oDRI36rVFj+NkJSKKqrTBveypClMufWTT0MK684Lz69CzHJKIoiptWibvHZCSYGr/yKYhBnMiiq20PffRLetRd9yEtGZbUD1ngvDNRoiIelHa4D6yaQjvfEf4jUdNBHd96NJCljkqwDJHIkpFaYM7AKf1YOZV8dSBZi5lji7KPnZARMVU2uD+b/Yccn5sFlU1jfr5U7lioI7fvXbNosoXE5Y5ElEaSjug+tXv/izvJiwQAV78dzcuOj783ouw49kjODE9gwsbdZw+O4fZ+fP3ECxzJKK0lLbnPl+EHTM8qp0Do3smm9g8vg8P7JoCAOy8YyOmtt2AHb9zFcsciSgTpe2510QKFeC3Pn2o42M/FeQv/gWwzJGIslPanvtdH7o07yZ08CclmWbOcvEvIspaaXvuXxi5EgDwlf3Hcm7JeUGVL6yKIaIslbbnDrQGLF0qUrKyerBhrX5hVQwRZanUwb1Ii4f5lS9c/IuIiqC0aRnAvDZLEkQAKHBhow4RYPrMLFYPNnDm7Jxx4lRNZFHli18CuZqbXBNRDkob3NNak6VRr1lLFE1ryJsez6oYIspbaYP79r2HE3/OFQN1bLt5gzUw+8fZKyeioittcJ+eCV9XJooVA3VMPnRD6OPYKyeiMij1gGpSGvUatt28Ie9mEBElpu+D+2CjzmUAiKhySpuWiWv5shoevpVBnYiqqS+D+9BgA8+PXZ93M4iIUtN3aRkBOKGIiCqvtMF98/svivw9AuAz165hKoaIKq+0wf3xf/YPcdkly0Mf5++dOjTYwM47Ni4sOEZEVGWp5dxF5GMA/hOAGoD/pqrjSb/Gt/7gI9gz2eSkIiKiLqkEdxGpAfjPAP4xgOMAvi8ie1X1R0m/FicVEREtllZa5hoAL6vqT1X1LIAnANyS0msREVGXtIL7EID2HayPe8cWiMi9IjIhIhOnTp1KqRlERP0preAuhmMdG56q6iOqOqyqwytXrkypGURE/Smt4H4cQPsmp+8BcCKl1yIioi5pBffvA7hMRNaJyDIAdwLYm9JrERFRF1HV8Ef18sQiNwH4E7RKIR9V1YcDHnsKwKtdhy8G8PNUGte7IrYJKGa7itgmoJjtYpvcFbFdebbpvapqzGunFtzjEpEJVR3Oux3titgmoJjtKmKbgGK2i21yV8R2FbFNQIlnqBIRkR2DOxFRBRU5uD+SdwMMitgmoJjtKmKbgGK2i21yV8R2FbFNxc25ExFR74rccycioh4xuBMRVVDhgruIfExEjojIyyIylmM7LhWR50TkRRE5LCK/7x3fLiJNEZny/t2UcbuOisgh77UnvGMXici3ROTH3v8rMm7T+rbzMSUib4rI/VmfKxF5VEReF5EX2o5Zz42IbPV+z46IyJaM27VDRF4SkR+KyNdFZNA7vlZEZtrO2Z9n2Cbr+5XFubK0aVdbe46KyJR3PKvzZIsDuf9ehVLVwvxDa8LTTwC8D8AyAAcBXJFTW1YB+KD38bsA/F8AVwDYDuBf5XiOjgK4uOvYHwEY8z4eA/CHOb+H/w/Ae7M+VwA+DOCDAF4IOzfee3kQwAUA1nm/d7UM23UDgKXex3/Y1q617Y/L+FwZ36+szpWpTV1f/yKAhzI+T7Y4kPvvVdi/ovXcC7NUsKqeVNUfeB//GsCL6FrZskBuAfCY9/FjAEbyawo+CuAnqto94zh1qvodAL/sOmw7N7cAeEJV31bVVwC8jNbvXybtUtW/VtU579P9aK2/lBnLubLJ5FwFtUlEBMDtAL6a9OuGtMkWB3L/vQpTtOAeulRwHkRkLYBNAL7rHfo973b60axTIGitrvnXInJARO71jr1bVU8CrV9GAJdk3KZ2d6LzDzDPcwXYz02Rftf+KYD/0fb5OhGZFJH/LSK/lXFbTO9XEc7VbwF4TVV/3HYs0/PUFQcK/3tVtOAeulRw1kTknQCeAnC/qr4J4M8AvB/ARgAn0bpVzNJmVf0ggBsB3CciH8749a2ktUjcJwE86R3K+1wFKcTvmoh8DsAcgMe9QycBrFHVTQD+AMBficjfy6g5tverCOfqLnR2GjI9T4Y4YH2o4VguMaxowb1QSwWLSB2tN/RxVX0aAFT1NVWdV9VzAP4CGd9yqeoJ7//XAXzde/3XRGSV1+ZVAF7Psk1tbgTwA1V9zWtjrufKYzs3uf+uicjdAD4B4DPqJWy92/lfeB8fQCtn+4Es2hPwfuV6rkRkKYBPAdjV1tbMzpMpDqDAv1e+ogX3wiwV7OX4vgTgRVX947bjq9oediuAF7q/N8U2LReRd/kfozUo9wJa5+hu72F3A/hGVm3q0tG7yvNctbGdm70A7hSRC0RkHYDLAHwvq0ZJawP5zwL4pKqeaTu+Ulp7EENE3ue166cZtcn2fuV6rgD8NoCXVPW4fyCr82SLAyjo71WHPEZxQ0anb0JrRPonAD6XYzv+EVq3Uz8EMOX9uwnAfwdwyDu+F8CqDNv0PrRG4g8COOyfHwC/AeDbAH7s/X9RDudrAMAvAFzYdizTc4XWheUkgFm0elD3BJ0bAJ/zfs+OALgx43a9jFZu1v/d+nPvsbd57+1BAD8AcHOGbbK+X1mcK1ObvONfBvAvuh6b1XmyxYHcf6/C/nH5ASKiCipaWoaIiBLA4E5EVEEM7kREFcTgTkRUQQzuREQVxOBORFRBDO5ERBX0/wE7ux43TbYu1AAAAABJRU5ErkJggg==\n",
+ "text/plain": [
+ "<Figure size 432x288 with 1 Axes>"
+ ]
+ },
+ "metadata": {
+ "needs_background": "light"
+ },
+ "output_type": "display_data"
+ }
+ ],
+ "source": [
+ "fig, ax = plt.subplots()\n",
+ "ax.scatter(-np.log(foldseek[\"pdb e value\"]), -np.log(foldseek[\"afdb e value\"]))"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 22,
+ "id": "7677f488-71e3-4591-80b3-e82bcfc85f04",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "image/png": "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\n",
+ "text/plain": [
+ "<Figure size 432x288 with 1 Axes>"
+ ]
+ },
+ "metadata": {
+ "needs_background": "light"
+ },
+ "output_type": "display_data"
+ }
+ ],
+ "source": [
+ "fig, ax = plt.subplots()\n",
+ "ax.scatter(foldseek[\"plddt\"], -np.log(foldseek[\"pdb e value\"]))\n",
+ "ax.set_xlabel(\"avg. pLDDT\")\n",
+ "ax.set_ylabel(\"-log(eval)\")\n",
+ "ax.set_title(\"AlphaFold reconstruction confidence vs PDB foldseek score\");"
+ ]
+ }
+ ],
+ "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": "3.9.6"
+ }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}
diff --git a/fs_query.sh b/fs_query.sh
new file mode 100755
index 0000000000000000000000000000000000000000..3cba3ae89156a55f295b61cf35f034d284ae20ed
--- /dev/null
+++ b/fs_query.sh
@@ -0,0 +1,19 @@
+#!/bin/bash -ex
+#SBATCH -J mkquery
+#SBATCH -t 60:00
+#SBATCH -c 16
+#SBATCH -N 1
+#SBATCH --mem=64G
+#SBATCH -o /g/arendt/npapadop/cluster/fs_mkquery.out
+#SBATCH -e /g/arendt/npapadop/cluster/fs_mkquery.err
+
+module load GCC
+module load bzip2
+
+FOLDSEEK="/g/arendt/npapadop/repos/foldseek/build/bin/foldseek"
+STRUCTURES="/scratch/npapadop/spongilla_best_model/"
+cd /scratch/npapadop
+mkdir -p foldseek_spongilla
+cd foldseek_spongilla
+
+$FOLDSEEK createdb "$STRUCTURES" spongilla --threads 16
diff --git a/fs_search_afdb.sh b/fs_search_afdb.sh
new file mode 100755
index 0000000000000000000000000000000000000000..29b403ee9749b5d4b7e15bc1d735d7bb3249c75c
--- /dev/null
+++ b/fs_search_afdb.sh
@@ -0,0 +1,24 @@
+#!/bin/bash -ex
+#SBATCH -J fs_search
+#SBATCH -t 30:00
+#SBATCH -c 16
+#SBATCH -N 1
+#SBATCH --mem=64G
+#SBATCH -o /g/arendt/npapadop/cluster/fs_search.out
+#SBATCH -e /g/arendt/npapadop/cluster/fs_search.err
+
+module load GCC
+module load bzip2
+
+FOLDSEEK="/g/arendt/npapadop/repos/foldseek/build/bin/foldseek"
+QUERYDB="/scratch/npapadop/foldseek_spongilla/spongilla"
+TARGETDB="/scratch/npapadop/foldseek_target/afdb"
+ALIGNMENT="/scratch/npapadop/foldseek_results/afdb"
+cd /scratch/npapadop
+
+"$FOLDSEEK" search "$QUERYDB" "$TARGETDB" "$ALIGNMENT" tmpFolder -a --threads 16
+"$FOLDSEEK" aln2tmscore "$QUERYDB" "$TARGETDB" "$ALIGNMENT" "$ALIGNMENT"_aln_tmscore
+"$FOLDSEEK" createtsv "$QUERYDB" "$TARGETDB" "$ALIGNMENT"_aln_tmscore "$ALIGNMENT"_aln_tmscore.tsv
+"$FOLDSEEK" convertalis "$QUERYDB" "$TARGETDB" "$ALIGNMENT" "$ALIGNMENT"_score.tsv
+
+module unload
\ No newline at end of file
diff --git a/fs_search_pdb.sh b/fs_search_pdb.sh
new file mode 100755
index 0000000000000000000000000000000000000000..62b369cb26a475cc7b1f7bad9624854bd6696a20
--- /dev/null
+++ b/fs_search_pdb.sh
@@ -0,0 +1,24 @@
+#!/bin/bash -ex
+#SBATCH -J fs_search_pdb
+#SBATCH -t 30:00
+#SBATCH -c 16
+#SBATCH -N 1
+#SBATCH --mem=64G
+#SBATCH -o /g/arendt/npapadop/cluster/fs_search_pdb.out
+#SBATCH -e /g/arendt/npapadop/cluster/fs_search_pdb.err
+
+module load GCC
+module load bzip2
+
+FOLDSEEK="/g/arendt/npapadop/repos/foldseek/build/bin/foldseek"
+QUERYDB="/scratch/npapadop/foldseek_spongilla/spongilla"
+TARGETDB="/scratch/npapadop/foldseek_target/pdb"
+ALIGNMENT="/scratch/npapadop/foldseek_results/pdb"
+cd /scratch/npapadop
+
+"$FOLDSEEK" search "$QUERYDB" "$TARGETDB" "$ALIGNMENT" tmpFolder -a --threads 16
+"$FOLDSEEK" aln2tmscore "$QUERYDB" "$TARGETDB" "$ALIGNMENT" "$ALIGNMENT"_aln_tmscore
+"$FOLDSEEK" createtsv "$QUERYDB" "$TARGETDB" "$ALIGNMENT"_aln_tmscore "$ALIGNMENT"_aln_tmscore.tsv
+"$FOLDSEEK" convertalis "$QUERYDB" "$TARGETDB" "$ALIGNMENT" "$ALIGNMENT"_score.tsv
+
+module unload
\ No newline at end of file
diff --git a/fs_search_swissprot.sh b/fs_search_swissprot.sh
new file mode 100755
index 0000000000000000000000000000000000000000..bc1d49af5a1d0ed203ea0421891ecc4be57b6487
--- /dev/null
+++ b/fs_search_swissprot.sh
@@ -0,0 +1,24 @@
+#!/bin/bash -ex
+#SBATCH -J fs_search_swissprot
+#SBATCH -t 30:00
+#SBATCH -c 16
+#SBATCH -N 1
+#SBATCH --mem=64G
+#SBATCH -o /g/arendt/npapadop/cluster/fs_search_swissprot.out
+#SBATCH -e /g/arendt/npapadop/cluster/fs_search_swissprot.err
+
+module load GCC
+module load bzip2
+
+FOLDSEEK="/g/arendt/npapadop/repos/foldseek/build/bin/foldseek"
+QUERYDB="/scratch/npapadop/foldseek_spongilla/spongilla"
+TARGETDB="/scratch/npapadop/foldseek_target/swissprot"
+ALIGNMENT="/scratch/npapadop/foldseek_results/swissprot"
+cd /scratch/npapadop
+
+"$FOLDSEEK" search "$QUERYDB" "$TARGETDB" "$ALIGNMENT" tmpFolder -a --threads 16
+"$FOLDSEEK" aln2tmscore "$QUERYDB" "$TARGETDB" "$ALIGNMENT" "$ALIGNMENT"_aln_tmscore
+"$FOLDSEEK" createtsv "$QUERYDB" "$TARGETDB" "$ALIGNMENT"_aln_tmscore "$ALIGNMENT"_aln_tmscore.tsv
+"$FOLDSEEK" convertalis "$QUERYDB" "$TARGETDB" "$ALIGNMENT" "$ALIGNMENT"_score.tsv
+
+module unload
\ No newline at end of file
diff --git a/predict_structure.sh b/predict_structure.sh
index d63aad301c4604766e9a0567ff2808474fcde751..193de402e3f2c55f1364cf1211463af96662b6a9 100755
--- a/predict_structure.sh
+++ b/predict_structure.sh
@@ -1,8 +1,8 @@
#!/bin/bash -ex
-#SBATCH -J predict
+#SBATCH -J test_colab
#SBATCH -t 30:00
-#SBATCH -o /g/arendt/npapadop/cluster/alphafold.out
-#SBATCH -e /g/arendt/npapadop/cluster/alphafold.err
+#SBATCH -o /g/arendt/npapadop/cluster/alphafold_test.out
+#SBATCH -e /g/arendt/npapadop/cluster/alphafold_test.err
#SBATCH -p gpu
#SBATCH -C gpu=A100
#SBATCH --gres=gpu:1
@@ -15,12 +15,10 @@ module load GCC
module load bzip2
module load CUDA
source ~/.bash_profile
-conda activate /g/arendt/npapadop/repos/condas/maf
+conda activate /g/arendt/npapadop/repos/condas/colabfold
BASE="/scratch/npapadop/"
-BATCH=$1
-cd "${BASE}"
-colabfold_batch msas/"$BATCH"/ spongilla_structures/ --stop-at-score 85
+colabfold_batch "$BASE"/msas/test/ "$BASE"/test_res/ --stop-at-score 85
module unload