batch1 run finished; setting up analysis

.gitignore

+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/
+

analysis/.ipynb_checkpoints/Untitled-checkpoint.ipynb

-{
- "cells": [],
- "metadata": {},
- "nbformat": 4,
- "nbformat_minor": 5
-}

analysis/Untitled.ipynb

-{
- "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
-}

fs_query.sh

+#!/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

fs_search_afdb.sh

+#!/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

fs_search_pdb.sh

+#!/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

fs_search_swissprot.sh

+#!/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

predict_structure.sh

 #!/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