Skip to content

GitLab

"git@developer.sourcefind.cn:OpenDAS/dynamo.git" did not exist on "8af8c82faa2ee8fcab976d9d686e73116d64531b"
Commit e09dd313 authored by jnwei's avatar jnwei
Browse files

Fixes imports to colab notebook.

parent 099769d2
Hide whitespace changes
Inline Side-by-side
Showing with 84 additions and 102 deletions
notebooks/OpenFold.ipynb
View file @ e09dd313
{ {
"nbformat": 4,
"nbformat_minor": 0,
"metadata": {
"accelerator": "GPU",
"colab": {
"name": "OpenFold.ipynb",
"provenance": [],
"collapsed_sections": []
},
"kernelspec": {
"display_name": "Python 3",
"name": "python3"
},
"language_info": {
"name": "python"
}
},
"cells": [ "cells": [
{ {
"cell_type": "markdown", "cell_type": "markdown",
...@@ -57,10 +40,12 @@ ...@@ -57,10 +40,12 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null,
"metadata": { "metadata": {
"id": "rowN0bVYLe9n", "cellView": "form",
"cellView": "form" "id": "rowN0bVYLe9n"
}, },
"outputs": [],
"source": [ "source": [
"#@markdown ### Enter the amino acid sequence to fold ⬇️\n", "#@markdown ### Enter the amino acid sequence to fold ⬇️\n",
"sequence = 'MAAHKGAEHHHKAAEHHEQAAKHHHAAAEHHEKGEHEQAAHHADTAYAHHKHAEEHAAQAAKHDAEHHAPKPH' #@param {type:\"string\"}\n", "sequence = 'MAAHKGAEHHHKAAEHHEQAAKHHHAAAEHHEKGEHEQAAHHADTAYAHHKHAEEHAAQAAKHDAEHHAPKPH' #@param {type:\"string\"}\n",
...@@ -78,16 +63,16 @@ ...@@ -78,16 +63,16 @@
"\n", "\n",
"#@markdown After making your selections, execute this cell by pressing the\n", "#@markdown After making your selections, execute this cell by pressing the\n",
"#@markdown *Play* button on the left." "#@markdown *Play* button on the left."
], ]
"execution_count": null,
"outputs": []
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null,
"metadata": { "metadata": {
"id": "woIxeCPygt7K", "cellView": "form",
"cellView": "form" "id": "woIxeCPygt7K"
}, },
"outputs": [],
"source": [ "source": [
"#@title Install third-party software\n", "#@title Install third-party software\n",
"#@markdown Please execute this cell by pressing the *Play* button on \n", "#@markdown Please execute this cell by pressing the *Play* button on \n",
...@@ -97,75 +82,54 @@ ...@@ -97,75 +82,54 @@
"#@markdown **Note**: This installs the software on the Colab \n", "#@markdown **Note**: This installs the software on the Colab \n",
"#@markdown notebook in the cloud and not on your computer.\n", "#@markdown notebook in the cloud and not on your computer.\n",
"\n", "\n",
"import sys\n", "import os, time\n",
"from IPython.utils import io\n", "from IPython.utils import io\n",
"import os\n", "from sys import version_info\n",
"import subprocess\n", "import subprocess\n",
"import tqdm.notebook\n",
"\n", "\n",
"TQDM_BAR_FORMAT = '{l_bar}{bar}| {n_fmt}/{total_fmt} [elapsed: {elapsed} remaining: {remaining}]'\n", "python_version = f\"{version_info.major}.{version_info.minor}\"\n",
"\n", "\n",
"python_version = '.'.join(sys.version.split('.')[:2]) #get string like \"3.9\"\n", "\n",
"os.system(\"wget -qnc https://github.com/conda-forge/miniforge/releases/latest/download/Mambaforge-Linux-x86_64.sh\")\n",
"os.system(\"bash Mambaforge-Linux-x86_64.sh -bfp /usr/local\")\n",
"os.system(\"mamba config --set auto_update_conda false\")\n",
"os.system(f\"mamba install -y -c conda-forge -c bioconda kalign2=2.04 hhsuite=3.3.0 openmm=7.7.0 python={python_version} pdbfixer\")\n",
"\n",
"\n",
"os.system(\"pip install -q \\\"torch<2\\\" biopython ml_collections py3Dmol modelcif\")\n",
"\n", "\n",
"try:\n", "try:\n",
" with io.capture_output() as captured:\n", " with io.capture_output() as captured:\n",
" %shell sudo apt install --quiet --yes hmmer\n",
"\n",
" # Install py3dmol.\n",
" %shell pip install py3dmol\n",
"\n",
" %shell rm -rf /opt/conda\n",
" %shell wget -q -P /tmp \\\n",
" https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-x86_64.sh \\\n",
" && bash /tmp/Miniconda3-latest-Linux-x86_64.sh -b -p /opt/conda \\\n",
" && rm /tmp/Miniconda3-latest-Linux-x86_64.sh\n",
"\n",
" PATH=%env PATH\n",
" %env PATH=/opt/conda/bin:{PATH}\n",
"\n",
" # Install the required versions of all dependencies.\n",
" %shell conda install -y -q conda==4.13.0\n",
" %shell conda install -y -q -c conda-forge -c bioconda \\\n",
" kalign2=2.04 \\\n",
" hhsuite=3.3.0 \\\n",
" python={python_version} \\\n",
" openmm=7.7.0 \\\n",
" pdbfixer \\\n",
" 2>&1 1>/dev/null\n",
" %shell pip install -q \\\n",
" ml-collections==0.1.0 \\\n",
" PyYAML==5.4.1 \\\n",
" biopython==1.79 \\\n",
" modelcif==0.7\n",
"\n", "\n",
" # Create a ramdisk to store a database chunk to make Jackhmmer run fast.\n", " # Create a ramdisk to store a database chunk to make Jackhmmer run fast.\n",
" %shell sudo apt install --quiet --yes hmmer\n",
" %shell sudo mkdir -m 777 --parents /tmp/ramdisk\n", " %shell sudo mkdir -m 777 --parents /tmp/ramdisk\n",
" %shell sudo mount -t tmpfs -o size=9G ramdisk /tmp/ramdisk\n", " %shell sudo mount -t tmpfs -o size=9G ramdisk /tmp/ramdisk\n",
"\n", "\n",
" %shell wget -q -P /content \\\n", " %shell wget -q -P /content \\\n",
" https://git.scicore.unibas.ch/schwede/openstructure/-/raw/7102c63615b64735c4941278d92b554ec94415f8/modules/mol/alg/src/stereo_chemical_props.txt\n", " https://git.scicore.unibas.ch/schwede/openstructure/-/raw/7102c63615b64735c4941278d92b554ec94415f8/modules/mol/alg/src/stereo_chemical_props.txt\n",
"\n", "\n",
" # Install AWS CLI\n", " %shell mkdir -p /content/openfold/openfold/resourcees\n",
" %shell curl \"https://awscli.amazonaws.com/awscli-exe-linux-x86_64.zip\" -o \"awscliv2.zip\"\n", " \n",
" %shell unzip -qq awscliv2.zip\n", " commit = \"099769d2ecfd01a8baa8d950030df454a042c910\"\n",
" %shell sudo ./aws/install\n", " os.system(f\"pip install -q git+https://github.com/aqlaboratory/openfold.git@{commit}\")\n",
" %shell rm awscliv2.zip\n", " \n",
" %shell rm -rf ./aws\n", " %shell cp -f /content/stereo_chemical_props.txt /usr/local/lib/python3.10/site-packages/openfold/resources/\n",
"\n",
"except subprocess.CalledProcessError as captured:\n", "except subprocess.CalledProcessError as captured:\n",
" print(captured)\n", " print(captured)"
" raise" ]
],
"execution_count": null,
"outputs": []
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null,
"metadata": { "metadata": {
"id": "VzJ5iMjTtoZw", "cellView": "form",
"cellView": "form" "id": "VzJ5iMjTtoZw"
}, },
"outputs": [],
"source": [ "source": [
"#@title Install OpenFold\n", "#@title Download model weights \n",
"#@markdown Please execute this cell by pressing the *Play* button on \n", "#@markdown Please execute this cell by pressing the *Play* button on \n",
"#@markdown the left.\n", "#@markdown the left.\n",
"\n", "\n",
...@@ -180,13 +144,6 @@ ...@@ -180,13 +144,6 @@
"\n", "\n",
"try:\n", "try:\n",
" with io.capture_output() as captured:\n", " with io.capture_output() as captured:\n",
" # Run setup.py to install only Openfold.\n",
" %shell rm -rf openfold\n",
" %shell git clone \"{GIT_REPO}\" openfold 2>&1 1> /dev/null\n",
" %shell mkdir -p /content/openfold/openfold/resources\n",
" %shell cp -f /content/stereo_chemical_props.txt /content/openfold/openfold/resources\n",
" %shell /usr/bin/python3 -m pip install -q ./openfold\n",
"\n",
" if(weight_set == 'AlphaFold'):\n", " if(weight_set == 'AlphaFold'):\n",
" %shell mkdir --parents \"{ALPHAFOLD_PARAMS_DIR}\"\n", " %shell mkdir --parents \"{ALPHAFOLD_PARAMS_DIR}\"\n",
" %shell wget -O {ALPHAFOLD_PARAMS_PATH} {ALPHAFOLD_PARAM_SOURCE_URL}\n", " %shell wget -O {ALPHAFOLD_PARAMS_PATH} {ALPHAFOLD_PARAM_SOURCE_URL}\n",
...@@ -194,7 +151,14 @@ ...@@ -194,7 +151,14 @@
" --directory=\"{ALPHAFOLD_PARAMS_DIR}\" --preserve-permissions\n", " --directory=\"{ALPHAFOLD_PARAMS_DIR}\" --preserve-permissions\n",
" %shell rm \"{ALPHAFOLD_PARAMS_PATH}\"\n", " %shell rm \"{ALPHAFOLD_PARAMS_PATH}\"\n",
" elif(weight_set == 'OpenFold'):\n", " elif(weight_set == 'OpenFold'):\n",
" # Install AWS CLI\n",
" %shell curl \"https://awscli.amazonaws.com/awscli-exe-linux-x86_64.zip\" -o \"awscliv2.zip\"\n",
" %shell unzip -qq awscliv2.zip\n",
" %shell sudo ./aws/install\n",
" %shell rm awscliv2.zip\n",
" %shell rm -rf ./aws\n",
" %shell mkdir --parents \"{OPENFOLD_PARAMS_DIR}\"\n", " %shell mkdir --parents \"{OPENFOLD_PARAMS_DIR}\"\n",
"\n",
" %shell aws s3 cp \\\n", " %shell aws s3 cp \\\n",
" --no-sign-request \\\n", " --no-sign-request \\\n",
" --region us-east-1 \\\n", " --region us-east-1 \\\n",
...@@ -203,14 +167,17 @@ ...@@ -203,14 +167,17 @@
" else:\n", " else:\n",
" raise ValueError(\"Invalid weight set\")\n", " raise ValueError(\"Invalid weight set\")\n",
"except subprocess.CalledProcessError as captured:\n", "except subprocess.CalledProcessError as captured:\n",
" print(captured)\n", " print(captured)"
" raise" ]
],
"execution_count": null,
"outputs": []
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null,
"metadata": {
"cellView": "form",
"id": "_FpxxMo-mvcP"
},
"outputs": [],
"source": [ "source": [
"#@title Import Python packages\n", "#@title Import Python packages\n",
"#@markdown Please execute this cell by pressing the *Play* button on \n", "#@markdown Please execute this cell by pressing the *Play* button on \n",
...@@ -219,8 +186,8 @@ ...@@ -219,8 +186,8 @@
"import unittest.mock\n", "import unittest.mock\n",
"import sys\n", "import sys\n",
"\n", "\n",
"sys.path.insert(0, f'/usr/local/lib/python{python_version}/dist-packages/')\n",
"sys.path.insert(0, f'/usr/local/lib/python{python_version}/site-packages/')\n", "sys.path.insert(0, f'/usr/local/lib/python{python_version}/site-packages/')\n",
"sys.path.append(f'/opt/conda/lib/python{python_version}/site-packages')\n",
"\n", "\n",
"# Allows us to skip installing these packages\n", "# Allows us to skip installing these packages\n",
"unnecessary_modules = [\n", "unnecessary_modules = [\n",
...@@ -245,6 +212,10 @@ ...@@ -245,6 +212,10 @@
"import py3Dmol\n", "import py3Dmol\n",
"import torch\n", "import torch\n",
"import shutil\n", "import shutil\n",
"import tqdm\n",
"import tqdm.notebook\n",
"\n",
"TQDM_BAR_FORMAT = '{l_bar}{bar}| {n_fmt}/{total_fmt} [elapsed: {elapsed} remaining: {remaining}]'\n",
"\n", "\n",
"# Prevent shell magic being broken by openmm, prevent this cryptic error:\n", "# Prevent shell magic being broken by openmm, prevent this cryptic error:\n",
"# \"NotImplementedError: A UTF-8 locale is required. Got ANSI_X3.4-1968\"\n", "# \"NotImplementedError: A UTF-8 locale is required. Got ANSI_X3.4-1968\"\n",
...@@ -280,13 +251,7 @@ ...@@ -280,13 +251,7 @@
"from IPython import display\n", "from IPython import display\n",
"from ipywidgets import GridspecLayout\n", "from ipywidgets import GridspecLayout\n",
"from ipywidgets import Output" "from ipywidgets import Output"
], ]
"metadata": {
"id": "_FpxxMo-mvcP",
"cellView": "form"
},
"execution_count": null,
"outputs": []
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
...@@ -301,10 +266,12 @@ ...@@ -301,10 +266,12 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null,
"metadata": { "metadata": {
"id": "2tTeTTsLKPjB", "cellView": "form",
"cellView": "form" "id": "2tTeTTsLKPjB"
}, },
"outputs": [],
"source": [ "source": [
"#@title Search against genetic databases\n", "#@title Search against genetic databases\n",
"\n", "\n",
...@@ -420,16 +387,16 @@ ...@@ -420,16 +387,16 @@
"plt.ylabel('Non-Gap Count')\n", "plt.ylabel('Non-Gap Count')\n",
"plt.yticks(range(0, num_alignments + 1, max(1, int(num_alignments / 3))))\n", "plt.yticks(range(0, num_alignments + 1, max(1, int(num_alignments / 3))))\n",
"plt.show()" "plt.show()"
], ]
"execution_count": null,
"outputs": []
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null,
"metadata": { "metadata": {
"id": "XUo6foMQxwS2", "cellView": "form",
"cellView": "form" "id": "XUo6foMQxwS2"
}, },
"outputs": [],
"source": [ "source": [
"#@title Run OpenFold and download prediction\n", "#@title Run OpenFold and download prediction\n",
"\n", "\n",
...@@ -693,9 +660,7 @@ ...@@ -693,9 +660,7 @@
"# --- Download the predictions ---\n", "# --- Download the predictions ---\n",
"shutil.make_archive(base_name='prediction', format='zip', root_dir=output_dir)\n", "shutil.make_archive(base_name='prediction', format='zip', root_dir=output_dir)\n",
"files.download(f'{output_dir}.zip')" "files.download(f'{output_dir}.zip')"
], ]
"execution_count": null,
"outputs": []
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
...@@ -789,5 +754,22 @@ ...@@ -789,5 +754,22 @@
"* BFD: (modified), by Steinegger M. and Söding J., modified by DeepMind, available under a [Creative Commons Attribution-ShareAlike 4.0 International License](https://creativecommons.org/licenses/by/4.0/). See the Methods section of the [AlphaFold proteome paper](https://www.nature.com/articles/s41586-021-03828-1) for details." "* BFD: (modified), by Steinegger M. and Söding J., modified by DeepMind, available under a [Creative Commons Attribution-ShareAlike 4.0 International License](https://creativecommons.org/licenses/by/4.0/). See the Methods section of the [AlphaFold proteome paper](https://www.nature.com/articles/s41586-021-03828-1) for details."
] ]
} }
] ],
"metadata": {
"accelerator": "GPU",
"colab": {
"collapsed_sections": [],
"name": "OpenFold.ipynb",
"provenance": []
},
"kernelspec": {
"display_name": "Python 3",
"name": "python3"
},
"language_info": {
"name": "python"
}
},
"nbformat": 4,
"nbformat_minor": 0
} }
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment