ProteinStructure
所属分类:生物医药技术
开发工具:Python
文件大小:0KB
下载次数:0
上传日期:2023-09-26 09:19:57
上 传 者:
sh-1993
说明: 阿尔法福尔德,
(Alphafold,)
文件列表:
.dockerignore (32, 2023-08-10)
CONTRIBUTING.md (973, 2023-08-10)
LICENSE (11358, 2023-08-10)
afdb/ (0, 2023-08-10)
alphafold/ (0, 2023-08-10)
alphafold/__init__.py (663, 2023-08-10)
alphafold/common/ (0, 2023-08-10)
alphafold/common/__init__.py (655, 2023-08-10)
alphafold/common/confidence.py (7973, 2023-08-10)
alphafold/common/confidence_test.py (1434, 2023-08-10)
alphafold/common/mmcif_metadata.py (7561, 2023-08-10)
alphafold/common/protein.py (20739, 2023-08-10)
alphafold/common/protein_test.py (5791, 2023-08-10)
alphafold/common/residue_constants.py (35625, 2023-08-10)
alphafold/common/residue_constants_test.py (9256, 2023-08-10)
alphafold/common/testdata/ (0, 2023-08-10)
alphafold/common/testdata/2rbg.pdb (225504, 2023-08-10)
alphafold/common/testdata/5nmu.pdb (788048, 2023-08-10)
alphafold/common/testdata/glucagon.pdb (51273, 2023-08-10)
alphafold/data/ (0, 2023-08-10)
alphafold/data/__init__.py (634, 2023-08-10)
alphafold/data/feature_processing.py (8575, 2023-08-10)
alphafold/data/mmcif_parsing.py (14182, 2023-08-10)
alphafold/data/msa_identifiers.py (2966, 2023-08-10)
alphafold/data/msa_pairing.py (17220, 2023-08-10)
alphafold/data/parsers.py (21397, 2023-08-10)
alphafold/data/pipeline.py (10419, 2023-08-10)
alphafold/data/pipeline_multimer.py (11126, 2023-08-10)
alphafold/data/templates.py (40677, 2023-08-10)
alphafold/data/tools/ (0, 2023-08-10)
alphafold/data/tools/__init__.py (639, 2023-08-10)
alphafold/data/tools/hhblits.py (5504, 2023-08-10)
alphafold/data/tools/hhsearch.py (3601, 2023-08-10)
alphafold/data/tools/hmmbuild.py (4576, 2023-08-10)
alphafold/data/tools/hmmsearch.py (4556, 2023-08-10)
alphafold/data/tools/jackhmmer.py (8386, 2023-08-10)
alphafold/data/tools/kalign.py (3387, 2023-08-10)
alphafold/data/tools/utils.py (1223, 2023-08-10)
... ...
![header](https://github.com/spcp12/ProteinStructure/blob/master/imgs/header.jpg)
# AlphaFold
This package provides an implementation of the inference pipeline of AlphaFold
v2. For simplicity, we refer to this model as AlphaFold throughout the rest of
this document.
We also provide:
1. An implementation of AlphaFold-Multimer. This represents a work in progress
and AlphaFold-Multimer isn't expected to be as stable as our monomer
AlphaFold system. [Read the guide](https://github.com/spcp12/ProteinStructure/blob/master/#updating-existing-installation) for how
to upgrade and update code.
2. The [technical note](https://github.com/spcp12/ProteinStructure/blob/master/docs/technical_note_v2.3.0.md) containing the models
and inference procedure for an updated AlphaFold v2.3.0.
3. A [CASP15 baseline](https://github.com/spcp12/ProteinStructure/blob/master/docs/casp15_predictions.zip) set of predictions along
with documentation of any manual interventions performed.
Any publication that discloses findings arising from using this source code or
the model parameters should [cite](https://github.com/spcp12/ProteinStructure/blob/master/#citing-this-work) the
[AlphaFold paper](https://github.com/spcp12/ProteinStructure/blob/master/https://doi.org/10.1038/s41586-021-03819-2) and, if
applicable, the
[AlphaFold-Multimer paper](https://github.com/spcp12/ProteinStructure/blob/master/https://www.biorxiv.org/content/10.1101/2021.10.04.463034v1).
Please also refer to the
[Supplementary Information](https://github.com/spcp12/ProteinStructure/blob/master/https://static-content.springer.com/esm/art%3A10.1038%2Fs41586-021-03819-2/MediaObjects/41586_2021_3819_MOESM1_ESM.pdf)
for a detailed description of the method.
**You can use a slightly simplified version of AlphaFold with
[this Colab notebook](https://github.com/spcp12/ProteinStructure/blob/master/https://colab.research.google.com/github/deepmind/alphafold/blob/main/notebooks/AlphaFold.ipynb)**
or community-supported versions (see below).
If you have any questions, please contact the AlphaFold team at
[alphafold@deepmind.com](https://github.com/spcp12/ProteinStructure/blob/master/mailto:alphafold@deepmind.com).
![CASP14 predictions](https://github.com/spcp12/ProteinStructure/blob/master/imgs/casp14_predictions.gif)
## Installation and running your first prediction
You will need a machine running Linux, AlphaFold does not support other
operating systems. Full installation requires up to 3 TB of disk space to keep
genetic databases (SSD storage is recommended) and a modern NVIDIA GPU (GPUs
with more memory can predict larger protein structures).
Please follow these steps:
1. Install [Docker](https://github.com/spcp12/ProteinStructure/blob/master/https://www.docker.com/).
* Install
[NVIDIA Container Toolkit](https://github.com/spcp12/ProteinStructure/blob/master/https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/install-guide.html)
for GPU support.
* Setup running
[Docker as a non-root user](https://github.com/spcp12/ProteinStructure/blob/master/https://docs.docker.com/engine/install/linux-postinstall/#manage-docker-as-a-non-root-user).
1. Clone this repository and `cd` into it.
```bash
git clone https://github.com/deepmind/alphafold.git
cd ./alphafold
```
1. Download genetic databases and model parameters:
* Install `aria2c`. On most Linux distributions it is available via the
package manager as the `aria2` package (on Debian-based distributions this
can be installed by running `sudo apt install aria2`).
* Please use the script `scripts/download_all_data.sh` to download
and set up full databases. This may take substantial time (download size is
556 GB), so we recommend running this script in the background:
```bash
scripts/download_all_data.sh
> download.log 2> download_all.log &
```
* **Note: The download directory `` should *not* be a
subdirectory in the AlphaFold repository directory.** If it is, the Docker
build will be slow as the large databases will be copied into the docker
build context.
* It is possible to run AlphaFold with reduced databases; please refer to
the [complete documentation](https://github.com/spcp12/ProteinStructure/blob/master/#genetic-databases).
1. Check that AlphaFold will be able to use a GPU by running:
```bash
docker run --rm --gpus all nvidia/cuda:11.0-base nvidia-smi
```
The output of this command should show a list of your GPUs. If it doesn't,
check if you followed all steps correctly when setting up the
[NVIDIA Container Toolkit](https://github.com/spcp12/ProteinStructure/blob/master/https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/install-guide.html)
or take a look at the following
[NVIDIA Docker issue](https://github.com/spcp12/ProteinStructure/blob/master/https://github.com/NVIDIA/nvidia-docker/issues/1447#issuecomment-801479573).
If you wish to run AlphaFold using Singularity (a common containerization
platform on HPC systems) we recommend using some of the third party Singularity
setups as linked in https://github.com/deepmind/alphafold/issues/10 or
https://github.com/deepmind/alphafold/issues/24.
1. Build the Docker image:
```bash
docker build -f docker/Dockerfile -t alphafold .
```
If you encounter the following error:
```
W: GPG error: https://developer.download.nvidia.com/compute/cuda/repos/ubuntu1804/x86_64 InRelease: The following signatures couldn't be verified because the public key is not available: NO_PUBKEY A4B469963BF863CC
E: The repository 'https://developer.download.nvidia.com/compute/cuda/repos/ubuntu1804/x86_64 InRelease' is not signed.
```
use the workaround described in
https://github.com/deepmind/alphafold/issues/463#issuecomment-1124881779.
1. Install the `run_docker.py` dependencies. Note: You may optionally wish to
create a
[Python Virtual Environment](https://github.com/spcp12/ProteinStructure/blob/master/https://docs.python.org/3/tutorial/venv.html)
to prevent conflicts with your system's Python environment.
```bash
pip3 install -r docker/requirements.txt
```
1. Make sure that the output directory exists (the default is `/tmp/alphafold`)
and that you have sufficient permissions to write into it.
1. Run `run_docker.py` pointing to a FASTA file containing the protein
sequence(s) for which you wish to predict the structure (`--fasta_paths`
parameter). AlphaFold will search for the available templates before the
date specified by the `--max_template_date` parameter; this could be used to
avoid certain templates during modeling. `--data_dir` is the directory with
downloaded genetic databases and `--output_dir` is the absolute path to the
output directory.
```bash
python3 docker/run_docker.py \
--fasta_paths=your_protein.fasta \
--max_template_date=2022-01-01 \
--data_dir=$DOWNLOAD_DIR \
--output_dir=/home/user/absolute_path_to_the_output_dir
```
1. Once the run is over, the output directory shall contain predicted
structures of the target protein. Please check the documentation below for
additional options and troubleshooting tips.
### Genetic databases
This step requires `aria2c` to be installed on your machine.
AlphaFold needs multiple genetic (sequence) databases to run:
* [BFD](https://github.com/spcp12/ProteinStructure/blob/master/https://bfd.mmseqs.com/),
* [MGnify](https://github.com/spcp12/ProteinStructure/blob/master/https://www.ebi.ac.uk/metagenomics/),
* [PDB70](https://github.com/spcp12/ProteinStructure/blob/master/http://wwwuser.gwdg.de/~compbiol/data/hhsuite/databases/hhsuite_dbs/),
* [PDB](https://github.com/spcp12/ProteinStructure/blob/master/https://www.rcsb.org/) (structures in the mmCIF format),
* [PDB seqres](https://github.com/spcp12/ProteinStructure/blob/master/https://www.rcsb.org/) – only for AlphaFold-Multimer,
* [UniRef30 (FKA UniClust30)](https://github.com/spcp12/ProteinStructure/blob/master/https://uniclust.mmseqs.com/),
* [UniProt](https://github.com/spcp12/ProteinStructure/blob/master/https://www.uniprot.org/uniprot/) – only for AlphaFold-Multimer,
* [UniRef90](https://github.com/spcp12/ProteinStructure/blob/master/https://www.uniprot.org/help/uniref).
We provide a script `scripts/download_all_data.sh` that can be used to download
and set up all of these databases:
* Recommended default:
```bash
scripts/download_all_data.sh
```
will download the full databases.
* With `reduced_dbs` parameter:
```bash
scripts/download_all_data.sh reduced_dbs
```
will download a reduced version of the databases to be used with the
`reduced_dbs` database preset. This shall be used with the corresponding
AlphaFold parameter `--db_preset=reduced_dbs` later during the AlphaFold run
(please see [AlphaFold parameters](https://github.com/spcp12/ProteinStructure/blob/master/#running-alphafold) section).
:ledger: **Note: The download directory `` should *not* be a
subdirectory in the AlphaFold repository directory.** If it is, the Docker build
will be slow as the large databases will be copied during the image creation.
We don't provide exactly the database versions used in CASP14 – see the
[note on reproducibility](https://github.com/spcp12/ProteinStructure/blob/master/#note-on-casp14-reproducibility). Some of the
databases are mirrored for speed, see [mirrored databases](https://github.com/spcp12/ProteinStructure/blob/master/#mirrored-databases).
:ledger: **Note: The total download size for the full databases is around 556 GB
and the total size when unzipped is 2.62 TB. Please make sure you have a large
enough hard drive space, bandwidth and time to download. We recommend using an
SSD for better genetic search performance.**
:ledger: **Note: If the download directory and datasets don't have full read and
write permissions, it can cause errors with the MSA tools, with opaque
(external) error messages. Please ensure the required permissions are applied,
e.g. with the `sudo chmod 755 --recursive "$DOWNLOAD_DIR"` command.**
The `download_all_data.sh` script will also download the model parameter files.
Once the script has finished, you should have the following directory structure:
```
$DOWNLOAD_DIR/ # Total: ~ 2.62 TB (download: 556 GB)
bfd/ # ~ 1.8 TB (download: 271.6 GB)
# 6 files.
mgnify/ # ~ 120 GB (download: 67 GB)
mgy_clusters_2022_05.fa
params/ # ~ 5.3 GB (download: 5.3 GB)
# 5 CASP14 models,
# 5 pTM models,
# 5 AlphaFold-Multimer models,
# LICENSE,
# = 16 files.
pdb70/ # ~ 56 GB (download: 19.5 GB)
# 9 files.
pdb_mmcif/ # ~ 238 GB (download: 43 GB)
mmcif_files/
# About 199,000 .cif files.
obsolete.dat
pdb_seqres/ # ~ 0.2 GB (download: 0.2 GB)
pdb_seqres.txt
small_bfd/ # ~ 17 GB (download: 9.6 GB)
bfd-first_non_consensus_sequences.fasta
uniref30/ # ~ 206 GB (download: 52.5 GB)
# 7 files.
uniprot/ # ~ 105 GB (download: 53 GB)
uniprot.fasta
uniref90/ # ~ 67 GB (download: 34 GB)
uniref90.fasta
```
`bfd/` is only downloaded if you download the full databases, and `small_bfd/`
is only downloaded if you download the reduced databases.
### Model parameters
While the AlphaFold code is licensed under the Apache 2.0 License, the AlphaFold
parameters and CASP15 prediction data are made available under the terms of the
CC BY 4.0 license. Please see the [Disclaimer](https://github.com/spcp12/ProteinStructure/blob/master/#license-and-disclaimer) below
for more detail.
The AlphaFold parameters are available from
https://storage.googleapis.com/alphafold/alphafold_params_2022-12-06.tar, and
are downloaded as part of the `scripts/download_all_data.sh` script. This script
will download parameters for:
* 5 models which were used during CASP14, and were extensively validated for
structure prediction quality (see Jumper et al. 2021, Suppl. Methods 1.12
for details).
* 5 pTM models, which were fine-tuned to produce pTM (predicted TM-score) and
(PAE) predicted aligned error values alongside their structure predictions
(see Jumper et al. 2021, Suppl. Methods 1.9.7 for details).
* 5 AlphaFold-Multimer models that produce pTM and PAE values alongside their
structure predictions.
### Updating existing installation
If you have a previous version you can either reinstall fully from scratch
(remove everything and run the setup from scratch) or you can do an incremental
update that will be significantly faster but will require a bit more work. Make
sure you follow these steps in the exact order they are listed below:
1. **Update the code.**
* Go to the directory with the cloned AlphaFold repository and run `git
fetch origin main` to get all code updates.
1. **Update the UniProt, UniRef, MGnify and PDB seqres databases.**
* Remove `/uniprot`.
* Run `scripts/download_uniprot.sh `.
* Remove `/uniclust30`.
* Run `scripts/download_uniref30.sh `.
* Remove `/uniref90`.
* Run `scripts/download_uniref90.sh `.
* Remove `/mgnify`.
* Run `scripts/download_mgnify.sh `.
* Remove `/pdb_mmcif`. It is needed to have PDB SeqRes and
PDB from exactly the same date. Failure to do this step will result in
potential errors when searching for templates when running
AlphaFold-Multimer.
* Run `scripts/download_pdb_mmcif.sh `.
* Run `scripts/download_pdb_seqres.sh `.
1. **Update the model parameters.**
* Remove the old model parameters in `/params`.
* Download new model parameters using
`scripts/download_alphafold_params.sh `.
1. **Follow [Running AlphaFold](https://github.com/spcp12/ProteinStructure/blob/master/#running-alphafold).**
#### Using deprecated model weights
To use the deprecated v2.2.0 AlphaFold-Multimer model weights:
1. Change `SOURCE_URL` in `scripts/download_alphafold_params.sh` to
`https://storage.googleapis.com/alphafold/alphafold_params_2022-03-02.tar`,
and download the old parameters.
2. Change the `_v3` to `_v2` in the multimer `MODEL_PRESETS` in `config.py`.
To use the deprecated v2.1.0 AlphaFold-Multimer model weights:
1. Change `SOURCE_URL` in `scripts/download_alphafold_params.sh` to
`https://storage.googleapis.com/alphafold/alphafold_params_2022-01-19.tar`,
and download the old parameters.
2. Remove the `_v3` in the multimer `MODEL_PRESETS` in `config.py`.
## Running AlphaFold
**The simplest way to run AlphaFold is using the provided Docker script.** This
was tested on Google Cloud with a machine using the `nvidia-gpu-cloud-image`
with 12 vCPUs, 85 GB of RAM, a 100 GB boot disk, the databases on an additional
3 TB disk, and an A100 GPU. For your first run, please follow the instructions
from [Installation and running your first prediction](https://github.com/spcp12/ProteinStructure/blob/master/#installation-and-running-your-first-prediction)
section.
1. By default, Alphafold will attempt to use all visible GPU devices. To use a
subset, specify a comma-separated list of GPU UUID(s) or index(es) using the
`--gpu_devices` flag. See
[GPU enumeration](https://github.com/spcp12/ProteinStructure/blob/master/https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/user-guide.html#gpu-enumeration)
for more details.
1. You can control which AlphaFold model to run by adding the `--model_preset=`
flag. We provide the following models:
* **monomer**: This is the original model used at CASP14 with no
ensembling.
* **monomer\_casp14**: This is the original model used at CASP14 with
`num_ensemble=8`, matching our CASP14 configuration. This is largely
provided for reproducibility as it is 8x more computationally expensive
for limited accuracy gain (+0.1 average GDT gain on CASP14 domains).
* **monomer\_ptm**: This is the original CASP14 model fine tuned with the
pTM head, providing a pairwise confidence measure. It is slightly less
accurate than the normal monomer model.
* **multimer**: This is the [AlphaFold-Multimer](https://github.com/spcp12/ProteinStructure/blob/master/#citing-this-work) model.
To use this model, provide a multi-sequence FASTA file. In addition, the
UniProt database should have been downloaded.
1. You can control MSA speed/quality tradeoff by adding
`--db_preset=reduced_dbs` or `--db_preset=full_dbs` to the run command. We
provide the following presets:
* **reduced\_dbs**: This preset is optimized for speed and lower hardware
requirements. It runs with a reduced version of the BFD database. It
requires 8 CPU cores (vCPUs), 8 GB of RAM, and 600 GB of disk space.
* **full\_dbs**: This runs with all genetic databases used at CASP14.
Running the command above with the `monomer` model preset and the
`reduced_dbs` data preset would look like this:
```bash
python3 docker/run_docker.py \
--fasta_paths=T1050.fasta \
--max_template_date=2020-05-14 \
--model_preset=monomer \
--db_preset=reduced_dbs \
--data_dir=$DOWNLOAD_DIR \
--output_dir=/home/user/absolute_path_to_the_output_dir
```
1. After generating the predicted model, AlphaFold runs a relaxation
step to improve local geometry. By default, only the best model (by
pLDDT) is relaxed (`--models_to_relax=best`), but also all of the models
(`--models_to_relax=all`) or none of the models (`--models_to_relax=none`)
can be relaxed.
1. The relaxation step can be run on GPU (faster, but could be less stable) or
CPU (slow, but stable). This can be controlled with `--enable_gpu_relax=true`
(default) or `--enable_gpu_relax=false`.
1. AlphaFold can re-use MSAs (multiple sequence alignments) for the same
sequence via `--use_precomputed_msas=true` option; this can be useful for
trying different AlphaFold parameters. This option assumes that the
directory structure generated by the first AlphaFold run in the output
directory exists and that the protein sequence is the same.
### Running AlphaFold-Multimer
All steps are the same as when running the monomer system, but you will have to
* provide an input fasta with multiple sequences,
* set `--model_preset=multimer`,
An example that folds a protein complex `multimer.fasta`:
```bash
python3 docker/run_docker.py \
--fasta_paths=multimer.fasta \
--max_template_date=2020-05-14 \
--model_preset=multimer \
--data_dir=$DOWNLOAD_DIR \
--output_dir=/home/user/absolute_path_to_the_output_dir
```
By default the multimer system will run 5 seeds per model (25 total predictions)
for a small drop in accuracy you may wish to run a single seed per model. This
can be done via the `--num_multimer_predictions_per_model` flag, e.g. set it to
`--num_multimer_predictions_per_model=1` to run a single seed per model.
### AlphaFold prediction speed
The table below reports prediction runtimes for proteins of various lengths. We
only measure unrelaxed structure prediction with three recycles while
excluding runtimes from MSA and template search. When running
`docker/run_docker.py` with `--benchmark=true`, this runtime is stored in
`timings.json`. All runtimes are from a single A100 NVIDIA GPU. Prediction
speed on A100 for smaller structures can be improved by increasing
`global_config.subbatch_size` in `alphafold/model/config.py`.
No. residues | Prediction time (s)
-----------: | ------------------:
100 | 4.9
200 | 7.7
300 | 13
400 | 18
500 | 29
600 | 36
700 | 53
800 | 60
900 | 91
1,000 | 96
1,100 | 140
1,500 | 280
2,000 | 450
2,500 | 969
3,000 | 1,240
3,500 | 2,465
4,000 | 5,660
4,500 | 12,475
5,000 | 18,824
### Examples
Below are examples on how to use AlphaFold in different scenarios.
#### Folding a monomer
Say we have a monomer with the sequence ``. The input fasta should be:
```fasta
>sequence_name
```
Then run the following command:
```bash
python3 docker/run_docker.py \
--fasta_paths=monomer.fasta \
--max_template_date=2021-11-01 \
--model_preset=monomer \
--data_dir=$DOWNLOAD_DIR \
--output_dir=/home/user/absolute_path_to_the_output_dir
```
#### Folding a homomer
Say we have a homomer with 3 copies of the same sequence ``. The input
fasta should be:
```fasta
>sequence_1
近期下载者:
相关文件:
收藏者: