ATOM3D: Tasks On Molecules in 3 Dimensions
Project description
ATOM3D: Tasks On Molecules in 3 Dimensions
ATOM3D enables machine learning on three-dimensional molecular structure.
Features
- Access to several datasets involving 3D molecular structure.
- LMDB data format for storing lots of molecules (and associated metadata).
- Utilities for splitting/filtering data based on many criteria.
For more detailed information, read the documentation.
Installation
Install with:
pip install atom3d
To use rdkit functionality, please install within conda:
conda create -n atom3d python=3.6 pip rdkit
conda activate atom3d
pip install atom3d
Usage
Downloading a dataset
From python:
import atom3d.datasets as da
da.download_dataset('lba', PATH_TO_DATASET) # Download LBA dataset.
Or, download and unzip from the website.
Loading a dataset
From python:
import atom3d.datasets as da
dataset = da.load_dataset(PATH_TO_DATASET, {'lmdb','pdb','silent','sdf','xyz','xyz-gdb'})
print(len(dataset)) # Print length
print(dataset[0].keys()) # Print keys
LMDB datasets
LMDB allows for compressed, fast, random access to your structures, all within a single database. Currently, we support creating LMDB datasets from PDB files, silent files, and xyz files.
Creating an LMDB dataset
From command line:
python -m atom3d.datasets PATH_TO_PDB_DIR PATH_TO_DATASET --filetype {pdb,silent,xyz,xyz-gdb}
For more usage, please see the documentation.
Contribute
As a living repository, we welcome contributions of additional datasets, methods, and functionality! See the Contributing section of the documentation for details.
Support
For support, please file an issue at https://github.com/drorlab/atom3d/issues.
License
The project is licensed under the MIT license.
Reference
We provide an overview on ATOM3D and details on the preparation of all datasets in our preprint:
R. J. L. Townshend, M. Vögele, P. Suriana, A. Derry, A. Powers, Y. Laloudakis, S. Balachandar, B. Jing, B. Anderson, S. Eismann, R. Kondor, R. B. Altman, R. O. Dror "ATOM3D: Tasks On Molecules in Three Dimensions", arXiv:2012.04035
Please cite this work if some of the ATOM3D code or datasets are helpful in your scientific endeavours. For specific datasets, please also cite the respective original source(s), given in the preprint.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
File details
Details for the file atom3d-0.2.6.tar.gz
.
File metadata
- Download URL: atom3d-0.2.6.tar.gz
- Upload date:
- Size: 44.9 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.1 CPython/3.10.5
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | fdf23811cd08fffea3244b9b1300fc8ffe808c06fa5c69c85d5d4bb21833e256 |
|
MD5 | 589dd6a5f476ff7595ea31d8f9753a24 |
|
BLAKE2b-256 | 8c5b787e98992b4f9f99d542315489f043ffbb6874130ae4f165921163d006c7 |
File details
Details for the file atom3d-0.2.6-py3-none-any.whl
.
File metadata
- Download URL: atom3d-0.2.6-py3-none-any.whl
- Upload date:
- Size: 52.7 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.1 CPython/3.10.5
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 9d26096c245e1ce46262081f5af5e88912eb1cc4d6e319d47b9f4241cb7f73f9 |
|
MD5 | 8e4370648fe5867f1e8d75eb3a628f7b |
|
BLAKE2b-256 | ac07c75ce6b77db7abf8c6a0ebdaaf8f8fb291be5de2214139aa035f51939cd1 |