Skip to main content

Reaction atom-mapping from transformers

Project description

Extraction of organic chemistry grammar from unsupervised learning of chemical reactions

Enable robust atom mapping on valid reaction SMILES. The atom-mapping information was learned by an ALBERT model trained in an unsupervised fashion on a large dataset of chemical reactions.

Installation

From pip

conda create -n rxnmapper python=3.6 -y
conda activate rxnmapper
pip install rxnmapper

From github

You can install the package and setup the environment directly from github using:

git clone https://github.com/rxn4chemistry/rxnmapper.git 
cd rxnmapper
conda create -n rxnmapper python=3.6 -y
conda activate rxnmapper
pip install -e .

RDkit

In both installation settings above, the RDKit dependency is not installed automatically, unless you include the extra when installing: pip install "rxmapper[rdkit]". It can also be installed via Conda or Pypi:

# Install RDKit from Conda
conda install -c conda-forge rdkit

# Install RDKit from Pypi
pip install rdkit
# for Python<3.7
# pip install rdkit-pypi

Usage

Basic usage

from rxnmapper import RXNMapper
rxn_mapper = RXNMapper()
rxns = ['CC(C)S.CN(C)C=O.Fc1cccnc1F.O=C([O-])[O-].[K+].[K+]>>CC(C)Sc1ncccc1F', 'C1COCCO1.CC(C)(C)OC(=O)CONC(=O)NCc1cccc2ccccc12.Cl>>O=C(O)CONC(=O)NCc1cccc2ccccc12']
results = rxn_mapper.get_attention_guided_atom_maps(rxns)

The results contain the mapped reactions and confidence scores:

[{'mapped_rxn': 'CN(C)C=O.F[c:5]1[n:6][cH:7][cH:8][cH:9][c:10]1[F:11].O=C([O-])[O-].[CH3:1][CH:2]([CH3:3])[SH:4].[K+].[K+]>>[CH3:1][CH:2]([CH3:3])[S:4][c:5]1[n:6][cH:7][cH:8][cH:9][c:10]1[F:11]',
  'confidence': 0.9565619900376546},
 {'mapped_rxn': 'C1COCCO1.CC(C)(C)[O:3][C:2](=[O:1])[CH2:4][O:5][NH:6][C:7](=[O:8])[NH:9][CH2:10][c:11]1[cH:12][cH:13][cH:14][c:15]2[cH:16][cH:17][cH:18][cH:19][c:20]12.Cl>>[O:1]=[C:2]([OH:3])[CH2:4][O:5][NH:6][C:7](=[O:8])[NH:9][CH2:10][c:11]1[cH:12][cH:13][cH:14][c:15]2[cH:16][cH:17][cH:18][cH:19][c:20]12',
  'confidence': 0.9704424331552834}]

To account for batching and error handling automatically, you can use BatchedMapper instead:

from rxnmapper import BatchedMapper
rxn_mapper = BatchedMapper(batch_size=32)
rxns = ['CC[O-]~[Na+].BrCC>>CCOCC', 'invalid>>reaction']

# The following calls work with input of arbitrary size. Also, they do not raise 
# any exceptions but will return ">>" or an empty dictionary for the second reaction.
results = list(rxn_mapper.map_reactions(rxns))  # results as strings directly
results = list(rxn_mapper.map_reactions_with_info(rxns))  # results as dictionaries (as above)

Testing

You can run the examples above with the test suite as well:

  1. In your Conda environment: pip install -e .[dev]
  2. pytest tests from the root

Examples

To learn more see the examples.

Data

Data can be found at: https://ibm.box.com/v/RXNMapperData

Citation

@article{schwaller2021extraction,
  title={Extraction of organic chemistry grammar from unsupervised learning of chemical reactions},
  author={Schwaller, Philippe and Hoover, Benjamin and Reymond, Jean-Louis and Strobelt, Hendrik and Laino, Teodoro},
  journal={Science Advances},
  volume={7},
  number={15},
  pages={eabe4166},
  year={2021},
  publisher={American Association for the Advancement of Science}
}

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

rxnmapper-0.4.0.tar.gz (3.0 MB view details)

Uploaded Source

Built Distribution

rxnmapper-0.4.0-py3-none-any.whl (3.0 MB view details)

Uploaded Python 3

File details

Details for the file rxnmapper-0.4.0.tar.gz.

File metadata

  • Download URL: rxnmapper-0.4.0.tar.gz
  • Upload date:
  • Size: 3.0 MB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/5.1.1 CPython/3.12.6

File hashes

Hashes for rxnmapper-0.4.0.tar.gz
Algorithm Hash digest
SHA256 2ea81c3ae2fc5a81dcd875a3af4e5e79d38ea48c9b0d7484c3eddc130d194d76
MD5 1f5046195a43be42c56459c7f48c023a
BLAKE2b-256 ba434e6c444c9ad7c14b782df6cb22e5c88880707a06973706ca1ecf5e425337

See more details on using hashes here.

File details

Details for the file rxnmapper-0.4.0-py3-none-any.whl.

File metadata

  • Download URL: rxnmapper-0.4.0-py3-none-any.whl
  • Upload date:
  • Size: 3.0 MB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/5.1.1 CPython/3.12.6

File hashes

Hashes for rxnmapper-0.4.0-py3-none-any.whl
Algorithm Hash digest
SHA256 f7f7af125051d3db500ef330bc0d75fe1f92931f18aa625d96a23e8cc8c13c1f
MD5 e6e1a7f915dc274c3c9090366d6d0bd9
BLAKE2b-256 b68df5fe0beac8ffcff26f0e513cc74b3b298df54b6100f7a0f53cba46ed81c7

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page