Skip to main content

An Easy to install version of the jtnn encoder for generation of latent molecule features.

Project description

jtnnencoder

Pip installable version of the Junction Tree Variational Autoencoder https://arxiv.org/abs/1802.04364. The original, full repository can be found here: https://github.com/wengong-jin/icml18-jtnn

Intended to be used as a simple interface for generating molecular features for molecules based on JTNN latent vectors.

Install

$ pip install jtnnencoder
$ pip install torch

You will also need rdkit:

$ conda install -c rdkit rdkit

Use

from jtnnencoder import JTNNEmbed

smiles = ['CC1(C)[C@H]2C[C@H](C/C=C\CCCC(=O)O)[C@@H](NC(=O)c3csc4ccc(O)cc34)[C@@H]1C2']
jtnn = JTNNEmbed(smiles)
features = jtnn.get_features()

features is then a numpy ndarray of dimension (n_smiles x n_features).

Project details


Release history Release notifications | RSS feed

This version

0.1

Download files

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

Source Distribution

jtnnencoder-0.1.tar.gz (19.0 MB view details)

Uploaded Source

Built Distribution

jtnnencoder-0.1-py3-none-any.whl (19.0 MB view details)

Uploaded Python 3

File details

Details for the file jtnnencoder-0.1.tar.gz.

File metadata

  • Download URL: jtnnencoder-0.1.tar.gz
  • Upload date:
  • Size: 19.0 MB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/3.2.0 pkginfo/1.6.0 requests/2.24.0 setuptools/50.3.2 requests-toolbelt/0.9.1 tqdm/4.50.2 CPython/3.7.8

File hashes

Hashes for jtnnencoder-0.1.tar.gz
Algorithm Hash digest
SHA256 f340b813d11b1189d06f693b1ebb00258a42cc8b475b7cb7587e4aea57eb894c
MD5 3caab492c7522ffa11b2f0655b188ec3
BLAKE2b-256 a6c43594f729f9c0fb21d3dbda1e2642d67446e8629ae7af550e7eb1f2ab4544

See more details on using hashes here.

File details

Details for the file jtnnencoder-0.1-py3-none-any.whl.

File metadata

  • Download URL: jtnnencoder-0.1-py3-none-any.whl
  • Upload date:
  • Size: 19.0 MB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/3.2.0 pkginfo/1.6.0 requests/2.24.0 setuptools/50.3.2 requests-toolbelt/0.9.1 tqdm/4.50.2 CPython/3.7.8

File hashes

Hashes for jtnnencoder-0.1-py3-none-any.whl
Algorithm Hash digest
SHA256 e7f7868a7e58bc8841a3430c35c5314a6b35fce491166b96bd6a549b5aab8654
MD5 f7bb9f9005d1ba20b0d01abbba3cb373
BLAKE2b-256 283b1429b80a59eeb0917d17fd0f9fe1fecbaf22a592b7862e8f8eef888f088e

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