Data

Tools

Indexes

Applications

Experiments

Open Source Science

hcatgnet

Contains all the code to replicate the experiments and results described in the paper: "HHCat-GNet: a Human-Interpretable GNN Tool for Ligand Optimization in Asymmetric Catalysis"

https://github.com/edaguilarb/hcatgnet

Science Score: 67.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ✓
    CITATION.cff file
    Found CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ✓
    .zenodo.json file
    Found .zenodo.json file
  • ✓
    DOI references
    Found 2 DOI reference(s) in README
  • ✓
    Academic publication links
    Links to: zenodo.org
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (10.3%) to scientific vocabulary

Keywords

asymmetric-catalysis graph-neural-networks organic-synthesis
Last synced: 10 months ago · JSON representation ·

Repository

Contains all the code to replicate the experiments and results described in the paper: "HHCat-GNet: a Human-Interpretable GNN Tool for Ligand Optimization in Asymmetric Catalysis"

Basic Info
Statistics
  • Stars: 0
  • Watchers: 1
  • Forks: 1
  • Open Issues: 0
  • Releases: 3
Topics
asymmetric-catalysis graph-neural-networks organic-synthesis
Created over 2 years ago · Last pushed about 1 year ago
Metadata Files
Readme Citation

README.md

HCat-GNet: Homogeneous Catalyst Graph Neural Network

DOI

Overview

HCat-GNet (Homogeneous Catalyst Graph Neural Network) is a cutting-edge, open-source platform designed to facilitate the virtual evaluation and optimization of homogeneous catalysts. Utilizing Graph Neural Networks (GNNs), HCat-GNet predicts the selectivity of homogeneous catalytic reactions based solely on SMILES representations of participant molecules, significantly speeding up the process of ligand optimization in asymmetric catalysis.

Features

  • Predictive Accuracy: Delivers highly accurate predictions of enantioselectivity for metal-ligand catalyzed asymmetric reactions.
  • Interpretability: Provides insights into how different ligand modifications affect reaction outcomes, enhancing human understanding and guiding experimental design.
  • Flexibility: Agnostic to reaction type, capable of handling a variety of catalytic processes without the need for domain-specific adjustments.

Installation

Prerequisites

  • Python 3.8 or 3.9
  • Pip (Python package installer)

Setup Instructions

  1. Clone the Repository: ```bash git clone https://github.com/EdAguilarB/hcatgnet.git

cd HCat-GNet

  1. Install Dependencies: bash pip install -r requirements.txt

Usage

To run all experiments as described in our paper bash python run_experiments.py

To run the experiments using the CircuS descriptors bash python run_experiments.py --descriptors circus

License

Distributed under the MIT License. See LICENSE for more information.

Contact

Main developer: eduardo.aguilar-bejarano@nottingham.ac.uk

Correspongding author: g.figueredo@nottingham.ac.uk

Owner

  • Name: Eduardo Aguilar
  • Login: EdAguilarB
  • Kind: user
  • Location: Nottingham

University of Nottingham Chemistry PhD student. Exploring the application of AI to chemical synthesis.

Citation (CITATION.cff) 

cff-version: 1.0.1
message: "If you use this software, please cite it as below."
authors:
- family-names: "Aguilar"
  given-names: "Eduardo"
  orcid: "https://orcid.org/0009-0007-6251-2350"
- family-names: "Figueredo"
  given-names: "Grazziela"
  orcid: "https://orcid.org/0000-0003-4094-7680"
title: "hcatgnet"
version: 1.0.1
doi: 10.5281/zenodo.13954089
date-released: 2024-10-18
url: "https://github.com/EdAguilarB/hcatgnet"

GitHub Events

Total
  • Release event: 2
  • Delete event: 5
  • Push event: 22
  • Pull request event: 10
  • Create event: 7
Last Year
  • Release event: 2
  • Delete event: 5
  • Push event: 22
  • Pull request event: 10
  • Create event: 7

Issues and Pull Requests

Last synced: 10 months ago

All Time
  • Total issues: 0
  • Total pull requests: 4
  • Average time to close issues: N/A
  • Average time to close pull requests: less than a minute
  • Total issue authors: 0
  • Total pull request authors: 1
  • Average comments per issue: 0
  • Average comments per pull request: 0.0
  • Merged pull requests: 4
  • Bot issues: 0
  • Bot pull requests: 0
Past Year
  • Issues: 0
  • Pull requests: 4
  • Average time to close issues: N/A
  • Average time to close pull requests: less than a minute
  • Issue authors: 0
  • Pull request authors: 1
  • Average comments per issue: 0
  • Average comments per pull request: 0.0
  • Merged pull requests: 4
  • Bot issues: 0
  • Bot pull requests: 0
View more stats
Top Authors
Issue Authors
Pull Request Authors
  • EdAguilarB (15)
Top Labels
Issue Labels
Pull Request Labels

Dependencies

requirements.txt pypi
  • CGRtools *
  • captum ==0.6.0
  • doptools *
  • icecream *
  • matplotlib ==3.7.1
  • molvs ==0.1.1
  • numpy >=1.25
  • pandas >=2.1.0
  • plotly ==5.15.0
  • rdkit *
  • scikit_learn >=1.3
  • scipy ==1.10.1
  • seaborn ==0.13.0
  • torch >=2.0.1
  • torch_geometric >=2.4.0
  • torchaudio >=2.0.2
  • tqdm >=4.66.0