Data

Tools

Indexes

Applications

Experiments

Open Source Science

bart_lmwg_model

https://github.com/cmwoodley/bart_lmwg_model

Science Score: 44.0%

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
  • ○
    Academic publication links
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (11.7%) to scientific vocabulary
Last synced: 9 months ago · JSON representation ·

Repository

Basic Info
  • Host: GitHub
  • Owner: cmwoodley
  • License: cc-by-4.0
  • Language: Jupyter Notebook
  • Default Branch: master
  • Size: 26.3 MB
Statistics
  • Stars: 0
  • Watchers: 1
  • Forks: 0
  • Open Issues: 0
  • Releases: 3
Created about 3 years ago · Last pushed almost 2 years ago
Metadata Files
Readme License Citation

README.md

BART Model for the Rheological Property Prediction from LMWGs

This repository contains the dataset and scripts used to train BART models for the prediction of low molecular weight gelator rheological properties. The notebooks folder contains an example notebook for the prediction of rheological properties from smiles strings.

For ease of use, we also provide a Google Colab implementation of our code to predict rheological properties in a web browser.

Requirements

  • pymc3
  • arviz
  • sklearn
  • rdkit
  • matplotlib
  • seaborn

Installation

Installation should take approximately 10 minutes on a normal PC. No non-standard hardware is required.

  1. Clone this repository: git clone https://github.com/cmwoodley/BART_LMWG_model.git
  2. Create conda environment and install the required packages:

Conda installation on Windows: conda env create -f environment_windows.yml For installation on Linux (tested on WSL2 in Windows11) conda env create -f environment.yml

Usage

To build these models locally, run the training script provided in scripts/train.py: python train.py

Building models with train.py should take less than 10 minutes on a normal PC. Running train.py generates the quantitative results described in the paper.

Serialised models are saved in ./models. Summary of predictions and scoring metrics are saved in the reports folder.

An example notebook (notebooks/notebook1.ipynb) is provided with examples of predictions on a simgle LMWG and batches of LMWG.

License

Shield: CC BY-SA 4.0

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

CC BY-SA 4.0

Contact

If you have any questions or suggestions, please feel free to contact me at cwoodley@liverpool.ac.uk.

Owner

  • Login: cmwoodley
  • Kind: user

Citation (CITATION.cff) 

cff-version: 1.1.0
message: "If you use this software, please cite it as below."
authors:
  - family-names: Christopher
    given-names: Woodley
title: BART_LMWG_model
version: v1.0.1
date-released: 2023-06-20

GitHub Events

Total
Last Year

Dependencies

environment.yml pypi
  • arviz ==0.12.1
  • cachetools ==5.3.2
  • certifi ==2024.2.2
  • cftime ==1.6.3
  • contourpy ==1.1.1
  • cycler ==0.12.1
  • deprecat ==2.1.1
  • dill ==0.3.5.1
  • fastprogress ==1.0.3
  • filelock ==3.13.1
  • fonttools ==4.49.0
  • importlib-resources ==6.1.1
  • joblib ==1.3.2
  • kiwisolver ==1.4.5
  • llvmlite ==0.39.1
  • matplotlib ==3.7.5
  • netcdf4 ==1.6.5
  • numba ==0.56.0
  • numpy ==1.20.3
  • pandas ==2.0.3
  • patsy ==0.5.6
  • pillow ==10.2.0
  • pymc3 ==3.11.5
  • pyparsing ==3.1.1
  • pytz ==2024.1
  • rdkit ==2023.9.5
  • scikit-learn ==1.3.2
  • scipy ==1.7.3
  • seaborn ==0.13.2
  • semver ==3.0.2
  • theano-pymc ==1.1.2
  • threadpoolctl ==3.3.0
  • tzdata ==2024.1
  • wrapt ==1.16.0
  • xarray ==2023.1.0
  • xarray-einstats ==0.5.1