Data

Tools

Indexes

Applications

Experiments

Open Source Science

eutectic-prediction

ML model based on support vector regression integrating experimental data, COSMO-RS simulations, and cheminformatic descriptors for computing the melting points of deep eutectic solvents and predicting solid-liquid equilibriums

https://github.com/astylavrinenko/eutectic-prediction

Science Score: 57.0%

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
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (7.3%) to scientific vocabulary

Keywords

cosmo-rs-descriptors deep-eutectic-solvents machine-learning melting-point-prediction solid-liquid-equilibrium
Last synced: 6 months ago · JSON representation ·

Repository

ML model based on support vector regression integrating experimental data, COSMO-RS simulations, and cheminformatic descriptors for computing the melting points of deep eutectic solvents and predicting solid-liquid equilibriums

Basic Info
  • Host: GitHub
  • Owner: AstyLavrinenko
  • Language: Jupyter Notebook
  • Default Branch: main
  • Homepage:
  • Size: 1.15 GB
Statistics
  • Stars: 5
  • Watchers: 2
  • Forks: 1
  • Open Issues: 0
  • Releases: 0
Topics
cosmo-rs-descriptors deep-eutectic-solvents machine-learning melting-point-prediction solid-liquid-equilibrium
Created over 3 years ago · Last pushed over 2 years ago
Metadata Files
Readme Citation

README.md

Prerequisites

  • Python 3.7.15 # Requirements
  • conda config --append channels conda-forge
  • conda install --file requirements.txt # Prediction of melting temperature for deep eutectic solvents

Deep eutectic solvents (DESs) represent an environmental-friendly alternative to the conventional organic solvents. The application area of DESs is determined by their liquid range, thus, the prediction of solid-liquid equilibrium (SLE) diagram is essential for the development of new DESs. Herein, we present machine learning model based on support vector regression for computing melting points of DESs.

The data that support the findings of this study are openly available in this repository https://github.com/AstyLavrinenko/Eutectic-prediction

There are dataset, generated descriptors, feature selection and optimisation algorithms, and developed machine learning model which were used in the project. Such descriptors as sigmamoments, sigmaprofiles, and infinite_dilution were calculated using COSMOtherm software.

Reference

If you are utilizing data from this repository, please include a citation referencing https://doi.org/10.1021/acssuschemeng.3c05207

Citation (CITATION.cff) 

# This CITATION.cff file was generated with cffinit.
# Visit https://bit.ly/cffinit to generate yours today!

cff-version: 1.2.0
title: >-
  Machine Learning Approach for the Prediction of Eutectic  
  Temperatures for Metal-Free Deep Eutectic Solvents
message: >-
  If you use this software, please cite it using the
  metadata from this file.
type: software
authors:
  - given-names: Anastasia K.
    family-names: Lavrinenko
    orcid: 'https://orcid.org/0000-0001-9863-8325'
  - given-names: Ivan Yu.
    family-names: Chernyshov
    orcid: 'https://orcid.org/0000-0002-4452-2025'
  - given-names: Evgeny A.
    family-names: Pidko
    orcid: 'https://orcid.org/0000-0001-9242-9901'
identifiers:
  - type: doi
    value: 10.1021/acssuschemeng.3c05207
repository-code: 'https://github.com/AstyLavrinenko/Eutectic-prediction'
abstract: >-
  Deep eutectic solvents (DESs) represent an
  environmental-friendly alternative to conventional organic
  solvents. Their liquid range determines the areas of
  application and therefore the prediction of the
  solid-liquid equilibrium (SLE) diagrams is essential for
  the development of new DESs. Such predictions are not yet
  possible using the current state-of-the-art computational
  models. Herein we present an alternative model based on
  support vector regression integrating experimental data,
  COSMO-RS simulations and cheminformatic descriptors for
  computing the melting points of DESs and predicting SLEs.
  The model was developed based on the manually collected
  database of 1648 mixture melting temperatures for 237
  experimentally described DESs and its accuracy was
  demonstrated by 5-fold cross-validation (R2 ~ 0.8). The
  presented methodology holds promise as a basis for the
  automated high-throughput screening of molecular
  combinations in the search for new DESs compositions with
  pre-defined characteristics.
keywords:
  - deep eutectic solvents
  - COSMO-RS
  - machine learning
  - solid-liquid equilibrium
  - melting point prediction
license: MIT
date-released: '2023-02-01'

GitHub Events

Total
  • Watch event: 3
  • Fork event: 1
Last Year
  • Watch event: 3
  • Fork event: 1