Data

Tools

Indexes

Applications

Experiments

Open Source Science

logkpredict

https://github.com/critical-materials-institute/logkpredict

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 (11.4%) to scientific vocabulary
Last synced: 10 months ago · JSON representation ·

Repository

Basic Info
  • Host: GitHub
  • Owner: Critical-Materials-Institute
  • License: mit
  • Language: Python
  • Default Branch: main
  • Size: 5.21 MB
Statistics
  • Stars: 4
  • Watchers: 1
  • Forks: 2
  • Open Issues: 5
  • Releases: 0
Created almost 5 years ago · Last pushed about 3 years ago
Metadata Files
Readme License Citation

README.md

LOGKPREDICT

LOGKPREDICT is a code that links HostDesigner with Chemprop. LOGKPREDICT predicts stability constants, log K values, using model trained with a modified chemprop and a stability constant database that is yet-to-be released. The primary purpose for this code is to provide an additional metric to rank molecules created using HostDesigner.

Please check the documentation of HostDesigner for how to use LOGPREDICT once it is installed.

Installation of LOGKPREDICT together with the corresponding modified version of CHEMPROP:

0) Make sure that you have the Conda environment installed on your system (Linux, Mac OS, or Windows). For this purpose, use either the full Conda environment or the minimal version of Conda, which is called Miniconda.

1) Download chemprop-1.5.2 from chemprop repository.

2) Go into the main chemprop-1.5.2 directory and issue the following commands:

conda env create -f environment.yml

conda activate chemprop

pip install -e .

3) Download LOGKPREDICT from this repository, put it into a directory from the PATH on your system, and change the permissions of LOGKPREDICT to make it executable, for example by issuing the command:

chmod 755 LOGKPREDICT

4) Download model.pt from this repository and set the environmental variable LOGKPREDICT_DIR to point to the directory where model.pt resides.

Example: If using bash shell, add the line to the .bashrc file (or file containing environment variables):

export LOGKPREDICT_DIR='/path/to/directory/'

5) You can test the installation by downloading logkinput and logkoutput from this repository (and renaming logkoutput to a different name, for example logkpredict0) and issuing the command "LOGKPREDICT" in the same directory where logkinput resides. The logkoutput should coincide with logk_output0.

Owner

  • Name: Critical Materials Institute (CMI)
  • Login: Critical-Materials-Institute
  • Kind: organization
  • Email: CMIdirector@ameslab.gov

The Critical Materials Institute is a U.S. DOE Energy Innovation Hub

Citation (CITATION.cff) 

cff-version: 2.0.0
message: "If you use this software, please cite it as below."
authors:
- family-names: "Zahariev"
  given-names: "Federico"
  orcid: "https://orcid.org/0000-0002-3223-3576"
- family-names: "Pérez García"
  given-names: "Marilú"
  orcid: "https://orcid.org/0000-0001-9987-117X"
title: "LOGKPREDICT"
version: "2.0"
date-released: 2023-06
url: "https://github.com/Critical-Materials-Institute/LOGKPREDICT"

GitHub Events

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