OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
AI Evaluation & Observability

Molscore

MolScore is a Python framework for scoring de novo compounds and evaluating and benchmarking goal-directed generative models in molecular design. It supports JSON-defined objectives, configurable score transformation and aggregation, benchmark and curriculum modes, and molecule-set metrics through its moleval subpackage.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Molscore — OpenViST project profile in AI Evaluation & Observability.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use MolScore when a de novo molecular-design workflow needs configurable compound scoring, benchmark comparisons or downstream molecule-set evaluation.

Who it is for

  • Researchers developing or evaluating generative models for de novo molecular design.
  • Teams comparing molecule-generation models, objectives or optimization methods against molecular-design benchmarks.
  • Practitioners who need configurable scoring criteria for generated compounds.

Documented uses

  • Define a multi-parameter molecular-design objective in JSON.
  • Score candidate compounds generated by a model.
  • Benchmark models, objectives or optimization methods using available presets.
  • Calculate evaluation metrics for a set of molecules.
  • Build a sequence of objectives using curriculum mode.
Before you choose

Requirements & limits

The repository is public and MIT-licensed. The README documents installation through PyPI or from GitHub.

  • Objectives are configured in JSON, and a GUI is provided to help write configuration files.
  • The scoring catalogue spans descriptors, synthesizability, similarity, QSAR and docking; the required tools depend on the functions selected.
  • The README identifies some docking tools as requiring a license.
  • The repository documents Python 3.6+; the supplied materials do not specify execution-platform guarantees.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Install MolScore from PyPI

Set up the Python package so it can be used in a molecular-design evaluation workflow.

Before you start

  • Python 3.6+ is indicated in the repository README.
  • A Python package-installation environment.

Steps

  1. Install the package with the command below.

    Documented command
    pip install molscore --upgrade

  2. Consult the repository tutorials for guidance on defining objectives or implementing scoring.

Expected outcome

The documented PyPI installation command installs MolScore; the tutorials cover the next configuration and use stages.

Guide limitations

  • This setup recipe does not run a scoring job or verify compatibility with a particular environment.
  • Some scoring options depend on external tools, and the README notes that certain docking tools require a license.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
16 October 2026
Original website title
MorganCThomas/MolScore · Official homepage title · retained in its source language
How we review sourcesSuggest a correction