OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
AI Models

Plapt

Plapt is a pretrained-transformer model with command-line and Python interfaces for predicting protein–ligand binding affinity from protein sequences and ligand strings.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Plapt — OpenViST project profile in AI Models.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Plapt when protein sequence and ligand-string inputs are available and the task is to generate model-based affinity estimates for candidate comparison or a research workflow.

Who it is for

  • Drug-discovery researchers comparing candidate ligands for a protein.
  • Developers and research teams incorporating affinity prediction into command-line or Python workflows.

Documented uses

  • Estimate binding affinity for one protein and multiple ligand candidates.
  • Predict affinity across multiple protein–ligand inputs.
  • Save CLI prediction results to a JSON file.
  • Call candidate-scoring and affinity-prediction functions from Python.
Before you choose

Requirements & limits

The public repository identifies the project as MIT-licensed. Its README documents local CLI and Python use, as well as Docker.

  • Inputs are one-dimensional protein sequences and ligand strings, rather than a documented graphical workflow.
  • The README names ProtBERT and ChemBERTa as pretrained feature encoders and describes a branching neural-network architecture.
  • The project offers both CLI and Python usage; the CLI can save output to JSON.
  • The Docker image may download additional model weights on first use inside the container.

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

Predict candidate affinities with the CLI

Submit protein sequence and ligand strings to the command-line interface and save prediction results.

Before you start

  • A local copy of the repository.
  • Conda, or Python 3 with virtual-environment support and pip.
  • Protein sequence and ligand strings in the input formats shown in the README.

Steps

  1. Clone the repository and change into its directory.

  2. Set up the environment with Conda using environment.yml, or create and activate a Python virtual environment and install requirements.txt.

  3. Run plapt_cli.py with -t for protein sequence input and -m for one or more ligand strings.

  4. Add -o results.json to write results to a file.

Expected outcome

The CLI returns affinity predictions for the supplied protein–ligand input and can save results as JSON.

Guide limitations

  • The guide follows the repository’s documented commands; they have not been executed here.
  • The README notes that a Docker image does not contain all model weights; first use inside the container downloads them.
Documentation 1 ↗
Evidence and transparency

Sources & review

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