The intend is to solve the forward-reaction prediction problem, where the reactants are known and the interest is in generating the reaction products using Deep learning. This Graphical User Interface takes simplified molecular-input line-entry system (SMILES) as an input and generates the product SMILE & molecule.

Beam search is used in Version 2, to generate top 5 predictions.
Maximum input length for the model is 15 (excluding spaces).

Features

  • Cheminformatics
  • Neural Networks
  • NLP
  • Deep Learning
  • Python
  • Qt
  • SMILES

Project Samples

Project Activity

See All Activity >

License

MIT License

Follow CRP - Chemical Reaction Prediction

CRP - Chemical Reaction Prediction Web Site

You Might Also Like
Gen AI apps are built with MongoDB Atlas Icon
Gen AI apps are built with MongoDB Atlas

The database for AI-powered applications.

MongoDB Atlas is the developer-friendly database used to build, scale, and run gen AI and LLM-powered apps—without needing a separate vector database. Atlas offers built-in vector search, global availability across 115+ regions, and flexible document modeling. Start building AI apps faster, all in one place.
Start Free
Rate This Project
Login To Rate This Project

User Reviews

Be the first to post a review of CRP - Chemical Reaction Prediction!

Additional Project Details

Operating Systems

Linux, Windows

User Interface

Qt

Programming Language

Python

Related Categories

Python Chemistry Software, Python Machine Learning Software, Python Deep Learning Frameworks, Python Natural Language Processing (NLP) Tool

Registered

2018-07-12