Skip to content

RXN Reaction Preprocessing

IBM RXN for Chemistry

RXN Reaction Preprocessing is a pipeline for preprocessing chemical-reaction datasets, covering standardization, filtering, augmentation, splitting and tokenization.

Catalog updated ·

Overview

RXN Reaction Preprocessing is a tool from the IBM RXN for Chemistry ecosystem for preprocessing chemical-reaction data. It provides standardization, filtering, stable train/validation/test splits, data augmentation and tokenization, with an rxn-data-pipeline command-line entry point and Hydra-based structured configuration for building flexible pipelines.

It is released under MIT and distributed via PyPI (rxn-reaction-preprocessing). It is a data-preprocessing tool independent of RXN-Sandbox.

Key Features

  • Standardization, filtering and augmentation of chemical-reaction datasets.
  • Stable train/validation/test splits and tokenization.
  • `rxn-data-pipeline` entry point with Hydra-based structured configuration.

Use Cases

  • Preprocess chemical-reaction datasets for machine-learning tasks such as reaction prediction.
  • Build reaction-data pipelines combining standardization, splitting, augmentation and tokenization.

How to Use

Install with pip install rxn-reaction-preprocessing[rdkit] and run via rxn-data-pipeline. See https://rxn4chemistry.github.io/rxn-reaction-preprocessing/.

Sources and verification

This entry describes capabilities documented by the linked project sources. Catalog edits are not evidence of a successful run, compatibility test or scientific performance evaluation.

Read the editorial and verification policy

Related resources

LlaSMol

Model

LlaSMol is a family of chemistry large language models fine-tuned on the SMolInstruct instruction dataset (four released models) covering tasks such as name conversion, property prediction and reaction prediction, with the code under the MIT license.

Open sourcePython

Molecular Property Prediction · Cheminformatics · Reaction Prediction · Retrosynthesis

RxnMapper uses attention from an unsupervised ALBERT model to assign atom mappings to valid reaction SMILES, returning mapped reactions and confidence scores through a Python interface.

Open sourcePython

Cheminformatics · Reaction Prediction

rxnutils

Open Source

rxnutils is a Python toolkit for chemical reaction datasets, reaction templates and template extraction.

Open sourcePython

Cheminformatics · Reaction Prediction

AQME

Open Source

AQME builds quantum-mechanical working environments end to end: conformer generation, input preparation, output checking and descriptor calculation across its CSEARCH, CMIN, QPREP, QCORR and QDESCP modules.

Open sourcePython

Cheminformatics · Computational Chemistry · Quantum Chemistry

ASKCOS

Platforms

ASKCOS is a scientific synthesis-planning platform with retrosynthesis, forward prediction and reaction-analysis modules, offered through a hosted interface and modular deployment documentation.

Python

Reaction Prediction · Retrosynthesis

autodE

Open Source

autodE automates reaction energy profile calculation from reactant and product SMILES, including transition-state location, conformer searching and atom mapping, through wrappers for external electronic-structure codes.

Open sourcePython

Reaction Prediction · Computational Chemistry · Quantum Chemistry

Related guides

Overview

MCP vs Skills vs Agents vs APIs: What's the Difference?

Understand how APIs, MCP servers, Skills, and agents divide interface, procedural guidance, execution, and planning responsibilities in chemistry workflows—and how to choose or combine them without confusing access with scientific validity.