Other Resources

AiZynthFinder

AiZynthFinder is a free tool for retrosynthetic planning developed at AstraZeneca that C-CAS researchers contributed to. The default algorithm is based on a Monte Carlo tree search that recursively breaks down a molecule to purchasable precursors. The tree search is guided by a policy that suggests possible precursors by utilizing a neural network trained on a library of known reaction templates. This setup is completely customizable as the tool supports multiple search algorithms and expansion policies.

Publications:

Genheden, S., Thakkar, A., Chadimová, V., Reymond, J.L., Engkvist, O., Bjerrum, E., AiZynthFinder: a fast, robust and flexible open-source software for retrosynthetic planning. J. Cheminf. 2020, 12, 70. https://doi.org/10.1186/s13321-020-00472-1

Saigiridharan, L., Hassen, A.K., Lai, H., Torren-Peraire, P., Engkvist, O. and Genheden, S., 2024. AiZynthFinder 4.0: developments based on learnings from 3 years of industrial application. J. Cheminf. 2024 16..57. https://doi.org/10.1186/s13321-024-00860-x

Wiest, O., Bauer, C., Helquist, P., Norrby, P.O. and Genheden, S., 2024. Finding relevant retrosynthetic disconnections for stereocontrolled reactions. J. Chem. Inf. Mod. 2024, 64, 5796-5805. https://doi.org/10.1021/acs.jcim.4c00370

 
Tutorial material:

AiZynthFinder Tutorial


ALFABET

This library contains the trained graph neural network model for the prediction of homolytic bond dissociation energies (BDEs) of organic molecules with C, H, N, and O atoms. This package offers a command-line interface to the web-based model predictions at bde.ml.nrel.gov.

ALFABET Github


DoMiNO

DoMiNO is a multi-scale framework that decomposes MD dynamics into several temporal resolutions, each governed by a neural graph ordinary differential equation (GraphODE) and is adaptively fused for final predictions.

DoMiNO Github

Publication:

 Sun, F.; Huang, Z.; Cao, Y.; Luo, X.; Wang, W.; Sun, Y. DoMiNO: Decomposing Molecular Dynamics with Multi-Scale Neural Graph Ordinary Differential Equations. ACM Trans. Knowl. Discov. Data 2026, accepted. https://doi.org/10.1145/3822365


Hands-On Data Science for Chemists

This book serves as a practical introduction to the integration of data science and chemistry. Designed specifically for chemists, it bridges the gap between these fields, offering step-by-step tutorials and real-world applications to tackle complex chemical problems. Whether you are new to data science or looking to enhance your research with machine learning, programming, and data visualization, this guide provides the tools you need to harness the power of data science in your chemistry work.

C2D Web Book


PATRO

This repository contains the code for Pathway-Aware Template-Based Retrosynthesis (DOI: 10.1021/acs.jcim.6c01458). This single-step model augments the template relevance model from ASKCOS to consider the reaction pathway history when making predictions.

PATRO Github

Publication:

Zhang, J. J.; Ha, S. K.; Roh, J.; Tu, Z.; Verna, P.; Coley, C. W.; Jensen, K. F. Pathway-Aware Template-Based Retrosynthesis. J. Chem. Inf. Model. 2026, 66, 7489–7500. https://doi.org/10.1021/acs.jcim.6c01458


Q2MM

Q2MM stands for quantum (mechanics) to molecular mechanics or quantum guided molecular mechanics, depending on what you prefer. Q2MM is open source software for force field optimization.

Q2MM Github


TrustGen

TrustGen is the first dynamic benchmarking platform designed to evaluate trustworthiness across multiple dimensions and model types, including text-to-image, large language, and vision-language models. TrustGen leverages modular components--metadata curation, test case generation, and contextual variation--to enable adaptive and iterative assessments, overcoming the limitations of static evaluation methods.

TrustGen