AstraZeneca - Molecular AI's repositories
aizynthfinder
A tool for retrosynthetic planning
deep-molecular-optimization
Molecular optimization by capturing chemist’s intuition using the Seq2Seq with attention and the Transformer
DockStream
DockStream: A Docking Wrapper to Enhance De Novo Molecular Design
pysmilesutils
Utilities for working with SMILES based encodings of molecules for deep learning (PyTorch oriented)
reaction_utils
Utilities for working with datasets of chemical reactions, reaction templates and template extraction.
reinvent-hitl
Code for paper "Human-in-the-Loop Assisted de Novo Molecular Design".
aizynthtrain
Tools to train synthesis prediction models
route-distances
Tools and routines to calculate distances between synthesis routes and to cluster them.
NonadditivityAnalysis
Notebook for standardization of actvity data, nonadditivity analysis and its evaluation.
Siamese-RNN-Self-Attention
Contains code for Siamese Recurrent Neural Network with Self-Attention for Bioactivity Prediction
Levenshtein
Levenshtein SMILES augmentation for reaction datasets
IcolosCommunity
Repository contains jupyter notebooks illustrating the use of the Icolos workflow manager
maize-contrib
Contributed and additional nodes for maize
MMP_project
Code for paper
transformer_rl
Evaluation of Reinforcement Learning in Transformer-based Molecular Design
IcolosData
Contains the data required for the example workflows and jupyter notebooks utilizing the Icolos workflow manager
reinvent-scoring-gpflow
Code for paper "Human-in-the-Loop Assisted de Novo Molecular Design".