modlab (Computer-Assisted Drug Design group ETH Zürich)'s repositories
virtual_libraries
Supporting code for the paper «Generative molecular design in low data regimes»
dragonfly_gen
De novo drug design with deep interactome learning
de_novo_design_RNN
Code for "De novo molecular design with chemical language models"
hybridCLMs
Supporting code for the paper «Leveraging molecular structure and bioactivity with chemical language models for drug design»
scaffold_hopping_whales
Code to perform scaffold hopping and virtual screening using WHALES descriptors.
whales_descriptors
python code for calculating the WHALES (Weighted Holistic Atom Localization and Entity Shape) molecular descriptors
LSTM_peptides
Long short-term memory recurrent neural networks for learning peptide and protein sequences to later design new, similar examples.
rna_binding
Translating from Proteins to Ribonucleic Acids for Ligand-Binding Site Detection
ai-on-a-chip
This code was written for the publication "Combining generative artificial intelligence and on-chip synthesis for de novo drug design"
compress_fingerprints
Autoencoder compression of fingerprints
delfta
Δ-QML for medicinal chemistry
minisci
Identifying opportunities for late-stage C-H alkylation with in silico reaction screening and high-throughput experimentation