Deep drug design for molecular scaffold hopping
- 1Department of Biosystems Science and Engineering, Molecular Design Laboratory, ETH Zurich, Klingelbergstrasse 48, Basel, Switzerland, 4056
- 2Roche Pharma Research and Early Development (pRED, Hoffmann-La Roche Ltd., Grenzacherstrasse 124, Basel, Switzerland, 4070
Abstract
Structure-based virtual screening serves as a primary approach for ligand prioritization from large molecular libraries, but accurately predicting the activity of chemical entities on novel drug targets remains a formidable challenge. Here, we present an interactome-based graph transformer network for rapid bioactivity prediction and de novo ligand design. Integrating three-dimensional pocket geometry with two-dimensional ligand graphs yields a joint representation for direct affinity prediction, which generalizes well across sparse datasets. To validate practical utility, we performed a zero-shot generative ligand design to identify scaffold hops from the complex natural product ibogaine, a noncompetitive inhibitor of the serotonin transporter. The top-ranked design and its rational analogs were synthesized and exhibited equipotent isofunctional in vitro activity alongside favorable pharmacokinetic properties directly upon initial generation. This workflow establishes a blueprint for molecular engineering that seamlessly bridges the automated design of lead-like, synthetically accessible small molecules with efficient bioactivity prediction.
Related
- Scaffold hopping of furans into 3-cyanopyridines
- Synthesis of Nitrogen‐Containing Heterocyclic Scaffolds and Applications in Scaffold Hopping: Development of an Aripiprazole Analog
- GCMDiff: a condition-guided diffusion framework for pharmacophore-fragment drug discovery and target-specific molecular design
- From Generative Molecular Design to Agentic Artificial Intelligence in Drug Discovery
- Target-Specific De Novo Drug Design via Fine-Tuned Language Models and Molecular Docking, Molecular Dynamics Simulation Validation
BibTeX
@misc{pachonangona2026deep,
title = {{Deep drug design for molecular scaffold hopping}},
author = {Irene Pachon-Angona and Carl C. G. Schiebroek and Manuel G. Schriefer Treiber and Mattis Hilleke and Michael Iff and Achi Haider and Petra Schneider and Uwe Grether and Stephan Allenspach and Kenneth Atz and Gisbert Schneider},
howpublished = {ChemRxiv},
year = {2026},
month = sep,
doi = {10.26434/chemrxiv.15008337/v1},
url = {https://chemrxiv.org/doi/full/10.26434/chemrxiv.15008337/v1},
note = {CC BY},
}
RIS
TY - UNPB
TI - Deep drug design for molecular scaffold hopping
AU - Irene Pachon-Angona
AU - Carl C. G. Schiebroek
AU - Manuel G. Schriefer Treiber
AU - Mattis Hilleke
AU - Michael Iff
AU - Achi Haider
AU - Petra Schneider
AU - Uwe Grether
AU - Stephan Allenspach
AU - Kenneth Atz
AU - Gisbert Schneider
PY - 2026
DA - 2026/09/04
PB - ChemRxiv
DO - 10.26434/chemrxiv.15008337/v1
UR - https://chemrxiv.org/doi/full/10.26434/chemrxiv.15008337/v1
AB - Structure-based virtual screening serves as a primary approach for ligand prioritization from large molecular libraries, but accurately predicting the activity of chemical entities on novel drug targets remains a formidable challenge. Here, we present an interactome-based graph transformer network for rapid bioactivity prediction and de novo ligand design. Integrating three-dimensional pocket geometry with two-dimensional ligand graphs yields a joint representation for direct affinity prediction, which generalizes well across sparse datasets. To validate practical utility, we performed a zero-shot generative ligand design to identify scaffold hops from the complex natural product ibogaine, a noncompetitive inhibitor of the serotonin transporter. The top-ranked design and its rational analogs were synthesized and exhibited equipotent isofunctional in vitro activity alongside favorable pharmacokinetic properties directly upon initial generation. This workflow establishes a blueprint for molecular engineering that seamlessly bridges the automated design of lead-like, synthetically accessible small molecules with efficient bioactivity prediction.
ER -