Beyond Drug Discovery: The Nanotechnology Molecular Optimization (NMO) Benchmark
Abstract
Generative molecular design is shaped by simple proxy benchmarks for drug-like properties and models pretrained on large pharmaceutical datasets. This combination yields strong benchmark metrics but limits transferability to domains structurally distinct from drug discovery. To overcome this limitation and drive discovery toward real, scientifically grounded targets, we introduce the Nanotechnology Molecular Optimization (NMO) Benchmark, which bridges machine learning (ML) and quantum materials science. NMO acts simultaneously as a rigorous testbed for the ML community and a discovery engine for nanotechnology research. The suite replaces proxy oracles with quantum simulations and introduces strict protocols that prioritize scientific utility over leaderboard-oriented overfitting. The physics-based NMO tasks impose hard structural constraints and rugged fitness landscapes, posing fundamentally new requirements on generative models. Notably, advanced molecular optimization methods underperform much simpler approaches on the NMO tasks. We develop a new baseline method identifying the critical components to solve the NMO tasks, including a novel representation for modeling structural constraints and a domain-agnostic pretraining strategy to eliminate pharmaceutical dataset bias. Our results surpass state-of-the-art physical properties and reveal previously unknown structural motifs, offering new insights for the nanotechnology community and demonstrating that ML can drive genuine scientific discovery.
Related
- MLIP Detective: Active Failure Mode Discovery Beyond Benchmark Scores for Machine-Learning Interatomic Potentials
- The Pnictogen Oracle Provider: Multi-Fidelity Graph Landscapes To Benchmark Molecular Optimization
- Rescuable Stagnation: A Diagnostic for Benchmark Suitability in LLM-Guided Materials Optimization
- Accuracy, Reliability, and Efficiency of a MACE Machine-Learning Interatomic Potential for Aspirin: A Reproducible Benchmark for Molecular Simulation
- Hybrid-CatBoost: an empirical comparison of molecular representations for aqueous-solubility prediction on the TDC benchmark
BibTeX
@misc{blaschke2026beyond,
title = {{Beyond Drug Discovery: The Nanotechnology Molecular Optimization (NMO) Benchmark}},
author = {Matthias Blaschke and Daniel Kienzle and Zsuzsanna Koczor-Benda and Julian Lorenz and Rainer Lienhart and Fabian Pauly},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2606.30170},
eprint = {2606.30170},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2606.30170},
}
RIS
TY - UNPB
TI - Beyond Drug Discovery: The Nanotechnology Molecular Optimization (NMO) Benchmark
AU - Matthias Blaschke
AU - Daniel Kienzle
AU - Zsuzsanna Koczor-Benda
AU - Julian Lorenz
AU - Rainer Lienhart
AU - Fabian Pauly
PY - 2026
DA - 2026/09/25
PB - arXiv
DO - 10.48550/arxiv.2606.30170
UR - https://arxiv.org/abs/2606.30170
AB - Generative molecular design is shaped by simple proxy benchmarks for drug-like properties and models pretrained on large pharmaceutical datasets. This combination yields strong benchmark metrics but limits transferability to domains structurally distinct from drug discovery. To overcome this limitation and drive discovery toward real, scientifically grounded targets, we introduce the Nanotechnology Molecular Optimization (NMO) Benchmark, which bridges machine learning (ML) and quantum materials science. NMO acts simultaneously as a rigorous testbed for the ML community and a discovery engine for nanotechnology research. The suite replaces proxy oracles with quantum simulations and introduces strict protocols that prioritize scientific utility over leaderboard-oriented overfitting. The physics-based NMO tasks impose hard structural constraints and rugged fitness landscapes, posing fundamentally new requirements on generative models. Notably, advanced molecular optimization methods underperform much simpler approaches on the NMO tasks. We develop a new baseline method identifying the critical components to solve the NMO tasks, including a novel representation for modeling structural constraints and a domain-agnostic pretraining strategy to eliminate pharmaceutical dataset bias. Our results surpass state-of-the-art physical properties and reveal previously unknown structural motifs, offering new insights for the nanotechnology community and demonstrating that ML can drive genuine scientific discovery.
ER -