Gianaurelio Cuniberti

Li Chen, Leonardo Medrano Sandonas, Shirong Huang et al.

Digital sensing faces challenges in developing sustainable methods to extend the applicability of customized e-noses to complex body odor volatilome (BOV). To address this challenge, we developed MORE-ML, a computational framework that integrates quantum-mechanical (QM) property data of e-nose molecular building blocks with machine learning (ML) methods to predict sensing-relevant properties. Within this framework, we expanded our previous dataset, MORE-Q, to MORE-QX by sampling a larger conformational space of interactions between BOV molecules and mucin-derived receptors. This dataset provides extensive electronic binding features (BFs) computed upon BOV adsorption. Analysis of MORE-QX property space revealed weak correlations between QM properties of building blocks and resulting BFs. Leveraging this observation, we defined electronic descriptors of building blocks as inputs for tree-based ML models to predict BFs. Benchmarking showed CatBoost models outperform alternatives, especially in transferability to unseen compounds. Explainable AI methods further highlighted which QM properties most influence BF predictions. Collectively, MORE-ML combines QM insights with ML to provide mechanistic understanding and rational design principles for molecular receptors in BOV sensing. This approach establishes a foundation for advancing artificial sensing materials capable of analyzing complex odor mixtures, bridging the gap between molecular-level computations and practical e-nose applications.

Federico Ravera, Leonardo Medrano Sandonas, Andrea Vezzoli et al.

Molecular Field-Coupled Nanocomputing (MolFCN) is a promising beyond-CMOS paradigm in which information is propagated electrostatically rather than through charge transport, enabling ultra-low-power logic. Identifying molecules with stable logic states, efficient clock-field switching, and reliable information propagation, however, remains an open challenge. In this Letter, we introduce LUFFY (Layered Unified Framework for MolFCN systematic analYsis), a framework for the rational design and validation of molecular candidates for MolFCN architectures. Starting from 27 synthetically accessible molecules, we combine conformational sampling and electrostatic analysis in neutral and oxidized states to derive robust descriptors of molecular response. In particular, we extract the V${in}$-to-Aggregated-Charge Transcharacteristics (VACTs), capturing the field-induced charge response, and introduce energy-averaged models validated via ab initio molecular dynamics to account for conformational diversity. Finally, we use the resulting molecular responses to evaluate device-level propagation and demonstrate stable information transfer. These results directly link molecular structure to functional information flow, identifying conformationally robust electrostatic response as a key requirement for MolFCN operation. Overall, this work establishes a unified and transferable framework for the identification and validation of MolFCN molecular candidates, bridging molecular design and circuit-level functionality. By unifying previously fragmented approaches into a sustainable methodology, LUFFY enables rational and scalable molecular discovery and establishes a foundation for data-driven design strategies that accelerate the development of ultra-low-power information processing technologies.

Leonardo Medrano Sandonas, David Balcells, Anton Bochkarev et al.

Artificial intelligence is transforming molecular and materials science, but its growing computational and data demands raise critical sustainability challenges. In this Perspective, we examine resource considerations across the AI-driven discovery pipeline--from quantum-mechanical (QM) data generation and model training to automated, self-driving research workflows--building on discussions from the ``SusML workshop: Towards sustainable exploration of chemical spaces with machine learning'' held in Dresden, Germany. In this context, the availability of large quantum datasets has enabled rigorous benchmarking and rapid methodological progress, while also incurring substantial energy and infrastructure costs. We highlight emerging strategies to enhance efficiency, including general-purpose machine learning (ML) models, multi-fidelity approaches, model distillation, and active learning. Moreover, incorporating physics-based constraints within hierarchical workflows, where fast ML surrogates are applied broadly and high-accuracy QM methods are used selectively, can further optimize resource use without compromising reliability. Equally important is bridging the gap between idealized computational predictions and real-world conditions by accounting for synthesizability and multi-objective design criteria, which is essential for practical impact. Finally, we argue that sustainable progress will rely on open data and models, reusable workflows, and domain-specific AI systems that maximize scientific value per unit of computation, enabling efficient and responsible discovery of technological materials and therapeutics.

Adrian Ehrenhofer, Thomas Wallmersperger, Gianaurelio Cuniberti

Large Language Models (LLMs) are increasingly applied in the fields of mechanical engineering and materials science. As models that establish connections through the interface of language, LLMs can be applied for step-wise reasoning through the Processing-Structure-Property-Performance chain of material science and engineering. Current LLMs are built for adequately representing a dataset, which is the most part of the accessible internet. However, the internet mostly contains non-scientific content. If LLMs should be applied for engineering purposes, it is valuable to investigate models for their intrinsic knowledge -- here: the capacity to generate correct information about materials. In the current work, for the example of the Periodic Table of Elements, we highlight the role of vocabulary and tokenization for the uniqueness of material fingerprints, and the LLMs' capabilities of generating factually correct output of different state-of-the-art open models. This leads to a material knowledge benchmark for an informed choice, for which steps in the PSPP chain LLMs are applicable, and where specialized models are required.