Search

The recent advances in computational chemistry rely on large data collections of chemical compounds and reactions. However, not all entries in these datasets are correct. Toniato and colleagues present here an automated approach to identify incorrect reactions, using the effect of catastrophic forgetting in neural networks.

Organic chemical reactions can be divided into classes that allow chemists to use the knowledge they have about optimal conditions for specific reactions in the context of other reactions of similar type. Schwaller et al. present here an efficient method based on transformer neural networks that learns a chemical space in which reactions of a similar class are grouped together.

Humanity’s Last Exam, a multi-modal benchmark at the frontier of human knowledge, is designed to be an expert-level closed-ended academic benchmark with broad subject coverage.

Reaction optimisation is a challenging yet essential process in chemistry. Here, authors develop a machine learning framework for automated and highly parallel multi-objective reaction optimisation, validated in pharmaceutical process development.

Multi-fidelity Bayesian optimization methods are studied on molecular and material discovery tasks, and guidelines are provided to recommend cheaper and informative low-fidelity sources when using this technique in experimental settings.

The fast evaluation of global minimum adsorption energy (GMAE) is crucial for catalyst screening. Here, authors designed a multi-modal transformer called AdsMT to rapidly predict the GMAE without site binding information

In organic chemistry, synthetic routes for new molecules are often specified in terms of reacting molecules only. The current work reports an artificial intelligence model to predict the full sequence of experimental operations for an arbitrary chemical equation.

Large language models can be queried to perform chain-of-thought reasoning on text descriptions of data or computational tools, which can enable flexible and autonomous workflows. Bran et al. developed ChemCrow, a GPT-4-based agent that has access to computational chemistry tools and a robotic chemistry platform, which can autonomously solve tasks for designing or synthesizing chemicals such as drugs or materials.

Large language models are increasingly used for diverse tasks, yet we have limited insight into their understanding of chemistry. Now ChemBench—a benchmarking framework containing more than 2,700 question–answer pairs—has been developed to assess their chemical knowledge and reasoning, revealing that the best models surpass human chemists on average but struggle with some basic tasks.

Organic reactions can readily be learned by deep learning models, however, stereochemistry is still a challenge. Here, the authors fine tune a general model using a small dataset, then predict and validate experimentally regio- and stereo-selectivity for various carbohydrates transformations.

A computational deep learning approach is used to design synthetic proteins that target the neosurfaces formed by protein–ligand interactions, with applications in the development of new therapeutic modalities such as molecular glues or cell-based therapies.

Machine learning techniques are widely employed in chemical science, but are application specific and their development requires dedicated expertise. Jablonka and colleagues fine-tune the GPT-3 model and show that it can provide surprisingly accurate answers to a wide range of chemical questions.

Extracting experimental operations for chemical synthesis from procedures reported in prose is a tedious task. Here the authors develop a deep-learning model based on the transformer architecture to translate experimental procedures from the field of organic chemistry into synthesis actions.

Data-driven generative methods have the potential to greatly facilitate molecular design tasks for drug design.

Explainable artificial intelligence (XAI) can be used to extract input-output relationships, making them a useful tool in chemistry to understand structure-property relationships, but a key limitation of XAI methods is that they are developed for technically oriented users. Here, an XpertAI framework that integrates XAI methods with large language models is developed, enabling automatic generation of accessible natural language explanations of raw chemical data.

The largest available database of potentially exfoliable 2D materials has been obtained via high-throughput calculations using van der Waals density functional theory.

Advances in computational omics technologies are enabling access to the hidden diversity of natural products, and artificial intelligence approaches are facilitating key steps in harnessing the therapeutic potential of such compounds, including biological activity prediction. This article discusses synergies between these fields to effectively identify drug candidates from the plethora of molecules produced by nature, and how to address the challenges in realizing the potential of these synergies.