Nature Computational Science presents a Focus that explores the field of computational psychiatry and its key challenges, from privacy concerns to the ethical use of artificial intelligence, offering new insights into the future of mental health care.

Large language models (LLMs) offer promising ways to enhance psychotherapy through greater accessibility, personalization and engagement. This Perspective introduces a typology that categorizes the roles of LLMs in psychotherapy along two critical dimensions: autonomy and emotional engagement.

A comprehensive benchmark, called MaCBench, is developed to evaluate how vision language models handle different aspects of real-world chemistry and materials science tasks.

This study presents SciToolAgent, a large language model-based agent that orchestrates scientific tools via a knowledge graph, enabling automated and effective execution of scientific research workflows.

This study presents a neural symbolic regression approach that autonomously uncovers network dynamics from data. It was demonstrated to refine existing models of gene regulation and ecology, and identify epidemic transmission patterns across spatial scales to yield scientific insights.

Investigating crystalline materials often requires calculations for many variations of a system, substantially increasing the computational burden. By training a transferable neural wavefunction across these variations, the cost can be reduced by approximately 50-fold for systems such as graphene and lithium hydride.

This study presents ECloudGen, which uses latent diffusion to generate electron clouds from protein pockets and decodes them into molecules. The adopted two-stage training expands the chemical space accessible to generative drug design.

A large perturbation model that integrates diverse laboratory experiments is presented to predict biological responses to chemical or genetic perturbations and support various biological discovery tasks.

This study presents a flexible AI-based method for compressing microscopy images, achieving high compression while preserving details critical for analysis, with support for task-specific optimization and arbitrary-resolution decompression.

The authors introduce a method that combines physics and machine learning to design dynamic unstructured proteins with tunable ensemble properties like size, shape, sensing and binding.

In order to realize the potential of mental health AI applications to deliver improved care, a multipronged approach is needed, including representative AI datasets, research practices that reflect and anticipate potential sources of bias, stakeholder engagement, and equitable design practices.

Nature Computational Science presents a Focus that explores the field of computational psychiatry and its key challenges, from privacy concerns to the ethical use of artificial intelligence, offering new insights into the future of mental health care.

Computational psychiatry is increasingly delivering causal evidence by focusing on interventions research and clinical trials. Causal evidence could improve patient outcomes through improved precision, repurposing, novel interventions, scaling of psychotherapy and better translation to the clinic.

Self-driving laboratories that integrate robotic production with artificial intelligence have the potential to accelerate innovation in biotechnology. Because self-driving labs can be complex and not universally applicable, it is useful to consider their suitable use cases for successful integration into discovery workflows. Here, we review strategies for assessing the suitability of self-driving labs for biochemical design problems.

This issue of Nature Computational Science features a Focus that highlights both the promises and perils of large language models, their emerging applications across diverse scientific domains, and the opportunities to overcome the challenges that lie ahead.

Strong barriers remain between neuromorphic engineering and machine learning, especially with regard to recent large language models (LLMs) and transformers. This Comment makes the case that neuromorphic engineering may hold the keys to more efficient inference with transformer-like models.