We provide our recommendations on effectively writing computational science manuscripts.

Training foundation models often requires a costly budget and excessive computational resources. In this study, a low-cost instruction learning framework is proposed that could enable the rapid adoption of visual-language pathology applications.

An associative-learning-enhanced model, called OrganADR, is developed to predict adverse drug reactions at the organ level. OrganADR could be applied in emerging combination pharmacotherapies and improve medication safety.

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.

This study presents a co-designed neuromorphic computing and neural network system for efficient and affordable modeling of ionic and electronic interactions in large-scale material systems.

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.

In this Resource, the authors present FedProt, a tool that enables privacy-preserving, federated differential protein abundance analysis across multiple institutions. Its results match the results of centralized analysis, enabling secure, collaborative proteomics without sensitive data sharing.

A neural code conversion method is introduced using deep neural network representations to align brain data across individuals without shared stimuli. The approach enables accurate inter-individual brain decoding and visual image reconstruction across sites.

Researchers replicated 156 psychological experiments using three large language models (LLMs) instead of human participants. LLMs achieved 73–81% replication rates but showed amplified effect sizes and challenges with socially sensitive topics.

Predicting the effects of mutations on antibody–antigen binding is a key challenge in therapeutic antibody development. Orders of magnitude more data will be needed to unlock accurate, robust prediction.

The adoption of generative artificial intelligence (AI) code assistants in scientific software development is promising, but user studies across an array of programming contexts suggest that programmers are at risk of over-reliance on these tools, leading them to accept undetected errors in generated code. Scientific software may be particularly vulnerable to such errors because most research code is untested and scientists are undertrained in software development skills. This Comment outlines the factors that place scientific code at risk and suggests directions for research groups, educators, publishers and funders to counter these liabilities.

We provide our recommendations on effectively writing computational science manuscripts.

We discuss different strategies to improve the writing of titles and abstracts.

Many humanists are skeptical of language models and concerned about their effects on universities. However, researchers with a background in the humanities are also actively engaging with artificial intelligence — seeking not only to adopt language models as tools, but to steer them toward a more flexible, contextual representation of written culture.

Decision-making inherently involves cause–effect relationships that introduce causal challenges. We argue that reliable algorithms for decision-making need to build upon causal reasoning. Addressing these causal challenges requires explicit assumptions about the underlying causal structure to ensure identifiability and estimatability, which means that the computational methods must successfully align with decision-making objectives in real-world tasks.

We provide recommendations on how to write an effective presubmission enquiry.