Reviews & Analysis

Sustainability awareness is lacking in the development of AI systems and algorithms for healthcare. The authors discuss resource sustainability issues in energy, storage and domain knowledge, and present potential solutions.

An in vitro biological system of cultured brain cells has learned to play Pong. This feat opens up an avenue towards the convergence of biological and machine intelligence.

With the explosion of machine learning models of increasing complexity for research applications, more attention is needed for the development of good quality codebases. Sören Dittmer, Michael Roberts and colleagues discuss how to embrace guiding principles from traditional software engineering, including the approach to incrementally grow software, and to use two types of feedback loop, testing correctness and efficacy.

Although computer vision techniques are often data-driven, they can be enhanced by including the physical models underlying image formation as constraints. Achuta Kadambi et al. provide an overview of various techniques to incorporate physics into data-driven vision pipelines.

To fulfil the potential of quantum machine learning for practical applications in the near future, it needs to be robust against adversarial attacks. West and colleagues give an overview of recent developments in quantum adversarial machine learning, and outline key challenges and future research directions to advance the field.

A new geometric deep learning method can reconstruct cellular and subcellular trajectories and characterize mobility in microscopic imaging, for a broad range of challenging scenarios.

There are numerous algorithms for generating Shapley value explanations. The authors provide a comprehensive survey of Shapley value feature attribution algorithms by disentangling and clarifying the fundamental challenges underlying their computation.

There is a continuing demand for high-quality, large-scale annotated datasets in medical imaging supported by machine learning. A new study investigates the importance of what type of instructions crowdsourced annotators receive.

Language models trained on proteins can help to predict functions from sequences but provide little insight into the underlying mechanisms. Vu and colleagues explain how extracting the underlying rules from a protein language model can make them interpretable and help explain biological mechanisms.

Cancer diagnosis and treatment decisions often focus on one data source. Steyaert and colleagues discuss the current status and challenges of data fusion, including electronic health records, molecular data, digital pathology and radiographic images, in cancer research and translational development.

One of the main advances in deep learning in the past five years has been graph representation learning, which enabled applications to problems with underlying geometric relationships. Increasingly, such problems involve multiple data modalities and, examining over 160 studies in this area, Ektefaie et al. propose a general framework for multimodal graph learning for image-intensive, knowledge-grounded and language-intensive problems.

Predicting whether T cell receptors bind to specific peptides is a challenging problem because most binding examples in the training data involve only a few peptides. A new approach uses meta-learning to improve predictions for binding to peptides for which no or little binding data exists.

Deep space exploration missions will require new technologies that can support astronaut health systems, as well as biological monitoring and research systems that can function independently from Earth-based mission control centres. A NASA workshop explored how artificial intelligence advances could help address these challenges and, in this second of two Review articles based on the findings from the workshop, the intersection between artificial intelligence and space biology is discussed.

Deep-space exploration missions require new technologies that can support astronaut health systems as well as biological monitoring and research systems that can function independently from Earth-based mission control centres. A NASA workshop explored how artificial intelligence advances could help address these challenges and, in this first of two Review articles based on the findings from the workshop, a vision for autonomous biomonitoring and precision space health is discussed.

An increasing number of regulations demand transparency in automated decision-making processes such as in automated online recruitment. To provide meaningful transparency, Sloane et al. propose the use of ‘nutritional’ labels that display specific information about an automated decision system, depending on the context.

Predicting RNA degradation is a fundamental task in designing RNA-based therapeutic agents. Dual crowdsourcing efforts for dataset creation and machine learning were organized to learn biological rules and strategies for predicting RNA stability.

Gathering big datasets has become an essential component of machine learning in many scientific areas, but it is unavoidable that some data values are missing. An important and growing effect that needs careful attention, especially when heterogeneous data sources are combined, is that of structured missingness, where data values are missing not at random, but with a specific structure.

Machine translation of languages can now automatically detect different cell types from single-cell transcriptomic data. Such a feat opens the prospect of dissecting complex clinical samples such as heterogenous tumours at scale.

A goal of AI is to develop autonomous artificial agents with a wide set of skills. The authors propose the immersion of intrinsically motivated agents within rich socio-cultural worlds, focusing on language as a way for artificial agents to develop new cognitive functions.

Applying deep reinforcement learning to robot control poses challenges. The authors review methods for transferring deep reinforcement learning policies learned in simulation to the real world.