Articles in 2022

Policymakers and researchers consistently call for greater human accountability for AI technologies. We should be clear about two distinct features of accountability.

The performance of machine learning models is usually compared via the mean value of a selected performance measure such as the area under the receiver operating characteristic curve on a specific benchmark data set. However, this measure, its mean value or even relative differences between models do not provide a good prediction of whether the results can translate to other data sets. Gosiewska and colleagues present here a comparison based on Elo ranking, which offers a probabilistic interpretation of how much better one model is than another.

In animals, both body and neural control have co-evolved to be adaptable to the environment. While a newborn foal learns quickly how to use its legs, traditional robotic approaches require careful engineering and calibration for stable walking robots. Bio-inspired robotics aims to bridge this gap.

Producing high-quality 3D refractive index maps from 2D intensity-only measurements is a long-standing objective in computational microscopy, with many applications involving the visualization of cellular and subcellular structures. A new method can reconstruct high-contrast and artefact-free images by employing the neural fields technique, which can learn a continuous 3D representation using a neural network that maps spatial coordinates to the refractive index values.

Genomic sequencing offers a wealth of information that could be analysed with deep neural networks. But despite good performance, neural networks can choose random features for their prediction. Kassani et al. present a method to stabilize the features selected by a DNN to make it more interpretable.

To understand reactions in organic chemistry, ideally simple rules would help us predict the outcome of new reactions, but in reality such rules are not easily identified. Chen and Jung extract generalized reaction templates from data and show that they can be used in graph neural networks to predict the outcome of reactions and, despite simplification, still represent a high percentage of existing reactions.

PROTACs can directly and selectively degrade proteins, which opens promising applications in the design of novel drugs, but designing effective PROTACs is a hard challenge due to the complexity of pharmacokinetics. Zheng et al. use a deep generative model to create likely candidates and screen them further to identify a novel BRD4-degrading PROTAC.

Changing weather conditions pose a challenge for autonomous vehicles. Almalioglu and colleagues use a geometry-aware learning technique that fuses visual, lidar and radar information, such that the benefits of each can be used under different weather conditions.

There is growing interest in using machine learning to mitigate climate change. But as avoiding catastrophic temperature rises becomes more urgent, action is also needed to understand the environmental impact of machine learning research.

Kinetic models of metabolism capture time-dependent behaviour of cellular states and provide valuable insights into cellular physiology, but, due to the lack of experimental data, traditional kinetic modelling can be unreliable and computationally inefficient. A generative framework based on deep learning called REKINDLE can efficiently parameterize large-scale kinetic models, enabling new opportunities to study cellular metabolic behaviour.

Single-cell datasets continue to grow in size and complexity, calling for computational tools to process and analyse data. Yang et al. present a contrastive learning framework to learn cell representations from single-cell multiomics datasets.

Federated learning and unsupervised anomaly detection are common techniques in machine learning. The authors combine them, using multicentred datasets and various diseases, to automate the segmentation of brain abnormalities without the need for annotations or sharing private local data.

It has become rapidly clear in the past few years that the creation, use and maintenance of high-quality annotated datasets for robust and reliable AI applications requires careful attention. This Perspective discusses challenges, considerations and best practices for various stages in the data-to-AI pipeline, to encourage a more data-centric approach.

Designing viable molecular candidates is pivotal to devising low-cost and sustainable storage systems. A reinforcement learning framework has been developed that can identify stable candidates for redox flow batteries in the large search space of organic radicals.

Directed, active transport of cargo is essential for life on all length scales. A new system of artificial microtubules — consisting of a fibre with an embedded periodic array of magnetic inclusions — provides controlled active transport of microcargo by a rotating magnetic field, even under adverse flow conditions.

Finding stable radical compounds for redox flow batteries is a challenging molecular design task. Sowndarya et al. combine an AlphaZero-based framework with a surrogate objective function trained on quantum chemistry simulations to generate suitable radical candidates that are stable. The approach promises to contribute to the development of low-cost, reliable energy storage technologies.

Deep learning models for sequential data can be trained to make accurate predictions from large biological datasets. New tools from computer vision and natural language processing can help us make these models interpretable to biologists.

Targeted drug delivery is an exciting application of nanorobotics, but directing particles in the blood stream to the right location and in sufficient number is challenging. Gu and colleagues have developed a microtubule scaffold with embedded micromagnets that allows cargo, such as drug particles, to be transported in microvascular networks with precision and speed.