Articles in 2022

Microscopy-based drug screens with fluorescent markers can shed light on how drugs affect biological processes. Without adding markers and imaging channels, which is cumbersome and costly, a new generative deep-learning method extracts new fluorescence channels from images, potentially improving the drug-discovery pipeline.

As with last summer, COVID-19 is still with us, but there is a semblance of what life was like before the pandemic. Here, we recommend AI podcasts from the past year that may inform, inspire or entertain, as we get an opportunity to travel or take time away from regular activities.

China is pushing ahead of the European Union and the United States with its new synthetic content regulations. New draft provisions would place more responsibility on platforms to preserve social stability, with potential costs for online freedoms. They show that the Chinese Communist Party is prepared to protect itself against the unique threats of emerging technologies.

Artificial intelligence (AI) can support managers by effectively delegating management decisions to AI. There are, however, many organizational and technical hurdles that need to be overcome, and we offer a first step on this journey by unpacking the core factors that may hinder or foster effective decision delegation to AI.

So-called noisy intermediate-scale quantum devices will be capable of a range of quantum simulation tasks, provided that the effects of noise can be sufficiently reduced. A neural error mitigation approach is developed that uses neural networks to improve the estimates of ground states and ground-state observables of molecules and quantum systems obtained using quantum simulations on near-term devices.

Using the natural dynamics of a legged robot for locomotion is challenging and can be computationally complex. A newly designed quadruped robot called Morti uses a central pattern generator inside two feedback loops as an adaptive method so that it efficiently uses the passive elasticity of its legs and can learn to walk within 1 h.

Neural networks can be implemented by using purified DNA molecules that interact in a test tube. Convolutional neural networks to classify high-dimensional data have now been realized in vitro, in one of the most complex demonstrations of molecular programming so far.

Artificial DNA circuits that can perform neural network-like computations have been developed, but scaling up these circuits to recognize a large number of patterns is a challenging task. Xiong, Zhu and colleagues experimentally demonstrate a convolutional neural network algorithm using a synthetic DNA-based regulatory circuit in vitro and develop a freeze–thaw approach to reduce the computation time from hours to minutes, paving the way towards more powerful biomolecular classifiers.

An end-to-end machine learning approach that can learn which mechanisms determine cell fate and competition from a large time-lapse microscopy dataset is developed. The approach makes use of a probabilistic autoencoder to learn an interpretable representation of the organization of cells, and provides cell fate predictions that can be tested in drug screening experiments.

Deep learning methods can provide useful predictions for drug design, but their hyperparameters need to be carefully tweaked to give good performance on a specific problem or dataset. Li et al. present here a method that finds appropriate architectures and hyperparameters for a wide range of drug design tasks and can achieve good performance without human intervention.

Soon into the COVID-19 pandemic, civil-rights groups raised the alarm over the increase in digital surveillance infringing on individual rights. But there are other potential harms as tech companies accelerate their expansion into new areas essential to public-service provision.

Unsupervised machine learning algorithms reduce the dependence on curated, labeled datasets that are characteristic of supervised machine learning. The authors argue that the developmental science of infant cognition could inform the design of unsupervised machine learning approaches.

Exoskeletons can assist movement in upper limb impairments to recover mobility and independence, but rigid or heavy exoskeletons can be impractical. Georgarakis and colleagues have developed a soft, tendon-driven device that assists shoulder movements and counteracts gravity to reduce muscle fatigue.

Neural networks in the brain often exhibit chaotic dynamics that can be captured by a small number of dimensions. Farrell et al. find that recurrent neural networks trained with gradient-based learning rules exhibit similar features. This helps form robust but generalizable input representations.

Robots usually learn to use tools from direct experience or from observing the use of a tool. While knowledge can be transferred between similar tools, novel and creative use of tools is challenging. Tee and colleagues present a method where skill transfer does not come from experience of using other tools but from using the robot’s own limbs.

While reinforcement learning can be a powerful tool for complex design tasks such as molecular design, training can be slow when problems are either too hard or too easy, as little is learned in these cases. Jeff Guo and colleagues provide a curriculum learning extension to the REINVENT de novo molecular design framework that provides problems of increasing difficulty over epochs such that the training process is more efficient.

Both proteins and natural language are essentially based on a sequential code, but feature complex interactions at multiple scales, which can be useful when transferring machine learning models from one domain to another. In this Review, Ferruz and Höcker summarize recent advances in language models, such as transformers, and their application to protein design.

A variational autoencoder is trained on a dataset of quantum optics experiment configurations and learns an interpretable representation of the relationship between experiment setup and quantum entanglement. The approach can be used to explore new experiment designs with specific, highly entangled states.