Research articles

Knowledge of the wide array of epigenomic signals provides biological insight into the state of a give cell type, but it is infeasible to experimentally characterize all possible types of epigenomic signal in the multitude of cell types in the human body. The authors present Ocelot, a machine learning approach for imputing cell-type-specific epigenomic signals along the genome.

Quantum annealers are computational models implemented on quantum hardware that can efficiently solve combinatorial optimization problems. Annealing schedules with enhanced performance can be discovered with a Monte Carlo tree search algorithm and an enhanced version incorporating value and policy neural networks—as inspired by DeepMind’s AlphaZero.

Molecular representations are hard to design due to the large size of the chemical space, the amount of potentially important information in a molecular structure and the relatively low number of annotated molecules. Still, the quality of these representations is vital for computational models trying to predict molecular properties. Wang et al. present a contrastive learning approach to provide differentiable representations from unlabelled data.

High-throughput single-cell sequencing data can provide valuable biological insights but are computationally challenging to analyse due to the dimensionality of the data and batch-specific biases. Kopp and colleagues have developed a variational auto-encoder-based method using a novel loss function for simultaneous batch correction and dimensionality reduction.

Tropical diseases, such as malaria, can develop resistance to specific drugs. Godinez and colleagues present here a generative design approach to find new anti-malarial drugs to circumvent this resistance.

The Large Hadron Collider produces 40 million collision events per second, most of which need to be discarded by a real-time filtering system. Unsupervised deep learning algorithms are developed and deployed on custom electronics to search for rare events indicating new physics, rather than for specific events led by theory.

High-fidelity haptic sensors with three-dimensional sensing surfaces are needed to advance dexterous robotic manipulation. The authors develop a sensor design that offers accurate force sensation across a three-dimensional surface while being robust, low-cost and easy to fabricate.

The combination of object recognition and viewpoint estimation is essential for visual understanding. However, convolutional neural networks often fail to generalize to object category–viewpoint combinations that were not seen during training. The authors investigate the impact of data diversity and architectural choices on the capability of generalizing to out-of-distribution combinations.

Controllers for robotic locomotion patterns deal with complex interactions and need to be carefully designed or extensively trained. Thor and Manoonpong present a modular approach for neural pattern generators that allows incremental and fast learning.

The investigation of single-cell epigenomics with technologies such as single-cell chromatin accessibility sequencing (scCAS) presents an opportunity to expand the understanding of gene regulation at the cellular level. The authors develop a probabilistic generative model to better characterize cell heterogeneity and accurately annotate the cell type of scCAS data.

Molecules are often represented as topological graphs while their true three-dimensional geometry contains a lot of valuable information. Xiaomin Fang and colleagues present a self-supervised molecule representation method that uses this geometric data in graph neural networks to predict a range of molecular properties.

Piezoresistors can be used in strain sensors for soft machines, but the traditional design process relies on intuition and human ingenuity alone. Haitao Yang and colleagues present a method built on genetic algorithms and other machine learning methods to design and fabricate strain sensors with improved capabilities.

Neural networks have become a useful approach for predicting biological function from large-scale DNA and protein sequence data; however, researchers are often unable to understand which features in an input sequence are important for a given model, making it difficult to explain predictions in terms of known biology. The authors introduce scrambler networks, a feature attribution method tailor-made for discrete sequence inputs.

In artificial neural networks, a typical neuron generally performs a simple summation of inputs. Using computational and electrophysiological data, the authors show that a single neuron predicts its future activity. Neurons that predict their own future responses are a potential mechanism for learning in the brain and neural networks.

Routine eye clinic imaging could help screen patients with cardiovascular risk as studies indicate strong associations between biomarkers in the retina and the heart. This potential is supported by a multimodal study, employing a deep learning model, that can infer cardiac functional indices based on retinal images and demographic data.

To train machine learning models for medical imaging, large amounts of training data are needed. Zhou and colleagues instead propose a method of weak supervision which uses the information of radiology reports to learn visual features without the need for expert labelling.

Reinforcement learning has shown remarkable success in areas such as game-playing and protein folding, but it has not been extensively explored in modelling cell behaviour. The authors develop an approach that uses deep reinforcement learning to uncover collective cell behaviours and the underlying mechanism of cell migration from 3D time-lapse images of tissues.