Articles in 2021

A protein’s three-dimensional structure and properties are defined by its amino-acid sequence, but mapping protein sequence to protein function is a computationally highly intensive task. A new generative adversarial network approach learns from natural protein sequences and generates new, diverse protein sequence variations, which are experimentally tested.

While deep learning models have allowed the extraction of fingerprints from the structural description of molecules, they can miss information that is present in the molecular descriptors that chemists use. Shen and colleagues present a method to combine both sources of information into two-dimensional fingerprint maps, which can be used in a wide variety of pharmaceutical tasks to predict the properties of drugs.

The propagation of ultrashort pulses in optical fibres, of interest in scientific studies of nonlinear systems, depends sensitively on both the input pulse and the fibre characteristics and normally requires extensive numerical simulations. A new approach based on a recurrent neural network can predict complex nonlinear propagation in optical fibre, solely from the input pulse intensity profile, and helps to design experiments in pulse compression and ultra-broadband supercontinuum generation.

Extensive work has gone into developing peripheral auditory models that capture the nonlinear processing of the ear. But the resulting models are prohibitively slow to use at scale for most machine hearing systems. The authors present a convolutional neural network model that replicates hallmark features of cochlear signal processing, potentially enabling real-time applications.

Advanced electron microscopy and spectroscopy techniques can reveal useful structural and chemical details at the nanoscale. An unsupervised deep learning approach helps to reconstruct 3D images and observe the relationship between optical and structural properties of semiconductor nanocrystals, of interest in optoelectronic applications.

Model interpretability is important in genomics. Koo and Ploenzke show that exponential activations in the first layer of convolutional neural networks lead to interpretable and robust representations of genomic sequence motifs.

Cryo-electron microscopy (cryo-EM) can be used to determine the three-dimensional structure of proteins at atomic-scale resolution. It is challenging to observe the dynamics of proteins using cryo-EM because of their large sizes and complex structural assemblies. A new deep-learning approach called DEFMap extracts the dynamics associated with the atomic fluctuations that are hidden in cryo-EM density maps.

It is a challenging task for any research field to screen the literature and determine what needs to be included in a systematic review in a transparent way. A new open source machine learning framework called ASReview, which employs active learning and offers a range of machine learning models, can check the literature efficiently and systemically.

In drug discovery and repurposing, systematic analysis of genome-wide gene expression of chemical perturbations on human cell lines is a useful approach, but is limited due to a relatively low experimental throughput. Computational, deep learning methods can help. In this work a graph neural network called Deep Chemical Expression is developed that can predict chemical-induced gene expression profiles. It is applied to identify drug repurposing candidates for COVID-19 treatments.

Self-driving vehicles must reliably detect the drivable area in front of them in any weather condition. An actively developed sensor approach is camera-based road segmentation, but it is limited by the visible spectrum. Radar-based approaches are a promising alternative and a new method extracts the drivable area from raw radar data by training a deep neural network using paired camera data, which can be labelled automatically using pretrained computer vision models.

Organic chemical reactions can be divided into classes that allow chemists to use the knowledge they have about optimal conditions for specific reactions in the context of other reactions of similar type. Schwaller et al. present here an efficient method based on transformer neural networks that learns a chemical space in which reactions of a similar class are grouped together.

Computational augmentation of microscopic images aims at reducing the need to chemically label or stain cells to extract information. The popular U-Net model often employed for these tasks uses mostly local information. A new method for augmenting microscopic images is presented that allows for global information to be used at each step of the process.

Autonomous flight is challenging for small flying robots, given the limited space for sensors and on-board processing capabilities, but a promising approach is to mimic optical-flow-based strategies of flying insects. A new development improves this technique, enabling smoother landings and better obstacle avoidance, by giving robots the ability to learn to estimate distances to objects by their visual appearance.

To remove artefacts from medical imaging, machine learning can be a useful tool, but supervised approaches need examples of the same image with and without artefacts. Liu et al. present a method to train an artefact removal network without needing matching images of corrupted and uncorrupted images.

The transcription process of DNA is highly complex and while short DNA sequence motifs recognized by transcription factors are well known, less is known about the context in the DNA sequence that determines whether a transcription factor will actually bind its motif. Zheng and colleagues present a method that uses convolutional neural networks to identify sequence features that help predict whether transcribing proteins can bind to their target sequences in DNA.

Microrobotics offers great potential for precise drug delivery as medication can be released in the bloodstream only where it is needed. But the dynamic environment of the bloodstream is a challenge for navigation. An approach presented by Ahmed and colleagues combines magnetic and acoustic fields to allow swarms of particles to swim against a current.

The annotation of the visual signs of emotions can be important for psychological studies and even human–computer interactions. Instead of only ascribing discrete emotions, Toisoul and colleagues use a single neural network that predicts emotional labels on a spectrum of valence and arousal without separate face-alignment steps.

Reticular frameworks are crystalline porous materials with desirable properties such as gas separation, but their large design space presents a challenge. An automated nanoporous materials discovery platform powered by a supramolecular variational autoencoder can efficiently explore this space.

Turbulence modelling is an essential flow simulation tool, but is typically dependent on physical insight and engineering intuition. Novati et al. develop a multi-agent reinforcement learning approach for learning turbulence models that can generalize across grid sizes and flow conditions.

Many approved drugs can be used to treat diseases other than the one they were developed for, which has the added benefit that the safety of the drug has already been tested. To identify possible candidates for re-purposing trials, Liu et al. have developed a method to use existing electronic patient data to simulate clinical trials and identify drugs that influence the progression of diseases with which they were not previously associated.