Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain
the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in
Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles
and JavaScript.
Zeroth-order optimization is used on problems where no explicit gradient function is accessible, but single points can be queried. Hoffman et al. present here a molecular design method that uses zeroth-order optimization to deal with the discreteness of molecule sequences and to incorporate external guidance from property evaluations and design constraints.
The provisioning of information about product attributes in e-commerce environments is today left entirely to owners of online platforms. Product transparency in online stores can be increased by client-side enrichment of retailer Web pages.
A well-known internet truth is that if the product is free, you are the product being sold. But with a growing range of regulations and web content tools, users can gain more control over the data they interact with.
The black-box nature of neural networks is a concern for high-stakes medical applications in which decisions must be based on medically relevant features. The authors develop an interpretable machine learning-based framework that aims to follow the reasoning processes of radiologists in providing predictions for cancer diagnosis in mammography.
The COVID-19 pandemic sparked the need for international collaboration in using clinical data for rapid development of diagnosis and treatment methods. But the sensitive nature of medical data requires special care and ideally potentially sensitive data would not leave the organization which collected it. Xiang Bai and colleagues present a privacy-preserving AI framework for CT-based COVID-19 diagnosis and demonstrate it on data from 23 hospitals in China and the United Kingdom.
Digitally recreating the likeness of a person used to be a costly and complex process. Through the use of generative models, AI-generated characters can now be made with relative ease. Pataranutaporn et al. discuss in this Perspective how this technology can be used for positive applications in education and well-being.
To train deep learning methods to segment very small subcellular structures, the training data have to be labelled by experts as the optical effects at such a small scale and the narrow depth of focus make it difficult to identify individual structures. Sekh et al. use a physics-based simulation approach to train neural networks to automatically segment subcellular structures despite the optical artefacts.
Geometric representations are becoming more important in molecular deep learning as the spatial structure of molecules contains important information about their properties. Kenneth Atz and colleagues review current progress and challenges in this emerging field of geometric deep learning.
Newly sequenced organisms present a challenge for protein function prediction, as they lack experimental characterisation. A network-propagation approach that integrates functional network relationships with protein annotations, transferred from well-studied organisms, produces a more complete picture of the possible protein functions.
Predicting the function of proteins in newly sequenced organisms is a challenging problem. Mateo Torres et al. present here a method to transfer the functional relations from known organisms and improve the prediction using network diffusion.
To improve desired properties of drugs or other molecules, deep learning can be used to guide the optimization process. Chen et al. present a method that optimizes molecules one fragment at a time and requires fewer parameters and training data while still improving optimization performance.
Predicting binding of ligands to molecular targets is a key task in the development of new drugs. To improve the speed and accuracy of this prediction, Méndez–Lucio and colleagues developed DeepDock, a method that uses geometric deep learning to inform a statistical potential to find conformations of ligand–target pairs.
Although the initial inspiration of neural networks came from biology, insights from physics have helped neural networks to become usable. New connections between physics and machine learning produce powerful computational methods.
As service and industrial robots enter our lives, new types of cybersecurity issues emerge that involve the manipulation of a robot’s behaviour. Now is the time to develop countermeasures.
Radiofrequency pulses of different shapes can increase the efficiency of applications such as broadcasting or medical imaging, but finding the optimal shape for a specific use can be computationally costly. Shin and colleagues present a new method based on deep reinforcement learning to design radiofrequency pulses for use in MRI, which is demonstrated to cover different types of optimization goals for each application.
RNA structure profiling methods suffer from missing values in RNA structurome data. Inspired by a computer vision approach, Gong and colleagues develop a deep learning method that imputes missing RNA structure scores and increases the structural coverage of the transcriptome.
Substantial advances have been made in the past decade in developing high-performance machine learning models for medical applications, but translating them into practical clinical decision-making processes remains challenging. This Perspective provides insights into a range of challenges specific to high-dimensional, multimodal medical imaging.
The proliferation of molecular biology and bioinformatics tools necessary to generate huge quantities of immune receptor data has not been matched by frameworks that allow easy data analysis. The authors present immuneML, an open-source collaborative ecosystem for machine learning analysis of adaptive immune receptor repertoires.
Identifying a chemical substance using mass spectrometry without knowing its structure is challenging. To help detect novel designer drugs from their mass spectra, Skinnider et al. describe a generative model that is biased towards creating potentially psychoactive molecules and thus helps identify potential candidates for a specific sample.
Providing patient specific predictions for drug responses is challenging as preclinical data across a large population is hard to collect. Sharifi-Noghabi and colleagues present a semi-supervised method to predict drug response from limited data that can generalize successfully to different tissue types.