Volume 5 Issue 7, July 2023

With the explosion of machine learning models of increasing complexity for research applications, more attention is needed for the development of good quality codebases. Sören Dittmer, Michael Roberts and colleagues discuss how to embrace guiding principles from traditional software engineering, including the approach to incrementally grow software, and to use two types of feedback loop, testing correctness and efficacy.

Sustainability awareness is lacking in the development of AI systems and algorithms for healthcare. The authors discuss resource sustainability issues in energy, storage and domain knowledge, and present potential solutions.

The temporal nature of the transcriptome is important for understanding many biological processes, but it is challenging to measure. By leveraging datasets with multiple time series, Woicik and colleagues present a model that accurately extrapolates genomic measurements to unmeasured timepoints, including developmental gene expression, drug-induced perturbations and cancer gene mutations.

The stochastic features of memristors make them suitable for computation and probabilistic sampling; however, implementing these properties in hardware is extremely challenging. Lin et al. introduce an approach that leverages the cycle-to-cycle read variability of memristors as a physical random variable for in situ, real-time random number generation, and demonstrate it on a risk-sensitive reinforcement learning task.

It is challenging to obtain a sufficient amount of high-quality annotated images for deep-learning applications in medical imaging, and practical methods often use a combination of labelled and unlabelled data. A dual-view framework builds on such semi-supervised approaches and uses two independently trained critic networks that learn from each other to generate segmentation masks in different medical imaging modalities.

Integrating gene expression across tissues is crucial for understanding coordinated biological mechanisms. Viñas et al. present a neural network for multi-tissue imputation of gene expression, exploiting the shared regulatory architecture of tissues.

Computer-aided drug design has a high computational cost and a newly identified drug candidate might be unsuitable due to a range of drug properties. Lam and colleagues trained a model based on graph convolutional variational encoders that predicts a range of properties simultaneously to accelerate virtual screening.

Reaction–diffusion processes, which can be found in many fundamental spatiotemporal dynamical phenomena in chemistry, biology, geology, physics and ecology, can be modelled by partial differential equations (PDEs). Physics-informed deep learning approaches can accelerate the discovery of PDEs and Rao et al. improve interpretability and generalizability by strong encoding of the underlying physics structure in the neural network.

Optimal control of quantum many-body systems is needed to make use of quantum technologies, but is challenging due to the exponentially large dimension of the Hilbert space as a function of the number of qubits. Metz and Bukov propose a framework combining matrix product states and reinforcement learning that allows control of a larger number of interacting quantum particles than achievable with standard neural-network-based methods.

This Reusability Report revisits a recently developed machine learning method for precision oncology, called ‘transfer of cell line response prediction’ (TCRP). Emily So et al. confirm the reproducibility of the previously reported results in drug-response prediction and also test the reusability of the method on new case studies with clinical relevance.

Federated learning can be used to train medical AI models on sensitive personal data while preserving important privacy properties; however, the sensitive nature of the data makes it difficult to evaluate approaches reproducibly on real data. The MedPerf project presented by Karargyris et al. provides the tools and infrastructure to distribute models to healthcare facilities, such that they can be trained and evaluated in realistic settings.