News & Views

To address the challenge of pretraining foundational models with large datasets, a multi-task approach is proposed, thus helping to overcome the data scarcity problem in biomedical imaging.

A recent study proposes a computational method for the design of free-form metamaterials systems. The method simplifies the design process by avoiding the use of anisotropic materials that are usually required for the conventional methods. The method can be applied in designing both two-dimensional and three-dimensional metamaterials that are subject to multiple physical fields.

A method leverages protein structural data to predict T-cell receptor–peptide interactions for unseen peptide epitopes, which can be particularly useful for applications in cancer immunotherapy, autoimmunity studies, and vaccine design.

A recent study shows that, by leveraging nonlinear optical processes in disordered media, photonic processors can transform high-dimensional machine-learning data, using nonlinear functions that are otherwise challenging for digital electronic processors to compute.

A two-stage learning algorithm is proposed to directly uncover the symbolic representation of rules for skill acquisition from large-scale training log data.

CASTLE, a deep learning approach, extracts interpretable discrete representations from single-cell chromatin accessibility data, enabling accurate cell type identification, effective data integration, and quantitative insights into gene regulatory mechanisms.

MISATO, a dataset for structure-based drug discovery combines quantum mechanics property data and molecular dynamics simulations on ~20,000 protein–ligand structures, substantially extends the amount of data available to the community and holds potential for advancing work in drug discovery.

Multicellular modeling is increasingly being used to understand biological systems. SimuCell3D is a tool that allows mechanically realistic simulations, using the deformable cell model, to be developed and run.

Cooperation is crucial for human prosperity, and population structure fosters it through pairwise interactions and coordinated behavior in larger groups. A recent study explores the evolution of behavioral strategies in higher-order population structures, including pairwise and multi-way interactions to reveal that higher-order interactions promote cooperation across networks, especially when they are formed by conjoined communities.

A recent study introduces a machine learning approach to investigate the effects of mutations on protein sensors commonly employed in fluorescence microscopy, thus enabling the discovery of high-performance sensors.

A neural network-based method for advancing orbital-free density functional theory (OFDFT) is developed, which reaches DFT accuracy and maintains lower cost complexity.

Determining what guest can effectively bind in a host, or the reverse, is a central challenge in chemistry. To address this, an electron-density-based transformer method of generating and optimizing host–guest binders is proposed, applied to two different host systems and validated by experiment.

One of the greatest limitations of deep neural networks is the difficulty of interpreting what they learn from the data. Deep distilling addresses this problem by extracting human-comprehensible and executable code from observations.

A method for correcting errors in the spatial-genetic reconstruction of DNA microscopy is proposed, leading to more accurate results and potential to resolve new biology.

A technique that leverages duplicate records in crowdsourcing data could help to mitigate the effects of biases in research and services that are dependent on government records.

EmerGNN is a flow-based graph neural network (GNN) approach that advances on conventional methodologies for predicting drug–drug interactions in emerging drugs by effectively leveraging biomedical networks.

It is difficult to identify stable surface reconstructions of complex materials. Now a Monte Carlo sampling strategy is coupled with a machine learning interatomic potential that is iteratively improved via active learning during the search.

Enzymatic pathways control a host of cellular processes, but the complexity of such pathways has made them difficult to predict. Elektrum combines neural architecture search, kinetic models and transfer learning to effectively discover CRISPR–Cas9 cleavage kinetics.

The visualization and analysis of biological events using fluorescence microscopy is limited by the noise inherent in the images obtained. Now, a self-supervised spatial redundancy denoising transformer is proposed to address this challenge.

A recent study presents an approach for characterizing and quantifying the pore space in assemblies of particles, enabling research into pore-scale flow physics and insight into the interplay between the solid and void phases in granular materials.