Articles in 2022

Data visualization is widely used in science, but interpreting such visualizations is prone to error. Here a dynamic visualization is introduced for capturing more information and improving the reliability of visual interpretations.

Quantum algorithms for simulating quantum dynamics have shown promising results to overcome the difficulties from the classical counterparts. This Perspective summarizes the recent developments in the field, and further discusses the limitations and research opportunities towards the goal of quantum advantage.

A framework is presented to extrapolate the range of behaviors for influenza antibodies. Using this basis set of behaviors, the collective action of multiple antibodies can be teased apart to describe the individual antibodies within.

A computational workflow centered on probabilistic machine learning is developed to reconstruct the energy dispersion from photoemission band-mapping data. The workflow uncovers previously inaccessible momentum-space structural information at scale.

Design choices for dimensionality reduction on calcium imaging recordings are systematically evaluated, and a method called calcium imaging linear dynamical system (CILDS) is proposed for performing deconvolution and dimensionality reduction jointly.

This work provides a physics-based theoretical framework for accurate protein–ligand binding affinity estimation based on molecular dynamics simulations, enhanced sampling, non-parametric reweighting and the orientation quaternion formalism.

A hybrid functional (CF22D) with higher across-the-board accuracy for chemistry than most existing non-doubly hybrid functionals is presented by using a large database and a performance-triggered iterative supervised training method.

A density functional recommender enables chemical space exploration by selecting the best exchange–correlation functional for each system, outperforming the use of a single functional for all systems or transfer learning models.

As artificial intelligence begins to profoundly impact structural biology, one of the next challenges is to predict protein structures from individual sequences alone. A deep learning model addresses this challenge by representing single sequences with protein language models and distilling knowledge from multi-sequence structure predictors.

Antigen–antibody prediction remains a complex computational challenge. Simulations with the new Absolut! package provide novel insights into the models and datasets tackling this problem.

Leveraging both the simple pileup input and full-alignment input, small variant calling using noisy long reads has improved speed and accuracy.

In this study, a supervised protein language model is proposed to predict protein structure from a single sequence. It achieves state-of-the-art accuracy on orphan proteins and is competitive with other methods on human-designed proteins.

This study presents a model-agnostic framework that pairs deep neural operators and Bayesian experimental design for the accurate prediction of extreme events, such as rogue waves, pandemic spikes and structural ship failures.

The Absolut! framework can generate synthetic three-dimensional antibody–antigen structures to assist machine learning and dataset construction for antibody design. Most importantly, the relative machine learning performance learnt on Absolut! datasets is shown to transfer to experimental datasets.

Immunotherapy has begun to make a transformative impact on oncology practice, and mathematical modeling has been used to provide quantitative insights into this field. This Review discusses how models are being designed for direct clinical integration to improve the success rate of immunotherapy.

A method for making large-scale nanophotonic simulations more computationally efficient is proposed, enabling a wide range of studies to be less time- and memory-intensive.

To understand whether or not the design of machine learning systems can integrate domain expertise, a recent work proposes methodologies to synthesize domain science with machine learning, which shows added benefits.

Partial differential equations are typically solved on every element of a discretization basis before extracting the desired information, and each input requires one solution. In this study, a strategy is proposed to directly compute the quantities of interest, bypassing full-basis solutions and avoiding repetition over inputs.

Three machine learning methods are developed for discovering physically meaningful dimensionless groups and scaling parameters from data, with the Buckingham Pi theorem as a constraint.

Recent changes to our submission system, including a better integration with the Code Ocean platform, make the code peer review process more effortless for authors and referees.