News & Views

Filter By:

Article Type
Year
  • The problem of automatically determining state variables for physical systems is challenging, but essential in the modeling process of almost all scientific and engineering processes. A deep neural network-based approach is proposed to find state variables for systems whose data are given as video frames.

    • Boris Kramer
    News & Views
  • The design of protein sequences that can precisely fold into pre-specified 3D structures is a challenging task. A recently proposed deep-learning algorithm improves such designs when compared with traditional, physics-based protein design approaches.

    • Jue Wang
    News & Views
  • A graph neural network-based tool is introduced to perform unsupervised cell clustering using spatially resolved transcriptomics data that can uncover cell identities, interactions, and spatial organization in tissues and organs.

    • Xin Zhou
    News & Views
  • Aptamers are expected to be next-generation drugs, but identifying candidate aptamers is a challenging task given the large search space. Now, an artificial intelligence (AI)-powered tool called RaptGen is proposed for improving the successful identification of aptamer sequences.

    • Majid Khabbazian
    • Hosna Jabbari
    News & Views
  • Characterizing the brain’s connectome at multiple scales is essential for unraveling fundamental principles of cortical information processing and how it impacts behavior. A GPU-based implementation for connectome pruning is proposed, achieving greater than 100-fold speedups over previous CPU-based implementations.

    • Xi-Nian Zuo
    News & Views
  • The identification of robust and generalizable biomarkers based on microbial abundance data is a challenging task. An algorithm shows an enhanced classification performance by quantifying shifts in microbial co-abundances.

    • Leo Lahti
    News & Views
  • Variational Monte Carlo is one of the most accurate methods to solve the many-electron Schrödinger equation, but suffers from high computational cost. A recent study uses a weight-sharing technique to accelerate the neural network-based variational Monte Carlo method, allowing accurate and effective simulations of molecules.

    • Huan Tran
    News & Views
  • A dynamic model of SARS-CoV-2 transmission is integrated with a 63-sector economic model to identify control strategies for optimizing economic production while keeping schools and universities operational, and for constraining infections such that emergency hospital capacity is not exceeded.

    • Aditya Goenka
    • Lin Liu
    News & Views
  • A robust and reliable codec is the backbone for any digital DNA storage. A recent work introduces a codec based on ancient Chinese philosophy, yin–yang, that outperforms other codecs in terms of reliability and physical information density.

    • Manish K. Gupta
    News & Views
  • Predicting the risk of acute graft-versus-host-disease after transplantation is challenging due to the presence of multimodal data and continuous evolution of disease states. A dynamic probabilistic algorithm has recently been proposed to address these challenges.

    • Vibhuti Gupta
    News & Views
  • Scallop2, a tool that enables accurate reference-guided transcriptome assembly, capitalizes on recent developments in short-read sequencing protocols for single-cell RNA sequencing by leveraging multi-end and paired-end information.

    • Guillermo E. Parada
    • Martin Hemberg
    News & Views
  • A recent study proposes a mathematical model of SARS-CoV-2 to help identify mechanistic correlates of protection, which can be used to assist in determining vaccine efficacy.

    • Joshua T. Schiffer
    News & Views
  • A combination of experimental evaluation with computational modeling sheds light on how aging and limited lifespan influence population dynamics.

    • Ata Kalirad
    • Ralf J. Sommer
    News & Views
  • A combination of Bayesian inference, physics modeling, and Markov chain Monte Carlo sampling allows for accurate inference of biomolecule numbers and their photophysical state in cellular clusters.

    • Jean-Baptiste Masson
    News & Views
  • A fast and accurate time–frequency analysis is challenging for many applications, especially in the current big data era. A recent work introduces a fast continuous wavelet transform that effectively boosts the analysis speed without sacrificing the resolution of the result.

    • Madhur Srivastava
    News & Views
  • Precise numerical simulations of turbulent flows in practical applications are still challenging. A recent quantum-inspired computational method improves the way to account for the interscale correlations in turbulence, and further sheds light on the development of quantum computing algorithms for efficient turbulence simulations.

    • Koji Fukagata
    News & Views
  • Integrating multi-modal features is challenging due to the differences in the underlying distributions of each data type and the nonlinear associations across modalities. The deepManReg model improves the identification and interpretability of associations between modalities defining complex phenotypes.

    • Daniel Osorio
    News & Views
  • An adaptive and computationally efficient machine-learning-based biasing technique for rare-event sampling is introduced, allowing an effective generation of high-dimensional free energy surfaces associated with complex processes, such as protein folding.

    • Mark E. Tuckerman
    News & Views
  • The accurate determination of correlation energy is a challenging task in many-electron quantum chemistry calculations, especially for metals. A recent work proposes an efficient scheme to speed up the calculation of correlation energy, reducing the computational time by up to two orders of magnitude.

    • Jianwei Sun
    News & Views
  • A new study proposes a full-scale model of the entorhinal cortex–dentate gyrus–CA3 network, providing a conceptual overview of the computational properties of this brain network, to show that it is an efficient pattern separator.

    • Ad Aertsen
    News & Views