Search

During developmental processes such as embryogenesis, how a group of cells fold into specific structures, is a central question in biology that defines how living organisms form. Establishing tissue-level morphology critically relies on how every single cell decides to position itself relative to its neighboring cells. Despite its importance, it remains a major challenge to understand and predict the behavior of every cell within the living tissue over time during such intricate processes. To tackle this question, we propose a geometric deep learning model that can predict multicellular folding and embryogenesis, accurately capturing the highly convoluted spatial interactions among cells. We demonstrate that multicellular data can be represented with both granular and foam-like physical pictures through a unified graph data structure, considering both cellular interactions and cell junction networks. We successfully use our model to achieve two important tasks, interpretable 4-D morphological sequence alignment, and predicting local cell rearrangements before they occur at single-cell resolution. Furthermore, using an activation map and ablation studies, we demonstrate that cell geometries and cell junction networks together regulate local cell rearrangement which is critical for embryo morphogenesis. This approach provides a novel paradigm to study morphogenesis, highlighting a unified data structure and harnessing the power of geometric deep learning to accurately model the mechanisms and behaviors of cells during development. It offers a pathway toward creating a unified dynamic morphological atlas for a variety of developmental processes such as embryogenesis.

This study investigates the excesses observed in the diphoton and $b\bar b$ data around $95\;{\rm GeV}$ within the framework of the $B-L$ supersymmetric model (B-LSSM). Comparing with the minimal supersymmetric standard model, the B-LSSM incorporates two singlet chiral Higgs bosons which mix with the SM-like Higgs boson due to the gauge kinetic mixing effect. The richer Higgs sector indicates that designating the B-LSSM specific CP-even Higgs state as the lightest Higgs boson has great potential to explain the excesses at around $95\;{\rm GeV}$. Considering the two-loop effective potential corrections to the squared Higgs mass matrix, it is found that the signal strengthes $\mu(h_{95})_{\gamma\gamma}$, $\mu(h_{95})_{b b}$ can be described simultaneously in the experimental $1\sigma$ interval. And the B-LSSM specific parameters $\tan\beta'$, $B_\eta$, $g_{YB}$, $M_{Z'}$ affect the theoretical predictions on the light Higgs boson masses and signal strengthes $\mu(h_{95})_{\gamma\gamma}$, $\mu(h_{95})_{bb}$ significantly., Comment: 28 pages, 5 figures. arXiv admin note: text overlap with arXiv:2405.07243

Multicellular self-assembly into functional structures is a dynamic process that is critical in the development and diseases, including embryo development, organ formation, tumor invasion, and others. Being able to infer collective cell migratory dynamics from their static configuration is valuable for both understanding and predicting these complex processes. However, the identification of structural features that can indicate multicellular motion has been difficult, and existing metrics largely rely on physical instincts. Here we show that using a graph neural network (GNN), the motion of multicellular collectives can be inferred from a static snapshot of cell positions, in both experimental and synthetic datasets., Comment: Accepted for publication at PRX Life

Utilizing Deep Reinforcement Learning (DRL) for Reconfigurable Intelligent Surface (RIS) assisted wireless communication has been extensively researched. However, existing DRL methods either act as a simple optimizer or only solve problems with concurrent Channel State Information (CSI) represented in the training data set. Consequently, solutions for RIS-assisted wireless communication systems under time-varying environments are relatively unexplored. However, communication problems should be considered with realistic assumptions; for instance, in scenarios where the channel is time-varying, the policy obtained by reinforcement learning should be applicable for situations where CSI is not well represented in the training data set. In this paper, we apply Meta-Reinforcement Learning (MRL) to the joint optimization problem of active beamforming at the Base Station (BS) and phase shift at the RIS, motivated by MRL's ability to extend the DRL concept of solving one Markov Decision Problem (MDP) to multiple MDPs. We provide simulation results to compare the average sum rate of the proposed approach with those of selected forerunners in the literature. Our approach improves the sum rate by more than 60% under time-varying CSI assumption while maintaining the advantages of typical DRL-based solutions. Our study's results emphasize the possibility of utilizing MRL-based designs in RIS-assisted wireless communication systems while considering realistic environment assumptions., Comment: To be published in proceedings of the 2023 IEEE Conference on Global Communications (GLOBECOM)

Under many physiological and pathological conditions such as division and migration, cells undergo dramatic deformations, under which their mechanical integrity is supported by cytoskeletal networks (i.e. intermediate filaments, F-actin, and microtubules). Recent observations of cytoplasmic microstructure indicate interpenetration among different cytoskeletal networks, and micromechanical experiments have shown evidence of complex characteristics in the mechanical response of the interpenetrating cytoplasmic networks of living cells, including viscoelastic, nonlinear stiffening, microdamage, and healing characteristics. However, a theoretical framework describing such a response is missing, and thus it is not clear how different cytoskeletal networks with distinct mechanical properties come together to build the overall complex mechanical features of cytoplasm. In this work, we address this gap by developing a finite-deformation continuum-mechanical theory with a multi-branch visco-hyperelastic constitutive relation coupled with phase-field damage and healing. The proposed interpenetrating-network model elucidates the coupling among interpenetrating cytoskeletal components, and the roles of finite elasticity, viscoelastic relaxation, damage, and healing in the experimentally-observed mechanical response of interpenetrating-network eukaryotic cytoplasm.

As a unique probe, precision measurement of \textit{pp} solar neutrinos is important for studying the Sun's energy mechanism, monitoring thermodynamic equilibrium, and studying neutrino oscillation in the vacuum-dominated region. For a large-scale liquid scintillator detector, one bottleneck for \textit{pp} solar neutrino detection comes from pile-up events of intrinsic $^{14}$C decays. This paper presents a few approaches to discriminate \textit{pp} solar neutrinos and $^{14}$C pile-up events by considering the difference in their time and spatial distributions. In this work, a Geant4-based Monte Carlo simulation is constructed. Then multivariate analysis and deep learning technology were adopted respectively to investigate the capability of $^{14}$C pile-up reduction. As a result, the BDTG model and VGG network showed good performance in discriminating \textit{pp} solar neutrinos and $^{14}$C double pile-up events. Their signal significance can achieve 10.3 and 15.6 using only one day of statistics. In this case, the signal efficiency is 51.1\% for discrimination using the BDTG model when rejecting 99.18\% $^{14}$C double pile-up events, and the signal efficiency is 42.7\% for the case using the VGG network when rejecting 99.81\% $^{14}$C double pile-up events.

Evaluating safety performance in a resource-efficient way is crucial for the development of autonomous systems. Simulation of parameterized scenarios is a popular testing strategy but parameter sweeps can be prohibitively expensive. To address this, we propose HiddenGems: a sample-efficient method for discovering the boundary between compliant and non-compliant behavior via active learning. Given a parameterized scenario, one or more compliance metrics, and a simulation oracle, HiddenGems maps the compliant and non-compliant domains of the scenario. The methodology enables critical test case identification, comparative analysis of different versions of the system under test, as well as verification of design objectives. We evaluate HiddenGems on a scenario with a jaywalker crossing in front of an autonomous vehicle and obtain compliance boundary estimates for collision, lane keep, and acceleration metrics individually and in combination, with 6 times fewer simulations than a parameter sweep. We also show how HiddenGems can be used to detect and rectify a failure mode for an unprotected turn with 86% fewer simulations., Comment: Published at IROS 2022