搜索结果：Biophysical

Accurate prediction of grape phenology is essential for timely vineyard management decisions, such as scheduling irrigation and fertilization, to maximize crop yield and quality. While traditional biophysical models calibrated on historical field data can be used for season-long predictions, they lack the precision required for fine-grained vineyard management. Deep learning methods are a compelling alternative but their performance is hindered by sparse phenology datasets, particularly at the cultivar level. We propose a hybrid modeling approach that combines multi-task learning with a recurrent neural network to parameterize a differentiable biophysical model. By using multi-task learning to predict the parameters of the biophysical model, our approach enables shared learning across cultivars while preserving biological structure, thereby improving the robustness and accuracy of predictions. Empirical evaluation using real-world and synthetic datasets demonstrates that our method significantly outperforms both conventional biophysical models and baseline deep learning approaches in predicting phenological stages, as well as other crop state variables such as cold-hardiness and wh

Single-particle cryo-electron microscopy (cryo-EM) has become a cornerstone of structural biology, enabling near-atomic resolution analysis of macromolecules through advanced computational methods. However, the development of cryo-EM processing tools is constrained by the scarcity of high-quality annotated datasets. Synthetic data generation offers a promising alternative, but existing approaches lack thorough biophysical modeling of heterogeneity and fail to reproduce the complex noise observed in real imaging. To address these limitations, we present CryoCCD, a synthesis framework that unifies versatile biophysical modeling with the first conditional cycle-consistent diffusion model tailored for cryo-EM. The biophysical engine provides multi-functional generation capabilities to capture authentic biological organization, and the diffusion model is enhanced with cycle consistency and mask-guided contrastive learning to ensure realistic noise while preserving structural fidelity. Extensive experiments demonstrate that CryoCCD generates structurally faithful micrographs, enhances particle picking and pose estimation, as well as achieves superior performance over state-of-the-art bas

Biophysical neuron models link measurements of neural activity to underlying cellular mechanisms. Yet, a central challenge is that the kinetics of many ion channels are poorly characterized, and practical simplifications -- omitting channels or reducing morphological detail -- introduce systematic gaps between model and biology. Bridging these gaps requires approaches that can flexibly discover unmodeled dynamics while preserving mechanistic interpretability. Here, we introduce a hybrid modeling framework that embeds neural ordinary differential equations into conductance-based biophysical models to capture unknown currents or mis-specified channel kinetics. By parameterizing the neural ODE in terms of voltage-dependent steady-state and time-constant functions, we recover interpretable gating dynamics directly from voltage recordings without assuming a functional form. We show that the hybrid model fits the gating kinetics of 2400 ion channel models and recovers unknown gating dynamics from single current-clamp recordings, generalizing to out-of-distribution stimulus regimes under realistic inputs and parameter misspecification. We also use our method to reduce a multicompartment m

There is a growing body of work seeking to replicate the success of machine learning (ML) on domains like computer vision (CV) and natural language processing (NLP) to applications involving biophysical data. One of the key ingredients of prior successes in CV and NLP was the broad acceptance of difficult benchmarks that distilled key subproblems into approachable tasks that any junior researcher could investigate, but good benchmarks for biophysical domains are rare. This scarcity is partially due to a narrow focus on benchmarks which simulate biophysical data; we propose instead to carefully abstract biophysical problems into simpler ones with key geometric similarities. In particular we propose a new class of closed-form test functions for biophysical sequence optimization, which we call Ehrlich functions. We provide empirical results demonstrating these functions are interesting objects of study and can be non-trivial to solve with a standard genetic optimization baseline.

Recent advances in neural interfacing have enabled significant improvements in human-computer interaction, rehabilitation, and neuromuscular diagnostics. Motor unit (MU) decomposition from surface electromyography (sEMG) is a key technique for extracting neural drive information, but traditional blind source separation (BSS) methods fail to incorporate biophysical constraints, limiting their accuracy and interpretability. In this work, we introduce a novel Biophysical-Model-Informed Source Separation (BMISS) framework, which integrates anatomically accurate forward EMG models into the decomposition process. By leveraging MRI-based anatomical reconstructions and generative modeling, our approach enables direct inversion of a biophysically accurate forward model to estimate both neural drive and motor neuron properties in an unsupervised manner. Empirical validation in a controlled simulated setting demonstrates that BMISS achieves higher fidelity motor unit estimation while significantly reducing computational cost compared to traditional methods. This framework paves the way for non-invasive, personalized neuromuscular assessments, with potential applications in clinical diagnostic

Background: Cystic fibrosis (CF) airway mucus exhibits reduced mucin sialylation, increasing viscosity and impairing mucociliary clearance (MCC). NEU1 inhibition has been proposed to restore MCC, but its quantitative pharmacokinetic and rheological effects, particularly with inhaled delivery, remain uncharacterized. Objective: To develop an integrated pharmacokinetic/pharmacodynamic (PK/PD) and biophysical model to assess the efficacy of an inhaled NEU1 inhibitor. Methods: Empirical and preclinical NEU1 inhibition data were combined with inhalation PK/PD modeling and a biophysical viscosity framework linking mucin sialylation and extracellular DNA. Synthetic cohort simulations (N = 200) were reconciled with empirical PK benchmarks using Latin hypercube parameter sampling. Cross-validation, hold-out testing, and causal inference methods (inverse probability of treatment weighting and targeted maximum likelihood estimation) quantified predicted effects on lung function (delta FEV1). Results: With reconciled parameters (F_dep = 0.12; k_abs = 0.21 per hour; k_muc = 0.24 per hour), epithelial lining fluid drug levels reached a peak concentration of 7.5 micromolar (95 percent CI: 6 to 10

Biomedical research increasingly relies on 3D cell culture models and AI-based analysis can potentially facilitate a detailed and accurate feature extraction on a single-cell level. However, this requires for a precise segmentation of 3D cell datasets, which in turn demands high-quality ground truth for training. Manual annotation, the gold standard for ground truth data, is too time-consuming and thus not feasible for the generation of large 3D training datasets. To address this, we present a novel framework for generating 3D training data, which integrates biophysical modeling for realistic cell shape and alignment. Our approach allows the in silico generation of coherent membrane and nuclei signals, that enable the training of segmentation models utilizing both channels for improved performance. Furthermore, we present a new GAN training scheme that generates not only image data but also matching labels. Quantitative evaluation shows superior performance of biophysical motivated synthetic training data, even outperforming manual annotation and pretrained models. This underscores the potential of incorporating biophysical modeling for enhancing synthetic training data quality.

Transcranial ultrasonic stimulation (TUS) has the potential to usher in a new era for human neuroscience by allowing spatially precise and high-resolution non-invasive targeting of both deep and superficial brain regions. Currently, fundamental research on the mechanisms of interaction between ultrasound and neural tissues is progressing in parallel with application-focused research. However, a major hurdle in the wider use of TUS is the selection of optimal parameters to enable safe and effective neuromodulation in humans. In this paper, we will discuss the major factors that determine both the safety and efficacy of TUS. We will discuss the thermal and mechanical biophysical effects of ultrasound, which underlie its biological effects, in the context of their relationships with tunable parameters. Based on this knowledge of biophysical effects, and drawing on concepts from radiotherapy, we propose a framework for conceptualising TUS dose.

The biophysical interactions between the T cell receptor (TCR) and its ligands determine the specificity of the cellular immune response. However, the immense diversity of receptors and ligands has made it challenging to discover generalizable rules across the distinct binding affinity landscapes created by different ligands. Here, we present an optimization framework for discovering biophysical rules that predict whether TCRs share specificity to a ligand. Applying this framework to TCRs associated with a collection of SARS-CoV-2 peptides we systematically characterize how co-specificity depends on the type and position of amino-acid differences between receptors. We also demonstrate that the inferred rules generalize to ligands highly dissimilar to any seen during training. Our analysis reveals that matching of steric properties between substituted amino acids is more important for receptor co-specificity than the hydrophobic properties that prominently determine evolutionary substitutability. Our analysis also quantifies the substantial importance of positions not in direct contact with the peptide for specificity. These findings highlight the potential for data-driven approache

Advances in machine learning have boosted the use of Earth observation data for climate change research. Yet, the interpretability of machine-learned representations remains a challenge, particularly in understanding forests' biophysical reactions to climate change. Traditional methods in remote sensing that invert radiative transfer models (RTMs) to retrieve biophysical variables from spectral data often fail to account for biases inherent in the RTM, especially for complex forests. We propose to integrate RTMs into an auto-encoder architecture, creating an end-to-end learning approach. Our method not only corrects biases in RTMs but also outperforms traditional techniques for variable retrieval like neural network regression. Furthermore, our framework has potential generally for inverting biased physical models. The code is available on https://github.com/yihshe/ai-refined-rtm.git.

The technique presented here identifies tethered mould designs, optimised for growing cultured tissue with very highly-aligned cells. It is based on a microscopic biophysical model for polarised cellular hydrogels. There is an unmet need for tools to assist mould and scaffold designs for the growth of cultured tissues with bespoke cell organisations, that can be used in applications such as regenerative medicine, drug screening and cultured meat. High-throughput biophysical calculations were made for a wide variety of computer-generated moulds, with cell-matrix interactions and tissue-scale forces simulated using a contractile-network dipole-orientation model. Elongated moulds with central broadening and one of the following tethering strategies are found to lead to highly-aligned cells: (1) tethers placed within the bilateral protrusions resulting from an indentation on the short edge, to guide alignment (2) tethers placed within a single vertex to shrink the available space for misalignment. As such, proof-of-concept has been shown for mould and tethered scaffold design based on a recently developed biophysical model. The approach is applicable to a broad range of cell types that

Biophysical models describing complex, cellular phenomena typically include systems of nonlinear differential equations with many free parameters. While experimental measurements can fix some parameters, those describing internal cellular processes frequently remain inaccessible. Hence, a proliferation of free parameters risks overfitting the data, limiting the model's predictive power. In this study, we develop robust methods, applying statistical analysis and dynamical-systems theory, to reduce a biophysical model's complexity. We demonstrate our techniques on an elaborate computational model designed to describe active, mechanical motility of auditory hair cells. Specifically, we use two statistical measures, the total-effect and PAWN indices, to rank each free parameter by its influence on selected, core properties of the model. With the resulting ranking, we fix most of the less influential parameters, yielding a low-parameter model with optimal predictive power. We validate the theoretical model with experimental recordings of active hair-bundle motility, specifically by using Akaike and Bayesian information criteria after obtaining maximum-likelihood fits. As a result, we de

A challenge in global change biology is to predict how species will respond to future environmental change and to manage these responses. To make such predictions and management actions robust to novel futures, we need to accurately characterize how organisms experience their environments and the biological mechanisms by which they respond. All organisms are thermodynamically connected to their environments through the exchange of heat and water at fine spatial and temporal scales and this exchange can be captured with biophysical models. Although mechanistic models based on biophysical ecology have a long history of development and application, their use in global change biology remains limited despite their enormous promise and increasingly accessible software. We contend that greater understanding and training in the theory and methods of biophysical models is vital to expand their application. Our review shows how biophysical models can be implemented to understand and predict climate change impacts on species' behavior, phenology, survival, distribution, and abundance. We illustrate the types of outputs that can be generated, and the data inputs required for different implemen

Cartilage is a connective tissue that covers the surfaces of bones in joints and provides a smooth gliding surface for movement. It is characterized by specific biophysical properties that allow it to withstand compressive loads, distribute mechanical forces, and maintain tissue integrity. The bi-ophysical properties of cartilage are primarily determined by its extracellular matrix, which is composed of collagen fibers, proteoglycans, and water. The collagen fibers provide tensile strength, the proteoglycans provide compressive resistance, and the water content provides lubrication and shock absorption. The potential for greater knowledge of cartilage function through refinement and engineering-level understanding could inform the design of interventions for cartilage dysfunction and pathology. The aim is to assist to present basic principles of cartilage modeling and discussing the underlying physics and assumptions with relatively simple settings, and also it presents the derivation of multiphase cartilage models that are consistent with the discussions. Furthermore, modern developments align the structure captured in the models with observed complexities. The interactions betwee

Long-term focused attention with visualization and breathing exercises is at the core of various Eastern traditions. Neurocognitive and psychosomatic phenomena demonstrated during such exercises were instrumentally explored with EEG and other sensors. Neurocognitive modeling in the form of meditative visualization produced persistent temperature effects in the body long after the exercise finished; this raises the question about their psychosomatic or biophysical origin. The work explores this question by comparing experiments with focusing attention inside and outside the body. EEG, temperature, heart and breathing sensors monitor internal body conditions, high resolution differential calorimetric sensors are used to detect thermal effects outside the body. Experiments with 159 attempts (2427 operator-sensor sessions) were carried over five months, control measurements run in the same conditions in parallel to experimental series. Increase of body temperature up to moderate fever zone 38.5 C and intentional control of up and down trend of core temperature by 1.6 C are demonstrated. Persistent temperature variations last >60 min. Experiments also demonstrated induced thermal flu

We present a new method to reconstruct and manipulate the spectral properties of human skin from simple RGB albedo captures. To this end, we leverage Monte Carlo light simulation over an accurate biophysical human skin layering model parameterized by its most important components, thereby covering a plausible range of colors. The practical complexity of the model allows us to learn the inverse mapping from any albedo to its most probable associated skin properties. Our technique can faithfully reproduce any skin type, being expressive enough to automatically handle more challenging areas like the lips or imperfections in the face. Thanks to the smoothness of the skin parameters maps recovered, the albedo can be robustly edited through meaningful biophysical properties.

The approximation capability of ANNs and their RNN instantiations, is strongly correlated with the number of parameters packed into these networks. However, the complexity barrier for human understanding, is arguably related to the number of neurons and synapses in the networks, and to the associated nonlinear transformations. In this paper we show that the use of biophysical synapses, as found in LTCs, have two main benefits. First, they allow to pack more parameters for a given number of neurons and synapses. Second, they allow to formulate the nonlinear-network transformation, as a linear system with state-dependent coefficients. Both increase interpretability, as for a given task, they allow to learn a system linear in its input features, that is smaller in size compared to the state of the art. We substantiate the above claims on various time-series prediction tasks, but we believe that our results are applicable to any feedforward or recurrent ANN.

In view of ever-changing conditions both in the external world and in intrinsic brain states, maintaining the robustness of computations poses a challenge, adequate solutions to which we are only beginning to understand. At the level of cell-intrinsic properties, biophysical models of neurons permit one to identify relevant physiological substrates that can serve as regulators of neuronal excitability and to test how feedback loops can stabilize crucial variables such as long-term calcium levels and firing rates. Mathematical theory has also revealed a rich set of complementary computational properties arising from distinct cellular dynamics and even shaping processing at the network level. Here, we provide an overview over recently explored homeostatic mechanisms derived from biophysical models and hypothesize how multiple dynamical characteristics of cells, including their intrinsic neuronal excitability classes, can be stably controlled.