We present a model based on the concept of saturation for small $Q^2$ and small $x$. With only three parameters we achieve a good description of all Deep Inelastic Scattering data below $x=0.01$. This includes a consistent treatment of charm and a successful extrapolation into the photoproduction regime. The same model leads to a roughly constant ratio of diffractive and inclusive cross section.
mRNA technology has revolutionized vaccine development, protein replacement therapies, and cancer immunotherapies, offering rapid production and precise control over sequence and efficacy. However, the inherent instability of mRNA poses significant challenges for drug storage and distribution, particularly in resource-limited regions. Co-optimizing RNA structure and codon choice has emerged as a promising strategy to enhance mRNA stability while preserving efficacy. Given the vast sequence and structure design space, specialized algorithms are essential to achieve these qualities. Recently, several effective algorithms have been developed to tackle this challenge that all use similar underlying principles. We call these specialized algorithms "mRNA folding" algorithms as they generalize classical RNA folding algorithms. A comprehensive analysis of their underlying principles, performance, and limitations is lacking. This review aims to provide an in-depth understanding of these algorithms, identify opportunities for improvement, and benchmark existing software implementations in terms of scalability, correctness, and feature support.
Deep learning has emerged as a powerful framework for analyzing biomolecular dynamics trajectories, enabling efficient representations that capture essential system dynamics and facilitate mechanistic studies. We propose a neural network architecture incorporating Fourier Transform analysis to process trajectory data, achieving dual objectives: eliminating high-frequency noise while preserving biologically critical slow conformational dynamics, and establishing an isotropic representation space through the last hidden layer for enhanced dynamical quantification. Comparative protein simulations demonstrate our approach generates more uniform feature distributions than linear regression methods, evidenced by smoother state similarity matrices and clearer classification boundaries. Moreover, by using saliency score, we identified key structural determinants linked to effective energy landscapes governing system dynamics. We believe that the fusion of neural network features with physical order parameters creates a robust analytical framework for advancing biomolecular trajectory analysis.
RNA structure determination is essential for understanding its biological functions. However, the reconstruction process often faces challenges, such as atomic clashes, which can lead to inaccurate models. To address these challenges, we introduce the principal submanifold (PSM) approach for analyzing RNA data on a torus. This method provides an accurate, low-dimensional feature representation, overcoming the limitations of previous torus-based methods. By combining PSM with DBSCAN, we propose a novel clustering technique, the principal submanifold-based DBSCAN (PSM-DBSCAN). Our approach achieves superior clustering accuracy and increased robustness to noise. Additionally, we apply this new method for multiscale corrections, effectively resolving RNA backbone clashes at both microscopic and mesoscopic scales. Extensive simulations and comparative studies highlight the enhanced precision and scalability of our method, demonstrating significant improvements over existing approaches. The proposed methodology offers a robust foundation for correcting complex RNA structures and has broad implications for applications in structural biology and bioinformatics.
Deep learning models have become fundamental tools in drug design. In particular, large language models trained on biochemical sequences learn feature vectors that guide drug discovery through virtual screening. However, such models do not capture the molecular interactions important for binding affinity and specificity. Therefore, there is a need to 'compose' representations from distinct biological modalities to effectively represent molecular complexes. We present an overview of the methods to combine molecular representations and propose that future work should balance computational efficiency and expressiveness. Specifically, we argue that improvements in both speed and accuracy are possible by learning to merge the representations from internal layers of domain specific biological language models. We demonstrate that 'composing' biochemical language models performs similar or better than standard methods representing molecular interactions despite having significantly fewer features. Finally, we discuss recent methods for interpreting and democratizing large language models that could aid the development of interaction aware foundation models for biology, as well as their shortcomings.
Matthew Greenig, Haowen Zhao, Vladimir Radenkovic
et al.
Designing antibody sequences to better resemble those observed in natural human repertoires is a key challenge in biologics development. We introduce IgCraft: a multi-purpose model for paired human antibody sequence generation, built on Bayesian Flow Networks. IgCraft presents one of the first unified generative modeling frameworks capable of addressing multiple antibody sequence design tasks with a single model, including unconditional sampling, sequence inpainting, inverse folding, and CDR motif scaffolding. Our approach achieves competitive results across the full spectrum of these tasks while constraining generation to the space of human antibody sequences, exhibiting particular strengths in CDR motif scaffolding (grafting) where we achieve state-of-the-art performance in terms of humanness and preservation of structural properties. By integrating previously separate tasks into a single scalable generative model, IgCraft provides a versatile platform for sampling human antibody sequences under a variety of contexts relevant to antibody discovery and engineering. Model code and weights are publicly available at https://github.com/mgreenig/IgCraft.
Anno C. Kurth, Jasper Albers, Markus Diesmann
et al.
The structure of neural networks provides the stage on which their activity unfolds. Models of cerebral cortex linking connectivity to dynamics have primarily relied on probabilistic estimates of connectivity derived from paired electrophysiological recordings or single-neuron morphologies obtained by light microscopy (LM) studies. Only recently have electron microscopy (EM) data sets been processed and made available for volumes of cortex on the cubic millimeter scale, exposing the actual connectivity of neurons. Here, we construct a population-based, layer-resolved connectivity map from EM data, taking into account the spatial scale of local cortical connectivity. We compare the obtained connectivity with a map based on an established LM data set. Simulating spiking neural networks constrained by the derived microcircuit architectures shows that both models allow for biologically plausible ongoing activity when synaptic currents caused by neurons outside the network model are specifically adjusted for every population. However, differentially varying the external current onto excitatory and inhibitory populations reveals that only the EM-based model robustly exhibits biologically plausible dynamics. Our work confirms the long-standing hypothesis that a preference of excitatory neurons for inhibitory targets, not present in the LM-based model, promotes balanced activity in cortical microcircuits.
The technical virtual power plant (TVPP) is a promising paradigm to facilitate the integration of distributed energy resources (DERs) while incorporating operational constraints of both DERs and networks. Due to the volatility and limited predictability of DER generation and electric loads, the output capability of the TVPP is uncertain. In this regard, this paper proposes the robust capability curve (RCC) of the TVPP, which explicitly characterizes the allowable range of the scheduled power output that is executable for the TVPP under uncertainties. Implementing the RCC can secure the scheduling of the TVPP against unexpected fluctuations of operating conditions when the TVPP participates in the transmission-level dispatch. Mathematically, the RCC is the first-stage feasible set of an adjustable robust optimization problem. An uncertainty set model incorporating the variable correlation and uncertainty budget is employed, which makes the robustness and conservatism of the RCC adjustable. A novel methodology is proposed to estimate the RCC by the convex hull of several points on its perimeter. These perimeter points are obtained by solving a series of multi scenario-optimal power flow problems with worst-case uncertainty realizations identified based on a linearized network configuration. Case studies based on the IEEE-13 test feeder validate the effectiveness of the RCC to ensure the scheduling feasibility while hedging against uncertainties. The computational efficiency of the proposed RCC estimation method is also verified based on larger-scale test systems.
The problem of adaptive traffic signal control in the multi-intersection system has attracted the attention of researchers. Among the existing methods, reinforcement learning has shown to be effective. However, the complex intersection features, heterogeneous intersection structures, and dynamic coordination for multiple intersections pose challenges for reinforcement learning-based algorithms. This paper proposes a cooperative deep Q-network with Q-value transfer (QT-CDQN) for adaptive multi-intersection signal control. In QT-CDQN, a multi-intersection traffic network in a region is modeled as a multi-agent reinforcement learning system. Each agent searches the optimal strategy to control an intersection by a deep Q-network that takes the discrete state encoding of traffic information as the network inputs. To work cooperatively, the agent considers the influence of the latest actions of its adjacencies in the process of policy learning. Especially, the optimal Q-values of the neighbor agents at the latest time step are transferred to the loss function of the Q-network. Moreover, the strategy of the target network and the mechanism of experience replay are used to improve the stability of the algorithm. The advantages of QT-CDQN lie not only in the effectiveness and scalability for the multi-intersection system but also in the versatility to deal with the heterogeneous intersection structures. The experimental studies under different road structures show that the QT-CDQN is competitive in terms of average queue length, average speed, and average waiting time when compared with the state-of-the-art algorithms. Furthermore, the experiments of recurring congestion and occasional congestion validate the adaptability of the QT-CDQN to dynamic traffic environments.