Postoperative pancreatic fistula (POPF) is a serious complication after pancreatic resection, increasing morbidity, hospital stay, and healthcare costs. We present an automatic, end-to-end deep learning pipeline-from pancreatic segmentation to classification-for preoperative POPF risk estimation and stratification using preoperative CT scans. A data set with auto-segmented pancreas volumes and surgical outcomes was used to evaluate multiple architectures, including a custom lightweight 3D CNN baseline (CNN3D), R(2+1)D ResNet-18, and ResNet-MC3-18 models. Evaluation across multiple 3D architectures demonstrated promising predictive performance. This approach offers a clinically valuable tool and a methodological benchmark for pancreas-specific CT classification, supporting improved preoperative decision-making in pancreatic surgery.

Large perturbation models require training data encompassing chemical, cellular, and assay diversity. Current transcriptomic resources for small-molecule modeling, however, are fragmented across technologies, metadata conventions, controls, doses, and preprocessing pipelines. We introduce Chem-PerturBridge, a harmonized multi-dataset resource comprising over 37k compounds, 136 cellular contexts, and 1.25M transcriptomic samples across eight assay types, with standardized identifiers, metadata, and replicate-aware condition-level effects. We use the resource to evaluate matched-condition agreement across datasets and replicate agreement within datasets. Matched same-compound conditions generally show weak agreement in fine-grained logFC rankings and magnitudes across most dataset pairs, often falling below same-context different-compound baselines. In contrast, logFC direction agreement is substantially more stable and usually exceeds these baselines. We further evaluate Chem-PerturBridge as a pretraining resource for compound representation learning. Under a compound-held-out OP3 evaluation split, embeddings pretrained on Chem-PerturBridge improve over L1000-only embeddings, Morgan fingerprints, and the descriptor-free OP3 baseline across metrics. An extensive molecule-holdout evaluation across 11 datasets further shows that models trained on Chem-PerturBridge outperform or match those that are not. Chem-PerturBridge therefore supports both diagnostic evaluation of cross-dataset signature agreement and model-oriented reuse of heterogeneous perturbation transcriptomic data.

A multitude of findings and theories from cognitive, behavioural and computational neuroscience show that neural activity unfolds in a variety of meaningful temporal units. Behavioural research on event segmentation (ES) has shown that continuous experience is segmented into discrete events and sub-events, which aid real-time comprehension, memory, and decision-making. Computational neuroscience research observes and models ongoing brain activity as a series of stable population activity that occur across wide spatial and temporal scales, referred to as metastable neural activity (MNA). Through this review, we show that these isolated branches of literature, the cognitive theory of Event Segmentation (ES) and the mechanistic approach of metastability (MNA), actually study the same metastable neural states from different perspectives. While the behavioural branch offers a theory for the cognitive and behavioural utility of segmentation, the metastability literature provides the mechanistic account at the implementational level. We describe how metastable neural states act as the fundamental computational units of cognition and identify a number of core principles of how they operate. One is the spatio-temporally nested hierarchy of states, where longer-duration states in higher-order regions both constrain and are shaped by states in faster-operating regions. Another is that neural states are a reflection of underlying predictive models which shape perception, decision making, memory encoding and recall. And finally that neural states are periods of more modular processing, which are interspersed by boundaries where there is a reconfiguration of connectivity. Understanding how neural states emerge, interact, and shape cognition brings us closer to understanding the brain in its natural mode of operation.

Estimating viral substitution rates is central to evolutionary epidemiology, and recent interest in within-host evolution has sharpened the question of what such rates measure. I distinguish two classes of evolutionary rate estimand that are rarely separated in phylogenetic analysis: the virion-level substitution rate (VLSR), a molecular quantity counting mutational events along lineages, and consensus-level substitution rates (CLSRs), population-summary quantities counting changes in the consensus sequences. CLSRs are indexed by the consensus-generation rule. The VLSR and CLSRs are both biologically meaningful, but not interchangeable. Because the consensus-generation rule defines a given CLSR, it should be a routine reporting requirement. This reflection should help analysts make more informed methodological choices when working with sets of virus sequences.

Therapeutic mRNA design requires coordinating multiple interacting sequence features across the full transcript, where codon usage, untranslated regions (UTRs), and their coupling jointly determine stability, translation efficiency, and protein expression. Here, we present mRNA generation via unrolled trajectories and informed latent updates (mRNAutilus), a framework for simultaneous codon optimization and de novo UTR design directly from sequence. mRNAutilus combines a masked discrete diffusion model trained on millions of full-length mRNAs with Monte Carlo Tree Guidance to generate Pareto-efficient sequences under multiple functional objectives, using lightweight regressors over model embeddings to predict half-life, translation efficiency, and protein abundance. Unlike recent methods that design coding sequences and UTRs separately or rely on post hoc assembly and screening, mRNAutilus generates complete transcripts in a single process optimized across properties. Across diverse targets, zero-shot mRNAs encoding P. pyralis luciferase achieve over 400-fold higher expression than wild-type and outperform commercial and machine learning-designed baselines, including zero-shot generative approaches. Zero-shot SARS-CoV-2 Spike mRNAs exceed clinically used and commercial constructs and match or surpass lab-optimized designs with improved durability. We further demonstrate generality in therapeutic settings, including prime editing (PEMax) and programmable proteome modulation, where mRNAutilus-designed constructs enhance expression of peptide-guided E3 ligases (uAbs) for beta-catenin degradation. These results establish a sequence-based, multi-objective framework for generating functional mRNAs tailored to diverse biological applications.

In this paper, we propose an integro-differential model for the spatio-temporal evolution of infectious diseases with asymptomatic transmission. The model consists of a reaction-diffusion system with an integral memory term accounting for the distribution of the incubation period. We first analyze the asymptotic behavior and the properties of the integro-differential model. Then, we prove the local existence of a weak solution of the system by means of the Faedo-Galerkin method and a compactness argument. The model is applied to simulate the geographical evolution of a disease in Lebanon.

Multistate mechanisms underlie many of the complex functions observed in natural proteins. The ability to rationally design multistate proteins would have transformative implications for many areas of biotechnology, yet lies beyond the capabilities of existing deep learning frameworks for protein design. To address this gap, we introduce SwitchCraft, a versatile and programmatic framework for designing state-switching proteins based on backpropagation through compositional design constraints parameterized by structure prediction models. In silico evaluations demonstrate success on a wide range of state-switching functional primitives, from allosteric regulation of motifs to discrimination of bound ligand identities. Using these primitives, we demonstrate an in silico strategy for de novo design of fluorescent biosensors to arbitrary small molecule analytes. These results position SwitchCraft at the inception of a powerful paradigm for higher-order functional protein design. Code is available at https://github.com/bjing2016/switchcraft.

Candida albicans is a commensal microorganism that causes opportunistic infections, such as oral candidiasis, vaginitis affecting females, newborns, and immunocompromised patients. Biofilm formation can lead to a commensal organism becoming a life-threatening organism by introducing antifungal resistance. The experiment we did combines crystal violet staining for biofilm biomass and CFU counts to statistically construct an additive BVI model by analysing the experimental data. Our study on the data proposes a Biofilm-Virulence Index (BVI) as a novel and quantitative parameter for assessing antifungal drug resistance in Candida albicans. The effect of the drugs on inhibition zone diameter is twofold, first, linear increase with time during early biofilm formation, second, stabilizing in later phases and correlating directly with virulence. Most BVI values remained in the mild infection range, indicating successful virulence reduction by antifungal drugs. The BVI model model combines the study of biofilm and viable cell count in a single parameter. So, this makes comparison between samples easier during biofilm analysis. Findings suggest that combination of CFU and biofilm measurement may improve interpretation of antifungal response in Candida albicans. This approach could be useful in future experimental studies investigating biofilm associated resistance.

Habitat loss driven by climate and anthropogenic pressures alters patch morphology, with critical consequences for population persistence. Geometric and mechanistic metrics are commonly used to quantify degradation, yet their respective limitations remain poorly understood. Here, we address this gap using a reaction-diffusion framework for population growth and dispersal in a viable patch embedded in a hostile environment. We compare geometric descriptors of patch shape with a mechanistic metric derived from population growth near the extinction threshold. Along degradation trajectories, we find that geometric metrics systematically overestimate persistence, suggesting moderate and decelerating impacts, whereas mechanistic indicators reveal rapid, accelerating approaches to extinction. These results highlight fundamental limitations of geometric approaches and underscore the need for mechanistic assessments when evaluating biodiversity loss in complex landscapes.

We present AMix-2, a protein-text foundation model that establishes protein as a native modality in large language models (LLMs), unifying protein understanding and sequence design within a single foundation model. AMix-2 is built upon two key ideas: (1) a unified protein-text formulation that embeds natural language and protein sequence in a shared token space, enabling one model to perform biological reasoning and conditional design instead of separate downstream task-specialized models; and (2) a block-wise diffusion language modeling backbone that combines causal generation across blocks with bidirectional context and iterative refinement within blocks. This scheme better matches the intrinsic nature of proteins than a strict left-to-right factorization. To evaluate protein foundation models under realistic generalization settings, we further introduce ProteinArena, a comprehensive benchmark with time-aware and homology-aware protocols across various understanding and design tasks, and with baselines covering classical bioinformatics tools, protein-specialized models and LLMs. On ProteinArena, AMix-2 outperforms frontier LLMs and demonstrates competitive performance to task-specific protein models. Controlled experiments further show that the diffusion-based paradigm generally surpasses its autoregressive counterpart, highlighting the advantage of flexible generation order for protein sequences. We release both AMix-2 and ProteinArena to facilitate open research in protein foundation models.

We introduce a physically grounded framework for coordination in a population based on information constrained feedback in a partially observed stochastic dynamical system. Population size evolves as a continuous time birth death Markov process whose transition rates respond to a shared stochastic measurement signal correlated with the underlying population state. Individuals neither communicate directly nor optimise strategies; instead, coordination emerges from macro to micro feedback mediated by imperfect common information. We show that geometric Brownian motion arises as a limiting case of the conditional dynamics when measurement strength and population statistics satisfy suitable conditions. More generally, varying the signal to noise properties of the measurement channel produces a wider class of stochastic growth processes, including diffusive and jump like regimes, even though ensemble average growth remains exponential. In an appropriate limit the framework recovers the stochastic multiplicative growth model of Peters and Adamou, providing a physical interpretation of coordination as inference and feedback under partial observability.

The sensory cortices of the brain perform perceptual inference efficiently through their complex networks of neurons. One of the theoretical accounts of this process is the free-energy principle (FEP), which postulates that the brain performs variational Bayesian inference. Pioneering studies have shown that FEP can correspond to the predictive coding (PC) hypothesis under the Gaussian assumption and Laplace approximation. However, PC-based implementations of FEP within such a limited Gaussian regime have failed to capture several properties of biological neural networks, such as nonlinearity and heterogeneity of input--output properties within a network, and the biological implausibility of negative firing rates. This study shows that, when a broader class of probability distributions, namely the exponential family of distributions (EFD), is assumed for the variational posterior and prior, these missing characteristics are exhibited within the network, maintaining the FEP--PC correspondence up to the second cumulant of the posterior. We also show that the proposed model can be trained by biologically plausible local plasticity rules. Our results enrich the explanatory power of FEP regarding neural dynamics involved in perception as variational inference.

People often seek out ways to watch others perform complex action sequences (e.g., sports). What makes some sequences more enjoyable to watch than others? We generated 24 video clips of gameplay from a Flappy Bird-style video game. Clips varied in difficulty (how often players succeeded on average) and in moment-to-moment uncertainty (how likely the player was to crash at any given step). Participants (N=864) rated each video on one of three dimensions: how much they enjoyed it, how difficult the level appeared, or how dangerous the player's trajectory appeared. We found that participants preferred videos where the player seemed to be completing more difficult obstacle courses, but dangerousness did not predict enjoyment ratings. These findings show how procedurally generated stimuli can isolate the factors that affect how enjoyable an action sequence is to watch.

Activity cliffs, structurally similar compounds with large potency differences, are widely treated as intrinsic features of chemical datasets. We argue that apart from target biology, much of our cliff understanding is a consequence of the geometry induced by the chosen molecular representation, not a property of a molecule pair itself. We designed a six-step pipeline to systematically test this hypothesis. The pipeline consists of: assessing pairwise distance geometry, cliff enrichment, activity gradient distribution, persistent homology of the cliff subspace, predictive benchmarking for a chosen pair of an embedding and a metric, and eventually, analysis of the matched molecular pairs and stereoisomers. We applied the pipeline to fifteen configurations of embeddings and metrics to build a benchmark across three distinctive datasets known of activity cliffs challenges. No representation excels on all criteria: Morgan Tanimoto provides the strongest cliff enrichment and cross-scaffold generalization; MolFormer cosine provides the only meaningful stereochemical sensitivity; MACCS and RDKit Dice fingerprints are most sensitive to matched-molecular-pair transformations; ChemBERTa fails uniformly due to embedding collapse. These findings are not a ranking. They reflect the fact that different representations encode different aspects of molecular recognition, and that choosing one implicitly defines what an activity cliff actually is.

Spatio-temporal graph-based models have typically been used to forecast new cases of infectious diseases such as COVID-19 and chickenpox outbreaks. However, the use of stochastic modelling into their learning process has been surprisingly under-investigated and rarely considered entire data sets of large countries. As a result, it is unknown whether these models would provide accurate forecasts in real-world disease spread scenarios. In this work, we propose a spatio-temporal stochastic graph-based architecture that integrates a stochastic formulation and uncertainty approximation process to forecast new infectious disease cases. We find that our approach can adapt to encode large and small population geographical networks within a single model architecture. Using two real-world data sets, COVID-19 in the US and chickenpox in Hungary, we report an enhanced effect of the proposed architecture across predictions of the 2022 first wave for COVID-19 in the US and comparative results of chickenpox waves during 2012-2014 in Hungary. By benchmarking with four spatio-temporal graph-based models, quantitative results show competitive overall weekly performance of the proposed approach on forecasting new cases for all 3,218 US counties and all 20 Hungary counties. The proposed approach can represent overall epidemic progression relative to baselines, though with a one-step delay; while exhibiting a reduced sensitivity to high-frequency and low-amplitude variability.

Inferring dynamics from population snapshots is a fundamental challenge in machine learning and biology. In scRNA-sequencing (scRNA-seq), destructive measurements preclude direct tracking of individual cells across time, making trajectory inference underdetermined. Optimal Transport (OT) provides a principled framework for snapshot alignment, but a long-standing modeling question is which cost functions yield biologically meaningful couplings. Standard OT approaches rely on gene-expression distances, implicitly treating cells as independent points and neglecting structured cell-cell communication mediated by ligand-receptor signaling. We introduce CellBRIDGE (Cell-Based Regularized Interaction-Driven Gene Expression), which augments feature-based OT with a directed, typed interaction cost derived from ligand-receptor activity. By explicitly modeling cell-cell communication, CellBRIDGE improves cross-snapshot couplings and downstream trajectory estimates across synthetic and real scRNA-seq datasets relative to feature-only baselines. Notably, CellBRIDGE enables mechanistically interpretable in silico perturbations: on lung cancer data, silencing specific ligand-receptor pairs induces trajectory shifts that recapitulate expected effects of targeted pathway inhibition.

Luminal breast cancers represent the most prevalent molecular subtype of breast carcinoma, with Luminal A tumors generally associated with more favorable clinical outcomes than Luminal B tumors. Obesity-related inflammation and prolonged exposure to exogenous steroids have been implicated in the progression of luminal malignancies. This study evaluated 1,928 patients with Luminal A breast cancer and 1,610 patients with Luminal B breast cancer to examine associations among body mass index (BMI), age, ethnic background, menopausal status, and receptor expression, including estrogen receptor (ER), progesterone receptor (PR), and human epidermal growth factor receptor 2 (HER2). Patients with Luminal B tumors demonstrated a significantly greater mean BMI compared with those with Luminal A tumors. In addition, Luminal B tumors were more frequently observed among patients of African ancestry relative to White and Hispanic populations. Multivariable analyses revealed that elevated BMI and African ancestry were independently associated with increased odds of Luminal B carcinoma, whereas postmenopausal status was associated with lower risk. Mediation analysis further indicated that BMI partially explained the association between ancestry and Luminal B disease. These findings suggest that obesity and population-specific factors may contribute to the development of more aggressive luminal breast cancer phenotypes.

Collective action often requires institutions that make cooperation individually worthwhile. We ask whether democratic allocation of public-good return can transform a repeated public good into a self-sustaining cooperative institution, and how participation costs reshape that process. A simple evolutionary model shows that voted redistribution can support a prosocial allocation order, but can also sustain an antisocial allocation order or democratic free riding, in which individuals benefit from an institution maintained by others while avoiding the cost of participation. The model predicts competing effects of voting cost. Cost can suppress use of the institution to reward low contributors under strong selection, but can also thin the active electorate and erode contributor-rewarding support. We test these predictions in a preregistered online experiment with \NIncludedGroupsVone{} five-person groups. Endogenous democratic redistribution increased contributions relative to an equal-share public-goods control, with zero-cost voting producing the strongest temporal improvement. Voting costs did not mainly turn active voters toward low-contributor-rewarding allocation. Instead, they shifted behavior toward abstention and democratic free riding, made abstention locally rewarding, and widened the gap between post-task perceptions of democratic participation and the behavioral record. Democratic allocation can therefore stabilize cooperation, but participation costs can reduce the number of people actively sustaining the institution and can make that erosion less visible to participants themselves.

Random, untrained neural networks consistently match or exceed trained networks in representational similarity to early visual cortex. This puzzling finding challenges the assumption that learning improves brain alignment. We investigate it by tracking representational similarity analysis (RSA) alignment to human fMRI data across training for four learning rules: backpropagation (BP), feedback alignment (FA), predictive coding (PC), and spike-timing-dependent plasticity (STDP). Using 720 object images from the THINGS database and fMRI data from three subjects across six visual ROIs, we measure Spearman correlations between model and brain representational dissimilarity matrices at eight training checkpoints (epochs 0-40). We find that (1) a single epoch of training reduces V1 alignment by 25-90%, depending on the learning rule; (2) backpropagation reduces V1 alignment most severely (delta r = -0.080), while predictive coding and STDP preserve substantially more (delta r ~ -0.04); and (3) a weaker, opposite tendency appears in object-selective cortex (LOC), where BP shows the largest increase in alignment during training, although the absolute change is small. These results suggest that untrained architectures capture low-level visual statistics through inductive biases alone, and that global error signals (BP) reshape early representations more aggressively than local learning rules (PC, STDP), which better preserve brain-like structure.

Functional near-infrared spectroscopy (fNIRS) provides a noninvasive window into brain activity by measuring task-related changes in oxygenated and deoxygenated hemoglobin in the cortex. A key advantage of fNIRS is its promise of use with mobile participants in complex, real-world environments, such as walking, sports, classroom learning, driving simulations, or social interactions. However, analyzing fNIRS data is challenging because of motion artifacts, physiological noise, and other confounding factors. This challenge is further compounded by the limited availability of annotated datasets, which hinders the development and validation of new analysis pipelines, particularly given the growing use of AI methods. Recognizing these challenges, we introduce a 3D fNIRS simulator that uses mesh-based Monte Carlo simulations to create physiologically realistic, full-head synthetic recordings with high spatiotemporal fidelity. Our simulator combines anatomically accurate sensitivity profiles with parameterized models of hemodynamic responses, systemic physiology, and nonsystematic artifacts. As a result, users can generate virtually unlimited labeled datasets for testing denoising algorithms, data augmentation, mechanistic modeling, or \textit{in silico} experimentation. We validate the simulator using experimental fNIRS data from open-source finger-tapping, pain-assessment, and surgical-skill datasets and provide an open-source implementation to support reproducibility and broad adoption.

Collective information acquisition requires groups to combine personal evidence with social information while remaining coupled to the external state. Communication noise can affect this process, but the role of noise remains unclear. In an online experiment, 600 participants worked in four-person human groups estimating a room temperature across 25 rounds while receiving either faithful social information, comprehension noise in which each receiver saw independently perturbed social information, or production noise in which perturbations were stored before display and could be seen by multiple receivers. The thermometer cue was objectively veridical, but its reliability was subjectively uncertain and the unitless 50--250 room-temperature range created a task-induced conflict between displayed evidence and everyday temperature expectations. Production-noise groups spent more rounds tightly clustered around a wrong value than comprehension-noise groups (\(p=0.016\), group-level permutation). Production noise more often created a wrong common signal (\(p=0.025\), Fisher's exact test) and made that signal persist across more rounds (\(p=0.004\), permutation). Dynamic update models showed that production noise was not more harmful because people followed peers more strongly, but because the same peer influence acted on more correlated production-noise perturbations. Exploratory human analyses linked the mechanism to psychological patterns while a GPT-agent experiment clarified a boundary condition: GPT agents registered uncertainty through reduced confidence without reproducing human-scale production-noise vulnerability. Overall, noise did not simply degrade collective information acquisition. Comprehension noise could sometimes improve correction relative to the faithful control, whereas production noise could turn perturbations into common evidence and stabilize consensus on error.

Dynamic conformational changes of proteins are crucial for their cellular functions. Here we present a unified refinement pipeline for flexible protein structures in both CryoEM and in situ CryoET. Using a Gaussian mixture model-based focused alignment procedure, we improve resolution of small domains in highly dynamic proteins and reveal intricate conformational changes. The method corrects the per-subunit motion of TRPV1 and captures the rotary dynamics of ATP synthase within mitochondria.

The free energy principle casts perception as variational inference, but its biological implementation is underspecified. The generalized-coordinate formalism is not a literal claim that neurons compute arbitrary Taylor expansions. This paper argues that generalized synchronization (GS) provides the missing bottom-up mechanism. Certain recurrent circuits satisfy a contraction property: nearby trajectories converge exponentially. A contracting circuit driven by structured sensory input synchronizes to driving dynamics. Under generic embedding conditions, the resulting synchronization map embeds the low-dimensional sensory manifold into neural state space. The geometry predicted by the free energy principle is not imposed from above by an explicitly Bayesian neural calculus. It arises from ordinary recurrent dynamics. I then propose a developmental extension. Hebbian plasticity acting on the correlations generated by sensory-driven synchronization shapes the embedded manifold into recurrent connectivity, producing a continuous attractor network that approximates the embedded sensory manifold. Prediction-separation results bound the representational fidelity of the resulting circuit by prediction accuracy: where the network predicts future observations well, the synchronization map separates underlying states; where prediction fails, the representation collapses. The collapses are observable as categorical perception, metameric equivalence, and discrimination thresholds. On this view, mature head-direction, grid-cell, and stimulus-driven visual manifolds are developmental products of three interacting processes: dynamical contraction, generalized synchronization, and correlation-based plasticity. The central open problems are whether the Hebbian fixed point exists and whether Hebbian dynamics produce a sufficiently accurate predictor on the relevant input distribution.

The mechanisms that lead to dry Age-related Macular Degeneration are largely unelucidated, which prevents the introduction of effective therapies. Experimental support exists in the literature for the hypothesis that choroidal endothelial cell (ChEC) dysfunction precedes the loss of macular retinal pigmented epithelial (RPE), which may be only a secondary consequence of inadequate blood supply. If so, interventions at the level of ChEC could constitute an under investigated therapeutic strategy. Datasets regarding the transcriptional changes in early or intermediate dry AMD are publicly available, but for some some of them the information about ChECs have not been analyzed, or not analyzed using the most powerful and recent software tools. We present here new data generated by our bioinformatics analysis of these datasets. The main new finding is that angiogenesis is initiated in dry AMD, as it is in wet AMD. However, contrary to wet AMD, in dry AMD angiogenesis fails to execute, and therefore the blood supply that supports the RPE becomes gradually insufficient, leading to their dysfunctionality and death. The data support a unitary hypothesis of the origin / initiation / etiology of both dry and wet AMD, namely that both are initiated by ChEC dysfunction - either insufficient / abortive angiogenesis in dry AMD, or excessive angiogenesis in wet AMD. Pathway analysis also reveals as perturbed Notch and TNF signaling, endothelial to mesenchymal transition (EndoMT), mitochondria, "fluid shear stress", "osteoclast differentiation" and "calcification/osteoporosis". Overall, the new data provide a rationale for experimental studies, to validate and further characterize these perturbations, and investigate strategies to correct them.

The aquaculture industry needs to address several challenges to secure sustainable seafood production that can serve an increasing global demand. One major challenge is to ensure good fish health and acceptable welfare during production since the improvement of fish welfare is of vital importance in current and future production systems. In this study, this is addressed by developing and implementing methods to identify fish behaviors in response to intrusive objects both on individual and on a group basis. A novel approach for detecting, tracking, and estimating the 3D position of individual fish has thus been developed, and specifically designed to track the caudal fins of farmed fish in industrial sea cages. The tracking data was subjected to a novel stereo-vision method adapted to estimate fish positions, velocities, accelerations, and turning and pitch angles. Datasets obtained from industrial-scale fish farms were then analyzed to identify the impact of structures of varying shapes, sizes, and colors on fish behavior. The method was trained using manually labeled caudal fins, and used YOLOv8 with ByteTrack as an object detector and tracker, SuperGlue for matching detections in the left and right frames, and triangulation to reconstruct the 3D positions of the fish. Different image pre-processing and augmentation methods for enhancing object detection accuracy were tested and their performance compared, while RAFT-Stereo was tested for depth estimation purposes. The obtained results both validate the method's performance against previous research efforts, and demonstrate the novelty and potential of this method in providing more insight into behavioral dynamics in sea-cages.

During pandemics, public health agencies need to rapidly assess whether a new viral variant is more transmissible than existing lineages. For co-circulating variants, relative fitness can be expressed as a selective coefficient, as the differential population growth rate (DPGR) estimated from genomic surveillance, or, with additional assumptions, as a contrast in epidemic reproduction numbers $R_t$. We show that DPGR estimates a pairwise growth-rate difference. Under a specified generation-interval model, this difference can be transformed into reproduction-number space; in the equal-generation-time SIR special case, it reduces to a scaled difference in variant-specific $R_t$. Related growth-rate contrasts also appear in multinomial logistic and growth-advantage random-walk models, although those methods differ from DPGR in likelihood, smoothing, priors, and data inputs. We evaluate the theory across five SARS-CoV-2 and influenza analyses totaling more than 2,200 matched data points. SIR simulation recovers the expected mapping when the true $R_t$ is known, and retrospective SARS-CoV-2 analyses show sustained DPGR signals 43 to 65 days before variant dominance, with 95\% sign accuracy in our analysis. DPGR is approximately transitive across lineage triplets, near zero for selected functionally similar sublineages, and directionally consistent across countries. These results connect sequence-count-based fitness estimates to reproduction-number contrasts through an assumption-explicit growth-rate bridge.

Reservoir computing, a type of recurrent neural network, is a promising approach for temporal learning as it separates dynamic processing from the trained readout layer. However, classical Echo State Networks (ESNs) often require task-specific tuning of their architecture and hyperparameters to achieve good performance. This paper introduces EARLY (Evolutionary Algorithm for Reservoir Learning and Yielding), a framework designed to evolve both the topology and hyperparameters of multi-reservoir ESNs. Inspired by the modular organisation of the brain, EARLY encodes architectures as graph-based genomes and applies crossover, mutation, and selection to discover effective configurations. Our goal is to create both generic architectures and tasks inducing generalization. The method is evaluated on temporal learning tasks from the CogScale dataset. Results show that evolved architectures outperform those obtained with random search on several tasks and exhibit structural differences depending on task difficulty: simpler tasks yield lightweight architectures, while more complex tasks favour richer modular organisations. These findings suggest that evolutionary search can help identify reusable reservoir structures for a broader range of temporal problems. The evolved architectures are further evaluated on a cross-situational learning dataset to assess their ability to adapt to new environments.

Surrogate Safety Measures (SSMs) are extensively utilised in the evaluation of traffic risk in automated driving contexts. However, the majority of SSM-based evaluations employ fixed thresholds that fail to capture the human response to sustained borderline conditions or the reaction to brief, high-risk peaks. The present work proposes a biologically inspired reinterpretation of SSM thresholds. This is modelled as spiking thresholds of leaky integrate-and-fire (LIF) neurons, with multiple SSM inputs combined into a spiking neural network (SNN). The SNN is trained to emit spikes that are aligned with human braking onsets. The training data was recorded in a controlled car-following experiment using the 3D-CoAutoSim platform with CARLA/Unreal and a 6-DOF motion platform, where induced critical events were generated. The results demonstrate that the learned spiking activity qualitatively aligns with braking behaviour across scenarios and captures reactions that are not consistently explained by threshold crossings alone. Analysis across participants further indicates that learned input thresholds remain relatively consistent, while learned decay factors encode different temporal sensitivities for the SSMs. The findings of this study indicate that spiking dynamics may serve as a mechanism to facilitate the convergence of objective SSMs with subjective human safety perception.

Not all clinically relevant adverse effects are structurally inferable from molecular graphs - regardless of model quality or architectural complexity. This study introduces an operational taxonomy of the structural information limits that prevent structure-based toxicity prediction, independent of the learning algorithm employed. Graph Neural Networks (GNNs) have emerged as a natural approach for molecular toxicity prediction, operating directly on atomic connectivity without the information loss inherent to fixed-length fingerprints. However, the fraction of a drug's known pharmacological profile that is actually inferable from molecular structure remains systematically underexplored. A systematic case study using acetylsalicylic acid (ASA, Aspirin) - one of the most comprehensively characterized drugs in pharmacology - serves as model compound. A Message Passing Neural Network (MPNN) is trained on the Tox21 benchmark and GNNExplainer is applied to characterize atom-level attribution. Results indicate that molecular structure explains approximately 45% (5/11) of known ASA adverse effects. A four-category Gap Taxonomy (GAP-1 through GAP-4) is introduced distinguishing between principally non-encodable effects, data gaps arising from Missing Not At Random (MNAR) mechanisms, assay panel mismatches, and representation errors. The MNAR gap is empirically quantified via a systematic ChEMBL query (42 documented assays, 0 retrievable bioactivity entries). An attention pooling experiment localizes the representation error to the MPNN message passing layers rather than the aggregation step. The Gap Taxonomy has direct implications for drug safety signal detection and regulatory frameworks including Good Pharmacovigilance Practice (GVP) guidelines and New Approach Methodologies (NAMs). Structural limits identified are confirmed in a companion DDI ablation study.

D-peptide binders targeting L-proteins have promising therapeutic potential. Despite rapid advances in machine learning-based target-conditioned peptide design, generating D-peptide binders remains largely unexplored. In this work, we show that by injecting axial features to $E(3)$-equivariant (polar) vector features, it is feasible to achieve cross-chirality generalization from homo-chiral (L--L) training data to hetero-chiral (D--L) design tasks. By implementing this method within a latent diffusion model, we achieved D-peptide binder design that not only outperforms existing tools in \textit{in silico} benchmarks, but also demonstrates efficacy in wet-lab validation. To our knowledge, our approach represents the first wet-lab validated generative AI for the \textit{de novo} design of D-peptide binders, offering new perspectives on handling chirality in protein design. Codes are available at https://github.com/YZY010418/PepMirror