Transcription factors (TFs) regulate gene expression through complex and co-operative mechanisms. While many TFs act together, the logic underlying TFs binding and their interactions is not fully understood yet. Most current approaches for TF binding site prediction focus on individual TFs and binary classification tasks, without a full analysis of the possible interactions among various TFs. In this paper we investigate DNA TF binding site recognition as a multi-label classification problem, achieving reliable predictions for multiple TFs on DNA sequences retrieved in public repositories. Our deep learning models are based on Temporal Convolutional Networks (TCNs), which are able to predict multiple TF binding profiles, capturing correlations among TFs andtheir cooperative regulatory mechanisms. Our results suggest that multi-label learning leading to reliable predictive performances can reveal biologically meaningful motifs and co-binding patterns consistent with known TF interactions, while also suggesting novel relationships and cooperation among TFs.

Knotted proteins embed a physical (i.e., open) knot within their native structures. For decades, significant effort has been devoted to elucidating the functional role of knots in proteins, yet no consensus has been reached. Here, using extensive Monte Carlo off-lattice simulations of a simple structure-based model, we isolate the effect of topology by comparing simulations that preserve the linear topology of the chain with simulations that allow chain crossings. This controlled framework enables us to isolate topological effects from sequence, structure and energetic contributions. We show that protein kinetic stability, defined as resistance to unfolding at a fixed temperature, is higher in knotted proteins. Additionally, kinetic stability increases significantly with knot depth, whereas foldability (or folding efficiency) is comparatively less affected. By considering a simple model of protein evolution in which amino-acid alphabet size is used as a proxy for evolutionary time, we find that increasing primary-sequence complexity through the addition of biotic amino acids predominantly enhances kinetic stability. Taken together, these results indicate that kinetic stability is a functional advantage conferred by protein knots and suggest that evolutionary pressure for kinetic stability could contribute to the persistence of knotted proteins.

Modern imaging instruments can produce terabytes to petabytes of data for a single experiment. The biggest barrier to processing big image datasets has been computational, where image analysis algorithms often lack the efficiency needed to process such large datasets or make tradeoffs in robustness and accuracy. Deep learning algorithms have vastly improved the accuracy of the first step in an analysis workflow (region segmentation), but the expansion of domain specific feature extraction libraries across scientific disciplines has made it difficult to compare the performance and accuracy of extracted features. To address these needs, we developed a novel feature extraction library called Nyxus. Nyxus is designed from the ground up for scalable out-of-core feature extraction for 2D and 3D image data and rigorously tested against established standards. The comprehensive feature set of Nyxus covers multiple biomedical domains including radiomics and cellular analysis, and is designed for computational scalability across CPUs and GPUs. Nyxus has been packaged to be accessible to users of various skill sets and needs: as a Python package for code developers, a command line tool, as a Napari plugin for low to no-code users or users that want to visualize results, and as an Open Container Initiative (OCI) compliant container that can be used in cloud or super-computing workflows aimed at processing large data sets. Further, Nyxus enables a new methodological approach to feature extraction allowing for programmatic tuning of many features sets for optimal computational efficiency or coverage for use in novel machine learning and deep learning applications.

Brains remain unrivaled in their ability to recognize and generate complex spatiotemporal patterns. While AI is able to reproduce some of these capabilities, deep learning algorithms remain largely at odds with our current understanding of brain circuitry and dynamics. This is prominently the case for backpropagation through time (BPTT), the go-to algorithm for learning complex temporal dependencies. In this work we propose a general formalism to approximate BPTT in a controlled, biologically plausible manner. Our approach builds on, unifies and extends several previous approaches to local, time-continuous, phase-free spatiotemporal credit assignment based on principles of energy conservation and extremal action. Our starting point is a prospective energy function of neuronal states, from which we calculate real-time error dynamics for time-continuous neuronal networks. In the general case, this provides a simple and straightforward derivation of the adjoint method result for neuronal networks, the time-continuous equivalent to BPTT. With a few modifications, we can turn this into a fully local (in space and time) set of equations for neuron and synapse dynamics. Our theory provides a rigorous framework for spatiotemporal deep learning in the brain, while simultaneously suggesting a blueprint for physical circuits capable of carrying out these computations. These results reframe and extend the recently proposed Generalized Latent Equilibrium (GLE) model.

For several decades, experimental and computational studies have been used to investigate the potential functional role of knots in protein structures. A property that has attracted considerable attention is thermal stability, i.e., the extent to which a protein retains its native conformation and biological activity at high temperatures, without undergoing denaturation or aggregation. Thermal stability is quantified by the melting temperature Tm, an equilibrium property that corresponds to the peak of heat capacity in differential scanning calorimetry (DSC) experiments. Experimental and computational studies report conflicting effects of knotting on protein thermal stability. Here, we use extensive Monte Carlo simulations of a simple C-alpha model of protein YibK, with energetics modeled by the Go potential, to show that Tm does not depend on the topological state of the protein. Our simulations further support the view that the discrepancy between the experimental and computational results stems from a pronounced separation of timescales for unknotting and unfolding that is inherent to deeply knotted proteins like YibK. In particular, the timescale separation implies that the complete unfolding-untying transition may not be accessible within the duration of a DSC experiment, whose apparent Tm measurements likely reflect a non-equilibrium distribution lacking unfolded states that are also unknotted.

It is difficult or infeasible to directly measure how much of a drug actually enters the human brain and a brain tumor, how long it remains there, and to estimate drug-specific or patient-specific parameters, as well as how changes in these parameters influence model outputs and pharmacokinetic characteristics. Compartmental modeling offers a powerful mathematical approach to describe drug distribution and elimination in the body using systems of differential equations. This study introduces TumorPred, an R/Shiny-based web application designed for model simulation, sensitivity analysis, and pharmacokinetic parameter calculation in a permeability-limited four-compartment brain model. The model closely mimics human brain functionality for drug delivery and aims to predict the pharmacokinetics of drugs in the brain blood, brain mass, and cranial and spinal cerebrospinal fluid (CSF) of the human brain. The app provides real-time output updates in response to input modifications and allows users to visualize and download simulated plots and data tables. The computational accuracy of TumorPred is validated against results from the Simcyp Simulator (Certara Inc.). TumorPred is freely accessible and serves as an invaluable computational tool and data-driven resource for advancing drug development and optimizing treatment strategies for more effective brain cancer therapy.

In this work, we define a practical identifiability criterion, (e, q)-identifiability, based on a parameter e, reflecting the noise in observed variables, and a parameter q, reflecting the mean-square error of the parameter estimator. This criterion is better able to encompass changes in the quality of the parameter estimate due to increased noise in the data (compared to existing criteria based solely on average relative errors). Furthermore, we leverage a weak-form equation error-based method of parameter estimation for systems with unobserved variables to assess practical identifiability far more quickly in comparison to output error-based parameter estimation. We do so by generating weak-form input-output equations using differential algebra techniques, as previously proposed by Boulier et al [1], and then applying Weak form Estimation of Nonlinear Dynamics (WENDy) to obtain parameter estimates. This method is computationally efficient and robust to noise, as demonstrated through two classical biological modelling examples.

Entropic forces play a fundamental role in nanoscale phenomena, from colloidal self-assembly to biomolecular disaggregation. Here, we develop an exact analytical theory and find general scaling laws for the entropic separation of tether-mediated nanofilament bundles, revealing that a single dimensionless parameter--the ratio of the excluded-volume radius to the tether length--dictates whether filaments are pushed apart or, contrary to the usual expectation, pulled together. This unexpected regime challenges the view that entropic forces invariably promote disaggregation, instead uncovering conditions under which the bundles can remain in attractive metastable states. Brownian dynamics simulations confirm this paradoxical effect, offering predictive insights for applications in biophysics, soft matter physics, and nanotechnology.

Phytolith analysis is a crucial tool for reconstructing past vegetation and human activities, but traditional methods are severely limited by labour-intensive, time-consuming manual microscopy. To address this bottleneck, we present Sorometry: a comprehensive end-to-end artificial intelligence pipeline for the high-throughput digitisation, inference, and interpretation of phytoliths. Our workflow processes z-stacked optical microscope scans to automatically generate synchronised 2D orthoimages and 3D point clouds of individual microscopic particles. We developed a multimodal fusion model that combines ConvNeXt for 2D image analysis and PointNet++ for 3D point cloud analysis, supported by a graphical user interface for expert annotation and review. Tested on reference collections and archaeological samples from the Bolivian Amazon, our fusion model achieved a global classification accuracy of 77.9\% across 24 diagnostic morphotypes and 84.5% for segmentation quality. Crucially, the integration of 3D data proved essential for distinguishing complex morphotypes (such as grass silica short cell phytoliths) whose diagnostic features are often obscured by their orientation in 2D projections. Beyond individual object classification, Sorometry incorporates Bayesian finite mixture modelling to predict overall plant source contributions at the assemblage level, successfully identifying specific plants like maize and palms in complex mixed samples. This integrated platform transforms phytolith research into an "omics"-scale discipline, dramatically expanding analytical capacity, standardising expert judgements, and enabling reproducible, population-level characterisations of archaeological and paleoecological assemblages.

Head-mounted miniaturized microscopes, commonly known as miniscopes, have undergone rapid development and seen widespread adoption over the past two decades, enabling the imaging of neural activity in freely-behaving animals such as rodents, songbirds, and non-human primates. These miniscopes facilitate numerous studies that are not feasible with head-fixed preparations. Recent advancements have enhanced their capabilities, allowing for faster imaging, larger fields of view, and deeper brain penetration. In this review, we examine the latest progress in one-photon and multi-photon miniscopes. We highlight the unique opportunities these devices present for neuroscience research, discuss the current technical challenges, and explore emerging technologies that promise to advance the development of miniscopes.

We introduce a subclass of Lie symmetries, called parameter-state symmetries, to analyse the local structural identifiability and observability of mechanistic models consisting of state-dependent ODEs with observed outputs. These symmetries act on parameters and states while preserving observed outputs at every time point. We prove that locally structurally identifiable parameter combinations and locally structurally observable states correspond to universal invariants of all parameter-state symmetries of a given model. We illustrate the framework on four previously studied mechanistic models, confirming known identifiability results and revealing novel insights into which states are observable, providing a unified symmetry-based approach for analysing structural properties of dynamical systems.

Antimicrobial resistance (AMR) poses a global health threat, reducing the effectiveness of antibiotics and complicating clinical decision-making. To address this challenge, we introduce abx_amr_simulator, a Python-based simulation package designed to model antibiotic prescribing and AMR dynamics within a controlled, reinforcement learning (RL)-compatible environment. The simulator allows users to specify patient populations, antibiotic-specific AMR response curves, and reward functions that balance immedi- ate clinical benefit against long-term resistance management. Key features include a modular design for configuring patient attributes, antibiotic resistance dynamics modeled via a leaky-balloon abstraction, and tools to explore partial observability through noise, bias, and delay in observations. The package is compatible with the Gymnasium RL API, enabling users to train and test RL agents under diverse clinical scenarios. From an ML perspective, the package provides a configurable benchmark environment for sequential decision-making under uncertainty, including partial observability induced by noisy, biased, and delayed observations. By providing a customizable and extensible framework, abx_amr_simulator offers a valuable tool for studying AMR dynamics and optimizing antibiotic stewardship strategies under realistic uncertainty.

The study of navigation behaviour and the associated brain dynamics have been a focus increasing research over the last decades. Coinciding with this has been an increased focus on a more ecological understanding of cognition. Here we review recent research seeking to provide a more naturalistic, ecological understanding of human navigation behaviour and brain dynamics. Research in this area falls into four categories: testing navigation in real-world environments, analysis of data collected from tracking individuals during daily life, navigation in simulated or virtual environments mimicking the real-world, and mobile brain recording methods. Combining these different approaches to understand the neural basis of navigation shows excellent promise. We conclude with future directions for this research area.

Data-driven discovery of governing equations from time-series data provides a powerful framework for understanding complex biological systems. Library-based approaches that use sparse regression over candidate functions have shown considerable promise, but they face a critical challenge when candidate functions become strongly correlated: numerical ill-conditioning. Poor or restricted sampling, together with particular choices of candidate libraries, can produce strong multicollinearity and numerical instability. In such cases, measurement noise may lead to widely different recovered models, obscuring the true underlying dynamics and hindering accurate system identification. Although sparse regularization promotes parsimonious solutions and can partially mitigate conditioning issues, strong correlations may persist, regularization may bias the recovered models, and the regression problem may remain highly sensitive to small perturbations in the data. We present a systematic analysis of how ill-conditioning affects sparse identification of biological dynamics using benchmark models from systems biology. We show that combinations involving as few as two or three terms can already exhibit strong multicollinearity and extremely large condition numbers. We further show that orthogonal polynomial bases do not consistently resolve ill-conditioning and can perform worse than monomial libraries when the data distribution deviates from the weight function associated with the orthogonal basis. Finally, we demonstrate that when data are sampled from distributions aligned with the appropriate weight functions corresponding to the orthogonal basis, numerical conditioning improves, and orthogonal polynomial bases can yield improved model recovery accuracy across two baseline models.

State space models (SSMs) have recently achieved strong performance on long sequence modeling tasks while offering improved memory and computational efficiency compared to transformer based architectures. However, their evaluation has been largely limited to synthetic benchmarks and application domains such as language and audio, leaving their behavior on sparse and stochastic temporal processes in biological imaging unexplored. In this work, we introduce the Single Molecule Localization Microscopy Challenge (SMLM-C), a benchmark dataset consisting of ten SMLM simulations spanning dSTORM and DNA-PAINT modalities with varying hyperparameter designed to evaluate state space models on biologically realistic spatiotemporal point process data with known ground truth. Using a controlled subset of these simulations, we evaluate state space models and find that performance degrades substantially as temporal discontinuity increases, revealing fundamental challenges in modeling heavy-tailed blinking dynamics. These results highlight the need for sequence models better suited to sparse, irregular temporal processes encountered in real world scientific imaging data.

Efficient interaction with the visual world requires not only accurate object identification but also precise localization of objects in space. While spatial ("where") processing has traditionally been attributed to dorsal stream pathways, recent work has shown that object position can also be decoded from responses in ventral stream areas such as the inferior temporal (IT) cortex. However, because object position in these paradigms is tightly coupled to pixel-based location, it remains unclear whether ventral stream position signals reflect perceptually meaningful spatial representations or simply inherited retinotopic structure. To address this question, we used the motion aftereffect, a classic visual illusion that shifts perceived object position without changing retinal input. Combining large-scale intracortical recordings in macaque IT with matched human psychophysics, we found that motion adaptation induces systematic direction-opponent biases in IT population codes for object position that mirror human perceptual reports, despite identical pixel-level stimuli. These effects are accompanied by adaptation-driven changes in the geometry of IT population representations. We further tested whether artificial vision systems exhibit similar dynamics. Standard feedforward, recurrent, and state-of-the-art video-based neural networks accurately encode object position but fail to produce adaptation-induced position shifts. However, applying empirically derived transformations based on IT adaptation dynamics to model feature spaces is sufficient to generate similar biases. Together, these results indicate that IT represents object position in perceptually aligned coordinates and also highlight a gap between biological and artificial vision systems in capturing history-dependent spatial coding.

The rapid development of generative models for single-cell gene expression data has created an urgent need for standardised evaluation frameworks. Current evaluation practices suffer from inconsistent metric implementations, incomparable hyperparameter choices, and a lack of biologically-grounded metrics. We present Generated Genetic Expression Evaluator (GGE), an open-source Python framework that addresses these challenges by providing a comprehensive suite of distributional metrics with explicit computation space options and biologically-motivated evaluation through differentially expressed gene (DEG)-focused analysis and perturbation-effect correlation, enabling standardized reporting and reproducible benchmarking. Through extensive analysis of the single-cell generative modeling literature, we identify that no standardized evaluation protocol exists. Methods report incomparable metrics computed in different spaces with different hyperparameters. We demonstrate that metric values vary substantially depending on implementation choices, highlighting the critical need for standardization. GGE enables fair comparison across generative approaches and accelerates progress in perturbation response prediction, cellular identity modeling, and counterfactual inference.

Cross-species antimicrobial resistance (AMR) prediction is fundamentally an out-of-distribution (OOD) generalization problem: models trained on one set of bacterial taxa must transfer to phylogenetically distinct genomes that may rely on different resistance mechanisms. Across species, resistance arises from a heterogeneous mixture of localized, horizontally transferred gene cassettes and diffuse species-specific genomic backgrounds, making successful transfer inherently mechanism-dependent. Using a strict species holdout protocol, we first establish an interpretable k-mer baseline with Kover and show that strong within-species performance collapses under true cross-species evaluation. This motivates representation-level approaches that preserve transferable biological signals rather than amplify phylogenetic shortcuts. We investigate genomic foundation model embeddings derived from Evo-1-8k-base and introduce diagnostics for layer selection based on activation scale, isotropy, effective rank, and cross-seed stability under native bfloat16 inference. These analyses identify a stability boundary in deeper layers and reveal that embeddings extracted near this boundary provide more robust representations for downstream prediction. To preserve localized resistance signals, we treat per-window embeddings as an ordered multivariate signal and apply MiniRocket to summarize multi-scale local activation patterns instead of relying on global pooling. Our results show that aggregation strategy plays a central role in cross-species AMR prediction and that preserving local activation patterns substantially improves generalization when resistance mechanisms are localized.

Agent-based models (ABMs) are widely used to estimate causal treatment effects via paired counterfactual simulation. A standard variance reduction technique is common random numbers (CRNs), which couples replicates across intervention scenarios by sharing the same random inputs. In practice, CRNs are implemented by reusing the same base seed, but this relies on a critical assumption: that the same draw index corresponds to the same modeled event across scenarios. Stateful pseudorandom number generators (PRNGs) violate this assumption whenever interventions alter the simulation's execution path, because any change in control flow shifts the draw index used for all downstream events. We argue that this execution-path-dependent draw indexing is not only a variance-reduction nuisance, but represents a fundamental mismatch between the scientific causal structure ABMs are intended to encode and the program-level causal structure induced by stateful PRNG implementations. Formalizing this through the lens of structural causal models (SCMs), we show that standard PRNG practices yield causally incoherent paired counterfactual comparisons even when the mechanistic specification is otherwise sound. We show that a remedy is to combine counter-based random number generators (e.g., Philox/Threefry) with event identifiers. This decouples random number generation from simulation execution order by making random draws explicit functions of the particular modeled event that called them, restoring the stable event-indexed exogenous structure assumed by SCMs.

Gene expression prediction, which predicts mRNA expression levels from DNA sequences, presents significant challenges. Previous works often focus on extending input sequence length to locate distal enhancers, which may influence target genes from hundreds of kilobases away. Our work first reveals that for current models, long sequence modeling can decrease performance. Even carefully designed algorithms only mitigate the performance degradation caused by long sequences. Instead, we find that proximal multimodal epigenomic signals near target genes prove more essential. Hence we focus on how to better integrate these signals, which has been overlooked. We find that different signal types serve distinct biological roles, with some directly marking active regulatory elements while others reflect background chromatin patterns that may introduce confounding effects. Simple concatenation may lead models to develop spurious associations with these background patterns. To address this challenge, we propose Prism, a framework that learns multiple combinations of high-dimensional epigenomic features to represent distinct background chromatin states and uses backdoor adjustment to mitigate confounding effects. Our experimental results demonstrate that proper modeling of multimodal epigenomic signals achieves state-of-the-art performance using only short sequences for gene expression prediction.

Evolutionary accumulation models (EvAMs) are an emerging class of machine learning methods designed to infer the evolutionary pathways by which features are acquired. Applications include cancer evolution (accumulation of mutations), anti-microbial resistance (accumulation of drug resistances), genome evolution (organelle gene transfers), and more diverse themes in biology and beyond. Following these themes, many EvAMs assume that features are gained irreversibly -- no loss of features can occur. Reversible approaches do exist but are often computationally (much) more demanding and statistically less stable. Our goal here is to explore whether useful information about evolutionary dynamics which are in reality reversible can be obtained from modelling approaches with an assumption of irreversibility. We identify, and use simulation studies to quantify, errors involved in neglecting reversible dynamics, and show the situations in which approximate results from tractable models can be informative and reliable. In particular, EvAM inferences about the relative orderings of acquisitions and the core dynamic structure of evolutionary pathways -- which features are likely present when another is acquired -- are robust to reversibility in many cases, while estimations of uncertainty and feature interactions are more error-prone.

The majority of research in both training Artificial Neural Networks (ANNs) and modeling learning in biological brains focuses on synaptic plasticity, where learning equates to changing the strength of existing connections. However, in biological brains, structural plasticity - where new connections are created and others removed - is also vital, not only for effective learning but also for recovery from damage and optimal resource usage. Inspired by structural plasticity, pruning is often used in machine learning to remove weak connections from trained models to reduce the computational requirements of inference. However, the machine learning frameworks typically used for backpropagation-based training of both ANNs and Spiking Neural Networks (SNNs) are optimized for dense connectivity, meaning that pruning does not help reduce the training costs of ever-larger models. The GeNN simulator already supports efficient GPU-accelerated simulation of sparse SNNs for computational neuroscience and machine learning. Here, we present a new flexible framework for implementing GPU-accelerated structural plasticity rules and demonstrate this first using the e-prop supervised learning rule and DEEP R to train efficient, sparse SNN classifiers and then, in an unsupervised learning context, to learn topographic maps. Compared to baseline dense models, our sparse classifiers reduce training time by up to 10x while the DEEP R rewiring enables them to perform as well as the original models. We demonstrate topographic map formation in faster-than-realtime simulations, provide insights into the connectivity evolution, and measure simulation speed versus network size. The proposed framework will enable further research into achieving and maintaining sparsity in network structure and neural communication, as well as exploring the computational benefits of sparsity in a range of neuromorphic applications.

Reaction time (RT) is a fundamental measure in cognitive and neurophysiological assessment, yet most existing RT systems require active user engagement and controlled environments, limiting their use in real-world settings. This paper introduces a low cost wrist-worn instrumentation platform designed to capture human reaction times (RT) across auditory, visual, and haptic modalities with millisecond latency in real-world conditions. The device integrates synchronized stimulus delivery and event detection within a compact microcontroller-based system, eliminating the need for user focus or examiner supervision. Emphasizing measurement fidelity, we detail the hardware architecture, timing control algorithms, and calibration methodology used to ensure consistent latency handling across modalities. A proof-of-concept study with six adult participants compares this system against a benchmark computer-based RT tool across five experimental conditions. The results confirm that the device achieves statistically comparable RT measurements with strong modality consistency, supporting its potential as a novel tool for non-obtrusive cognitive monitoring. Contributions include a validated design for time-critical behavioral measurement and a demonstration of its robustness in unconstrained, ambient-noise environments. It offers a powerful new tool for continuous, real-world cognitive monitoring and has significant potential for both research and clinical applications.

Smart agriculture applications, integrating technologies like the Internet of Things and machine learning/artificial intelligence (ML/AI) into agriculture, hold promise to address modern challenges of rising food demand, environmental pollution, and water scarcity. Alongside the concept of the phytobiome, which defines the area including the plant, its environment, and associated organisms, and the recent emergence of molecular communication (MC), there exists an important opportunity to advance agricultural science and practice using communication theory. In this article, we motivate to use the communication engineering perspective for developing a holistic understanding of the phytobiome communication and bridge the gap between the phytobiome communication and smart agriculture. Firstly, an overview of phytobiome communication via molecular and electrophysiological signals is presented and a multi-scale framework modeling the phytobiome as a communication network is conceptualized. Then, how this framework is used to model electrophysiological signals is demonstrated with plant experiments. Furthermore, possible smart agriculture applications, such as smart irrigation and targeted delivery of agrochemicals, through engineering the phytobiome communication are proposed. These applications merge ML/AI methods with the Internet of Bio-Nano-Things enabled by MC and pave the way towards more efficient, sustainable, and eco-friendly agricultural production. Finally, the implementation challenges, open research issues, and industrial outlook for these applications are discussed.

Predicting the outcome of antiretroviral therapies (ART) for HIV-1 is a pressing clinical challenge, especially when the ART includes drugs with limited effectiveness data. This scarcity of data can arise either due to the introduction of a new drug to the market or due to limited use in clinical settings, resulting in clinical dataset with highly unbalanced therapy representation. To tackle this issue, we introduce a novel joint fusion model, which combines features from a Fully Connected (FC) Neural Network and a Graph Neural Network (GNN) in a multi-modality fashion. Our model uses both tabular data about genetic sequences and a knowledge base derived from Stanford drug-resistance mutation tables, which serve as benchmark references for deducing in-vivo treatment efficacy based on the viral genetic sequence. By leveraging this knowledge base structured as a graph, the GNN component enables our model to adapt to imbalanced data distributions and account for Out-of-Distribution (OoD) drugs. We evaluated these models' robustness against OoD drugs in the test set. Our comprehensive analysis demonstrates that the proposed model consistently outperforms the FC model. These results underscore the advantage of integrating Stanford scores in the model, thereby enhancing its generalizability and robustness, but also extending its utility in contributing in more informed clinical decisions with limited data availability. The source code is available at https://github.com/federicosiciliano/graph-ood-hiv