Deep neural networks (DNNs) once showed increasing alignment with primate neural responses as they improved on computer vision benchmarks. This trend raised the exciting possibility that better models of biological vision would come as a byproduct of the deep learning revolution in artificial intelligence. However, the trend has reversed over recent years as DNNs have scaled to human or superhuman recognition accuracy, a divergence that may stem from modern DNNs learning to rely on different visual features than primates to solve tasks. Where will better computational models of biological vision come from? We propose that vision science must break from artificial intelligence to develop algorithms that are designed with biological visual systems in mind instead of internet data benchmarks. We predict that the next generation of deep learning models of biological vision will be trained with data diets, training routines, and objectives that are closer to those that shape human vision than those that are in use today.
This study presents a novel mathematical model derived from cohomology, leveraging the KEEL-proven theorem that establishes cohomology as tautological, generated by boundary classes of curves with fixed dual graphs. Simplicial complexes are constructed using skew-commutative graded algebra, and the structure theorem is applied to connect distinct homologies, enabling precise interpretations of the resulting geometric forms. The proposed model is utilized for protein structure analysis and prediction, with a specific application to the Flagellar Motor structure. This approach offers new insights into the geometric and algebraic foundations of biological macromolecular modeling, highlighting its potential for advancement in structural biology.
Automating the annotation of benthic imagery (i.e., images of the seafloor and its associated organisms, habitats, and geological features) is critical for monitoring rapidly changing ocean ecosystems. Deep learning approaches have succeeded in this purpose; however, consistent annotation remains challenging due to ambiguous seafloor images, potential inter-user annotation disagreements, and out-of-distribution samples. Marine scientists implementing deep learning models often obtain predictions based on one-hot representations trained using a cross-entropy loss objective with softmax normalization, resulting with a single set of model parameters. While efficient, this approach may lead to overconfident predictions for context-challenging datasets, raising reliability concerns that present risks for downstream tasks such as benthic habitat mapping and marine spatial planning. In this study, we investigated classification uncertainty as a tool to improve the labeling of benthic habitat imagery. We developed a framework for two challenging sub-datasets of the recently publicly available BenthicNet dataset using Bayesian neural networks, Monte Carlo dropout inference sampling, and a proposed single last-layer committee machine. This approach resulted with a > 95% reduction of network parameters to obtain per-sample uncertainties while obtaining near-identical performance compared to computationally more expensive strategies such as Bayesian neural networks, Monte Carlo dropout, and deep ensembles. The method proposed in this research provides a strategy for obtaining prioritized lists of uncertain samples for human-in-the-loop interventions to identify ambiguous, mislabeled, out-of-distribution, and/or difficult images for enhancing existing annotation tools for benthic mapping and other applications.
Automated breast cancer detection via computer vision techniques is challenging due to the complex nature of breast tissue, the subtle appearance of cancerous lesions, and variations in breast density. Mainstream techniques primarily focus on visual cues, overlooking complementary patient-specific textual features that are equally important and can enhance diagnostic accuracy. To address this gap, we introduce Multi-modal Cancer Detection Network (MMDCNet) that integrates visual cues with clinical data to improve breast cancer detection. Our approach processes medical images using computer vision techniques while structured patient metadata patterns are learned through a custom fully connected network. The extracted features are fused to form a comprehensive representation, allowing the model to leverage both visual and clinical information. The final classifier is trained based on the joint features embedding space of visual and clinical cues and experiments prove enhanced performance, improving accuracy from 79.38\% to 90.87\% on a Mini-DDSM dataset. Additionally, our approach achieves 97.05\% accuracy on an image-only dataset, highlighting the robustness and effectiveness of visual feature extraction. These findings emphasise the potential of multi-modal learning in medical diagnostics, paving the way for future research on optimising data integration strategies and refining AI-driven clinical decision support systems.
In this study, we built an end-to-end tumor-infiltrating lymphocytes (TILs) assessment pipeline within QuPath, demonstrating the potential of easily accessible tools to perform complex tasks in a fully automatic fashion. First, we trained a pixel classifier to segment tumor, tumor-associated stroma, and other tissue compartments in breast cancer H&E-stained whole-slide images (WSI) to isolate tumor-associated stroma for subsequent analysis. Next, we applied a pre-trained StarDist deep learning model in QuPath for cell detection and used the extracted cell features to train a binary classifier distinguishing TILs from other cells. To evaluate our TILs assessment pipeline, we calculated the TIL density in each WSI and categorized them as low, medium, or high TIL levels. Our pipeline was evaluated against pathologist-assigned TIL scores, achieving a Cohen's kappa of 0.71 on the external test set, corroborating previous research findings. These results confirm that existing software can offer a practical solution for the assessment of TILs in H&E-stained WSIs of breast cancer.
Mobile genetic elements like conjugative plasmids play a crucial role in shaping the genetic content and population dynamics of bacterial species. Bacterial populations often contain not one, but multiple co-circulating MGEs, which modify each other's population dynamics in a myriad of ways. Mathematical modeling is a powerful tool to gain intuition about the expected eco-evolutionary dynamics in a biological system with many interacting players. Here, we detail how to develop a mathematical model of plasmid co-infection, how to implement this computationally, and we give examples of what can be learned from such models.
Malignant gliomas (MGs), particularly glioblastoma, are among the most aggressive brain tumors, with limited treatment options and a poor prognosis. Maximal safe resection and the so-called Stupp protocol are the standard first-line therapies. Despite combining radiotherapy and chemotherapy in an intensive manner, it provides limited survival benefits over radiation therapy alone, underscoring the need for innovative therapeutic strategies. Emerging evidence suggests that alternative dosing schedules, such as less aggressive regimens with extended intervals between consecutive treatment applications, may improve outcomes, enhancing survival, delaying the emergence of resistance, and minimizing side effects. In this study, we develop, calibrate, and validate in animal models a novel ordinary differential equation-based mathematical model, using in vivo data to describe MG dynamics under combined chemoradiotherapy. The proposed model incorporates key biological processes, including cancer cell dormancy, phenotypic switching, drug resistance through persister cells, and treatment-induced effects. Through in silico trials, we identified optimized combination treatment protocols that may outperform the standard Stupp protocol. Finally, we computationally extrapolated the results obtained from the in vivo animal model to humans, showing up to a four-fold increase in median survival with protracted administration protocols in silico. Although further experimental and clinical validation is required, our framework provides a computational foundation to optimize and personalize treatment strategies for MG and potentially other cancers with similar biological mechanisms.
The human brain is a complex dynamical system which displays a wide range of macroscopic and mesoscopic patterns of neural activity, whose mechanistic origin remains poorly understood. Whole-brain modelling allows us to explore candidate mechanisms causing the observed patterns. However, it is not fully established how the choice of model type and the networks' resolution influence the simulation results, hence, it remains unclear, to which extent conclusions drawn from these results are limited by modelling artefacts. Here, we compare the dynamics of a biophysically realistic, linear-nonlinear cascade model of whole-brain activity with a phenomenological Wilson-Cowan model using three structural connectomes based on the Schaefer parcellation scheme with 100, 200, and 500 nodes. Both neural mass models implement the same mechanistic hypotheses, which specifically address the interaction between excitation, inhibition, and a slow adaptation current, which affects the excitatory populations. We quantify the emerging dynamical states in detail and investigate how consistent results are across the different model variants. Then we apply both model types to the specific phenomenon of slow oscillations, which are a prevalent brain rhythm during deep sleep. We investigate the consistency of model predictions when exploring specific mechanistic hypotheses about the effects of both short- and long-range connections and of the antero-posterior structural connectivity gradient on key properties of these oscillations. Overall, our results demonstrate that the coarse-grained dynamics are robust to changes in both model type and network resolution. In some cases, however, model predictions do not generalize. Thus, some care must be taken when interpreting model results.
Terracettes, striking, step-like landforms that stripe steep, vegetated hillslopes, have puzzled scientists for more than a century. Competing hypotheses invoke either slow mass-wasting or the relentless trampling of grazing animals, yet no mechanistic model has linked hoof-scale behavior to landscape-scale form. Here we bridge that gap with an active-walker model in which ungulates are represented as stochastic foragers moving on an erodible slope. Each agent weighs the energetic cost of climbing against the benefit of fresh forage; every hoof-fall compacts soil and lowers local biomass, subtly reshaping the energy landscape that guides subsequent steps. Over time, these stigmergic feedbacks concentrate traffic along cross-slope paths that coalesce into periodic tread-and-riser bands, morphologically analogous to natural terracettes. Our model illustrates how local foraging rules governing movement and substrate feedback can self-organize into large-scale topographic patterns, highlighting the wider role of decentralized biological processes in sculpting terrestrial landscapes.
Neurotensin receptor 1 (NTSR1), a member of the Class A G protein-coupled receptor superfamily, plays an important role in modulating dopaminergic neuronal activity and eliciting opioid-independent analgesia. Recent studies suggest that promoting \{beta}-arrestin-biased signaling in NTSR1 may diminish drugs of abuse, such as psychostimulants, thereby offering a potential avenue for treating human addiction-related disorders. In this study, we utilized a novel computational and experimental approach that combined nudged elastic band-based molecular dynamics simulations, Markov state models, temporal communication network analysis, site-directed mutagenesis, and conformational biosensors, to explore the intricate mechanisms underlying NTSR1 activation and biased signaling. Our study reveals a dynamic stepwise transition mechanism and activated transmission network associated with NTSR1 activation. It also yields valuable insights into the complex interplay between the unique polar network, non-conserved ion locks, and aromatic clusters in NTSR1 signaling. Moreover, we identified a cryptic allosteric site located in the intracellular region of the receptor that exists in an intermediate state within the activation pathway. Collectively, these findings contribute to a more profound understanding of NTSR1 activation and biased signaling at the atomic level, thereby providing a potential strategy for the development of NTSR1 allosteric modulators in the realm of G protein-coupled receptor biology, biophysics, and medicine.
Many drugs have been withdrawn from the market worldwide, at a cost of billions of dollars, because of patient fatalities due to them unexpectedly disturbing heart rhythm. Even drugs for ailments as mild as hay fever have been withdrawn due to an unacceptable increase in risk of these heart rhythm disturbances. Consequently, the whole pharmaceutical industry expends a huge effort in checking all new drugs for any unwanted side effects on the heart. The predominant root cause has been identified as drug molecules blocking ionic current flows in the heart. Block of individual types of ionic currents can now be measured experimentally at an early stage of drug development, and this is the standard screening approach for a number of ion currents in many large pharmaceutical companies. However, clinical risk is a complex function of the degree of block of many different types of cardiac ion currents, and this is difficult to understand by looking at results of these screens independently. By using ordinary differential equation models for the electrical activity of heart cells (electrophysiology models) we can integrate information from different types of currents, to predict the effect on whole heart cells and subsequent risk of side effects. The resulting simulations can provide a more accurate summary of the risk of a drug earlier in development and hence more cheaply than the pre-existing approaches.
Single-cell RNA sequencing (scRNA-seq) enables high-resolution analysis of cellular heterogeneity, but its complexity, which is marked by high dimensionality, sparsity, and batch effects, which poses major computational challenges. Transformer-based models have made significant advances in this domain but are often limited by their quadratic complexity and suboptimal handling of long-range dependencies. In this work, we introduce GeneMamba, a scalable and efficient foundation model for single-cell transcriptomics built on state space modeling. Leveraging the Bi-Mamba architecture, GeneMamba captures bidirectional gene context with linear-time complexity, offering substantial computational gains over transformer baselines. The model is pretrained on nearly 30 million cells and incorporates biologically informed objectives, including pathway-aware contrastive loss and rank-based gene encoding. We evaluate GeneMamba across diverse tasks, including multi-batch integration, cell type annotation, and gene-gene correlation, demonstrating strong performance, interpretability, and robustness. These results position GeneMamba as a practical and powerful alternative to transformer-based methods, advancing the development of biologically grounded, scalable tools for large-scale single-cell data analysis.
The inference of gene regulatory networks (GRNs) is a foundational stride towards deciphering the fundamentals of complex biological systems. Inferring a possible regulatory link between two genes can be formulated as a link prediction problem. Inference of GRNs via gene coexpression profiling data may not always reflect true biological interactions, as its susceptibility to noise and misrepresenting true biological regulatory relationships. Most GRN inference methods face several challenges in the network reconstruction phase. Therefore, it is important to encode gene expression values, leverege the prior knowledge gained from the available inferred network structures and positional informations of the input network nodes towards inferring a better and more confident GRN network reconstruction. In this paper, we explore the integration of multiple inferred networks to enhance the inference of Gene Regulatory Networks (GRNs). Primarily, we employ autoencoder embeddings to capture gene expression patterns directly from raw data, preserving intricate biological signals. Then, we embed the prior knowledge from GRN structures transforming them into a text-like representation using random walks, which are then encoded with a masked language model, BERT, to generate global embeddings for each gene across all networks. Additionally, we embed the positional encodings of the input gene networks to better identify the position of each unique gene within the graph. These embeddings are integrated into graph transformer-based model, termed GT-GRN, for GRN inference. The GT-GRN model effectively utilizes the topological structure of the ground truth network while incorporating the enriched encoded information. Experimental results demonstrate that GT-GRN significantly outperforms existing GRN inference methods, achieving superior accuracy and highlighting the robustness of our approach.
Language models have emerged as powerful predictors of the viability of biological sequences. During training these models learn the rules of the grammar obeyed by sequences of amino acids or nucleotides. Once trained, these models can take a sequence as input and produce a likelihood score as an output; a higher likelihood implies adherence to the learned grammar and correlates with experimental fitness measurements. Here we show that in-context learning can distort the relationship between fitness and likelihood scores of sequences. This phenomenon most prominently manifests as anomalously high likelihood scores for sequences that contain repeated motifs. We use protein language models with different architectures trained on the masked language modeling objective for our experiments, and find transformer-based models to be particularly vulnerable to this effect. This behavior is mediated by a look-up operation where the model seeks the identity of the masked position by using the other copy of the repeated motif as a reference. This retrieval behavior can override the model's learned priors. This phenomenon persists for imperfectly repeated sequences, and extends to other kinds of biologically relevant features such as reversed complement motifs in RNA sequences that fold into hairpin structures.
We propose a method to improve subject transfer in motor imagery BCIs by aligning covariance matrices on a Riemannian manifold, followed by computing a new common spatial patterns (CSP) based spatial filter. We explore various ways to integrate information from multiple subjects and show improved performance compared to standard CSP. Across three datasets, our method shows marginal improvements over standard CSP; however, when training data are limited, the improvements become more significant.
The subcellular localization of RNAs, including long non-coding RNAs (lncRNAs), messenger RNAs (mRNAs), microRNAs (miRNAs) and other smaller RNAs, plays a critical role in determining their biological functions. For instance, lncRNAs are predominantly associated with chromatin and act as regulators of gene transcription and chromatin structure, while mRNAs are distributed across the nucleus and cytoplasm, facilitating the transport of genetic information for protein synthesis. Understanding RNA localization sheds light on processes like gene expression regulation with spatial and temporal precision. However, traditional wet lab methods for determining RNA localization, such as in situ hybridization, are often time-consuming, resource-demanding, and costly. To overcome these challenges, computational methods leveraging artificial intelligence (AI) and machine learning (ML) have emerged as powerful alternatives, enabling large-scale prediction of RNA subcellular localization. This paper provides a comprehensive review of the latest advancements in AI-based approaches for RNA subcellular localization prediction, covering various RNA types and focusing on sequence-based, image-based, and hybrid methodologies that combine both data types. We highlight the potential of these methods to accelerate RNA research, uncover molecular pathways, and guide targeted disease treatments. Furthermore, we critically discuss the challenges in AI/ML approaches for RNA subcellular localization, such as data scarcity and lack of benchmarks, and opportunities to address them. This review aims to serve as a valuable resource for researchers seeking to develop innovative solutions in the field of RNA subcellular localization and beyond.
Deep learning-based antimicrobial peptide (AMP) discovery faces critical challenges such as low experimental hit rates as well as the need for nuanced controllability and efficient modeling of peptide properties. To address these challenges, we introduce OmegAMP, a framework that leverages a diffusion-based generative model with efficient low-dimensional embeddings, precise controllability mechanisms, and novel classifiers with drastically reduced false positive rates for candidate filtering. OmegAMP enables the targeted generation of AMPs with specific physicochemical properties, activity profiles, and species-specific effectiveness. Moreover, it maximizes sample diversity while ensuring faithfulness to the underlying data distribution during generation. We demonstrate that OmegAMP achieves state-of-the-art performance across all stages of the AMP discovery pipeline, significantly advancing the potential of computational frameworks in combating antimicrobial resistance.
Cell volume is controlled by osmotic regulation of the fluid content, via water efflux through the cell membrane. The rate of this process is controlled by the ability of the liquid to move through the meshwork of solid elements within the cell. While such dynamics have been interpreted in the frame of the poroelastic theory in the cytoplasm, the behavior of the nucleus remains unknown due to a lack of technique to probe it. Brillouin light scattering (BLS) allows to interrogate the sound velocity and attenuation of a sample in a non-contact manner, thus revealing the dynamic response of the material. In cells, such data were initially interpreted as the viscoelastic response of the actin meshwork, but later studies pointed out the importance of water content. To resolve this lack of consensus in the interpretation of the hypersonic data obtained from BLS spectra, and investigate the possible poroelastic nature of the nucleus, we vary the relative volume fraction of intracellular water and solid network by applying osmotic compressions to single cells. In the nucleus, we observe a non-linear increase in the sound velocity and attenuation with increasing osmotic pressure that we fit to a poroelastic model, providing an estimate of the friction coefficient between the water phase and the network. By comparing BLS data to volume measurements, our approach demonstrates clearly that Brillouin microscopy actually provides a measure of molecular concentration in living cells
Survival analysis often relies on Cox models, assuming both linearity and proportional hazards (PH). This study evaluates machine and deep learning methods that relax these constraints, comparing their performance with penalized Cox models on a benchmark of three synthetic and three real datasets. In total, eight different models were tested, including six non-linear models of which four were also non-PH. Although Cox regression often yielded satisfactory performance, we showed the conditions under which machine and deep learning models can perform better. Indeed, the performance of these methods has often been underestimated due to the improper use of Harrell's concordance index (C-index) instead of more appropriate scores such as Antolini's concordance index, which generalizes C-index in cases where the PH assumption does not hold. In addition, since occasionally high C-index models happen to be badly calibrated, combining Antolini's C-index with Brier's score is useful to assess the overall performance of a survival method. Results on our benchmark data showed that survival prediction should be approached by testing different methods to select the most appropriate one according to sample size, non-linearity and non-PH conditions. To allow an easy reproducibility of these tests on our benchmark data, code and documentation are freely available at https://github.com/compbiomed-unito/survhive.