Peer Revenue Publish or profit

Papers

Fresh from arXiv, typeset properly. Highlighted words trade on the market.

Quantitative Biology

q-bio Watch Quantitative Biology

Thursday 3 September

Quantitative Methods · Cross-listed from cs.AI

When Quantization Breaks Memory: Recurrent-State Write-Back in Low-Precision Temporal Inference

Ismail Erbas, Xavier Intes and Vikas Pandey

Quantization is widely used to reduce the computational and memory demands of neural-network inference. In recurrent networks, however, the quantized state is stored and returned at the next time step, so the rule used to store that state can alter subsequent computations. Here, we introduce recurrent-state write-back to denote this rule and isolate its effect in a compact GRU encoder–decoder for fluorescence lifetime imaging, a molecular imaging modality used in quantitative biological imaging. A central task is estimating two lifetime parameters, the short-lived component {\tau}1 and the long-lived component {\tau}2, from high-noise time-resolved fluorescence signals. Holding the trained model fixed, replacing continuous state propagation with deterministic 4-bit state storage increases estimation errors for {\tau}1 and {\tau}2 by approximately 70x and 300x, respectively. Failure occurs when repeated small updates remain below the write threshold, leaving the stored state nearly fixed while the network continues to propose change. Error feedback, residual memory, and direction memory carry information from these suppressed updates across time and recover accuracy without retraining. Precision sweeps show that increasing state precision can worsen a fixed recurrent solution, while matched training shows that compatibility with the state interface can be learned. To test whether this behavior extends beyond the GRU, we repeat the post-training intervention in an independently trained LSTM, where coarse write-back reproduces the failure, error feedback restores accuracy, and state-specific interventions reveal greater sensitivity of the cell state than the hidden state. Our results establish recurrent-state write-back as a key determinant of low-precision recurrent dynamics and identify the state-storage interface as a central design consideration for quantized recurrent inference.
Read the full abstract

Biomolecules

The physical foundation beneath protein generative modeling

Tianyu Lu and Po-Ssu Huang

Physical equations in protein modeling appear to have been replaced by generative models trained directly on structure data. By learning a mapping from noise to data, sampling de novo protein structures has become much more efficient. However, such models can also learn non-physical features and break down with out-of-distribution settings which are typical in protein design campaigns. In this review, we highlight where the physics persists in protein generative modeling pipelines and the issues that linger when physically relevant components of a macromolecular system are left unmodeled. We present a perspective that respecting the underlying physics of macromolecular systems, increasingly through learned representations that are physically grounded and updating generative models with experimental data, is foundational to generative modeling for functional protein design.
Read the full abstract

Neurons and Cognition

A Roadmap for MEG Foundation Models

Philipp Thölke, Hamza Abdelhedi, Yorguin Mantilla-Ramos et al. (+7 more)

Foundation models are beginning to reshape brain-signal analysis by moving the field beyond task-specific decoding pipelines toward reusable models pretrained on broad neural datasets. Magnetoencephalography (MEG) is a compelling but still underdeveloped target for this shift: it captures human cortical dynamics at millisecond resolution while offering stronger spatial interpretability than EEG, making it especially valuable for source-resolved studies of perception, language, cognition, and clinical brain function. Yet MEG foundation models remain at an early stage, with only a small number of MEG-specific and MEG-inclusive multi-modal models, modest pretraining corpora, and emerging but still limited benchmarks. This perspective lays down the basic concepts needed to understand MEG foundation models and provides a didactic overview of the field's key design choices, including tokenization, sensor- versus source-space representations, sensor-geometry encoding, backbone architectures, self-supervised objectives, and pretraining data. We then offer a roadmap for future development, organized around native MEG pretraining, adaptation of EEG foundation models, transfer from generic time-series models, and multi-modal integration with EEG, fMRI, MRI, behaviour, and stimulus features. We highlight the need for coordinated infrastructure, including diverse and reusable MEG datasets, rigorous evaluation across subjects, sites, tasks, and clinical settings, and responsible data-sharing practices that address consent, privacy, access, and governance.
Read the full abstract

All authors Philipp Thölke, Hamza Abdelhedi, Yorguin Mantilla-Ramos, Fouad Lbakali, Oumayma Gharbi, Catherine Duclos, Annalisa Pascarella, Vanessa Hadid, Oiwi Parker Jones, Karim Jerbi

Biomolecules

Advancing Alzheimer's Disease Treatment: Synergistic Ligand Combinations Targeting BACE1 via Multi-Ligand Simultaneous Docking

Pronama Biswas, Surya Shanbhog, Merla Sudha et al. (+1 more)

Alzheimer's disease is a progressive neurodegenerative disorder characterized by memory loss, cognitive decline, and behavioral changes, primarily affecting the elderly. Current treatments focus on symptom management as no therapies effectively halt or reverse disease progression. Newer therapies targeting BACE1, a key enzyme in amyloid plaque formation, have shown promise in clinical trials, though they have been limited by side effects and insufficient efficacy in slowing cognitive decline. This is the first study where multi-ligand simultaneous docking (MLSD) was employed to identify potential synergistic inhibitor combinations from among thousands of small molecules that could yield better results than the current phase-III inhibitors of BACE1. The recent phase III drugs such as Atabecestat, Elenbecestat, Lanabecestat, and Verubecestat were considered to be standards for comparison in this study. A library of small molecules with known IC50 values against BACE1 was filtered for flagging Pan-Assay Interference (PAINS) and "Brenk" compounds. Single-ligand docking revealed individual ligand interactions with the protein, forming the basis for creating ligand pairs tested in MLSD. Among these combinations, CHEMBL4078427 and CHEMBL3656158, CHEMBL4078427 and CHEMBL3695732, Verubecestat and CHEMBL3656158, and CHEMBL4078427 and Lanabecestat demonstrated excellent binding affinity of -19.90 kcal/mol, -18.45 kcal/mol, -18.07 kcal/mol, and -17.67 kcal/mol with the protein, which is significantly greater than those of phase-III inhibitors, along with inter-ligand interactions indicative of a synergistic effect. These findings underscore the transformative potential of MLSD in identifying synergistic compound interactions, paving the way for novel combination therapies in the treatment of Alzheimer's disease.
Read the full abstract

All authors Pronama Biswas, Surya Shanbhog, Merla Sudha, Belaguppa Manjunath Ashwin Desai

Quantitative Methods

Towards AI-Driven Nanomedicine Discovery: A Benchmark and Multimodal Learning Framework for Nano Self-Assembly Prediction

Quan Hao, Mengyue Fan, Zifan Dong et al. (+9 more)

Nano self-assembly organizes molecular components into bioactive nanoscale structures. Self-assembled nanoparticles (NAPs) derived from Chinese herbal formulas and applications such as anti-lung-cancer therapy demonstrate the substantial potential of self-assembly for nanomedicine discovery. Yet discovery still relies on costly wet-lab screening, while existing machine learning approaches lack standardized tasks, effective pairwise compatibility modeling, and public benchmarks with unified evaluation. To address these limitations, we formalize NSA prediction as a binary classification task for predicting self-assembly between molecular pairs and then establish NSA-Bench, the first public benchmark with curated molecular combinations, experimental conditions, self-assembly labels, and standardized evaluation protocols. We further develop NSA-Net, an interaction-aware multimodal framework that integrates complementary molecular evidence from graph topology, sequence semantics, and physicochemical descriptors to learn molecular-pair representations for self-assembly prediction. Extensive experiments on NSA-Bench show that NSA-Net achieves a ROC-AUC of $0.9470\pm0.0112$ (Small) and $0.9492\pm0.0062$ (Large). On the Small track, it surpasses the strongest machine-learning and graph-based baselines by 3.9 and 17.1 percentage points, respectively. Representation analyses reveal interpretable molecular characteristics associated with self-assembly prediction captured by the learned representations. Moreover, an NSA-Agent case study further demonstrates how NSA-Net predictions can support formulation refinement through experimental-condition-aware reasoning. Our code is available at https://github.com/developer-hq/NSA-Net.
Read the full abstract

All authors Quan Hao, Mengyue Fan, Zifan Dong, Jianduo Zhao, Changhao Xiao, Shangqing Jiao, Hao Zhang, Yudong Wang, Fei Xia, Jigang Wang, Liguo Zhang, Chong Qiu

Neurons and Cognition

Axonal delay dispersion decides whether a neuron detects an event or a sequence, and predicts cortical column diameter

Cheng Bi and Jipeng Sun

Cortical neurons fire sparsely – often fewer than one spike per sensory window – making rate coding insufficient and temporal coding a necessity. That conduction delays convert firing order into synchrony is long established. What governs which class of temporal feature a neuron detects – one volley of coincident input, or two in a particular order – has not been examined. We propose a delay-signature framework in which the axonal conduction delays converging on a dendritic branch constitute a physical key: only input sequences whose spike-time differences the delays compensate arrive synchronously, and coincidence detection, via calcium plateau thresholds, converts that synchrony into an all-or-none output. In simulations of an integrator-neuron model we report three results. First, a single physical scalar – the dispersion of the delay set – moves a population from event detection to order-selective sequence detection. The transition is emergent under random delays and connectivity: at narrow dispersion sequence detectors do not exist, and the dispersion at which they overtake event detectors tracks the inter-event interval with a slope statistically indistinguishable from one. This maps a computational distinction onto the anatomical one between myelinated and unmyelinated projections, making myelination a switch on what a neuron computes, not only a regulator of speed. Second, the same dispersion sets the code's limits: it bounds the longest codable interval and fixes an absolute timing tolerance of about a millisecond, with slowing better tolerated than speeding. Third, that millisecond window and horizontal conduction velocity together predict cortical column diameter, and the two areas with direct measurements fall where the relation puts them. One anatomically measurable parameter thus sets what a neuron detects and the limits of what it can represent.
Read the full abstract

Neurons and Cognition · Cross-listed from cs.LG

Prospective Coding Improves Learning in Deep Continuous-Time Recurrent Networks

Shivang Rawat, Mirko Morello, Flaviano Morone et al. (+1 more)

Temporal integration gives continuous-time recurrent networks memory, but in deep stacks it also delays bottom-up signals and attenuates top-down errors. We develop Recursive Quadrature Filters (RQFs), biologically motivated complex-valued temporal filters that are a special case of diagonal state-space models (SSMs), and ask whether this failure mode can be addressed by making each layer's bottom-up input prospective. Starting from an energy model, we derive the RQF dynamics and show that each RQF is a band-pass filter whose learnable parameters control its tuning frequency and bandwidth. We then make each layer's bottom-up input prospective using a parameter-free two-tap update that leaves the recurrent transition and parallel scan unchanged. We extend this correction to general diagonal SSMs and show that it mitigates depth-dependent gradient attenuation when temporal gradients are truncated, i.e., spatial-only backpropagation. We evaluate the intervention in RQFs, S5, and ORGaNICs (a nonlinear gated RNN) trained using full backpropagation through time (BPTT) and spatial-only backpropagation. Under full BPTT, prospective variants match or outperform their non-prospective controls in every model and configuration. A non-residual width-32 six-layer RQF reaches 96.09% accuracy on raw-audio Speech Commands with 31.9k parameters; a width-64 six-layer RQF reaches 83.56% on the 16,384-step Path-X task. These results identify RQFs as a parameter-efficient recurrent substrate and prospective-input coding as an input-side correction for deep continuous-time recurrent networks.
Read the full abstract

All authors Shivang Rawat, Mirko Morello, Flaviano Morone, David J. Heeger

Neurons and Cognition

High-Order Triadic Functional Connectivity in the Brain and Beyond

Qiang Li, Masoud Seraji, Yu-Ping Wang et al. (+2 more)

Here, we report high-order functional network connectivity as a promising way for studying the brain connectome. Traditional functional connectivity approaches capture only pairwise relationships between brain regions, overlooking complex multivariate dependencies that underlie cognition and behavior. First, we demonstrated that high-order interactions capture more information and can distinguish between resting-state and task-state brain activity. Second, we introduce a matrix-based entropy-functional method for estimating triadic interactions, which are statistical dependencies among triplets of brain regions, and apply it to large-scale functional brain networks. The resulting triadic networks revealed distinct community patterns that complement those observed in traditional pairwise functional connectivity analyses and simultaneously capture additional connection information. Despite the potential combinatorial explosion of triadic configurations, the networks exhibited constrained and hierarchical structures that allowed computation and interpretation. These findings position triadic connectivity as a promising next-step functional connectivity framework for probing brain network organization and high-order neural interactions, while also highlighting key biological and technical challenges that require careful consideration.
Read the full abstract

All authors Qiang Li, Masoud Seraji, Yu-Ping Wang, Godfrey D Pearlson, Vince D Calhoun

Neurons and Cognition · Cross-listed from cs.AI

Inferring Affective Consciousness in an Artificial Agent: A Case Study

Mark Solms, St John Grimbly, Bruce Bassett et al. (+7 more)

Creatures that display 'hedonic place preference behaviour' are thought by many scientists to experience feelings, on the assumption that their attraction to pleasure-producing substances which lack nutritional value (e.g. cocaine, morphine) cannot easily be attributed to unconscious instinctual behaviour. In this paper, we discuss how a simple artificial agent that instantiates attributes of an affective system engaging in felt uncertainty about its intrinsic needs in relation to environmental resources can similarly display hedonic place preference behaviour – through an apparently subjective form of information processing – while simultaneously being entirely deter-ministic. We outline some implications of this artificially engineered behaviour for our understanding of the physical basis of consciousness and the experience of free will.
Read the full abstract

All authors Mark Solms, St John Grimbly, Bruce Bassett, Evert Boonstra, Rowan Hodson, Nicolas Kuske, Kival Mahadew, Benjamin Rosman, Charel van Hoof, Jonathan Shock

Cell Behavior

Modeling Tissue Detachment and Rupture Using an Extended Vertex Model with T2-inverse Transitions

Shota Nishimoto and Yuichi Togashi

The vertex model is widely used to describe the mechanics of epithelial tissues, but its conventional formulation assumes that all cells remain tightly packed and always share edges with their neighbors, making it difficult to represent local detachment or gap formation. Here, we propose a minimal extension of the vertex model that enables cell detachment by introducing a new topological transformation, T2-inverse, which acts as the inverse of the classical T2 transition. When the imbalance of forces acting on a vertex, quantified by a tension metric $T$, exceeds a threshold, the T2-inverse splits the vertex into multiple vertices and creates a closed polygon that is incorporated as a pseudo-cell. This operation allows the model to represent the emergence and propagation of local detachment events. Using this framework, we simulate the stretching of a cell sheet and show that force-induced local detachments can accumulate to produce macroscopic tissue rupture. These results demonstrate that the proposed model extends the capability of the vertex model to describe tissue-level breakdown processes, including detachment and tearing, and provides a foundation for studying a broader class of epithelial mechanical phenomena.
Read the full abstract

Populations and Evolution · Cross-listed from cs.LG

Neural-Network Maxent: a general extension with learned nonlinearity, applied to time-series for Desert Locust distribution modelling

Alessandro Grassi, Edoardo Kimani Bellotto, Wassim El Azami et al. (+2 more)

Species Distribution Modelling (SDM) is essential for understanding how environmental conditions shape biodiversity, particularly for destructive pests such as the Desert Locust (Schistocerca gregaria), whose breeding dynamics are tightly coupled to rapidly evolving environmental conditions. Maxent has become the dominant method for presence-only data, but its reliance on a linear combination of hand chosen feature transforms limits its ability to capture the nonlinear, temporal relationships common in ecological monitoring, where covariates such as precipitation, soil moisture, and vegetation indices evolve meaningfully over time. Standard implementations flatten time-series covariates into independent features, discarding sequential structure that carries critical signal. We introduce RNN Maxent, an extension of the Maxent framework that replaces the fixed feature dictionary with a neural network, specifically a Gated Recurrent Unit (GRU), trained end to end via backpropagation. The approach preserves Maxent's presence only statistical foundations, background normalization, and probability calibration, differing only in that the nonlinearity is learned from data rather than fixed in advance. We apply RNN Maxent to map suitable habitat for the Desert Locust using 50 day environmental time series derived from ERA5 Land, MODIS, and Sentinel 3, maintaining a 7 day gap between covariates and presence records to yield forecasting behavior. Compared against standard Maxent, RNN Maxent improves performance across metrics (ROC AUC 0.862 std 0.036 vs. 0.792; F1 0.671 std 0.056 vs. 0.590).
Read the full abstract

All authors Alessandro Grassi, Edoardo Kimani Bellotto, Wassim El Azami, Sabrina Outmani, Maximilien Houel

Quantitative Methods

The Identification of Biological Stains at Crime Scenes: A Promising Role for Proteomics and Machine Learning

Anna Rosenberg, Stéphanie Laurent, Esther Morandeau et al. (+2 more)

Forensic body fluid identification is crucial for reconstructing crime scene events. While DNA analysis provides individualization, it lacks information about the fluid's origin. We developed and evaluated three complementary proteomic approaches using LC-HRMS/MS to identify blood, saliva, semen, urine, and vaginal fluid, including complex mixtures. The first method utilized fluid-specific peptide biomarkers, achieving high accuracy for pure fluids. The second employed peptide abundance ratios, demonstrating effectiveness in body fluid mixtures. The third, a machine learning model using Classifier Chain Random Forest, achieved 100% accuracy for pure fluids and promising results for mixtures. Our results revealed the complementarity of different tests, with the peptide-specific biomarker and machine-learning approaches being the most robust. This study demonstrates the potential of proteomics for comprehensive body fluid identification, offering valuable tools for forensic investigations.
Read the full abstract

All authors Anna Rosenberg, Stéphanie Laurent, Esther Morandeau, Alix Munoz, Joelle Vinh

Biomolecules

Structural control over equilibrium silicon and oxygen isotopic fractionation: A first-principles density-functional theory study

Merlin Méheut, Michele Lazzeri, Etienne Balan et al. (+1 more)

Isotopic fractionation factors for oxygen and silicon in selected silicates (quartz, enstatite, forsterite, lizardite, kaolinite) have been calculated using first-principles methods. Good agreement between theory and experiment is obtained in the case of oxygen. In the case of silicon, agreement and differences with existing estimates of equilibrium fractionation factors are discussed. The relationships between silicon fractionation factors and oxygen fractionation factors, silicate polymerization degree and chemical composition is studied. The previously stated relationship with the polymerization degree of the mineral is not confirmed. Nevertheless, our calculation suggests that silicon fractionation depends on the cationic content of the mineral, in a way similar to oxygen. Oxygen fractionation properties could thus provide some insights on silicon fractionation behavior.
Read the full abstract

All authors Merlin Méheut, Michele Lazzeri, Etienne Balan, Francesco Mauri

Biomolecules · Cross-listed from cs.LG

SimpleDesign: A Joint Model for Protein Sequence and Structure Codesign

Jiarui Lu, Yuyang Wang, Yizhe Zhang et al. (+4 more)

Proteins are fundamental to biological processes, with their function determined by the complex interplay between the amino acid sequence and the three-dimensional structure. Developing generative models capable of understanding this intrinsically multi-modal relationship is crucial for fields like drug discovery and protein engineering. Existing models often rely on a multi-stage training process where autoencoders that tokenize data into latent representations are trained in a first stage. Secondly, a generative model is trained on the latent representation of the autoencoder(s), i.e., generative modeling in a latent space. We hypothesize that this multi-stage training is not necessary to obtain performant co-design models and thus present SimpleDesign, an effective multi-modal protein design model trained directly in the data space. SimpleDesign leverages a single-stage end-to-end objective that combines discrete cross-entropy for sequences and a regression objective for structures. In order to effectively model the difference in sequence and structure modalities, we develop a Mixture-of-Transformer architecture that allows modality-specific processing while keeping global self-attention over both modalities. We train SimpleDesign on over 2M sequence-structure pairs achieving strong performance across co-design and unconditional sequence/structure generation benchmarks.
Read the full abstract

All authors Jiarui Lu, Yuyang Wang, Yizhe Zhang, Jiatao Gu, Navdeep Jaitly, Joshua M. Susskind, Miguel Ángel Bautista

Populations and Evolution · Cross-listed from physics.soc-ph

Large-Language Models as a Cognitive Virus

Ricard Solé, Giulio Ruffini, Francesca Castaldo et al. (+6 more)

Large-language models (LLMs) are rapidly becoming part of human culture, reshaping how information is produced, transmitted, and used. Here we propose that their diffusion can be understood through a viral analogy, with LLM use spreading through populations, becoming embedded in cognitive and cultural practices. We model transitions among uncoupled, coupled, and persistently dependent users, and show that the interplay between social transmission, recovery, and collective reinforcement can generate tipping points and technological lock-in. A central consequence is the possibility of runaway dynamics: once a critical threshold is crossed, small increases in adoption can trigger rapid population-level shifts toward persistent dependence, with abrupt losses in cognitive competence. The same framework, however, identifies conditions for cognitive immunization, based on reducing transmission and facilitating reversibility. Our results highlight how LLM adoption may involve nonlinear collective transitions with important consequences for cognitive autonomy.
Read the full abstract

All authors Ricard Solé, Giulio Ruffini, Francesca Castaldo, Marco Tuccio, Luis F. Seoane, Manlio de Domenico, Santiago F. Elena, David C. Krakauer, Michael Levin

Neurons and Cognition · Cross-listed from cs.CV

Tensor-based Brain Surface Modeling and Analysis

Moo K. Chung, Keith J. Worsley, Steve Robbins et al. (+1 more)

We present a unified computational approach to tensor-based morphometry in detecting the brain surface shape differences between two clinical groups based on magnetic resonance images. Our approach is novel in a sense that we combined surface modeling, surface data smoothing and statistical analysis in a coherent unified mathematical framework. The cerebral cortex has the topology of a 2D highly convoluted sheet. Between two different clinical groups, the local surface area and curvature of the cortex may differ. It is highly likely that such surface shape differences are not uniform over the whole cortex. By computing how such surface metrics differ, the regions of the most rapid structural differences can be localized. To increase the signal to noise ratio, diffusion smoothing based on the explicit estimation of Laplace-Beltrami operator has been developed and applied to the surface metrics. As an illustration, we demonstrate how this new tensor-based surface morphometry can be applied in localizing the cortical regions of the gray matter tissue growth and loss in the brain images longitudinally collected in the group of children.
Read the full abstract

All authors Moo K. Chung, Keith J. Worsley, Steve Robbins, Alan C. Evans

Wednesday 2 September

Biomolecules

Chemical and geometric representation fidelity improves drug–target affinity prediction

Yixiao Li, Yining Qian, Yefan Chen et al. (+5 more)

Predicting drug–target binding affinity (DTA) requires models to distinguish subtle chemical and structural determinants underlying molecular recognition. Although recent approaches increasingly incorporate richer drug and protein information, such information may be compressed, homogenized or discretized during representation construction, causing affinity-relevant distinctions to be lost before interaction modelling. We hypothesized that this representation-stage information loss constitutes an upstream bottleneck that cannot be reliably overcome by increasingly complex interaction predictors. To test this hypothesis, we developed ReGeoDTA, a representation-preserving framework that maintains affinity-relevant chemical heterogeneity in molecular representations and continuous geometric relationships in protein structures. Across three benchmark datasets, ReGeoDTA consistently improved affinity prediction, and the proposed representation-preserving strategies retained their benefits across diverse DTA architectures. Controlled representation degradation progressively reduced predictive performance, whereas increasing downstream predictor complexity failed to recover information lost during representation construction. These findings identify representation fidelity as an upstream design principle for accurate and generalizable drug–target affinity prediction, with potential implications for computational compound prioritization.
Read the full abstract

All authors Yixiao Li, Yining Qian, Yefan Chen, Zenghui Chen, Jiayue Sun, Yuhai Zhao, Cheng Tan, An-Yang Lu

Other Quantitative Biology

MarkerScout: A Disease-Agnostic Machine Learning Framework for Biomarker Prediction from Multi-Scale Mechanistic Models

Robert Moore, Frank Agayie-Ntim, Lindsey B. Crawford et al. (+5 more)

We demonstrate the framework on three infectious diseases derived from a companion mechanistic immune-simulation platform: SARS-CoV-2, Influenza A Virus, and Plasmodium falciparum. Each disease was evaluated across hospitalization and intensive care unit cohorts, yielding six cohorts in total. Best-pipeline cross-validated macro F1 ranged from 0.82 for IAV-HOSP to 0.99 for COV-ICU, and the framework produced tiered, direction-aware biomarker lists for each disease and phase. Interleukin-18 (IL-18) reached the strongest tier in both SARS-CoV-2 phases with consistent direction. When benchmarked against three separate, independently collected clinical ICU datasets, MarkerScout's top-ranked features outperformed 94.4% of randomly selected feature sets of equivalent size for SARS-CoV-2, with a weaker but directionally consistent advantage for Influenza A Virus (66.7%) and Plasmodium falciparum (60.7%).
Read the full abstract

All authors Robert Moore, Frank Agayie-Ntim, Lindsey B. Crawford, M. Jana Broadhurst, David M. Brett-Major, Prakash Packrisamy, Ahmed Abdeen Hamed, Tomas Helikar

Quantitative Methods

Self-Supervised Pretraining of Molecular Graph Encoders with LeJEPA

Michał Kulczykowski and Rafał Łabędzki

Self-supervised pretraining has transformed language and vision, but its value for molecular graph neural networks remains contested. We ask whether pretraining on a large unlabelled corpus improves molecular property prediction. We adapt LeJEPA, a predictor-free joint-embedding predictive architecture regularised by Sketched Isotropic Gaussian Regularisation (SIGReg), to molecular graphs, evaluating GPS and Chemprop-style D-MPNN encoders on the Wong et al. [1] antibiotic-activity dataset and ogbg-molhiv using a multi-seed, bootstrap-based protocol. Pretraining improves learned representations but does not robustly improve finetuning. A frozen probe on pretrained embeddings exceeds random initialisation on both tasks (ogbg-molhiv ROC-AUC 0.788 vs 0.665; +0.123), reaching the published self-supervised band, but this does not translate into finetuning gains. On the antibiotic scaffold split, a canonical partition is significant (delta AUPRC +0.041, p = 0.010), but the effect vanishes across five partitions (pooled +0.013, p = 0.095). Finetuning is null on the random split, ogbg-molhiv, and D-MPNN. The representational edge is nevertheless recoverable. Embeddings saturate at ~16-32 effective dimensions, whereas Morgan fingerprints improve to 1024 bits. At matched dimensionality, fingerprints lead validation (0.799 vs 0.782 at 128 dimensions) but trail shifted test scaffolds (0.759 vs 0.788). Truncating embeddings and combining them with a 1024-bit Morgan fingerprint raises ogbg-molhiv ROC-AUC from 0.805 to 0.832 (delta +0.027; 95% CI [+0.003, +0.054]; p = 0.014); an untrained encoder gains nothing (delta -0.003). Thus, pretraining supplies complementary information best realised through feature-level combination, while finetuning gains are weak and partition-dependent.
Read the full abstract

Cell Behavior

Coarse-Graining Agent-Based Models of Bacterial Infections

Wesley J. M. Ridgway and Raymond J. Spiteri

Agent-based models (ABMs) provide a natural framework for representing cell-level rules and spatial heterogeneity in bacterial infections, but their computational cost limits their use for macroscopic tissue-scale simulations and broad parameter exploration. We derive a deterministic coarse-grained description for a class of bacterial-infection ABMs in which immune cells and extracellular bacteria diffuse, immune cells ingest nearby bacteria, and intracellular bacterial loads evolve through prescribed birth and clearance processes. The first coarse-grained model is a semidiscrete reaction–diffusion system that retains a discrete internal state for each immune-cell bacterial load while representing cell and bacterial populations by continuum concentration fields. The key technical step is the derivation of state-dependent effective ingestion rates from the microscopic ABM parameters: these rates are obtained by solving an auxiliary diffusion problem around a single bacterium and computing the flux of immune cells into the interaction region. We then take a continuum limit in the internal state variable, yielding a state-structured reaction–diffusion system in which intracellular dynamics appear as advection and diffusion in state space. Numerical comparisons with ensemble-averaged ABM simulations show close agreement in biologically motivated parameter regimes. The resulting framework preserves the rule-based structure of the ABM while producing PDE models that are substantially more tractable for large-scale simulation and parameter studies.
Read the full abstract

Biomolecules

An Integrative Computational Approach to Predict Viral Epitopes by Targeting the MHC-TCR Complexation

Jaya Vasavi Pamidimukkala, Roshan Balaji, Nirav Pravinbhai Bhatt et al. (+1 more)

T-cell immunity acts as a major defense system against controlling viral infections in vertebrates. During viral entry, innate immune cells degrade the viral proteins (antigens) and present them on their surface via Major Histocompatibility (MHC) proteins. T-cell receptors (TCRs) recognize these antigens/peptides presented by MHC (pMHC), initiating a T-cell mediated immune response. Despite its significance, the mechanism by which pMHC-TCR binding triggers T-cell activation remains unclear. In this study, we employed an integrative computational approach combining Bioinformatics, Molecular Dynamics (MD) simulations, and Machine Learning (ML) to identify viral epitopes as potential vaccine candidates. We performed large-scale all-atom and coarse-grained MD simulations on MHC-peptide-TCR complexes embedded into dendritic and T-cells, for which experimental immunogenicity data is available. One hundred fifty such systems are simulated for 1 {\mu}s each to capture the conformational and dynamical changes that underlie T-cell activation. Our ML model (DynamiT), trained on simulation-derived structural and dynamical features extracted from 2500 time points, revealed key determinants responsible for T-cell activation with an accuracy of 73.3%. Notably, we have identified the bending of the TCR transmembrane region, major dynamic motions of the TCR{\alpha} constant region and the buried surface area at the pMHC and TCR interface as critical factors influencing immune response initiation. Our approach unravels the mechanism of T-cell mediated immune response and helps ML-guided screening of viral epitopes for vaccine development.
Read the full abstract

All authors Jaya Vasavi Pamidimukkala, Roshan Balaji, Nirav Pravinbhai Bhatt, Sanjib Senapati

Genomics

Enhancer-promoter proximity predicts transcriptional competence but not transcriptional output in the Drosophila brain

Olivier Messina, Loucif Remini, Christopher H. Bohrer et al. (+4 more)

How 3D genome architecture contributes to transcriptional specificity across neuronal cell types remains unclear. Here, we used multiplexed chromatin tracing to map chromatin architecture and cell identity at single-cell resolution in the adult Drosophila brain. We found that enhancer-promoter (E-P) proximity was increased in transcriptionally active compared with inactive neurons. Analysis of single traces revealed the existence of distinct proximal and distal E-P states, with active neurons enriched in the proximal state. However, this relationship broke down across active neuronal subtypes, where neither E-P proximity nor chromatin accessibility predicted transcriptional output. Thus, 3D genome organization distinguishes transcriptionally competent from inactive neuronal states without quantitatively specifying transcriptional output. Our findings support a model in which E-P proximity establishes a permissive structural state, while additional cell-type-specific regulatory mechanisms tune transcriptional output.
Read the full abstract

All authors Olivier Messina, Loucif Remini, Christopher H. Bohrer, Jean-Bernard Fiche, Jean-Charles Walter, Andrea Parmeggiani, Marcelo Nollmann

Biomolecules

Advances in Machine Learning for Directed Evolution: A Five-Year Retrospective

Bruce J. Wittmann

The last five-plus years have seen many protein engineering disciplines transformed by advances in machine learning (ML), but the same cannot be said for directed evolution. Reflecting on a previously co-authored perspective, I discuss why I believe this to be the case, arguing that a disconnect between the goals of machine-learning-assisted directed evolution (MLDE) researchers–"identify an optimal protein"–and the goals of directed evolution more broadly–"identify a sufficient protein given time and resource constraints"–is a principal culprit. As an example, I highlight how nearly all current MLDE methods neglect to account for the cost of DNA synthesis, resulting in strategies that have limited practical applicability regardless of the underlying models' capabilities. I close by discussing recent works that are exceptions to this overarching trend, and emphasize that the last five years of efforts in ML-assisted protein engineering and the prescribed reframe of MLDE objectives need not be mutually exclusive.
Read the full abstract

Quantitative Methods

Sparse concept attribution for histomorphological hypothesis generation from whole-slide classifiers

Tristan Lazard, Kenza Bouzid, Julius Hense et al. (+6 more)

Histology images contain rich morphological information and can provide insights into pathological processes. However, deriving hypotheses relating morphological phenotypes to clinical attributes is bottlenecked by a manual image interpretation step. Here, we demonstrate that this process can be automated through interpretable deep learning. We present SCOPE, a method to interpret slide-level classifiers by combining pathology-specific vision–language models with sparse concept attribution onto a generalist histomorphological concept bank. To measure whether such explanations recover known morphology, we introduce MorphoRecoveryBench, a benchmark of seven tasks with pathologist-curated reference descriptions. On this benchmark, dense concept attribution is indistinguishable from a random baseline, whereas sparse attribution recovers substantial known morphology; decomposing the pooled slide embedding reaches similar explanation correctness at a fraction of the computational cost. Post-hoc interpretation of whole-slide classifiers can thus generate morphological hypotheses at scale, for expert validation.
Read the full abstract

All authors Tristan Lazard, Kenza Bouzid, Julius Hense, Shruthi Bannur, Daniel Coelho de Castro, Daniel Shao, Rajesh Jena, Drew Williamson, Stephanie Hyland

Quantitative Methods

SurfSpec: Enhancing Off-Target-Agnostic Specificity by Bounding Pocket-Ligand Geometric Mismatch

Minyeong Hwang, Yoorim Gang, Ziseok Lee et al. (+5 more)

Lead optimization in structure-based drug design aims to improve target binding while avoiding unintended interactions with off-target pockets. However, existing affinity-driven methods do not explicitly control specificity, whereas current specificity-aware approaches commonly require prior knowledge of off-target structures. We address off-target-agnostic specificity-aware lead optimization by analyzing the geometric mismatch between a ligand and the target pocket. We provide a conservative specificity lower bound for geometrically separated off-targets without requiring access to off-target structures. By metricizing pocket–ligand mismatch, the triangle inequality shows that reducing target–ligand mismatch improves a conservative lower bound on mismatch to a separated off-target class, which can be translated into a specificity lower bound through an empirical geometry–affinity calibration. Motivated by this analysis, we introduce SurfSpec, an off-target-agnostic lead optimization framework that iteratively grows ligands toward under-occupied regions of the target pocket surface. SurfSpec alternates between linker generation toward selected target-surface patches, which provides geometric pseudo-labels, and refinement under a pocket-conditioned ligand prior, which restores these pseudo-labels into valid ligands. On the CrossDocked2020 test set, SurfSpec reduces geometric mismatch and outperforms evaluated off-target-agnostic lead optimization baselines in empirical specificity, while maintaining competitive target-affinity improvement.
Read the full abstract

All authors Minyeong Hwang, Yoorim Gang, Ziseok Lee, Wooyeol Lee, Young Bin Park, Jae-Mun Choi, Kyungsu Kim, Eunho Yang

Populations and Evolution

Architecture-dependent Effects of Trade-offs on Evolutionary Navigability and Epistasis

Nandita Chaturvedi

The structure of the genotype-phenotype map plays a central role in determining how populations move through fitness landscapes, yet less is known about how this structure interacts with environmental constraints and fitness trade-offs. Here, we study evolution on a tunable multilayer genotype-phenotype map in which binary genotypes are transformed through successive feed-forward layers before being evaluated by phenotype-level fitness functions. We explicitly model the phenotype to fitness transformation in order to compare an emergent trade-off fitness with a no-trade-off control. We explore different map architecture as models of more and less complex genotype-phenotype relationships by tuning the genotype length and number of layers. We find that ruggedness and navigability have a complex, architecture-dependent relationship. Landscapes with few local maxima can still have low navigability for wide and shallow maps, and navigability is high even at mean values of ruggedness for wide and deep maps. Trade-offs increase navigability in wide and shallow maps, while their effect is muted in other architectures. The effect of trade-offs on epistasis depends on evolutionary history. While trade-offs change which mutational neighborhoods are sampled by evolution, the background degree of epistatic interactions is set by map architecture. Finally, we use our framework to investigate micro-evolution of high-fitness populations and show that temporal covariance in allele-frequency changes can arise from the internal structure of a rugged genotype-phenotype map, producing signatures that resemble short-term alternating selection.
Read the full abstract

Neurons and Cognition · Cross-listed from cs.LG

A Common Measure of Communication for Speech Brain-Computer Interfaces

Dulhan Jayalath, Benjamin Ballyk and Oiwi Parker Jones

Speech brain-computer interfaces (speech BCIs) translate neural activity into language, offering a path towards restoring speech for people with paralysis and, more broadly, enabling new forms of natural human-computer interaction. Despite this promise, the field lacks a common measure of progress because systems use different datasets, recording methods, types of speech, and vocabularies, so their reported scores are rarely comparable. Underlying this measurement problem are two unresolved questions: (i) what distribution of words should a speech BCI enable a user to communicate, and (ii) how much information from this distribution can a system convey. We address both by deriving open-vocabulary mutual information (OVMI), an information-theoretic quantity that measures the information conveyed by a decoder relative to a reference distribution over the words a user may wish to communicate. This allows capabilities measured under different conditions, such as distinct vocabularies, to be evaluated on a common communication scale. We show that ordinarily reported accuracy, word error rate (WER), and other metrics computed only over the words a system supports can overstate how much of a user's intended speech the system can communicate. We then use OVMI to compare existing systems, expose trade-offs between how much of the user's language a system supports and how accurately it decodes those words, show that these comparisons depend on what the user is expected to communicate, and demonstrate that selecting a vocabulary to maximise OVMI yields up to 16.3% relative improvement in accuracy across three speech domains. OVMI therefore provides the speech BCI community with a principled way to compare heterogeneous systems, improve vocabulary design, and measure progress in the field.
Read the full abstract

Neurons and Cognition

Prediction emerges in RNNs trained for perception

Akanksha Gupta and Alejandro Tabas

The brain is highly proficient at making sense of noisy and ambiguous sensory inputs. Predictive processing hypothesises that this ability relies on prediction. However, it is unclear why the brain would have evolved to predict the sensory world, a computationally expensive process, in order to aid perception. Here we use simulations to argue that prediction naturally emerges in systems optimised for perception. We train recurrent neural networks (RNNs) to denoise a tokenised version of Bach's compositions at a range of noise levels. Afterwards, we enquire whether the states of the networks contain predictive information about the next token. We test this by freezing the RNN weights and training a linear readout from its states on prediction. We compare the performance of the linear readout with that of an independently trained linear benchmark model. The results show that the linear readout from the RNNs outperforms the benchmark model at moderate levels of noise, indicating that the networks rely on a predictive mechanism to support perception. We further show that the responses of the RNNs to sensory inputs are proportional to prediction error. Together, the results demonstrate that neural signatures of predictive processing emerge, without any further training constraints, from optimisation of perception.
Read the full abstract

Subcellular Processes · Cross-listed from physics.bio-ph

A viscoelastic theory for ultrasound-induced intracellular streaming

Niels Gieseler, Falko Ziebert and Ulrich S. Schwarz

Ultrasound is increasingly used to control biological cells, but its multiple physical effects, including radiation force, streaming, heating, and cavitation, require theoretical frameworks that can quantify their relative strengths. Here we develop a semi-analytical model to predict flow patterns and energy distributions of ultrasound-induced intracellular streaming. Cells are modeled as viscoelastic droplets immersed in a fluid with different viscoelastic properties. For this geometry, the momentum equation with an Oldroyd-B constitutive law is solved using a perturbation expansion commonly applied in acoustofluidics. The resulting equations for the different orders of the expansion are solved using partial wave expansion and explicit integration. We investigate our model for a range of parameters which is relevant both for synthetic polymer and for protein solutions. We find a series of flow reversals that we can connect to the distribution of energy into the different modes. We also consider density and compressibility contrasts, which shift these transitions and introduce new ones. Finally, we discuss the potential biological relevance of our mathematical results for cellular sensing and signaling.
Read the full abstract

Populations and Evolution

An adaptive time-tree transition kernel for Bayesian phylogenetic inference

Marius Brusselmans, Guy Baele, Samuel L. Hong et al. (+4 more)

Bayesian phylogenetic and phylodynamic analyses can be very time-consuming, owing to the combination of complex models that are used to estimate key parameters from increasingly large genomic data sets and their associated metadata. The use of high-performance computer hardware can – to a certain extent – alleviate the computational burden and markedly decrease the time to results. Still, even converging to the posterior can be a lengthy endeavour, with the burn-in aspect of such analyses potentially taking days or even weeks for large data sets. One of the key aspects that hampers performance in Bayesian phylogenetic inference is the efficiency with which tree topology proposals explore tree space. We here propose a novel adaptive tree transition kernel, which we call `subTreeLeap' (STL), which involves modifying the phylogeny by walking along patristic distance paths in the tree according to an adaptable radius parameter. STL is a general proposal, which can be used with contemporaneous or time-calibrated sequence data, being particularly suited to the latter due to respecting temporal precedence constraints. We carefully assess its impact on convergence and statistical mixing of the exploration of posterior tree space, by comparison to replicate “golden runs” obtained from lengthy analyses of empirical data under standard tree transition kernels. We find that STL successfully explores the same posterior tree space as standard kernels, but often does so in a more efficient manner. We discuss limitations as well as future potential improvements to STL that could substantially increase the speed at which Bayesian phylogenetic inferences are obtained.
Read the full abstract

All authors Marius Brusselmans, Guy Baele, Samuel L. Hong, Jiansi Gao, Marc A. Suchard, Andrew Rambaut, Luiz Max Carvalho