Quantitative Methods · Cross-listed from eess.IV
Beyond Discrimination: Evaluating Probability Calibration in Radiomics-Image Fusion for Renal Cell Carcinoma Classification
Yuan Liang, Morgan May, Abraham Campbell et al. (+3 more)
Reliable probability estimates are important for the clinical interpretation of machine-learning classifiers, yet radiomics–image fusion models for renal
cell carcinoma (RCC) are commonly evaluated primarily by discrimination. Using 396 patients from the KiTS23
dataset, we evaluated whether adding radiomics to four image-model families improved probabilistic performance in addition to discrimination. Seventeen individual models and four probability-average ensembles were assessed using discrimination, probability calibration, and proper scoring measures. Across 12 matched image-only versus fusion comparisons, AUC and AP improved in all 12, while Brier score and negative log likelihood (NLL) improved in 11 of 12 and expected calibration error (ECE) in eight of 12. The 3D MedVAE gated-fusion model achieved the strongest overall individual-model profile. Probability averaging across concatenation, cross-
attention, and gated fusion produced favourable point estimates across all five primary metrics relative to image-only models in all four families, although paired-bootstrap support was stronger for Brier score and NLL than for ECE. These findings show that radiomics–image fusion can improve probabilistic prediction quality beyond discrimination, while calibration behaviour varies across image architectures and fusion strategies. We show that our proposed probability-average ensemble models improve discrimination and calibration simultaneously across all architectures in the study.
Read the full abstract ▾
All authors Yuan Liang, Morgan May, Abraham Campbell, Sourav Bhattacharjee, Simon Caton, Pierpaolo Dondio
Neurons and Cognition · Cross-listed from cs.NE
DyssomniaNN: Multi-Scale Spiking Neural Modeling of Human Sleep Disorders and Perceived Restedness
Daniel Szelogowski
Clinical sleep medicine repeatedly documents profound divergences between objective sleep duration and subjective daytime impairment, notably exemplified by sleep state misperception in paradoxical insomnia and boundary instability in narcolepsy type 1. Here, we present DyssomniaNN: a multi-scale biophysical computational framework coupling Borbély's two-process regulation of sleep homeostasis and circadian drive with Saper's hypothalamic reciprocal flip-flop
circuit and a recurrent corticothalamic leaky integrate-and-fire spiking neural network. We formalize five clinical cohorts across an identical 72-hour photoperiod: healthy control, circadian rhythm sleep-wake disorder (delayed-phase), chronic insomnia, paradoxical insomnia, and narcolepsy type 1. The synthetic local field potential converges closely with empirical human electroencephalography spectra from the PhysioNet Sleep-EDF database across all canonical frequency bands (spectral mean absolute error of 0.33–0.35). Furthermore, we introduce the Well-Rested Index to quantify restorative efficacy. Simulations reveal that sleep duration fails to predict restorative recovery: paradoxical insomnia achieves normal total sleep time (21.15 h) yet yields low restoration (37.6%) from unsuppressed cortical beta-band intrusion, whereas hypocretin deficiency in narcolepsy produces severe nocturnal fragmentation (781 min of wake after sleep onset) and 35 sleep-onset rapid eye movement periods. DyssomniaNN provides an in silico platform for mechanistic sleep research and virtual neuropharmacology.
Read the full abstract ▾
Biomolecules · Cross-listed from cs.LG
Designing Protein Structures from Natural Language
Joseph Lee, Yanjing Li, Bo Qiang et al. (+7 more)
A central challenge in de novo
protein design is generating
proteins with desired structural and functional properties. Existing design models typically require a dedicated input representation for each property, limiting the design objectives they support. We develop Prompteina, the first all-atom structure generation model that supports new and broader design objectives specified in natural
language, analogous to text-to-image generation. To train Prompteina, we construct Prompteina-Data, a paired text–
protein structure
dataset of 1.8M structures and 50M+ captions describing global and residue-specific structural and functional properties. We adapt Proteina-Complexa, a pretrained structure generation model, through text-conditioned pretraining and finetuning that aligns residues with their corresponding text. Prompteina outperforms baselines on 15 of 18 structural properties and generates
proteins that more closely match descriptions of their intended functions. In binder design, it leads baselines on at least 13 of 20 targets and improves interface confidence by 14% over the strongest baseline. With iterative in silico feedback, Prompteina's gain over non-iterative generation is 57% larger than the next-best baseline on the hardest targets. Finally, we experimentally validate Prompteina designs against GM2A, a target with no reported de novo binders. We identify nine binders, with the strongest at an apparent $K_{\mathrm{D}}$ of 107 nM. These results establish natural
language as an effective and powerful conditioning interface for
protein structure generation.
Read the full abstract ▾
All authors Joseph Lee, Yanjing Li, Bo Qiang, Gregory Lau, Allyson Ettinger, Noah A. Smith, Rory Donovan-Maiye, David Baker, Hanna Hajishirzi, Pang Wei Koh
Quantitative Methods · Cross-listed from physics.optics
PhySeqNet: physics-informed fluorescent foci detection for BARseq spatial transcriptomics
Neha Goswami, John Hover, Renae Galluccio et al. (+4 more)
BARseq enables spatially resolved gene-expression profiling across intact tissue, but its sensitivity depends on accurate detection and decoding of dense fluorescent rolonies. Existing spot-calling approaches can be conservative where signals overlap, while supervised deep learning is limited by the lack of reliable manual ground truth in real tissue images. Here we present PhySeqNet, a physics-informed deep learning framework for annotation-free fluorescent foci detection in BARseq. PhySeqNet trains U-Net detectors entirely on semi-synthetic images generated from an instrument-matched optical model combined with real sample-free experimental noise, and is integrated into pyBARseq, a modular Python pipeline for BARseq analysis. PhySeqNet achieved high detection performance on held-out simulated data across wavelength bands. On real tissue images, where ground truth is unavailable, we evaluated detections by forward-model reconstruction: PhySeqNet with conservative barcode-aware non-maxima suppression (NMSB) achieved higher reconstruction fidelity (NCC and MS-SSIM) than the BarDensr single-shot
estimator, tuned classical spot detectors, and a pretrained deep-learning detector. In the analyzed
brain section, PhySeqNet with NMSB yielded a median of 51 counts per
cell versus 47 for BarDensr, with a similar number of genes detected per
cell. The recovered transcripts produced spatial expression patterns qualitatively consistent with Allen MERFISH reference data and preserved
cell-type composition after scANVI label transfer. These results show that physics-informed simulation can train practical, annotation-free detectors that improve BARseq sensitivity without disrupting downstream biological interpretation.
Read the full abstract ▾
All authors Neha Goswami, John Hover, Renae Galluccio, Yichen Wu, Huiqing Zhan, Xiaoyin Chen, Anthony M. Zador
Molecular Networks
Artificial Intelligence-Assisted Systems Biology Reconstruction of Diabetic Bone Marrow Dysfunction
Paolo Madeddu
This study aimed to reconstruct a regulatory network suitable for systems biology analysis of diabetic bone marrow. Three artificial intelligence large
language models independently analysed 18 Discovery and 43 Validation publications. Investigator guided integration produced a frozen network of 62 biological entities and 79 directed interactions. Open source software Gephi created a visual representation before and after main node removal. The plausibility of the reconstructed interactions was tested against independent curated knowledge resources, including the Kyoto Encyclopedia of Genes and Genomes, connectomeDB2025, Reactome, and Gene Ontology. Further analysis examined physiological correspondence, missing edge sensitivity, and graph constrained interrogation. Functional modules encompassed endothelial perivascular support, stem
cell retention and trafficking, neural circadian regulation, inflammatory myelopoiesis, metabolic stress, and epigenetic regulation. They intersected through shared effects on endothelial function and stem
cell behaviour. The endothelium was the principal connecting node. Computational removal of the endothelial node increased network fragmentation and diameter, while average directed path length remained essentially unchanged. External resources supported 60/79 interactions (75.9%); 19 remained unresolved, with none classified as contradictory. Complementary assessments supported biological plausibility and faithful interrogation of the reconstructed network. This investigator led dialogue with artificial intelligence provides a foundation for a systems level understanding of diabetic bone marrow dysfunction. The approach may facilitate the generation of testable hypotheses and the identification of mechanistic targets for coordinated restoration of disrupted niche interactions.
Read the full abstract ▾
Quantitative Methods
RetroTAC: Learning Route-Derived Synthetic Accessibility for PROTACs
Stefano Ribes, Jia Xin Zhu Zhu, Tingting Mo et al. (+4 more)
Proteolysis-targeting chimeras (PROTACs) enable targeted
protein degradation, expanding therapeutic opportunities beyond conventional inhibition. However, assembling their large, multifunctional structures creates synthetic challenges that hinder their discovery. Traditional synthetic-accessibility scores can overestimate this difficulty by penalizing PROTACs' molecular complexity while overlooking modular assembly from accessible building blocks. In contrast, retrosynthesis planning tools provide explicit routes but are computationally expensive, particularly for large molecules. Here, we introduce a human-interpretable, PROTAC-oriented route-derived score that rewards short synthetic depth and balanced joining of molecular fragments, and RetroTAC, a machine-learning surrogate that predicts this score directly from molecular structures. RetroTAC combines complementary models in an ensemble, achieving a root mean squared error of 0.13 and an $R^2$ of 0.65 on held-out molecules. We further evaluate its utility on PROTACs enumerated by recombining warheads, linkers, and E3-ligase ligands, followed by retrosynthetic planning and route analysis. Candidates selected for high predicted scores achieve a mean route-derived synthesizability of 0.73, compared with 0.31 for low-score candidates; 98.75% versus 51.00% are fully resolved under the tested search settings. These results support RetroTAC as a fast prioritization tool for virtual PROTAC libraries, connecting molecular screening with interpretable route characteristics while reserving explicit planning for selected candidates.
Read the full abstract ▾
All authors Stefano Ribes, Jia Xin Zhu Zhu, Tingting Mo, Lukáš Hudec, Kostas Papadopoulos, Atanas Patronov, Rocío Mercado
Populations and Evolution
Leaky protection reveals three patterns in the relative advantages of vaccination strategies across transmission intensity
Yiwen Xing, Jianyi Zhang, Haoliang Cui et al. (+5 more)
Targeted vaccination often prioritizes individuals who contribute most to transmission. However, this rationale may change under leaky protection, whereby vaccination reduces susceptibility at each exposure rather than fully preventing infection. Here, we use a survey-derived individual-level exposure framework for 2,279 residents to simulate infection dynamics across ranges of transmission intensity and vaccine efficacy. We compare two vaccination strategies: the high-exposure strategy (prioritizing highly exposed individuals) and the oldest-first strategy (prioritizing older individuals). As transmission intensity changes, we identify three patterns in the relative advantages of these two strategies. At low transmission, the high-exposure strategy outperforms the oldest-first strategy in reducing both epidemic peak size and final infection proportion. At intermediate transmission, it lowers epidemic peak size but increases final infection proportion, revealing a trade-off between these metrics. At high transmission, differences between the strategies narrow, and the oldest-first strategy has a slight advantage for both metrics. Overall, our findings highlight the importance of considering vaccine failure mode when evaluating vaccination policies under different transmission dynamics.
Read the full abstract ▾
All authors Yiwen Xing, Jianyi Zhang, Haoliang Cui, Zijie Yang, Qianning Wang, Lang Qin, Zheqi Wang, Zhongwei Jia
Neurons and Cognition
EEG Entrainment to Non-Speech Rhythmic Patterns Associated with Dimensions of Language Performance
Francisco J. Martínez-Murcia, Nicolás J. Gallego-Molina, Marco A. Formoso et al. (+1 more)
Developmental dyslexia (DLX) affects 5-12% of the global population and impairs learning to read. Its biological basis, particularly the difficulties observed in oral phonological tasks, remains debated. Entrainment, the coupling of
brain oscillations to
speech rhythms, is essential for encoding phonological representations. We investigated whether
brain entrainment to non-
speech rhythms could predict DLX in 48 participants listening to white noise amplitude-modulated at rates matching Spanish
speech units. Phase-amplitude coupling (PAC) analysis of electroencephalography (
EEG) signals yielded accurate DLX prediction for the 40 Hz stimulus using the Heights Ratio PAC measure (balanced accuracy 0.929, p = 0.0069, in the best case), indicating a stronger phonemic entrainment deficit in dyslexic individuals. Regression analysis in control (CTL) participants showed a strong dependence between reading performance scores and greater entrainment in
language-associated
brain regions. In particular, participants with poorer phonemic awareness, reading comprehension, or rapid automatized naming showed greater right-hemisphere entrainment to the 40 Hz stimulus. This finding adds evidence for the hemispheric compensatory mechanisms hypothesized in the literature. In conclusion, our methodology identifies dyslexia-specific entrainment patterns near
language-associated
brain regions, together with compensatory entrainment in right-hemisphere areas.
Read the full abstract ▾
All authors Francisco J. Martínez-Murcia, Nicolás J. Gallego-Molina, Marco A. Formoso, Andrés Ortiz
Neurons and Cognition
Beyond Anxiety and Avoidance: A Dynamic Feedback-Regulation Framework for Adult Romantic Attachment
Mateusz Pomianek
Adult attachment is commonly represented by attachment anxiety and avoidance, but these person-level dimensions do not by themselves specify how momentary relational conditions are perceived, compared with desired conditions, translated into action, and updated after interpersonal feedback. We present the Attachment Regulation and Control (ARC) framework as an integrative feedback-regulation account that makes these temporal assumptions explicit and empirically testable. In ARC, control refers to feedback-based regulation toward relational goals in the control-theoretic sense, not interpersonal dominance, coercion, or a generalized need for control. ARC does not claim a novel control-system architecture. Instead, it synthesizes established control-theoretic attachment ideas, secure-base representations, perceived partner responsiveness, relational discrepancy, dyadic regulation, and recovery into a parsimonious sequence for adult romantic relationships: perceived relational state, desired relational state, discrepancy, regulatory action, partner feedback, state updating, and recovery. The framework treats the discrepancy score itself as a falsifiable modeling restriction by comparing it with perceived-state-only, unconstrained perceived-plus-desired-state, and asymmetric discrepancy alternatives. Attachment anxiety and avoidance form core regulation moderators. Secure-base representation is a candidate requiring incremental prediction of recovery outcomes. Mentalized affectivity and regulation flexibility remain optional moderators, while adult disorganization is an independent extension outcome.
Read the full abstract ▾
Biomolecules · Cross-listed from cs.LG
MORAD: Reinforcement Learning with Multi-Objective Rewards for RNA Inverse Design
Jixin Tang, Ji Guo and Jun Zhao
We introduce MORAD, an online reinforcement learning framework for backbone-conditioned RNA
diffusion models that trains a single shared policy across diverse target backbones. Structure-conditioned RNA inverse design seeks nucleotide sequences compatible with a target three-dimensional backbone, yet existing reinforcement learning approaches either optimize a separate policy for each target backbone or rely on offline preference optimization, leaving online post-training of a reusable backbone-conditioned model largely unexplored. MORAD combines backbone-conditioned group sampling, group-relative reward normalization, and a forward-process
diffusion objective. Beyond existing RL rewards that primarily target tertiary structural quality, MORAD jointly optimizes six measurements spanning tertiary geometry, base pairing, ensemble behavior, and sequence composition. To aggregate these heterogeneous objectives despite differences in scale and optimization direction, MORAD maps each measurement to a bounded desirability score and combines them with a weighted
geometric mean. Compared with a tertiary-structure-only reward, this multi-objective formulation improves 10 of the 11 evaluation metrics that have a preferred direction. Applied to pretrained RIDE, MORAD improves GDT-TS by 16.0% (from 0.3300 to 0.3827) and pairing MCC by 19.4% (from 0.6110 to 0.7295), while reducing normalized ensemble defect by 27.5% (from 0.3906 to 0.2830). On the test set, MORAD outperforms RiboDiffusion, gRNAde, and RDesign across tertiary structural accuracy, secondary-structure pairing, and thermodynamic quality, establishing a new state of the art in structure-conditioned RNA inverse design.
Read the full abstract ▾
Neurons and Cognition
Excitability across scales: a unifying EI model
Thomas S.J. Burger and Rodolphe Sepulchre
Neuronal excitability is commonly modeled using different principles at the cellular and population scales, making it difficult to study how microscopic mechanisms shape macroscopic activity. We introduce a spatiotemporal excitatory-inhibitory (EI) model that unifies these scales through a common mixed-feedback architecture. The model retains the conductance-based
circuit structure of Hodgkin-Huxley models and describes intrinsic and synaptic currents through memductances whose temporal and spatial voltage dependence encodes dynamics at the relevant scale. In its minimal form, temporal excitability arises from fast excitatory feedback opposed by slower inhibitory feedback, while spatial excitability arises from short-range excitation opposed by longer-range inhibition, recovering the core lateral-inhibition motif of Amari neural fields. We show that combining these mechanisms gives rise to population excitability in strongly heterogeneous populations. In particular, the model generates population spikes that are localized in both space and time and possess population-level scales distinct from those of individual neuronal spikes, despite substantial
cell-to-
cell parameter variability. We then show that both intrinsic temporal excitability and spatial synaptic feedback are required for coherent mean-field events and robust spatiotemporal population rhythms. Finally, selective modulation of memductances in a subset of the population tunes the frequency of the population rhythm, illustrating how changes at the cellular scale can shape macroscopic dynamics. By separating
circuit architecture from modeling scale, the proposed framework provides a physically interpretable approach to analyzing and designing neuronal excitability across scales.
Read the full abstract ▾
Quantitative Methods · Cross-listed from cs.LG
Tensor-based Fusion of Multi-modal Data for Predicting Cancer Risk Levels
Ali Anaissi, Yuanzhe Jia, Qishun Peng et al. (+3 more)
Cancer diagnosis and treatment increasingly rely on multi-modal diagnostic technologies that generate high-dimensional
datasets. Although these
datasets are rich in pathological information, they pose considerable challenges in interpretation, dimensionality reduction, and clinical applicability. Conventional machine learning approaches often fail to extract meaningful cross-modal features, thereby limiting predictive accuracy in patient risk stratification. To address these limitations, this paper proposes an unsupervised machine learning framework that integrates feature extraction, tensor decomposition, and clustering to improve cancer risk prediction. The framework employs tensor decomposition to fuse heterogeneous genomic and clinical data, enabling the extraction of latent, biologically meaningful features that outperform unimodal feature sets. Multiple feature extraction strategies are investigated, and the resulting features are subsequently clustered using a range of clustering
algorithms. Comparative evaluations based on internal and external metrics are then used to identify the most effective configurations. The framework is validated on LinkedOmics data comprising 11,158 patients across 32 cancer types. For patient risk stratification, clinically relevant attributes such as tumor purity, pathological stage, and survival outcomes serve as ground-truth indicators. Experimental results demonstrate the superiority of tSVD+GMM, which consistently outperforms other configurations across clinical
benchmarks.
Read the full abstract ▾
All authors Ali Anaissi, Yuanzhe Jia, Qishun Peng, Weidong Huang, Ali Braytee, Junaid Akram
Genomics · Cross-listed from cs.LG
Double-Take: Improving Capacity, Binding, and Selectivity In Long-Context Within Bidirectional Memory
Vakul Raghavan, Utkarsh Grover, Mingyang Mao et al. (+2 more)
Processing a long sequence does not guarantee that distant information remains usable. As context grows, a fixed-size
memory must retain many associations, connect information across positions, and preserve relevant structure without being overwhelmed by everything it observes. These are distinct requirements: a
memory may store more information without representing the relationships needed for
retrieval, and it may transport those relationships without preserving the ones that matter. Thus, the challenge is not simply extending context length, but constructing a
memory that remains usable as context grows. We study this problem in large-chunk test-time training (TTT) and identify two basic failures: single-step writes accumulate interference, limiting capacity, while self-associative writes cannot form cross-position bindings. We introduce Double-Take (DT), which repairs these failures with multi-step unpinned updates and cross-position mixing, and adds bidirectional change-sensitive writes for selective retention. Capacity alone leaves end-to-end recall at the $0.10$ chance floor; adding binding raises it to $0.92$. Trained only on $32\,\mathrm{kb}$ genomic contexts, DT reaches $0.927$ AUROC at $131\,\mathrm{kb}$ and $0.856$ near $1\,\mathrm{Mb}$, while transferring zero-shot from human to mouse. Together, these results identify capacity, binding, and selectivity as three requirements for usable long-range
memory.
Read the full abstract ▾
All authors Vakul Raghavan, Utkarsh Grover, Mingyang Mao, Chengwen Wang, Xiaomin Lin
Neurons and Cognition
FlyHack: Stress-Testing Mechanistic Claims in a Connectome-Constrained Visual Model
Aashish Dhawan
Connectome-constrained neural networks make biological components directly accessible to intervention, but their mechanistic conclusions can still depend on the comparison model, intervention,
circuit representation and trained solution. We stress-test these dependencies in flyvis, a Drosophila motion-
vision model, using its 50-model ensemble, task-matched causal CNN controls and replicated interventions. At the level of model behaviour, three-level reverse-phi reversal in flyvis is strongly period- and velocity-dependent and also appears in task-matched CNNs; neither family reproduces the fly's stationary-sawtooth response.
Adversarial direction reversal requires a perturbation bound of 0.21–0.27 times stimulus contrast in flyvis versus 0.13–0.25 in CNNs, but the gap over a parameter-matched CNN largely closes for larger CNNs. At the level of mechanism, matching attribution to the intervention matters: for held-out-mean replacement, first-order edge attribution patching reaches pooled AUROC 0.970 and Spearman 0.872, versus 0.933 and 0.126 when its zero-aligned score is evaluated against the same ground truth.
Circuit conclusions also vary with representation and ensemble member. Greedy
cell-type sets meet a model-relative T4/T5 tuning criterion in 25 of 50 models, while T4/T5 output silencing reduces the tested optic-flow behaviour to at most two of eight clips in 40. In six models where the
cell-type search first succeeds, the corresponding connection sets can be pruned to 13–31 added classes; under an additional two-sided response-amplitude check, only two of those six first-success
cell-type sets still meet the tuning threshold. These results support a narrower use of connectome-constrained models: they make mechanistic hypotheses directly testable, but the resulting claims must be scoped to the model family, intervention, representation and trained solution.
Read the full abstract ▾
Biomolecules
TopoLIA: Topology-Inspired Latent Interaction Attention for Drug Discovery
Xiang Liu, Yiming Ren, Mustafa Hajij et al. (+2 more)
The growing sophistication of drug discovery calls for new advances in artificial intelligence (AI).
Transformers have underpinned recent breakthroughs in AI, yet their conventional source-target
attention mechanism can become a bottleneck for modeling complex interactions. Here, we introduce TopoLIA, a
topology-inspired latent interaction
attention mechanism that learns not only how much information should be exchanged between interaction partners, but also how that information should be transformed. Source-target-dependent
attention is mediated through a compact latent interaction space, providing a structured representation of complex interactions. We further incorporate topological spectral representations to capture multiscale data geometry and extract algebraic relationships. TopoLIA thus incorporates topological principles into both data representation and neural network architecture. We demonstrate TopoLIA on
protein-ligand binding, where persistent spectra encode multiscale topological and
geometric patterns in 3D
protein-ligand complexes, while latent interaction
attention (LIA) enables structured, source-target-dependent information exchange. We pretrain TopoLIA by reconstructing masked multiscale spectral
tokens from unlabeled molecular structures, yielding transferable structural representations without task-specific annotations. Across multiple scoring and docking
benchmarks, TopoLIA achieves state-of-the-art performance and consistently outperforms its standard-
attention counterpart. Rank analyses show that compact latent dimensions yield the best performance, supporting compact interaction spaces as an effective inductive bias for biomolecular learning. More broadly, LIA provides a general framework for structured, source-target-dependent information exchange that is applicable to diverse scientific and AI problems involving complex heterogeneous interactions.
Read the full abstract ▾
All authors Xiang Liu, Yiming Ren, Mustafa Hajij, Pietro Liò, Guo-Wei Wei