Papers

Scientific agents can move beyond automated model building by using accumulated evidence to revise both their questions and experimental strategies. The challenge is sustaining this adaptation across heterogeneous tasks without overfitting decisions to internal validation. Absorption, distribution, metabolism, excretion and toxicity (ADMET) prediction provides a demanding setting across diverse assays, datasets and chemical domains. We therefore developed ADMET-EvO, an evidence-gated agent that formalizes endpoints, generates falsifiable hypotheses and tests interventions across data, feature and model axes. It carries supported, rejected and inconclusive outcomes forward to guide each new cycle. Across the 22-task Therapeutics Data Commons (TDC) ADMET benchmark, ADMET-EvO achieved the highest task-normalized score of 96.77. Evidence-guided selection reduced cumulative fitting time by 72.2% within a predefined non-inferiority margin. It also formalized 43 toxicity-related tasks and constructed endpoint-specific predictors. Together, these results show how ADMET-EvO can accumulate evidence, revise its strategy and expand its research scope over time.

Stochastic switching between gene expression states, coupled with production and degradation dynamics, governs the accumulation of mRNA and proteins in cells. The concentrations of these accumulated entities dictate the phenotypic distribution of genetically identical cells. The underlying accumulation dynamics are well-captured by a two-state promoter switching model, with statistical and thermodynamic properties quantified via the Fano factor and entropy production rates. However, how these measures correlate with concentration distributions and their shifts under varying kinetic parameters remains largely unexplored. To this end, we use chemical master equations to study a generalized model of mRNA accumulation dynamics in the presence of stochastic switching between two activity states and state-dependent production and degradation rates. We derive exact expressions for the steady-state probability distribution and analytically compute the mean concentration, Fano factor, and entropy production rate (EPR). Simplifying these expressions, we identify contributions arising from stochastic switching rates and relaxation dynamics toward equilibrium in each activity state. Next, using our theoretical results, we characterize the variation in the Fano factor and EPR as a function of mean expression during modality changes of the distributions mediated by the variation of switching rates. We also identify the conditions in kinetic parameters that achieve the highest Fano factor and entropy production rates. Our findings establish a generalized framework for examining stochastic accumulation dynamics, clarifying how kinetic parameters dictate molecular distributions, noise, and dissipation. These insights extend readily to broader contexts coupling stochastic switching with accumulation, including protein burst dynamics, phenotype-switching-mediated drug intake, and queuing theory.

Proteolysis-targeting chimeras (PROTACs) have emerged as a transformative therapeutic strategy that selectively degrades historically ”undruggable” targets via the ubiquitin-proteasome system. Despite growing efforts to develop computational predictors of PROTAC degradation activity, existing supervised approaches remain severely challenged by data scarcity and imbalance across E3 ligases, limiting their ability to generalize beyond well-studied ligase contexts. In practice, labeled data are heavily concentrated on a few ligases (e.g., CRBN and VHL), while the majority of E3 ligases remain underexplored yet are critical for expanding the design space of targeted degraders. Developing methods that enable robust cross-ligase generalization with minimal labeled data is therefore essential for improving the practical utility of computational PROTAC discovery. We reformulate PROTAC degradation activity prediction across E3 ligases as a few-shot meta-learning problem and present ProMeta, a prototype-based graph neural network trained through episodic meta-learning on source-E3 tasks and evaluated on held-out target-E3 tasks through support-conditioned inference. ProMeta performs inference without updating the encoder by dynamically estimating class prototypes from minimal target-ligase support samples. On the CRBN-to-VHL benchmark, ProMeta achieves AUROC values of 0.796 under K=2, Q=3 and 0.883 under K=2, Q=5, improving by 19.9% and 6.8%, respectively, over the corresponding supervised GNN baseline. Reverse VHL-to-CRBN transfer under the same protocol yielded AUROC values of 0.702 (K=2, Q=3) and 0.821 (K=2, Q=5), confirming bidirectional applicability while revealing direction and data-regime dependence. Together, these results support ProMeta as a practical framework for cross-ligase few-shot prediction under the evaluated support/query protocols.

Manual counting and classification of bacterial colonies are critical yet labor-intensive tasks in microbiology, prone to human error particularly on densely populated plates. This work proposes a multi-task deep learning framework trained on the Annotated Germs for Automated Recognition (AGAR) dataset (18,000 images; 9,202 training / 3,067 testing) to automate Colony Forming Unit (CFU) enumeration and species classification. A custom multi-task CNN employing global regression served as the baseline, but demonstrated limited performance in clustered colony environments due to the absence of spatial localization. To address this, a YOLOv8 object detection architecture was adopted with high-resolution 1024x1024 inputs, enabling instance-level colony detection and label assignment. The model achieved a classification accuracy of 98.13% and a counting accuracy of 98.27% (within a 10-colony margin), demonstrating strong predictive capability. To bridge the gap between model performance and practical deployability, the trained model was optimized through unstructured and structured pruning, ONNX conversion, and reduced-precision inference (FP32, FP16, INT8). On a Raspberry Pi 4B, ONNX FP32 and FP16 variants offered the best balance between inference speed (~6.4s) and accuracy (MAE ~2.20). Unstructured pruning preserved predictive accuracy (MAE ~2.01) without runtime gains, while structured pruning resulted in significant accuracy degradation (MAE ~6.3), revealing the sensitivity of instance-level colony detection to architectural compression. These findings provide practical guidance for selecting optimization strategies in resource-constrained laboratory deployments.

Source-level analysis of interictal epileptiform discharges (IEDs) is relevant to presurgical evaluation and treatment planning because it helps characterize where epileptiform activity is likely to arise. Beyond detecting whether an IED is present, this setting requires assigning IED-positive activity to clinically meaningful brain-region categories. This setting is challenging because source-region evidence in short electroencephalography (EEG) windows can be subtle, partial, and affected by subject variability, class imbalance, and imperfect multimodal context. We present EEGBind, an EEG-centric multimodal binding framework for five-class source-level IED classification. EEGBind treats EEG as the primary modality and binds synchronized video-context features around an EEG-centric representation. Instead of relying on early or overly strong multimodal fusion, which may perturb the source-sensitive EEG representation, EEGBind uses video context as auxiliary evidence for robust classification. A view-consistent repair stage is further used to improve hidden-set robustness while preserving the learned source-class boundary. On the NeuroMM 2026 Grand Challenge Track 3 NMM-Source-IED benchmark, EEGBind achieves 0.8395 on weighted-F1 and outperforms strong competitors. These results support EEG-centric multimodal binding as a practical strategy for source-level IED classification. The open-source code is available at https://github.com/HKUSTGZ-ML4Health-Lab/NeuroMM2026_IED_Detection.

Research on adaptive systems has traditionally focused on behavior (what organisms do) and mechanism (how their machinery works). This paper focuses on a third level, computation, which considers what adaptive systems must compute to survive and reproduce. It is proposed that adaptation has its own computational structure, comprising a small set of primitive operations common to all adaptive systems, regardless of their physical form. Six primitives, Arouse, Orient, Valence, Position, Boundary, and Attune, were selected using four criteria: necessity for existence, universality across independently evolved lineages, evolutionary conservation, and irreducibility. From this, two main implications follow. First, in biological systems, the primitives provide a substrate-neutral method for cross-species comparisons, reframing elaborative behaviors like attention, memory, and decision-making as combinations of these computations. Second, in artificial systems, the primitives offer a new way to view current challenges in machine intelligence, such as confabulation, prompt injection, distractibility, reward hacking, and catastrophic forgetting, suggesting that these issues may arise from a lack of these computations. Thus, for biological and artificial systems that persist, no specific physical substrate is necessary; rather, these primitives must be implemented if the systems are to be adaptive. What biology offers to inform machine intelligence, then, is not the brain's neural design but the computational functions it evolved to perform. The Computational Primitives Theory (CPT) presented here is a working hypothesis, intended for further refinement through discussion, empirical testing, and application.

Passive acoustic monitoring produces far more bat recordings than experts can label. We show that simple model-generated pseudo-labels turn this surplus into effective supervision. We compare pseudo-labeling with other semi-supervised learning methods on an 18-species European corpus using only 10% of its training labels, then transfer the strongest approaches to South African field audio containing nine bat taxa and a nuisance class. Pseudo-labeling outperforms the other semi-supervised learning methods on every European measure, recovering up to 61.5% of the gap to full supervision. It transfers to field audio with gains of 10.69 points in species accuracy and 4.96 points in species macro-F1. We also introduce genus-aware smoothing, which directs uncertain target mass toward congeneric species. Combined with uniform smoothing, it reaches 79.16 species macro-F1, 4.73 points above hard targets. Simple pseudo-labels are therefore highly effective at this ecological data scale, while genus-aware targets inject useful biological structure at no annotation cost. https://code4conservation.github.io/UnlabeledEchoes/

Exploration of planetary bodies within our solar system will be essential for understanding the origin of life on Earth and the distribution of life in the universe. Planetary protection policy is concerned with balancing this desire for exploration against the risks of contaminating alien planets with Earth life, and contaminating Earth with alien life. However, at present, we have no fundamental scientific understanding of life's emergence or its nature beyond Earth. Given this nearly complete ignorance about the possibility of alien life, or Earth life's capacity to expand beyond our planet, it is difficult to reason about the real risks of space exploration. Here we contend that contemporary understandings of the risks of forward contamination are based on arguments which inconsistently apply our incomplete knowledge to the problem. We reason that a more assertive posture towards space exploration, focused on determining whether other planets in the solar system are inhabited, is warranted and explain why such a posture may not increase the epistemic risks of planetary contamination. Finally, we explore the consequences of our arguments for planetary protection protocols, and life detection efforts.

How cultural repertoires maintain diversity under selection is a fundamental question in cultural evolution. We address this using thirteen years of weekly popularity data for approximately 20,000 Irish traditional tunes, fitting ecological birth-process models under neutral, frequency-dependent, and per-tune selection hypotheses. We find strong evidence that tunes differ in intrinsic fitness - some are systematically more likely to be learned than others. We find that 29% of the variance in fitness can be explained by a mixture of social and melodic features. Some tunes appear to be carried along via linkage due to the tradition of playing tunes in sets, analogous to selective sweeps in genetics. By measuring changes in fitness over time and comparing this with recordings we precisely identify the mechanism by which a long-dormant tune can become fit through a popular recording. Despite the directional selection, repertoire diversity increases, driven by the continual arrival of new compositions. These results demonstrate that selection and diversity can coexist in a cultural ecosystem, and establish Irish traditional music as a quantitatively tractable system for studying the evolution of cultural variants and understanding what makes a tune stand out.

Critical systems sit near boundaries between qualitatively distinct behaviors. When inferring models of neural activity, this proximity to criticality is thought to require the precise tuning of parameters. Here, we show that as the number of neurons increases, criticality can emerge naturally without fine-tuning. When computing observable statistics from parameters (the forward problem), some small regions in parameter space map to large regions in statistics space. These special parameters are precisely those near criticality. Thus, when inferring parameters from experimental measurements (the inverse problem), models concentrate near critical points, and this concentration becomes stronger as the system grows. We illustrate this flow toward criticality across many large-scale recordings in the mouse brain. In the Curie-Weiss model of Ising spins, we find that all of the recordings collapse to a first-order phase transition, despite substantial differences in the underlying systems. Together, these results suggest a resolution to the tension between criticality and fine-tuning in models of neural activity.

Brain-age prediction models are commonly evaluated by predictive accuracy, yet accurate predictions alone do not establish that a model relies on reproducible or neurobiologically supported mechanisms. Post-hoc explanation methods can expose these mechanisms, but existing workflows typically stop at diagnosis or require correction targets to be specified before model analysis. We propose XAI-Refine, an automated explanation-knowledge loop for brain-age prediction from resting-state functional connectivity. At each iteration, XAI-Refine consolidates complementary post-hoc analyses across repeated training runs into reliable, structured model explanations. It converts each reliable explanation into a neutral neurobiological question, retrieves and verifies relevant literature, and compiles the verified evidence into an admissible set in the same typed explanation space. The target for refinement is defined as the minimal projection of the current model explanation onto the admissible set induced by applicable verified knowledge. This revised explanation is then translated into a differentiable constraint while preserving the originating model variable, measurement operator, and applicable scope. Candidate updates are promoted only when multi-seed validation confirms target-directed explanatory movement, predictive performance remains within a prespecified guardrail, and non-target explanatory drift remains bounded. Experiments on functional-connectivity-based brain-age prediction evaluate predictive performance, explanation reliability, literature alignment, and target-specific model revision, illustrating a structured route from post-hoc analysis to evidence-guided model refinement.

Periodic impulsive interventions arise naturally in the management of biological populations, including chemotherapy, pesticide application, and infectious-disease treatment. We develop general conditions for permanence in n-species population models subject to periodic multiplicative pulse disturbances. Our main result provides a sufficient condition for permanence in terms of weighted long-term growth rates on a Morse decomposition of the extinction set, explicitly separating the contributions of continuous population dynamics from those of the periodic pulse. To establish this result, we transform the impulsive system into an associated autonomous continuous-time dynamical system and use this correspondence to extend classical permanence theory to periodically pulsed models. We further show that the same conditions imply robust permanence under sufficiently small perturbations to the continuous dynamics, pulse period, and pulse effects. We illustrate the framework with two Lotka-Volterra models motivated by biological control: competition between chemotherapy-sensitive and chemotherapy-resistant cancer cells, and integrated control of an agricultural pest using pesticides and parasitoids. These examples demonstrate how intervention frequency and intensity interact with underlying ecological interactions to determine whether populations coexist or are excluded. Our results provide a general framework for analyzing persistence in ecological systems subject to repeated discrete disturbances.

Biological tissues grow by continuously producing, transporting, and reorganizing multiple interacting constituents. These processes are intrinsically coupled to finite deformation and residual stress. Existing models typically capture either finite growth kinematics or multi-constituent transport, but rarely both within a thermodynamically consistent setting. In particular, existing approaches do not consistently link the volume created by finite growth to the mass produced for each individual constituent. In this work, we develop a general continuum framework that unifies finite growth kinematics and multiphase mixture theory for fully saturated multi-constituent mixtures containing an arbitrary number of dilute dissolved solutes. Formulated in a solid-skeleton-based description, the framework rests on constituent-wise balance laws and a free-energy dissipation principle, from which thermodynamically admissible constitutive closures are derived for all mass-exchange, transport, reaction, and growth processes. The central novelty of the framework is a coupling between growth-induced volume creation and constituent mass production, expressed through volume accumulation fractions that distribute the newly created volume among the constituents while preserving saturation. We cast the resulting model in a total Lagrangian mixed weak form and specialize the general theory to a four-constituent, two-solute model of avascular tumor growth that couples nutrient transport, waste production, phenotype transitions between proliferative, hypoxic, and necrotic cells, volume growth, elastic deformation, and growth-induced residual stress. The model is implemented within a finite element setting and its capabilities are demonstrated on representative benchmark problems.

We study feasible stable equilibria of Lotka-Volterra systems and their higher-order extensions. We complete the classification of impossible ecological interaction networks with at most four species and extend several of these impossibility results to families with arbitrarily many species. We then show that these sign-pattern obstructions are specific to the pairwise Lotka-Volterra model: arbitrary prescribed growth rates and pairwise coefficients can be supplemented by higher-order interactions so as to admit a feasible asymptotically stable equilibrium. Through the correspondence with replicator dynamics, we interpret feasible equilibria of higher-order Lotka-Volterra systems as totally mixed symmetric Nash equilibria of symmetric multiplayer games, derive bounds on their number, and study their robustness under perturbations of the payoff tensors. We conclude by showing that every impossible ecology determines a nonempty open class of symmetric two-player games with no totally mixed evolutionarily stable strategy.

We consider a minimal pressure-based model of heterogeneous cell populations consisting of proliferative and non-proliferative cells with different mobilities. The model is formulated as a system of reaction–cross–diffusion equations describing the spatio-temporal dynamics of the cell densities. The model is known to admit one-dimensional travelling wave solutions with strictly segregated components: non-proliferative cells occupy a finite region at the leading edge, while proliferative cells remain at the rear. However, the speed, parameter dependence, and stability of these waves remain poorly understood. In this work, we derive an almost explicit variational bound on the wave speed by reformulating the problem as a free-boundary problem for a generalised porous–Fisher equation. The estimates we obtain apply to general pressure laws and growth kinetics, agree closely with the results of numerical simulations, and become sharp in the incompressible limit, where we formally recover a fully explicit characterisation of the wave speed. We then analyse the stability of the waves to show that segregated waves are stable only when non-proliferative cells are more mobile than proliferative cells. Finally, motivated by numerical observations of finger-like protrusions, we investigate the stability of incompressible segregated circular waves through asymptotic shape-perturbation analysis. This yields explicit expressions for the pressure, interface velocity, and growth rates of angular modes, thereby making evident the destabilisation mechanisms that may lead to the emergence of fingering instability. Interestingly, we find that, in contrast with the one-dimensional case, the stability of such circular waves is not determined solely by the relative value of the mobility coefficients, and thus instabilities may arise irrespective of which cell type has the larger mobility.

One of the central challenges in evolutionary dynamics is understanding why some species combinations persist while others disappear. Although cyclic-interaction models have provided fundamental insights into biodiversity maintenance, much less is known about how hierarchical competitive interactions shape long-term community organization. Here, we investigate a hierarchical extension of the May-Leonard model, in which species interact through a directed predation chain while undergoing reproduction and mortality. Combining mean-field analysis with Monte Carlo simulations, we show that the fully coexisting state is generically unstable, causing the dynamics to evolve toward lower-dimensional coexistence states. The simulations further reveal stochastic extinctions dominating small populations with the dynamics progressively approaching the mean-field predictions as the system size increases. Rather than permitting arbitrary species combinations, the hierarchical-interaction structure dynamically constrains coexistence by selecting only specific subsets of species for long-term persistence. We show that these admissible coexistence states have a natural graph-theoretic interpretation as independent sets in the hierarchical interaction network, thereby providing general constraints on coexistence in hierarchical communities. Together, these results establish a theoretical framework linking hierarchical interactions, dynamical selection, graph topology, and biodiversity organization, extending the classical May-Leonard model beyond cyclic competition.

Hi-M combines fluorescence in situ hybridization (FISH), automated microfluidics, sequential imaging, and computational chromatin tracing to measure the three-dimensional organization of selected genomic regions in single cells. This chapter describes a Hi-M workflow adapted for cryosections of adult Drosophila melanogaster brains, enabling chromatin tracing while preserving tissue architecture and cell identity. The protocol covers Oligopaint library design and amplification, fixation, brain dissection, cryoprotection, cryosectioning, sequential RNA-FISH for cell-type identification, sequential DNA-FISH labeling, automated acquisition, and chromatin trace reconstruction. We also provide practical guidance for experimental design, sample preparation, tissue handling, image acquisition, and data analysis, highlighting critical steps that influence tissue integrity, hybridization efficiency, image registration, barcode detection, and chromatin trace reconstruction. The workflow is readily adaptable to different genomic loci and cell types, providing a robust approach for studying 3D genome organization in intact adult tissues.

Dimensional attention in learning is often implemented as a globally shared attention vector, where each stimulus dimension corresponds to a single scalar. These scalars are learned by models through gradient-descent on error, where predictive features acquire more salience. We show that under multi-outcome learning, where models predict more than one outcome, this shared vector becomes unstable; it collapses to its bounds and prevents the models from learning meaningful attentional tunings for learning and generalization. We address this by introducing an outcome-indexed attentional matrix that converts globally shared attentional tuning into an outcome-indexed representation. We present an analysis of the unstable shared vectors and derive the conditions under which it holds. Empirically, three synthetic experiments benchmark the proposed attention matrices and show that they converge to meaningful representations, something shared attention vectors fail to do. These results suggest that outcome-indexed attentional matrices are a general fix for gradient-based attentional processes, which improves models of learning under multi-outcome conditions.

Cancer remains a major global health concern due to chemotherapy resistance and toxicity from high-dose treatments. To overcome these challenges, new therapeutic strategies targeting key proteins in cancer progression are essential. This study evaluates two phytochemicals, Carpaine (Car) and Rutin (Rut), from Carica papaya leaves, for their potential in enhancing cancer therapy by targeting B-cell lymphoma 2 (BCL-2) and WW domain-containing protein 1 (WWP1) proteins. We assessed their additive, allosteric, and synergistic effects using molecular docking, multi-ligand simultaneous docking (MLSD), molecular dynamics (MD) simulations, and MMPBSA analysis. Car and Rut showed an additive effect on BCL-2 by binding at distinct regions within the same pocket. MLSD revealed an improved binding affinity of -13.13 +/- 0.08 kcal/mol, compared with individual ligands or the commercial inhibitor Venetoclax. For WWP1, Car bound near the H-site and Rut near the Le-site, exhibiting an allosteric effect that increased Car's binding affinity in MLSD to -15.59 +/- 0.39 kcal/mol. Furthermore, Rut combined with bortezomib (Bort) demonstrated a synergistic interaction with WWP1. Binding energies were -7.64 +/- 0.156 kcal/mol for Bort, -10.26 +/- 0.07 kcal/mol for Rut, and -15.59 +/- 0.39 kcal/mol for MLSD, suggesting a more stable complex through synergy. These results suggest Car and Rut, particularly in combination with Bort, as promising candidates against cancer-related proteins BCL-2 and WWP1. Further experimental validation is warranted to explore their therapeutic potential.

Electroencephalography (EEG) microstate analysis commonly converts each scalp topography into a winner-take-all hard label and summarises the resulting sequence using duration, occurrence, coverage, transitions, and symbolic complexity. Although interpretable, this readout discards evidence strength, assignment ambiguity, and low-confidence periods. We introduce a template evidence trajectory framework that retains, at each sampled Global Field Power (GFP) peak, the evidence for all templates or subject-specific topographic communities. Conventional hard labels are treated as a compressed readout of this multivariate trajectory. We derive two evidence-aware extensions of classical descriptors: high-evidence episode duration and episode rate, which quantify temporal clustering and fragmentation of strong state evidence, and null-state Lempel-Ziv complexity (LZC), which explicitly encodes insufficient-evidence periods. We evaluated the framework across four resting-state EEG datasets spanning Alzheimer's disease and age-related variation. Fixed-state models included K-means, AAHC, and HMMs at K = 4 and K = 7, together with adaptive subject-specific Leiden and Infomap communities. Across 32 dataset-model cases, trajectory-derived duration effects exceeded matched hard-label effects in all cases at the representative setting and in 30-32 cases across a broader parameter grid. Null-state LZC improved over traditional LZC in most cases, while classification showed modest but consistent gains for trajectory or combined features. Retaining template evidence therefore provides a more sensitive readout of EEG topographic state dynamics while remaining compatible with conventional microstate analysis.

Predicting protein dynamics is a long-standing problem in computational structural biology. Often, protein function critically depends on local directed motions, such as hinge movements, catalytic loop rearrangements and domain reorientations, which can be characterized by directional flexibility and correlated structural motions of the protein backbone. While Molecular Dynamics (MD) simulations provide an established but often prohibitively expensive approach, recent deep generative models aim to reduce this cost by directly predicting conformational ensembles, emulating MD. However, due to their large size and the need to generate several states until the derived dynamical properties converge, these models remain expensive. In this work, we propose BackFlip-2: a fast SE(3)-equivariant graph neural network trained to directly predict dynamical descriptors, such as directional backbone flexibility and pairwise dynamic correlations, from an equilibrium structure. In a series of experiments, we show that our model matches the accuracy of substantially larger ensemble generation models while being orders of magnitude faster, and demonstrate that the proposed equivariant architecture is especially well-suited for capturing anisotropic motions in proteins. BackFlip-2 model weights, training and inference code are available at https://github.com/graeter-group/backflip.

Molecular size is coupled to composition, structure, and function, yet most 3D molecular generators require a predefined atom count. We introduce Equivariant-Free Transformer-Autoencoded Latent Flow Matching, a two-stage framework that samples a fixed-dimensional latent vector using flow matching and uses an autoregressive Transformer to determine molecular size, atom types, coordinates, and chemical attributes. Canonical atom ordering and rigid-pose alignment enable Transformers without equivariant layers, while decoded attributes guide bond reconstruction. On PCQM4Mv2, unconditional generation yields 87.9% unique, novel molecules passing sanitization and PoseBusters checks, exceeding baselines with lower end-to-end training and sampling time and higher end-to-end throughput. Across ten target HOMO-LUMO gaps, internal ranking retains 30% of screened candidates and increases the density functional theory-verified hit rate within 0.1 eV from 25.0% to 52.4%, while largely preserving novelty and diversity. These results demonstrate fixed-dimensional latent generation with autoregressive decoding as a practical approach to molecular design without prespecifying size.

Understanding why individuals respond differently to psilocybin requires modeling the drug's transcriptional perturbation signature at the cell-type level. I present a Transformer-based delta expression encoder that learns to classify differential gene expression status - upregulated, downregulated, or neutral - from single-nucleus RNA-sequencing data, without supervision from pathway annotations or prior biological knowledge. The model is trained on pseudobulk profiles from 623 examples spanning 18 cell types, 2 drug conditions, and 6 timepoints derived from the Liao et al. 2025 dataset, and achieves 69.4% weighted classification accuracy. Three principal findings are reported, alongside one direct test of a published hypothesis that returned a result inconsistent with that hypothesis. First, per-cell-type classification accuracy ranges from 28.3% (L2/3 IT, a primary HTR2A-expressing psilocybin target) to 99.6% (endothelial cells), consistent with known psilocybin response biology. Second, psilocybin-induced transcriptional downregulation is significantly more stereotyped across individuals than upregulation (Mann-Whitney U=18615.0, p<0.0001), a novel finding with a cortical depth gradient across excitatory subtypes. Third, attention-guided gene co-regulation analysis recovers drug-specific modules without pathway supervision. Separately, a direct test of whether baseline HTR2A expression predicts drug-response separability across cell types found a significant negative correlation (Spearman r = -0.7088, p = 0.0021), the opposite of what a simple HTR2A-gating account would predict.

Protein-conditioned 3D molecule generation is a central challenge in structure-based drug design, requiring a balance between pocket compatibility, molecular properties, and physical geometry. We propose PocketVE, a protein-pocket-conditioned variance-exploding (VE) diffusion framework that couples stable coordinate denoising with inference-time property guidance. Specifically, PocketVE combines an EDM-style training and sampling setup for 3D denoising, classifier-free guidance for multi-property steering, and adaptive protein perturbation as a training-time pocket regularizer.On the CrossDocked2020 benchmark under GenBench3D, PocketVE improves Valid$_{3\text{D}}$ from 58.6 to 80.6 and reduces strain energy from 457.4 to 127.9 relative to its guided TAGMol architectural parent; relative to TargetDiff, it attains comparable Valid$_{3\text{D}}$ with lower strain energy (127.9 vs.\ 306.0), while retaining competitive docking and molecular-property scores under moderate guidance. A guidance-scale study shows that moderate guidance gives a favorable balance between target-related objectives and geometric quality, whereas stronger guidance can degrade geometry and distributional fidelity. Pocket-permutation and PoseCheck diagnostics further support pocket-specific spatial compatibility with reduced steric conflicts. Overall, the results suggest that geometric stability and inference-time property guidance should be considered as coupled design objectives.

Background: This study evaluated interreader agreement and longitudinal performance of MRI methods for knee cartilage volume, thickness, and defect-area quantification. Methods: AI-presegmented masks from 1,189 phase III examinations underwent independent correction by two readers and adjudication. Cartilage volume, three-dimensional ray-tracing thickness (3D-RT), and ray-based defect area (3D-RBA), defined by a 1.5-mm thickness threshold, were calculated. Agreement was assessed using segmentation metrics, intraclass correlation coefficients (ICCs), repeated-measures Bland-Altman analysis, and minimal detectable change at 95% confidence (MDC95). The 3D-RBA framework was evaluated in 120 digital-phantom experiments from 40 participants. Longitudinal analyses included 374 participants, alternative-method comparisons included 65, and retrospective phase II analysis included 24 participants with four visits. Results: Overall AI-to-adjudicated-mask Dice was 0.964 +/- 0.029. Interreader ICCs for volume, thickness, and defect area were 0.956, 0.904, and 0.932; corresponding MDC95 values were 1,596.9 mm^3, 0.227 mm, and 147.4 mm^2. Geometric mean absolute percentage error for defect area was 5.62%, with spatial Dice of 0.961. In 374 participants, volume changes correlated positively with thickness changes (rho=0.431) and negatively with defect-area changes (rho=-0.221). Within-participant phase II correlations followed the same directions in both groups. Conclusions: The workflow demonstrated good interreader agreement. Controlled geometric results and longitudinal associations supported the feasibility of threshold-based defect-area estimation. Volume, thickness, and defect area provide complementary measures of cartilage structure.

The brain uses discrete spikes for dynamic computation, yet, how neural microcircuits (NMCs) solve temporal credit assignment using local spike timing remains a fundamental open question. Dominant spiking neural network (SNN) approaches circumvent this by approximating backpropagation through surrogate gradients, decoupling learning from biological spike timing. Here, we reformulate temporal credit assignment as a state separation problem: extracting task-required components induced by historical perturbations directly from the current neural state. This enables an online feedback learning framework for NMCs through a gradient tunneling (GT) algorithm and the lead-lag expansion technique that derives credit assignment from local synaptic spike timing, while remaining compatible with ANN-SNN hybrid architectures. Experimentally, GT-trained NMCs excel at long-timescale evidence integration and noise-robust memory retention, and perform comparably to leading SNN online learning methods on real-world benchmarks with far fewer parameters. The proposed framework addresses the two-decade-old NMC feedback learning problem and suggests a computationally plausible explanation for the brain's learning mechanisms.

Electroencephalography (EEG) is a noninvasive technology that is widely used to monitor brain states, and many efforts are focused on developing reliable and efficient data analysis methods for EEG recordings. Here, we apply ordinal analysis to the EEG recording of the resting state of 109 healthy subjects measured in two different conditions: with eyes closed (EC state) or eyes open (EO state). We study the robustness of the temporal permutation entropy ($PE$) and the spatial permutation entropy ($SPE$) with respect to the presence of blinking artifacts in the EO recordings, the duration of the recordings, and the number of EEG channels analyzed. We perform a paired statistical test to assess whether these quantities differ significantly in the EO and EC recordings of the same subject. We find that $PE$ and $SPE$ perform surprisingly well, as they detect significant differences when calculated from the raw signals, even within a short time interval ($PE$) or from a reduced number of electrodes ($SPE$).

The quantum model of the two-sentence liar paradox proposed by Aerts, Broekaert, and Smets is an early example of the use of quantum formalism to describe cognitive dynamics. Our reconstruction is primarily pedagogical in intent, but it also leads to a number of clarifications, and to some new observations, concerning the structure of the model. Rewriting the model in Dirac notation, we make explicit the distinction between truth values originating from a decision and from semantic inference, and show that the associated enlargement of the one-sentence state space corresponds to a factorization with respect to which the non-paradoxical configurations are separable while the genuine liar state is entangled. We also derive the Hamiltonian generating the four-state cyclic evolution, express it in compact operator form, and give the resulting transition probabilities in closed form. We emphasize that the liar cycle admits a unitarily equivalent representation in the four-dimensional truth-only space, where the unmeasured liar state is separable, so the dimensional enlargement is not required by the unitary part of the dynamics; it is required, however, by the measurement structure. The enlargement is also required by the dynamics as soon as revision processes are admitted, in which states with identical truth content but different origins have different successors, the origin degree of freedom then acting as a minimal form of cognitive memory. We conclude by discussing the possible relationship between the model and more general deliberative processes.

We introduce a probability-wave framework for modeling the collective behavior of interacting adaptive agents, deriving testable eigenmodes through a generalized behavioral intelligence (GBI) nonlocal probability-wave equation. This framework captures a broad range of human intelligence behaviors with analytical mechanisms and offers an indirect method to examine the Liu-Chen-Ao (LCA) hypothesis of nonlocal entangled nerve fibers in the brain through collective trader behaviors. Our empirical analysis of Chinese intraday stock market data demonstrates that adaptive entangled game modes explain 82-94% (89% overall) of observed decision patterns, a sharp contrast to the predictions of neoclassical finance based on independent rational agents. Moreover, 2-12% of behaviors show adaption to intraday news, events, and environments, characterized by dual equilibrium states and abrupt reference point shifts, while purely independent modes occur in less than 5% of cases. These findings empirically support the LCA hypothesis, as observable trading behaviors reflect underlying brain mechanisms and internal intelligence decision-making in behavioral psychology. Our results highlight the necessity of incorporating adaptive entangled game modules into artificial general intelligence (AGI) architectures, addressing the limitations of conventional artificial neural network (ANN)-based AI, which relies on trillions of opaque parameters. By integrating ANN-based AI with probability-wave-based entangled-brain simulations, machine learning can enrich AGI foundation models (FMs) and facilitate the development of human-like processing units (HPUs) that leverage brain-inspired mechanisms. Such HPUs may ultimately create more compact, efficient, and robust AGI systems, particularly for embodied intelligence and robotics.

Acidophilic proteins that remain stable and functional under highly acidic conditions, are important for industrial biocatalysis, acid-related bioprocessing, and the discovery of acid-stable enzymes. However, their identification relies heavily on time-consuming experimental screening methods. With the rapid growth of protein sequence databases, the need for computational identification methods that are both accurate and efficient has become stronger. The emergence of protein language models (PLMs) has significantly improved the sequence representation of downstream biological prediction tasks. This paper proposes MI-PEFT, a mixture-of-experts integrated parameter-efficient fine-tuning framework. Built on the ESM C-600M backbone, the framework incorporates LoRA-based PEFT methods and a DeepSeekMoE-based classification head to resolve the limitations of PEFT and significantly improve computational efficiency. Notably, this task is characterized by a significant class imbalance in the dataset, making high specificity particularly challenging. The experimental results demonstrate that MI-PEFT on PLMs, especially {\text{C}}^{\text{3}}\text{A}, serves as an efficient tool for identifying acidophilic proteins and a constrained pathway that helps resolve class-imbalance by preserving the pretrained representations.