archive
Every paper Pith has read. Search by title, abstract, or pith.
1822 papers in q-bio · page 2
-
-
Specialized clinical AI beats general models by 25-39 points on real questions
Expert Evaluation of Clinical AI Tools on Real Point-of-Care Clinical Queries
-
Generic parameters restrict exact lumping to obvious reductions
Lumping of reaction networks: Generic and critical parameters
-
Three-tier data upgrade proposed to make space biology AI-ready
Building AI-Ready Data Systems for Space Life Sciences, Aerospace Medicine, and Deep Space Exploration
-
Alzheimer's proteins form many stable patterns
Pattern formation in a Reaction-Diffusion Model for Amyloid-$\beta$ and Tau Interactions in Alzheimer's Disease
-
Transformers with active learning beat double-data baselines on PRRS epitopes
Transformer-Based Active Learning for Data-Efficient Vaccine Epitope Selection in PRRS
-
High-entanglement ZZ map cuts overfitting in quantum binding classifier
Exploring the Effects of Entanglement on Quantum Machine Learning of Pathogen Epitope-Receptor Binding
-
Habitual timing explains circadian peaks
Habitual lifestyle timing explains circadian timing, but daily lifestyle changes do not, in free-living humans across 2000 days
-
Tensor network models kids' emotional memory at 78% accuracy
Modelling Emotional Memory in Children with Tensor Networks
-
One simulation run drives evolutionary updates in queues
Discrete Event Population Updates: finding game theoretic emergent behaviour in queueing systems with simulation
-
Drug condition accuracy in embeddings fails to ensure cross-drug prediction
SVC-Probe: A Framework for Evaluating Perturbation Generalization in Spatial Foundation-Model Embeddings
-
Recovered expressions rebuild cell graphs for better scRNA-seq clusters
scKDGM: KAN-guided Dynamic Graph Masked Learning for Single-Cell RNA-seq Clustering
-
Maximum-likelihood paths often atypical of real evolutionary histories
Reconstructability of evolutionary intermediates in generative epistatic landscapes
-
Method adds coevolution to ancestral protein reconstruction
Towards coevolution-aware ancestral sequence reconstruction
-
Two-stage tuning aligns proteins to target amino-acid mixes
Two-Stage Fine-Tuning for Protein Sequence Generation with Targeted Amino-Acid Composition
-
MCIDs set for smartphone gait metrics in progressive MS
Establishing the Minimal Clinically Important Difference (MCID) for Smartphone-Derived Gait Measures in Multiple Sclerosis
-
Fusing Whisper acoustics with LLM language features detects dementia
Listening Between the Lines: Joint Learning of ASR Embeddings and LLM-Augmented Linguistics for Dementia Detection
-
Toolkit unifies CANN simulation and attractor analysis
CANNs: A Toolkit for Research on Continuous Attractor Neural Networks
-
XAI should become standard for validating ecological image models
Explainable AI for Biodiversity Monitoring and Ecological Image Analysis
-
scRNA-seq maps human fat-cell development to 15 states
Reconstructing the Developmental Trajectory of Adipocytes in Human Adipose Tissue Using Single-Cell RNA Sequencing
-
Reactive Nash equilibria map one-to-one to action subsets
Characterisation of reactive Nash equilibria in repeated additive games
-
Phylogenetic likelihoods gain up to 10x on multi-core CPUs and GPUs
BEAGLE 4.1: A high-performance library for computation on phylogenetic trees across diverse parallel architectures
-
ZIBeta distribution model outperforms regression in TPS prediction
Distribution-based deep multiple instance learning for tumor proportion scoring in NSCLC
-
Stronger inhibitory-to-excitatory synapses explain chronic stress effects
Modelling chronic stress as an excitatory-inhibitory perturbation in recurrent working-memory networks
-
GRAFT dataset links genes to traits in same Arabidopsis plants
GRAFT: Biological Graph and Hypergraph Benchmarks for Linked Gene Expression and Phenotypic Trait Prediction in Arabidopsis thaliana
-
Emulators match marine model skill over decades at lower cost
Deep learning model emulators for marine biogeochemistry forecasting from days to decades
-
Energy allocation links scaling exponents to von Bertalanffy growth
Metabolic scaling, von Bertalanffy growth and an exponent equation
-
Library scales phylogenetic shape inference to 850-node trees
Hyperiax and Phylogenetic Inference from Shape Data
-
Constant-factor approximation for parental parsimony score
The parental parsimony problem on binary, tree-child phylogenetic networks
-
Output-use feedback builds organized networks in agent systems
Surviving by Serving: Functional Relevance Drives Self-Organization in Complex Adaptive Systems
-
Raw breathing signals detect stress at 96.7 percent accuracy
State-Specific Respiratory Signatures for Affective and Stress Recognition: Interpretable Respiratory Markers, Autocorrelation Lags, and Compact CNN Models
-
Fixed milking order for cow cohorts limits H5N1 spread
On-farm management strategies for reducing H5N1 transmission in dairy cattle
-
Network triangles evade identification in Jukes-Cantor models
Semialgebraic Conditions for Identifying Triangles in Phylogenetic Networks
-
pVACtools v6 adds neoantigen prediction from splicing mutations
pVACtools v6: A comprehensive suite for neoantigen prediction, visualization, and therapy design
-
Risk-aware ordering holds Hit@10 at 0.9 in BACE library replay
Budget-Constrained Compound Library Prioritization with Risk Awareness and Uncertainty Quantification
-
Monotonic Bayesian learner maps saturation curves in seven measurements
Shape-Constrained Bayesian Active Learning of Self-Limiting Saturation Curves
-
AI agents succeed on 25% of long single-cell biology tasks
scBench-Long: Verifiable Benchmarking of Long-Horizon Single-Cell Biology
-
GRAINS runs genome graphs inside SSDs for up to 47.8x speedup
GRAINS: Storage-Aware Algorithm-Architecture Co-Design Enabling High-Performance and Low-Cost Graph-Based Genome Analysis
-
AI system finds decision theories that beat seeded models
Closing the Loop to Discover Psychological Theories with an Automated Cognitive Scientist
-
Vesicle solid domains roll, crumple then smooth with rising inflation
Frustrated shapes of solid domains in fluid membrane vesicles: From rolls and folds to crumples and wrinkles
-
Spline clock recovers true time-varying rates with tighter intervals
Smoothly Time-Varying Continuous Time Markov Chains in Phylogenetics
-
Additional food raises network deficiency in predator-prey models
An Investigation of Additional Food Models with Generalised Functional Response
-
fMRI multi-source transfer varies with source task composition
Beyond Single-Source Cognitive Taskonomy:Multi-Source Task Relations through fMRI Transfer Learning
-
Dirichlet-multinomial residuals normalize overdispersed sparse counts
Deviance-style normalization for jointly overdispersed counts
-
Clustering boosts polychronous group count by over 90 percent
Topology-Dependent Emergence of Polychronous Neuronal Groups: A Recurrence-Plot Characterization
-
One decoder matches larger models across molecule design constraints
Molexar: A Unified Multimodal Molecular Foundation Model for Drug Design
-
Real weights organize memory deeper than random in 34 networks
Weight geometry governs functional memory in complex systems
-
Neuro-symbolic model reaches 92.5% symbolic coverage in resistance calls
KG-TRACE: A Neuro-Symbolic Framework for Mechanistic Grounding in Antimicrobial Resistance Prediction
-
Meta-learning improves AI vision match to human judgments and cortex
Meta-learning as a principle for human-like visual representations
-
Closed-form sensitivities derived for evolutionary entropy in Lefkovitch matrices
Sensitivity of evolutionary entropy in Lefkovitch matrices