Quantitative Methods (Biology)
Mathematical and computational methods applied to biological systems.
q-bio.QM · 137 papersPersistent and anti-persistent stride-to-stride fluctuations: an ARFIMA decomposition consistent with closed-loop sensorimotor control
This paper uses ARFIMA models to show that fractal correlations in human walking are genuine long-memory processes, distinguishing them from short-memory effects.
minAction.net: Energy-First Neural Architecture Design -- From Biological Principles to Systematic Validation
minAction.net introduces energy-first neural architecture design, showing significant energy reduction and training efficiency gains with minimal accuracy loss.
Messaging strategies and the emergence of echo chambers in collective decision-making
Constraints on social information (discrete actions, limited attention) can cause echo chambers, making collective decisions sensitive and inaccurate.
CNN-ViT Fusion with Adaptive Attention Gate for Brain Tumor MRI Classification: A Hybrid Deep Learning Model
A hybrid CNN-ViT model with an Adaptive Attention Gate significantly improves brain tumor MRI classification accuracy by dynamically merging local and global features.
HyperEvoGen: Exploring deep phylogeny using non-Euclidean variational inference
HyperEvoGen uses a hyperbolic VAE to model protein evolution, accurately reconstructing phylogenies and generating sequences, overcoming limitations of traditional methods.
Multiplex Hypergraph Modeling of Higher Order Structures in Psychometric Networks
This paper presents a multiplex hypergraph framework to model higher-order symptom interactions in psychometric networks, applied to eating disorders.
Local growth laws determine global shape of molluscan shells
This paper shows that the diverse shapes of molluscan shells can be explained by a simple mathematical model based on local growth laws.
ProDock: From multi-target consensus docking into database-backed storage
ProDock is an open-source Python toolkit for reproducible protein-ligand docking, streamlining workflows and storing results in an SQLite database.
Quotient-Space Diffusion Models
Quotient-Space Diffusion Models simplify learning and improve generative AI by formally incorporating symmetries, outperforming prior methods for molecular structure generation.
CHRep: Cross-modal Histology Representation and Post-hoc Calibration for Spatial Gene Expression Prediction
CHRep predicts spatial gene expression from H&E slides using a two-phase framework with topology-preserving representation and post-hoc calibration.
Trustworthy Clinical Decision Support Using Meta-Predicates and Domain-Specific Languages
This paper introduces meta-predicates and a DSL to ensure clinical decision support systems use epistemologically appropriate and auditable evidence.
Calibeating Prediction-Powered Inference
Calibeating Prediction-Powered Inference introduces a method to post-hoc calibrate prediction scores on labeled data, improving semisupervised mean estimation efficiency.
PanGuide3D: Cohort-Robust Pancreas Tumor Segmentation via Probabilistic Pancreas Conditioning and a Transformer Bottleneck
PanGuide3D improves pancreas tumor segmentation across different CT cohorts by using probabilistic pancreas conditioning and a Transformer bottleneck.
Closing the Domain Gap in Biomedical Imaging by In-Context Control Samples
CS-ARM-BN uses control samples to close domain gaps in biomedical imaging, improving deep learning robustness across batches.
LAFA: A Framework for Reproducible Longitudinal Assessment of Protein Function Annotation Models
LAFA is a new framework for continuous, reproducible, and longitudinal assessment of protein function prediction models, addressing CAFA's periodic limitation.
VARIANT: Web Server for Decoding and Analyzing Viral Mutations at Genome and Protein Levels
VARIANT is a web server for comprehensive analysis of viral mutations, including novel patterns and RNA secondary structures, across diverse viral genomes.
Semi supervised GAN for smart microscopy, fast and data efficient cell cycle classification
This paper introduces SGAN for robust, data-efficient cell cycle classification in smart microscopy, achieving high accuracy with minimal labeled data.
AROMA: Augmented Reasoning Over a Multimodal Architecture for Virtual Cell Genetic Perturbation Modeling
AROMA is a multimodal AI that accurately and interpretably models genetic perturbations in virtual cells, outperforming prior methods.
scpFormer: A Foundation Model for Unified Representation and Integration of the Single-Cell Proteomics
scpFormer is a transformer-based foundation model for single-cell proteomics that unifies data from fragmented antibody panels.
Direct RNA sequence design under codon constraints using expressive tensor-based secondary structure models
A new algorithm enables direct RNA sequence design under codon constraints by using expressive tensor-based secondary structure models for accurate optimization.
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.