archive
Every paper Pith has read. Search by title, abstract, or pith.
156 papers in q-bio.QM · page 1
-
Trajectories identify stochastic parameters uniquely
Structural identifiability of partially-observed stochastic processes: from single-particle trajectories to total particle density data
-
Sphere-native transformer beats ChemBERTa on molecules with fewer params
Chem-GMNet: A Sphere-Native Geometric Transformer for Molecular Property Prediction
-
Fusion model forecasts both peak and durability of pertussis responses
Multitask Multimodal Fusion with Tabular Foundation Models for Peak and Durability Prediction of Pertussis Booster Response
-
LLM agent with RDKit tools beats drug design baselines by over 10 percent
ToolMol: Evolutionary Agentic Framework for Multi-objective Drug Discovery
-
Language descriptions capture monkey neuron selectivity
Letting the neural code speak: Automated characterization of monkey visual neurons through human language
-
Missed events correction clarifies IP3R Park and Drive modes
Accounting for Missed Events in the Bayesian Modeling of IP3R Multimodal Gating
-
NORI resolves ambiguous biology mappings orders of magnitude faster
NORI: Fast probabilistic inference for ambiguous observation-entity mappings
-
Benchmark with 40 epidemic datasets enables fair model comparisons
EpiCastBench: Datasets and Benchmarks for Multivariate Epidemic Forecasting
-
Analogical reasoning lifts LLM diversity in science by 90-173%
Unlocking LLM Creativity in Science through Analogical Reasoning
-
Seven papers let LLM workflow expand TPD databases by 81-92%
Beyond Manual Curation: Augmenting Targeted Protein Degradation Databases via Agentic Literature Extraction Workflows
-
Regression to the Mean and Dilution Share One Root Cause
The Same Problem by Different Names: Unifying Regression Dilution and Regression to the Mean
-
Generalist LLMs beat specialists on 1,920 CRISPR screens
AssayBench: An Assay-Level Virtual Cell Benchmark for LLMs and Agents
-
Five-phase curriculum stabilizes JEPA rollouts on ICU trajectories
Clin-JEPA: A Multi-Phase Co-Training Framework for Joint-Embedding Predictive Pretraining on EHR Patient Trajectories
-
Five-phase curriculum stabilizes EHR trajectory rollouts
Clin-JEPA: A Multi-Phase Co-Training Framework for Joint-Embedding Predictive Pretraining on EHR Patient Trajectories
-
Virtual L3 paths raise protein interaction prediction accuracy
Learning the Interaction Prior for Protein-Protein Interaction Prediction: A Model-Agnostic Approach
-
L3 paths added to any PPI predictor via graph prompts
Learning the Interaction Prior for Protein-Protein Interaction Prediction: A Model-Agnostic Approach
-
MiRA adds seven modes for multilayer biological networks
Interactively visualizing biological multilayer networks using MiRA
-
MiRA app enables interactive visualization of biological multilayer networks
Interactively visualizing biological multilayer networks using MiRA
-
Random forest surrogate cuts likelihood evaluations in phylogenetic SMC
Accelerating Bayesian Phylogenetic Inference via Delayed Acceptance Sequential Monte Carlo with Random Forest Surrogates
-
2B model surpasses larger ones on medical VQA with reasoning transfer
LiteMedCoT-VL: Parameter-Efficient Adaptation for Medical Visual Question Answering
-
Condensation transition emerges below critical entropy in probability simplex
Condensation Transition in Entropy-Constrained Probability Spaces
-
BP180 homotrimer model stays folded in simulations
A putative, computationally stable structure of homotrimeric BP180/collagen XVII
-
Expert fusion model lifts microbial operon accuracy
MicroFuse: Protein-to-Genome Expert Fusion for Microbial Operon Reasoning
-
Normalized optical density aligns myelin slides with 7T MRI
Automated Optical Density Normalization for Myelin Quantification: Cross-Modal Validation with 7T Ex Vivo MRI
-
No LLM masters all three protein design stages
VibeProteinBench: An Evaluation Benchmark for Language-interfaced Vibe Protein Design
-
No LLM masters every stage of language protein design
VibeProteinBench: An Evaluation Benchmark for Language-interfaced Vibe Protein Design
-
Pretrained model restores 3D microscopy images from sparse scans
MicroDiffuse3D: A Foundation Model for 3D Microscopy Imaging Restoration
-
R package MeTime stores all metabolomics steps in one container
MeTime: An R package for reproducible longitudinal metabolomics data analysis
-
Graph model connects protein networks to cancer pathways at 90% accuracy
PPI-Net connects molecular protein interactions to functional processes in disease
-
Flow matching on raw counts beats baselines with fewer parameters
Flow Matching for Count Data
-
Models trained on real folds design RNA under mixed constraints
GoForth: Language Models for RNA Design under Structure, Sequence, and Coding Constraints
-
Shared neural co-variability peaks in V1 and falls higher up
Partitioning Neural Co-Variability
-
Mutation modeling improves protein function prediction
Better Protein Function Prediction by Modeling Survivorship Bias
-
Slowing cyclin B synthesis lengthens early fly cell cycles
Mathematical Modeling of Early Embryonic Cell Cycles of Drosophila melanogaster
-
Scenario-guided multi-agents lead on biomedical discovery benchmarks
BioResearcher: Scenario-Guided Multi-Agent for Translational Medicine
-
Four dietary patterns emerge from UK survey via K-means
An Explainable Unsupervised-to-Supervised Machine Learning Framework for Dietary Pattern Discovery Using UK National Dietary Survey Data
-
Combined boundary and interior mapping improves planar shape analysis
Planar morphometry via functional shape data analysis and quasi-conformal mappings
-
Boundary registration plus quasi-conformal fill quantifies planar shape variation
Planar morphometry via functional shape data analysis and quasi-conformal mappings
-
Stochastic matching resolves bias-precision paradox in medical AI
Resolving the bias-precision paradox with stochastic causal representation learning for personalized medicine
-
Optimizers simulate Darwinian evolution with added drift noise
Direct From Darwin: Deriving Advanced Optimizers From Evolutionary First Principles
-
Optimizers like SGD derive from Darwinian evolution with added noise
Direct From Darwin: Deriving Advanced Optimizers From Evolutionary First Principles
-
Causal GRN methods beat correlations only in clean data
When Does Gene Regulatory Network Inference Break? A Controlled Diagnostic Study of Causal and Correlational Methods on Single-Cell Data
-
Curated AI finds 3.2x more verified drugs than frontier LLMs
Curated AI beats frontier LLMs at pharma asset discovery
-
FairEnc reduces demographic bias in glaucoma detection
FairEnc: A Fair Vision-Language Model with Fair Vision and Text Encoders for Glaucoma Detection
-
AlphaFold guidance raises TM-scores in Phenix cryo-EM models
Enhancing Cryo-EM Density Map Segmentation in Phenix for Improved Atomic Model Building
-
Zero-inflated beta mixture improves microbiome mediation estimates
A Zero-Inflated Beta Mixture Model for Marginal Mediation Analysis with Compositional Microbiome Mediators
-
Ocean microbe networks exceed null modularity by 0.15-0.40
Modularity Emerges from Action-Functional Constraints in Marine Metabolic Networks: A Biology-Scale Validation of the Network-Weighted Action Principle
-
Boltz-2 and fine-tuned DrugFormDTA top antiviral affinity benchmarks
Benchmarking open-source tools for in silico antiviral drug discovery
-
Edit-flow model localizes changes more accurately on indel-rich sequences
Tree-Conditioned Edit Flows for Ancestral Sequence Reconstruction
-
GNN embeddings predict yeast knockout phenotypes with R² of 0.36
Graph Neural Network based Hierarchy-Aware Embeddings of Knowledge Graphs: Applications to Yeast Phenotype Prediction