archive
Every paper Pith has read. Search by title, abstract, or pith.
83 papers in q-bio.GN · page 1
-
Homomorphic encryption on blockchain computes private polygenic risk scores
bioETH-PRS: Confidential Polygenic Risk Scoring without a Trusted Evaluator via Fully Homomorphic Encryption on a Programmable Blockchain
-
Latent GP and optimal transport track cell changes over time
Modeling Temporal scRNA-seq Data with Latent Gaussian Process and Optimal Transport
-
Machine learning ties lncRNA features to type 2 diabetes
Multi-Modal Machine Learning for Population- and Subject-Specific lncRNA-Type 2 Diabetes Association Analysis
-
Algorithm extracts active TF sites from mutation groups
Informational blueprints reveal condition-dependent gene regulatory architectures
-
Geometry-aware metric cuts single-cell trajectory error by 24 percent
PACE: Geometry-Aware Bridge Transport for Single-Cell Trajectory Inference
-
Protein-augmented diffusion predicts single-cell drug effects
StateXDiff: Cell State-Contextualized Multimodal Diffusion for Single-Cell Perturbation Prediction
-
Resampling yields reliable networks from scarce high-dimensional samples
A Resampling-Based Framework for Network Structure Learning in High-Dimensional Data
-
Reeb graphs from diffusion detect single-cell shapes more accurately than baselines
scShapeBench: Discovering geometry from high dimensional scRNAseq data
-
Genome embeddings predict microbiome abundances for novel species
Set-Aggregated Genome Embeddings for Microbiome Abundance Prediction
-
Local discrete programs re-rank DNA edits for higher rewards
LPDP: Inference-Time Reward Control for Variable-Length DNA Generation with Edit Flows
-
Protein embeddings classify bacterial operons at 0.71 ROC-AUC
SCOPE: Siamese Contrastive Operon Pair Embeddings for Functional Sequence Representation and Classification
-
Expert fusion model lifts microbial operon accuracy
MicroFuse: Protein-to-Genome Expert Fusion for Microbial Operon Reasoning
-
Hybrid model lowers error in grapevine trait prediction across years
A Linear-Transformer Hybrid for SNP-Based Genotype-to-Phenotype Prediction in Grapevine
-
Logistic regression outperforms complex models on rare breast cancer subtypes
Feature Dimensionality Outweighs Model Complexity in Breast Cancer Subtype Classification Using TCGA-BRCA Gene Expression Data
-
AI agent outperforms physicians on rare disease diagnosis
A Versatile AI Agent for Rare Disease Diagnosis and Risk Gene Prioritization
-
AI agent outperforms physicians on rare disease diagnosis
A Versatile AI Agent for Rare Disease Diagnosis and Risk Gene Prioritization
-
Multimodal LLM reasons with omics numbers and language together
OmicsLM: A Multimodal Large Language Model for Multi-Sample Omics Reasoning
-
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
-
Moments of group functions computed from Fourier coefficients alone
Statistics of a multi-factor function from its Fourier transform
-
Transformer learns directional gene-program influences from unperturbed single-cell data
ORBIT: Learning Gene Program Co-Activation Structure for Cell-Type-Stratified Pathway Rewiring Analysis in Single-Cell Transcriptomics
-
Data fusion lifts migraine prediction AUC from 0.644 to 0.688
EFGPP: Exploratory framework for genotype-phenotype prediction
-
Pipeline recovers 98.4% of known phenotype genes from 13 databases
PhenotypeToGeneDownloaderR: automated multi-source retrieval and validation of phenotype-associated genes
-
USB reconstructs discrete branching dynamics from snapshots
Beyond Continuity: Simulation-free Reconstruction of Discrete Branching Dynamics from Single-cell Snapshots
-
MCMC steering improves single-cell perturbation predictions
CellxPert: Inference-Time MCMC Steering of a Multi-Omics Single-Cell Foundation Model for In-Silico Perturbation
-
Fused signals and conformal calibration certify zero-miss DNA hazard screening under new-f
CRC-Screen: Certified DNA-Synthesis Hazard Screening Under Taxonomic Shift
-
HyCNNs approximate quadratics with exponentially fewer parameters
Hyper Input Convex Neural Networks for Shape Constrained Learning and Optimal Transport
-
A generalized gene co-expression method applied to AMD RNA-Seq data identifies stable…
Robust Clustering Analysis of Genes Related to Age-related Macular Degeneration using RNA-Seq
-
Metaheuristic selects reactions to fit GEMs on 9-28 media
A Combinatorial Optimisation Approach to Multi-factorial Gap-filling in Genome-scale Metabolic Models (GEMs)
-
Over 1000 TCR sequences flag long COVID vs recovery
T-cell repertoire response in individuals with post-acute sequelae of COVID-19
-
Frozen confidence scores boost multi-omics cancer subtyping
CMGL: Confidence-guided Multi-omics Graph Learning for Cancer Subtype Classification
-
Radiomic features distinguish molecular subtypes in tongue cancer
Imaging Exploration of Molecular Subtypes in Tongue Squamous Cell Carcinoma
-
Cathaya genome links defense gene loss to slow growth and symbiosis
The Cathaya argyrophylla Genome Reveals the Evolutionary Trade-offs of a Living Fossil
-
Supregraphs capture full read information in assembly graphs
Supregraph: Enabling Information-Optimal Assembly Graph Representation of a Read Set
-
GPU runs 20,000 GWAS phenotypes in 20 minutes
TorchGWAS : GPU-accelerated GWAS for thousands of quantitative phenotypes
-
Tree-guided diffusion creates cell-specific DNA regulators
Conditional Monte Carlo Tree Diffusion for Designing Cell-Type-Specific and Biologically Faithful Regulatory DNA
-
Quantum classifier finds combined gene set best for lung cancer subtyping
Quantum AI for Cancer Diagnostic Biomarker Discovery
-
Coherence metric flags stress beyond perturbation size
Geometric coherence of single-cell CRISPR perturbations reveals regulatory architecture and predicts cellular stress
-
Coherence metric links CRISPR size to stress and regulator type
Geometric coherence of single-cell CRISPR perturbations reveals regulatory architecture and predicts cellular stress
-
Hybrid inference yields lab-specific CNV guarantees
Combining Bayesian and Frequentist Inference for Laboratory-Specific Performance Guarantees in Copy Number Variation Detection
-
Documentation grounds LLMs for accurate bioinformatics commands
oxo-call: Documentation-grounded Skill Augmentation for Accurate Bioinformatics Command-line Generation with Large Language Models
-
LLMs generate features on the fly for DNA decision trees
Interpretable DNA Sequence Classification via Dynamic Feature Generation in Decision Trees
-
EvoLen preserves DNA motifs better than standard BPE
EvoLen: Evolution-Guided Tokenization for DNA Language Model
-
Evo2 learns local CTCF grammar but misses 3D chromatin structure
Probing 3D Chromatin Structure Awareness in Evo2 DNA Language Model
-
Web tool builds prokaryote family trees from 10,000+ genomes
WebCVTree4: A Newly Designed Phylogenetic and Taxonomic Study Platform for Prokaryotes Using Composition Vectors and Whole Genomes
-
Pipeline fixes circular bias in ecDNA cancer benchmarks
ECLIPSE: A Composable Pipeline for Predicting ecDNA Formation, Evolution, and Therapeutic Vulnerabilities in Cancer
-
Genomic language models ignore where regulatory DNA sits
The Mechanistic Invariance Test: Genomic Language Models Fail to Learn Positional Regulatory Logic
-
LLMs beat random on phage DNA tasks but fail at complex reasoning
PhageBench: Can LLMs Understand Raw Bacteriophage Genomes?
-
LLMs detect local DNA signals but weaken on multi-step genome tasks
GenomeQA: Benchmarking General Large Language Models for Genome Sequence Understanding
-
Transcriptomic models for ICI response generalize poorly across cohorts
Transcriptomic Models for Immunotherapy Response Prediction Show Limited Cross-cohort Generalisability
-
ML models recover NGS quality labels from QC and blocklist features
An Imbalanced Dataset with Multiple Feature Representations for Studying Quality Control of Next-Generation Sequencing