Copertina

What Topological and Geometric Structure Do Biological Foundation Models Learn? Evidence from 141 Hypotheses

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autore principale:	Kendiukhov, Ihor
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Quantitative Methods Machine Learning Genomics
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Discovery of a Hematopoietic Manifold in scGPT Yields a Method for Extracting Performant Algorithms from Biological Foundation Model Internals
di: Kendiukhov, Ihor
Pubblicazione: (2026)

Causal Circuit Tracing Reveals Distinct Computational Architectures in Single-Cell Foundation Models: Inhibitory Dominance, Biological Coherence, and Cross-Model Convergence
di: Kendiukhov, Ihor
Pubblicazione: (2026)

Learning Genomic Structure from $k$-mers
di: Thor, Filip, et al.
Pubblicazione: (2025)

Multi-Dimensional Spectral Geometry of Biological Knowledge in Single-Cell Transformer Representations
di: Kendiukhov, Ihor
Pubblicazione: (2026)

BarcodeMamba: State Space Models for Biodiversity Analysis
di: Gao, Tiancheng, et al.
Pubblicazione: (2024)

Modeling variable guide efficiency in pooled CRISPR screens with ContrastiveVI+
di: Weinberger, Ethan, et al.
Pubblicazione: (2024)

CRANE: Correcting Errors in Raw Nanopore Signals Using Hidden Markov Models
di: Ambrozak, Simon, et al.
Pubblicazione: (2026)

Mixed Models with Multiple Instance Learning
di: Engelmann, Jan P., et al.
Pubblicazione: (2023)

Scaling Laws for Masked-Reconstruction Transformers on Single-Cell Transcriptomics
di: Kendiukhov, Ihor
Pubblicazione: (2026)

SAGE-FM: A lightweight and interpretable spatial transcriptomics foundation model
di: Zhan, Xianghao, et al.
Pubblicazione: (2026)

Parameter-free representations outperform single-cell foundation models on downstream benchmarks
di: Souza, Huan, et al.
Pubblicazione: (2026)

Integrate Any Omics: Towards genome-wide data integration for patient stratification
di: Ma, Shihao, et al.
Pubblicazione: (2024)

scMRDR: A scalable and flexible framework for unpaired single-cell multi-omics data integration
di: Sun, Jianle, et al.
Pubblicazione: (2025)

A novel application of Shapley values for large multidimensional time-series data: Applying explainable AI to a DNA profile classification neural network
di: Elborough, Lauren, et al.
Pubblicazione: (2024)

Data Valuation with Gradient Similarity
di: Evans, Nathaniel J., et al.
Pubblicazione: (2024)

Evaluating DNA function understanding in genomic language models using evolutionarily implausible sequences
di: Jiang, Shiyu, et al.
Pubblicazione: (2025)

Multi-Modal and Multi-Attribute Generation of Single Cells with CFGen
di: Palma, Alessandro, et al.
Pubblicazione: (2024)

scDiffusion: conditional generation of high-quality single-cell data using diffusion model
di: Luo, Erpai, et al.
Pubblicazione: (2024)

Hierarchical novel class discovery for single-cell transcriptomic profiles
di: Senoussi, Malek, et al.
Pubblicazione: (2024)

Quantum Ensembling Methods for Healthcare and Life Science
di: Rhrissorrakrai, Kahn, et al.
Pubblicazione: (2025)

GCBLANE: A graph-enhanced convolutional BiLSTM attention network for improved transcription factor binding site prediction
di: Ferrao, Jonas Chris, et al.
Pubblicazione: (2025)

Sparse autoencoders reveal organized biological knowledge but minimal regulatory logic in single-cell foundation models: a comparative atlas of Geneformer and scGPT
di: Kendiukhov, Ihor
Pubblicazione: (2026)

MicroFuse: Protein-to-Genome Expert Fusion for Microbial Operon Reasoning
di: Cho, Seungik
Pubblicazione: (2026)

Optimizing Prognostic Biomarker Discovery in Pancreatic Cancer Through Hybrid Ensemble Feature Selection and Multi-Omics Data
di: Zobolas, John, et al.
Pubblicazione: (2025)

Hypergraph Representations of scRNA-seq Data for Improved Clustering with Random Walks
di: He, Wan, et al.
Pubblicazione: (2025)

Revolutionizing Genomics with Reinforcement Learning Techniques
di: Karami, Mohsen, et al.
Pubblicazione: (2023)

OmicsCL: Unsupervised Contrastive Learning for Cancer Subtype Discovery and Survival Stratification
di: Karagoz, Atahan
Pubblicazione: (2025)

GRAPE: Heterogeneous Graph Representation Learning for Genetic Perturbation with Coding and Non-Coding Biotype
di: Chi, Changxi, et al.
Pubblicazione: (2025)

From Syntax to Semantics: Geometric Stability as the Missing Axis of Perturbation Biology
di: Raju, Prashant C.
Pubblicazione: (2026)

CRADLE-VAE: Enhancing Single-Cell Gene Perturbation Modeling with Counterfactual Reasoning-based Artifact Disentanglement
di: Baek, Seungheun, et al.
Pubblicazione: (2024)

Pathway Tools version 28.0: Integrated Software for Pathway/Genome Informatics and Systems Biology
di: Karp, Peter D., et al.
Pubblicazione: (2015)

High-dimensional Many-to-many-to-many Mediation Analysis
di: Nguyen, Tien Dat, et al.
Pubblicazione: (2026)

Fusing Sequence Motifs and Pan-Genomic Features: Antimicrobial Resistance Prediction using an Explainable Lightweight 1D CNN-XGBoost Ensemble
di: Siddiqui, Md. Saiful Bari, et al.
Pubblicazione: (2025)

DeepSeq: High-Throughput Single-Cell RNA Sequencing Data Labeling via Web Search-Augmented Agentic Generative AI Foundation Models
di: Dajani, Saleem A. Al, et al.
Pubblicazione: (2025)

Multi-omics Prediction from High-content Cellular Imaging with Deep Learning
di: Mehrizi, Rahil, et al.
Pubblicazione: (2023)

DNA Language Model and Interpretable Graph Neural Network Identify Genes and Pathways Involved in Rare Diseases
di: Saadat, Ali, et al.
Pubblicazione: (2024)

Penalized Principal Component Analysis Using Smoothing
di: Hurwitz, Rebecca M., et al.
Pubblicazione: (2023)

Deciphering regulatory architectures from synthetic single-cell expression patterns
di: Pan, Rosalind Wenshan, et al.
Pubblicazione: (2024)

StateXDiff: Cell State-Contextualized Multimodal Diffusion for Single-Cell Perturbation Prediction
di: Shi, Peiting, et al.
Pubblicazione: (2026)

pHapCompass: Probabilistic Assembly and Uncertainty Quantification of Polyploid Haplotype Phase
di: Hosseini, Marjan, et al.
Pubblicazione: (2025)