Article

Gene-Family Encoding Boosts Domain-Adapted Single-Cell Language Models

2025-09-19

Abstract excerpt

Transformer-based single-cell foundation models often rely on ranked-gene (RG) sequences where genes, ranked by expression, are often not functionally related, weakening next-token learning and the structure of learned embeddings. Here, we introduce gene-family (GF) encoding, where expressed genes are grouped into functionally defined families, and ranking performed within each family. Using 100,000 gastric-cancer...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: 36c15256-8c03-503e-acdc-17bd9861233d
DOI: 10.1101/2025.09.16.676672

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Gene-Family Encoding Boosts Domain-Adapted Single-Cell Language ModelsDOI 10.1101/2025.09.16.676672Read

RegFormer: A Single-Cell Foundation Model Powered by Gene Regulatory HierarchiesSemantic proximity Read

GeneBag: training a cell foundation model for broad-spectrum cancer diagnosis and prognosis with bulk RNA-seq dataSemantic proximity Read

GeneBag: training a cell foundation model for broad-spectrum cancer diagnosis and prognosis with bulk RNA-seq dataSemantic proximity Read

Large Scale Foundation Model on Single-cell TranscriptomicsSemantic proximity Read

Tahoe-x1: Scaling Perturbation-Trained Single-Cell Foundation Models to 3 Billion ParametersSemantic proximity Read

Parameter-free representations outperform single-cell foundation models on downstream benchmarksSemantic proximity Read

scLong: A Billion-Parameter Foundation Model for Capturing Long-Range Gene Context in Single-Cell TranscriptomicsSemantic proximity Read

evoCancerGPT: Generating Zero-Shot Single-Cell and Single-Sample Cancer Progression Through Transfer LearningSemantic proximity Read

CAR T cell foundation model predicts immunotherapy responseSemantic proximity Read

CellFM: a large-scale foundation model pre-trained on transcriptomics of 100 million human cellsSemantic proximity Read

Cross-Tissue Generalization of Rare Cell-Type Representations in Single-Cell Foundation Models: A Benchmark Using Public Reference AtlasesSemantic proximity Read

scKEPLM: Knowledge enhanced large-scale pre-trained language model for single-cell transcriptomicsSemantic proximity Read