Bridging Large Language Models and Single-Cell Transcriptomics in Dissecting Selective Motor Neuron Vulnerability
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916734880972800 |
|---|---|
| author | Jiang, Douglas Dai, Zilin Zhang, Luxuan Yu, Qiyi Sun, Haoqi Tian, Feng |
| author_facet | Jiang, Douglas Dai, Zilin Zhang, Luxuan Yu, Qiyi Sun, Haoqi Tian, Feng |
| contents | Understanding cell identity and function through single-cell level sequencing data remains a key challenge in computational biology. We present a novel framework that leverages gene-specific textual annotations from the NCBI Gene database to generate biologically contextualized cell embeddings. For each cell in a single-cell RNA sequencing (scRNA-seq) dataset, we rank genes by expression level, retrieve their NCBI Gene descriptions, and transform these descriptions into vector embedding representations using large language models (LLMs). The models used include OpenAI text-embedding-ada-002, text-embedding-3-small, and text-embedding-3-large (Jan 2024), as well as domain-specific models BioBERT and SciBERT. Embeddings are computed via an expression-weighted average across the top N most highly expressed genes in each cell, providing a compact, semantically rich representation. This multimodal strategy bridges structured biological data with state-of-the-art language modeling, enabling more interpretable downstream applications such as cell-type clustering, cell vulnerability dissection, and trajectory inference. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_07896 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Bridging Large Language Models and Single-Cell Transcriptomics in Dissecting Selective Motor Neuron Vulnerability Jiang, Douglas Dai, Zilin Zhang, Luxuan Yu, Qiyi Sun, Haoqi Tian, Feng Genomics Artificial Intelligence Understanding cell identity and function through single-cell level sequencing data remains a key challenge in computational biology. We present a novel framework that leverages gene-specific textual annotations from the NCBI Gene database to generate biologically contextualized cell embeddings. For each cell in a single-cell RNA sequencing (scRNA-seq) dataset, we rank genes by expression level, retrieve their NCBI Gene descriptions, and transform these descriptions into vector embedding representations using large language models (LLMs). The models used include OpenAI text-embedding-ada-002, text-embedding-3-small, and text-embedding-3-large (Jan 2024), as well as domain-specific models BioBERT and SciBERT. Embeddings are computed via an expression-weighted average across the top N most highly expressed genes in each cell, providing a compact, semantically rich representation. This multimodal strategy bridges structured biological data with state-of-the-art language modeling, enabling more interpretable downstream applications such as cell-type clustering, cell vulnerability dissection, and trajectory inference. |
| title | Bridging Large Language Models and Single-Cell Transcriptomics in Dissecting Selective Motor Neuron Vulnerability |
| topic | Genomics Artificial Intelligence |
| url | https://arxiv.org/abs/2505.07896 |