Article

Consequences of training data composition for deep learning models in single-cell biology

2025-02-24

Abstract excerpt

<h4>ABSTRACT</h4> Foundation models for single-cell transcriptomics have the potential to augment (or replace) purpose-built tools for a variety of common analyses, especially when data are sparse. Recent work with large language models has shown that training data composition greatly shapes performance; however, to date, single-cell foundation models have ignored this aspect, opting instead to train on the large...

Topics

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

Identifiers and source

Literature Corpus work: 22c09f74-425a-5bbf-b4e3-6696484afe45
DOI: 10.1101/2025.02.19.639127

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Consequences of training data composition for deep learning models in single-cell biologyDOI 10.1101/2025.02.19.639127Read

Stack: In-Context Learning of Single-Cell BiologySemantic proximity Read

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

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

A Cross-Species Generative Cell Atlas Across 1.5 Billion Years of Evolution: The TranscriptFormer Single-cell ModelSemantic proximity Read

Large Scale Foundation Model on Single-cell TranscriptomicsSemantic proximity Read

scGenAI: A generative AI platform with biological context embedding of multimodal features enhances single cell state classificationSemantic proximity Read

CancerFoundation: A single-cell RNA sequencing foundation model to decipher drug resistance in cancerSemantic proximity Read

Scaling Dense Representations for Single Cell with Transcriptome-Scale ContextSemantic proximity Read

Learning multi-cellular representations of single-cell transcriptomics data enables characterization of patient-level disease statesSemantic proximity Read

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

Species-specific small models for cell type classification approach the performance of large single cell foundation modelsSemantic proximity Read

Inferring Disease Progressive Stages in Single-Cell Transcriptomics Using Weakly-Supervised Deep Learning ApproachSemantic proximity Read