1. SIMS: A deep-learning label transfer tool for single-cell RNA sequencing analysis
- Author
-
Gonzalez-Ferrer, Jesus, Lehrer, Julian, O’Farrell, Ash, Paten, Benedict, Teodorescu, Mircea, Haussler, David, Jonsson, Vanessa D, and Mostajo-Radji, Mohammed A
- Subjects
Information and Computing Sciences ,Biological Sciences ,Machine Learning ,Stem Cell Research - Induced Pluripotent Stem Cell - Human ,Networking and Information Technology R&D (NITRD) ,Neurosciences ,Stem Cell Research ,Human Genome ,Bioengineering ,Stem Cell Research - Induced Pluripotent Stem Cell ,Machine Learning and Artificial Intelligence ,Genetics ,1.1 Normal biological development and functioning ,Neurological ,Single-Cell Analysis ,Humans ,Deep Learning ,Sequence Analysis ,RNA ,Animals ,Brain ,Neurons ,Organoids ,Cell Differentiation ,Mice ,RNA sequencing ,TabNet ,brain organoids ,cell atlas ,label transfer ,machine learning ,neurodevelopment ,neuroscience data ,reference mapping ,single cell analysis - Abstract
Cell atlases serve as vital references for automating cell labeling in new samples, yet existing classification algorithms struggle with accuracy. Here we introduce SIMS (scalable, interpretable machine learning for single cell), a low-code data-efficient pipeline for single-cell RNA classification. We benchmark SIMS against datasets from different tissues and species. We demonstrate SIMS's efficacy in classifying cells in the brain, achieving high accuracy even with small training sets (
- Published
- 2024