Adaptive resampling for improved machine learning in imbalanced single-cell datasets
Navidi, Z.; Thoutam, A.; Hughes, M.; Raghavan, S.; Winter, P. S.; Crawford, L.; Amini, A. P.
Show abstract
While machine learning models trained on single-cell transcriptomics data have shown great promise in providing biological insights, existing tools struggle to effectively model underrepresented and out-of-distribution cellular features or states. We present a generalizable Adaptive Resampling (AR) approach that addresses these limitations and enhances single-cell representation learning by resampling data based on its learned latent structure in an online, adaptive manner concurrent with model training. Experiments on gene expression reconstruction, cell type classification, and perturbation response prediction tasks demonstrate that the proposed AR training approach leads to significantly improved downstream performance across datasets and metrics. Additionally, it enhances the quality of learned cellular embeddings compared to standard training methods. Our results suggest that AR may serve as a valuable technique for improving representation learning and predictive performance in single-cell transcriptomic models.
Matching journals
The top 4 journals account for 50% of the predicted probability mass.
Similar papers in this journal
Similar papers in this journal
- Learning interpretable cellular and gene signature embeddings from single-cell transcriptomic data 98%
- scMODAL: A general deep learning framework for comprehensive single-cell multi-omics data alignment with feature links 98%
- scDREAMER: atlas-level integration of single-cell datasets using deep generative model paired with adversarial classifier 98%
Similar papers in this journal
- scAlign: a tool for alignment, integration and rare cell identification from scRNA-seq data 97%
- CMOT: Cross Modality Optimal Transport for multimodal inference 97%
- scCross: A Deep Generative Model for Unifying Single-cell Multi-omics with Seamless Integration, Cross-modal Generation, and In-silico Exploration 97%
Similar papers in this journal
- scCausalVI disentangles single-cell perturbation responses with causality-aware generative model 98%
- Automated assignment of cell identity from single-cell multiplexed imaging and proteomic data 96%
- Learning multi-cellular representations of single-cell transcriptomics data enables characterization of patient-level disease states 96%
Similar papers in this journal
- Simultaneous dimensionality reduction and integration for single-cell ATAC-seq data using deep learning 97%
- Inferring spatial single-cell-level interactions through interpreting cell state and niche correlations learned by self-supervised graph transformer 96%
- INSCT: Integrating millions of single cells using batch-aware triplet neural networks 96%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.