Tamim Abdelaal

This study benchmarks four single-cell foundation models across four tasks, finding they do not consistently outperform traditional methods but show promise in protein expression prediction.

This paper creates a cross-species single-cell atlas of Macaca fascicularis using human reference labels to improve target qualification and toxicity interpretation in preclinical research.

The paper benchmarks tumor cell annotation methods on scRNA-seq data and finds Consensus annotation outperforms individual methods in precision.

SpaceWalker explores spatial transcriptomics data gradients to reveal tissue architecture and gene expression patterns through interactive visualization.

This study compares linear and non-linear joint embedding methods for bulk and single-cell multi-omics, finding non-linear methods excel in imputation and joint embeddings improve performance in supervised tasks.

This study benchmarks variational autoencoders on cancer transcriptomics data to evaluate hyperparameter effects and latent space biological relevance.

The paper uses spatial transcriptomics in DMD mouse models to identify gene expression signatures linked to histopathological changes in skeletal muscle.

scTopoGAN aligns single-cell datasets with non-overlapping cells or features using topology-guided GANs, outperforming existing methods in unsupervised settings.

This study evaluates six algorithms for cell type matching in spatial transcriptomics data and presents consensus strategies for improved analysis.

scMoC integrates scRNA-seq and scATAC-seq data to identify biologically meaningful cell clusters through RNA-guided imputation and cross-modal clustering.

SIRV infers spatial RNA velocities at single-cell resolution by integrating spatial transcriptomics with scRNA-seq data, revealing spatial differentiation patterns in developing tissues.

Cytosplore-Transcriptomics provides a scalable interactive framework for analyzing scRNA-seq data, enabling visualization and downstream analysis of large datasets.

SCHNEL is a scalable clustering tool for high-dimensional single-cell data that outperforms existing methods on cytometry datasets and handles large datasets efficiently.

SpaGE integrates spatial and scRNA-seq data to predict whole-transcriptome spatial gene expressions, outperforming existing methods and identifying new spatial gene patterns.

The paper benchmarks 20 automatic cell identification methods for single-cell RNA-sequencing data across eight datasets, finding that SVM performs best overall.

The paper introduces a Linear Discriminant Analysis classifier for predicting cell types in mass cytometry data, showing comparable performance to state-of-the-art methods and scalability to large datasets.