Alejandro Tejada-Lapuerta

The paper benchmarks gene expression reconstruction from single-cell latent representations, finding autoencoders perform best at low dimensionality and foundation models depend on decoder architecture.

Pertpy provides a modular framework for analyzing large-scale perturbation single-cell experiments, offering tools for metadata annotation and perturbation distance calculations.

scConcept improves single-cell representations by using contrastive learning instead of reconstruction, outperforming existing methods in multiple tasks.

CellFlow predicts single-cell phenotypes from complex perturbations using flow matching, demonstrating accuracy in cytokine stimulation, drug treatments, and developmental modeling.

This study uses synthetic data generation and explainable AI to uncover an intermediate subgroup in medulloblastoma, highlighting treatment disparities and supporting the continuum hypothesis between Groups 3 and 4.

Prophet predicts cellular phenotypes from perturbations using transfer learning, outperforming baselines and enabling in silico screening for therapeutic discovery.

Pretrained on 57 million dissociated and 53 million spatial human and mouse cells, a 49.3M-parameter transformer predicts niche, region, neighborhood composition and density, and carries spatial labels onto scRNA-seq.

This paper improves scRNA-seq dataset integration by introducing regularization strategies for cVAEs, enhancing batch correction while preserving biological variation.