Vincent Cabeli

Bidirectional Mamba2 plant genomic language models (318M to 3.2B parameters) trained on 320 land-plant genomes top a 22-task frozen-model aggregate; a small variant reaches 131,072 bp context.

This study identifies the pentose phosphate pathway's role in regulating myeloid versus lymphoid lineage specification in hematopoietic stem and progenitor cells through metabolic state-fate mapping.

BOTANIC-0 models are plant genomic foundation models pretrained on diverse plant genomes, achieving competitive performance in genomic tasks like variant effect prediction.

This study benchmarks batch integration methods for spatial transcriptomics using a cancer atlas, finding probabilistic methods excel in batch correction while graph-based methods perform better in spatial conservation.

CausalXtract identifies causal effects in live-cell imaging data by combining network and information-based frameworks, revealing novel interactions in tumor-on-chip systems.

This study uses deep learning to predict YAP1/TEAD activity from histology slides, linking histological patterns to disease aggressiveness in cancer patients.

This study evaluates deep learning-based representation methods for survival and gene essentiality prediction on bulk RNA-seq data, finding that non-DL methods perform comparably on survival tasks while DL methods excel in gene essentiality prediction.

PyDESeq2 provides a Python implementation of DESeq2 for bulk RNA-seq differential expression analysis, offering improved precision and performance on large datasets like TCGA.