Guillaume Obozinski

Clone-level multi-modal prediction of tumour drug response

This paper introduces scClone2DR, a framework predicting tumour drug response at the clone level using single-cell DNA/RNA sequencing and drug-screening data, showing improved accuracy in identifying clonal sensitivities and resistance.

Ensemble learning and ground-truth validation of synaptic connectivity inferred from spike trains

This paper introduces an ensemble artificial neural network (eANN) to improve neuronal connectivity inference from spike trains, showing it outperforms existing methods across different dynamical regimes.

A Graph Matching Approach to Tracking Neurons in Freely-Moving C. elegans

This paper introduces a graph matching method to track neurons in freely-moving C. elegans, achieving over 75% accuracy with five labeled frames.

Profiling drug sensitivity of leukemic stem cells via bulk-to-single-cell deconvolution

The paper develops a machine learning framework to estimate cell subtype-specific drug sensitivity from bulk data, applying it to leukemia datasets to identify potential therapeutic targets.