Research

We work at the intersection of statistics, machine learning and genomics. We are driven by the desire to understand and quantify how spatial patterns emerge from local rules in the context of biological dynamical systems, with implications in basic science, ecology and disease. See some of our most recent publications below.

2022

Hypergraph factorisation for multi-tissue gene expression imputation

Ramon Viñas, Chaitanya K. Joshi, Dobrik Georgiev, Bianca Dumitrascu, Eric R. Gamazon, Pietro Liò

Cold Spring Harbor Laboratory  ·  08 Aug 2022

multi-tissue imputationdeep learning

Link

MarkerMap: nonlinear marker selection for single-cell studies

Nabeel Sarwar, Wilson Gregory, George A. Kevrekidis, Soledad Villar, Bianca Dumitrascu

arXiv:2207.14106 [cs, q-bio, stat]  ·  28 Jul 2022

interpretabilitydeep learningscRNA-seq

Dimensionless machine learning: Imposing exact units equivariance

Soledad Villar, Weichi Yao, David W. Hogg, Ben Blum-Smith, Bianca Dumitrascu

arXiv  ·  02 Apr 2022

data augmentationinvarianceecologysymbolic regression

Preprint

Power analysis for spatial omics

Ethan A. G. Baker, Denis Schapiro, Bianca Dumitrascu, Sanja Vickovic, Aviv Regev

Cold Spring Harbor Laboratory  ·  31 Jan 2022

spatial transcriptomics

Preprint

2021

Deep learning for bioimage analysis in developmental biology

Adrien Hallou, Hannah G. Yevick, Bianca Dumitrascu, Virginie Uhlmann

Development  ·  07 Sep 2021

imagingdeep learning

Link

Optimal marker gene selection for cell type discrimination in single cell analyses

Bianca Dumitrascu, Soledad Villar, Dustin G. Mixon, Barbara E. Engelhardt

Nature Communications  ·  19 Feb 2021

interpretabilityscRNA-seq

Link

Approximate Latent Force Model Inference

Jacob D. Moss, Felix L. Opolka, Bianca Dumitrascu, Pietro Lió

arXiv  ·  01 Jan 2021

latent force modelsgene regulatory networksdynamical systems

Link