- Departmental Early Career Fellow
- This person is no longer active in the department.
I develop statistical and computational methods to characterize the interplay between morphology and genomics in the early development of organisms.
Biography
Previously, I was a Member in the School of Mathematics at the Institute for Advanced Study (IAS).
I received my PhD in Computational Biology from Princeton University. Before that, I did my undergraduate
studies at MIT where I earned a B.S. in Mathematics.
Research
My long term goal is understanding how single cells aggregate temporal and spatial, chemical and physical
information to make decisions about their identity, and how these decisions can be altered through optimal
perturbations and experimental design. Informed by both experiment and theory,
I am interested in interpretable and principled techniques, deep and shallow alike, with roots in
hypothesis testing, domain adaptation, representational learning, and active learning.
Current research directions and projects include:
* interpretable dimensionality reduction, linear and non-linear, for single cell gene expression studies
* multi-modal models of morphology, gene expression and epigenetics for the study of the early mouse embryo
* experimental design of combinatorial perturbations
* statistics of organic pattern formation and synchronization phenomena
* interpretable models for multi-agent trajectory prediction
Themes
Professional Activities
Invited Talks and Seminars
- Eliciting structure in genomics data, Institute for Mathematical and Statistical Innovation, Chicago, USA, 2021
- Data Science Lunch Seminar Series, NYU Data Science, NYC, USA, 2021
- The Computer Science & Engineering Department Seminar, University of Connecticut, Storrs, CN, USA, 2021
- Department of Statistics & Actuarial Science Seminar, University of Hong Kong, Hong Kong, 2021
- Models, Inference, and Algorithms Seminar, Broad Institute of MIT and Harvard, Boston, MA, USA, 2018
- Probabilistic Modeling in Genomics, Oxford University, Oxford, UK, 2016
- New York Area Population Genomics Workshop, NYC, USA, 2015
Publications
[* equal contribution]
[♦ corresponding author, co-corresponding authors]
Peer-reviewed (Journal & Conferences)
- [new!] Deep learning for bioimage analysis in developmental biology
Adrien Hallou, Hannah G. Yevick, ♦Bianca Dumitrascu, ♦Virginie Uhlmann
Development 15 September 2021; 148 (18): dev199616, doi: https://doi.org/10.1242/dev.199616 - Optimal marker gene selection for cell type discrimination in single cell analyses
Bianca Dumitrascu*, Soledad Villar*, Dustin G Mixon, Barbara E Engelhardt
Nature communications 12 (1), 1-8, https://doi.org/10.1038/s41467-021-21453-4 - Causal Network Inference from Gene Transcriptional Time Series Response to Glucocorticoids
Jonathan Lu*, Bianca Dumitrascu*, Ian C McDowell, Brian Jo, Alejandro Barrera, Linda K. Hong,Sarah M. Leichter, Timothy E. Reddy, Barbara E. Engelhardt
PLOS Computational Biology, 2021, https://doi.org/10.1371/journal.pcbi.1008223 - Sparse multi-output Gaussian processes for online medical time series prediction
Li-Fang Cheng, Bianca Dumitrascu, Gregory Darnell, Corey Chivers, Michael E Draugelis, Kai Li, and Barbara E Engelhardt
BMC Medical Informatics and Decision Making 20.1 (2020): 1-23, https://doi.org/10.1186/s12911-020-1069-4 - Nonparametric Bayesian multi-armed bandits for single cell experiment design
Federico Camerlenghi*, Bianca Dumitrascu*, Federico Ferrari*, Barbara E. Engelhardt, Stefano Favaro
Annals of Applied Statistics, 2020 - Patient-Specific Effects of Medication Using Latent Force Models with Gaussian Processes
Li-Fang Cheng, Bianca Dumitrascu, Michael Zhang, Corey Chivers, Michael Draugelis, Kai Li, Barbara E Engelhardt
AISTATS 2020 - netNMF-sc: leveraging gene–gene interactions for imputation and dimensionality reduction insingle-cell expression analysis
Rebecca Elyanow, Bianca Dumitrascu, Barbara E Engelhardt, and Benjamin J Raphael
Genome Research 30: 195-20, 2020; RECOMB 2019 - End-to-end training of deep probabilistic CCA for joint modeling of paired biomedical observations
Gregory Gundersen, Bianca Dumitrascu, Jordan T. Ash, Barbara E. Engelhardt
UAI 2019 - PG-TS: Improved Thompson Sampling for Logistic Contextual Bandits
Bianca Dumitrascu*, Karen Feng*, and Barbara E Engelhardt
NeurIPS 2018 - Statistical tests for detecting variance effects in quantitative trait studies
Bianca Dumitrascu, Gregory Darnell, Julien Ayroles, and Barbara E Engelhardt
Bioinformatics, 2018 - BIISQ: Bayesian nonparametric discovery of Isoforms and Individual Specific Quantification from RNA-seq data
Derek Aguiar, Li-Fang Cheng, Bianca Dumitrascu, Fantine Mordelet, Athma Pai, and Barbara E Engelhardt
Nature Communications, 9(1), 2018
Preprints
- Sequential Gaussian Processes for Online Learning of Nonstationary Functions
Michael Minyi Zhang, Bianca Dumitrascu, Sinead A. Williamson, Barbara E. Engelhardt - GT-TS: Experimental design for maximizing cell type discovery in single-cell data
Bianca Dumitrascu, Karen Feng, and Barbara E Engelhardt - Sparse Multi-Output Gaussian Processes for Medical Time Series Prediction
Li-Fang Cheng, Gregory Darnell, Bianca Dumitrascu, Corey Chivers, Michael E Draugelis, Kai Li, and Barbara E Engelhardt
