I lead the automated machine learning research team at Microsoft Research in Cambridge, MA. Broadly speaking, we work on scalable probabilistic models to search through complex optimization spaces. My own research interests include Gaussian processes, Bayesian nonparametrics and scalable inference methods. In computational biology, I have worked on statistical methods to perform genome-wide association studies and predictive models for CRISPR/Cas9 gene editing.
Internships available! (apply by Dec 2018). If you are a PhD/MS student with a strong background in machine learning/stats/applied math/optimization and interested in an internship working on machine learning please apply here
Automated machine learning in Azure . Joint model selection and hyperparameter tuning as a service is now available in Azure as part of the Azure ML offering. More details on Microsoft’s AI blog and the Azure blog. Also see CNET’s story.
Microsoft Research podcast. I was recently interviewed for the Microsoft Research podcast. The recording is available here and wherever you get your podcasts.
New CRISPR off-target and end-to-end guide design paper :
The paper is now out in Nature Biomedical Engineering. You can also read about it in this Microsoft blog piece, Gizmodo, and Endgadget. This work complements our earlier on-target work published in Nature Biotechnology.
(legend: * = equal contributions, corresponding)
Gaussian Process Prior Variational Autoencoders
Francesco Paolo Casale, Adrian V Dalca, Luca Saglietti, Jennifer Listgarten, Nicolo Fusi
Probabilistic Matrix Factorization for Automated Machine Learning
Nicolo Fusi, Rishit Sheth, Huseyn Melih Elibol
to appear in NIPS, 2018
Prediction of off-target activities for end-to-end CRISPR guide design
J Listgarten, M Weinstein, B Kleinstiver, AA Sousa, JK Joung, J Crawford, K Gao, M Elibol, L Hoang, J Doench, N Fusi (equal contributions and co-corresponding)
Nature Biomedical Engineering, in press (2018)
Orthologous CRISPR–Cas9 enzymes for combinatorial genetic screens
F. J. Najm, C. Strand, K. F. Donovan, M. Hegde, K. R. Sanson, E. W. Vaimberg, M. E. Sullender, E. Hartenian, Z. Kalani, N. Fusi, J. Listgarten, S. T. Younger, B. E. Bernstein, D. E Root & J. G. Doench
Nature Biotechnology, 2017
Probabilistic Matrix Factorization for Automated Machine Learning
Nicolo Fusi, Huseyn Melih Elibol
Predicting off-target effects for end-to-end CRISPR guide design
J. Listgarten*, M. Weinstein*, M. Elibol, L. Hoang, J. Doench, N. Fusi*
Impact of pre-adapted HIV-1 transmission
J. M. Carlson, V. Y. Du, N. Pfeifer, A. Bansal, V. Y.F. Tan, K. Power, C. J. Brumme, A. Kreimer, C. E. DeZiel, N. Fusi, M. Schaefer, M. A. Brockman, J. Gilmour, M. A. Price, W. Kilembe, R. Haubrich, M. John, S. Mallal, R. Shapiro, J. Frater, P. R. Harrigan, T. Ndung’u, S. Allen, D. Heckerman, J. Sidney, T. M. Allen, P. J.R. Goulder, Z. L. Brumme, E. Hunter, P. A. Goepfert
Nature Medicine, 2016.
Leveraging Non-Linear Genetic Effects on Function-Valued Traits for GWAS
N. Fusi* and J. Listgarten*
Optimized sgRNA design to maximize activity and minimize off-target effects for genetic screens with CRISPR-Cas9
J. G. Doench*, N. Fusi*, M. Sullender*, M. Hegde*, E. W. Vaimberg, K. F.* Donovan, I. Smith, Z. Tothova, C. Wilen , R. Orchard , H. W. Virgin, J. Listgarten*, D. E. Root.
Nature Biotechnology, 2016.
Press: Microsoft Research blog post Broad Institute blog post
Platform presentation at the 2015 American Society of Human Genetics meeting.
In Silico Predictive Modelling of CRISPR/Cas9 Guide Efficiency
N. Fusi*, Ian Smith, John Doench, J. Listgarten*
Note: This pre-print has been largely (though not entirely) absorbed into the Nature Biotechnology paper above.
Further Improvements to Linear Mixed Models for Genome-Wide Association Studies
C. Widmer, C. Lippert, O. Weissbrod, N. Fusi, C. Kadie, R. Davidson, J. Listgarten, and D. Heckerman
Scientific Reports, 2014.
Warped Linear Mixed Models for the Genetic Analysis of Transformed Phenotypes.
N. Fusi, C. Lippert, N. D. Lawrence and O. Stegle.
Nature Communications, 2014.
EBI press release
Platform presentation at the 2014 American Society of Human Genetics meeting.
A genome-to-genome analysis of associations between human genetic variation, HIV-1 sequence diversity, and viral control.
István Bartha, Jonathan M Carlson, Chanson J Brumme, Paul J McLaren, Zabrina L Brumme, Mina John, David W Haas, Javier Martinez-Picado, Judith Dalmau, Cecilio López-Galíndez, Concepción Casado, Andri Rauch, Huldrych F Günthard, Enos Bernasconi, Pietro Vernazza, Thomas Klimkait, Sabine Yerly, Stephen J O’Brien, Jennifer Listgarten, Nico Pfeifer, Christoph Lippert, Nicolo Fusi, Zoltán Kutalik, Todd M Allen, Viktor Müller, P Richard Harrigan, David Heckerman, Amalio Telenti, Jacques Fellay.
Whole genome transcriptome analysis identifies indices of fast and slow disease progression in two mouse models of amyotrophic lateral sclerosis.
G. Nardo, R. Iennaco, N. Fusi, N. D Lawrence, M. Marino, P. Heath, L. Ferraiuolo, P. J Shaw, and C. Bendotti.
Gaussian Processes for Big Data.
J. Hensman, N. Fusi and N. Lawrence.
Proceedings of the 29th Conference on Uncertainty in Artificial Intelligence, 2013.
Detecting regulatory gene-environment interactions with unmeasured environmental factors.
N. Fusi, C. Lippert, K. Borgwardt, N. Lawrence and O. Stegle.
Unravelling the enigma of selective vulnerability in neurodegeneration: motor neurons resistant to degeneration in ALS show distinct gene expression characteristics and decreased susceptibility to excitotoxicity.
A. Brockington, K. Ning, P.R. Heath, E. Wood, J. Kirby, N. Fusi, N. Lawrence, S.B. Wharton, P.G. Ince, and P.J. Shaw.
Acta Neuropathologica, 2012.
Joint Modelling of Confounding Factors and Prominent Genetic Regulators Provides Increased Accuracy in Genetical Genomics Studies.
N. Fusi*, O. Stegle*, and N. D. Lawrence.
PLoS Computational Biology, 2012.
Finding topics in diseases through the analysis of RNA-seq data.
N. Fusi and N. Lawrence.
In 22nd Annual Workshop on Mathematical and Statistical Aspects of Molecular Biology, 2012.
Explaining Confounding Factors in eQTL Studies using a Dictionary of Latent Variables.
N. Fusi, O. Stegle, and N. Lawrence.
In NIPS workshop on Machine Learning in Computational Biology, 2010.
Intrusion Detection via Artificial Immune System: a Performance-based Approach.
A. Visconti, N. Fusi, and H. Tahayori.
Biologically-Inspired Collaborative Computing: IFIP 20th World Computer Congress, 2008.
Probabilistic Latent Variable Models in Statistical Genomics
Advisor: Prof. Neil D. Lawrence.
University of Sheffield, Sheffield, UK, 2014.