David van Dijk PhD
Machine Learning & Computational Biology
I’m a postdoctoral fellow in the lab of Smita Krishnaswamy at Yale University in the departments of Genetics and Computer Science. My current research focuses on developing new machine learning methods, using graph signal processing and deep learning, for big biomedical data.
I co-developed the methods MAGIC and PHATE.
Previously, I worked with Eran Segal at the Weizmann Institute of Science, where I developed methods for predicting gene expression from DNA sequence.
I hold a Ph.D. in Computer Science, obtained under supervision of Jaap Kaandorp in the Computational Science group at the University of Amsterdam, and Eran Segal at the Weizmann Institute of Science.
Publications
van Dijk, David, S. Gigante, A. Strzalkowski, G. Wolf, and S. Krishnaswamy. Modeling dynamics of biological systems with deep generative neural networks. arXiv preprint arXiv:1802.03497 [to appear in 2019 International Conference on Sampling Theory and Applications (SampTA)]
A. Tong*, van Dijk*, David, J. S. S. III, M. Amodio, G. Wolf, and S. Krishnaswamy. Graph spectral regularization for neural network interpretability. arXiv preprint arXiv:1810.00424 [Accepted at ICLR 2019]
Scott Gigante, Jay S. Stanley III, Ngan Vu, David van Dijk, Kevin Moon, Guy Wolf, Smita Krishnaswamy. Compressed Diffusion. arXiv preprint arXiv:1902.00033 [to appear in 2019 International Conference on Sampling Theory and Applications (SampTA)]
van Dijk, David, R. Sharma, J. Nainys, K. Yim, P. Kathail, A. Carr, C. Burdziak, K. R. Moon, C. L. Chaffer, D. Pattabiraman, et al. Recovering gene interactions from single-cell data using data diffusion. Cell, 2018
van Dijk, David, E. Sharon, M. Lotan-Pompan, A. Weinberger, E. Segal, and L. B. Carey. Large-scale mapping of gene regulatory logic reveals context-dependent repression by transcriptional activators. Genome research, 27(1):87–94, 2017
K. R. Moon, J. Stanley, D. Burkhardt, van Dijk, David, G. Wolf, and S. Krishnaswamy. Manifold learning- based methods for analyzing single-cell rna-sequencing data. Current Opinion in Systems Biology, 2017
D. E. Lowther, B. A. Goods, L. E. Lucca, B. A. Lerner, K. Raddassi, van Dijk, David, A. L. Hernandez, X. Duan, M. Gunel, V. Coric, et al. Pd-1 marks dysfunctional regulatory t cells in malignant gliomas. JCI insight, 1(5), 2016
van Dijk, David, R. Dhar, A. M. Missarova, L. Espinar, W. R. Blevins, B. Lehner, and L. B. Carey. Slow- growing cells within isogenic populations have increased rna polymerase error rates and dna damage. Nature communications, 6:7972, 2015
L. Keren*, van Dijk*, David, S. Weingarten-Gabbay, D. Davidi, G. Jona, A. Weinberger, R. Milo, and E. Segal. Noise in gene expression is coupled to growth rate. Genome research, pages gr–191635, 2015
E. Sharon*, van Dijk*, David, Y. Kalma, L. Keren, O. Manor, Z. Yakhini, and E. Segal. Probing the e↵ect of promoters on noise in gene expression using thousands of designed sequences. Genome research, pages gr–168773, 2014
van Dijk, David, O. Manor, and L. B. Carey. Publication metrics and success on the academic job market. Current Biology, 24(11):R516–R517, 2014
L. B. Carey*, van Dijk*, David, P. M. Sloot, J. A. Kaandorp, and E. Segal. Promoter sequence determines the relationship between expression level and noise. PLoS biology, 11(4):e1001528, 2013
M. Dadiani, van Dijk, David, B. Segal, Y. Field, G. Ben-Artzi, T. Raveh-Sadka, M. Levo, I. Kaplow, A. Weinberger, and E. Segal. Two dna-encoded strategies for increasing expression with opposing effects on promoter dynamics and transcriptional noise. Genome Research, 2013
van Dijk, David, G. Ertaylan, C. A. Boucher, and P. M. Sloot. Identifying potential survival strategies of hiv-1 through virus-host protein interaction networks. BMC systems biology, 4(1):96, 2010
van Dijk, David, P. M. Sloot, J. Tay, M. C. Schut, et al. Individual-based simulation of sexual selection: A quantitative genetic approach. In ICCS, number 1, pages 2003–2011, 2010
S. Jaeger, G. Ertaylan, van Dijk, David, U. Leser, and P. Sloot. Inference of surface membrane factors of hiv-1 infection through functional interaction networks. PLoS One, 5(10):e13139, 2010
Preprint / In Review
K. R. Moon*, van Dijk*, David, Z. Wang*, D. Burkhardt, W. Chen, A. van den Elzen, M. J. Hirn, R. R. Coifman, N. B. Ivanova, G. Wolf, et al. Visualizing transitions and structure for high dimensional data exploration. bioRxiv [in revision at Nature Biotech], page 120378, 2019
M. Amodio*, van Dijk*, David, K. Srinivasan*, W. S. Chen, H. Mohsen, K. R. Moon, A. Campbell, Y. Zhao, X. Wang, M. Venkataswamy, A. Desai, R. V., P. Kumar, R. Montgomery, G. Wolf, and S. Krishnaswamy. Exploring single-cell data with deep multitasking neural networks. bioRxiv [in revision at Nature Methods], 2018
M. Amodio, van Dijk, David, R. Montgomery, G. Wolf, and S. Krishnaswamy. Out-of-sample extrapolation with neuron editing. arXiv preprint arXiv:1805.12198, 2018
W. S. Chen, N. Zivanovic, van Dijk, David, G. Wolf, B. Bodenmiller, and S. Krishnaswamy. Embedding the single-cell sample manifold to reveal insights into cancer pathogenesis and disease heterogeneity. bioRxiv, 2018 [In revision at Nature Methods]
D. B. Burkhardt, J. S. Stanley, A. L. Perdigoto, S. A. Gigante, K. C. Herold, G. Wolf, A. Giraldez, D. van Dijk*†, and S. Krishnaswamy*†. Enhancing experimental signals in single-cell rna-sequencing data using graph signal processing. bioRxiv:532846, 2019
David van Dijk, D. Burkhardt, M. Amodio, A. Tong, G. Wolf, and S. Krishnaswamy. Finding archetypal spaces for data using neural networks. arXiv:1901.09078, 2019 [Submitted to ICML 2019]