Ph.D. in Computer Science, Cornell University

Tri-Institutional Fellow in Computational Biology and Medicine

Google Scholar

Recent

• (Nov 2018) Introduction to Amazon SageMaker Object2Vec
• (Oct 2018) Amazon SageMaker Neural Topic Model now supports auxiliary vocabulary channel, new topic evaluation metrics, and training subsampling

Papers

• Patrick Ng (2017). dna2vec: Consistent vector representations of variable-length k-mers. arXiv:1701.06279
• A Chaiboonchoe, Patrick Ng*, et al. (2016) Systems level analysis of the Chlamydomonas reinhardtii metabolic network reveals variability in evolutionary co-conservation.Molecular BioSystems.
• Chun Nin Wong, Patrick Ng*, Angela E Douglas. (2011) Low-diversity bacterial community in the gut of the fruitfly Drosophila melanogaster. Environmental Microbiology.
• Patrick Ng, Uri Keich. (2010) Alignment Constrained Sampling. Journal of Computational Biology, 18(2): 155-168. RECOMB on Regulatory Genomics.
• Patrick Ng, Uri Keich. (2008) GIMSAN: A Gibbs motif finder with significance analysis. Bioinformatics, 24 (19): 2256-2257.
• Patrick Ng, Uri Keich. (2008) Factoring local sequence composition in motif significance analysis. Genome Informatics 21:15-26. International Conference on Genome Informatics (GIW), Gold Coast Australia.
• Uri Keich, Patrick Ng. (2007) A conservative parametric approach to motif significance analysis. Genome Informatics 19:61-72. International Conference on Genome Informatics (GIW), Singapore.
• Patrick Ng, Niranjan Nagarajan, Neil Jones, Uri Keich. (2006) Apples to apples: improving the performance of motif finders and their significance analysis in the Twilight Zone. Bioinformatics 22 (14): e393-e401. International Conference on Intelligent Systems for Molecular Biology (ISMB).
• Niranjan Nagarajan, Patrick Ng, Uri Keich. (2006) Refining motif finders with E-value calculations. RECOMB on Regulatory Genomics.

[* co-first author contribution]

Software

• dna2vec - Consistent vector representations of variable-length k-mers
• GIMSAN - software for motif-discovery equipped with a practical and reliable statistical significance analysis.
• ALICO - Alignment Constrained null set generator: a framework to generate randomized versions of an input multiple sequence alignment that preserve some of its crucial features including its dependence structure.
• GibbsILR - motif-finder that optimizes for the incomplete likelihood ratio (ILR)