New: I currently have an opening position for a Master's student in computer science with strong profile in mathematics. Prospective studends must have background in computer science (B.Cs Hons in computer science or equivalent) and broad and deep knowledge of linear algebra, probability theory, algorithms and optimization. Knowledge of dynamic programming is an asset. Interested prospective students shall contact me indicating in the subject of their email, their intent to be considered for this position. See further details about Master's Students below.
I currently have opening positions for undergraduate, Master's and PhD students. Partial financial support is available from the School of Computer Science and the Faculty of Science, in terms of scholarships and teaching assistatnships. Research assistatnships are currently available for outstanding PhD students only. Prospective students at all levels are encouraged to contact me about my short and long-term research projects in shallow and deep machine learning at the fundamental level and with applications to protein-protein interaction and dynamics, transcriptomics, microRNA prediction, integrative genome-wide analysis, and identification of cancer biomarkers.
The main topics for theses and projects are in foundations of shallow and deep machine learning and applications in genomics, interactomics, and transcriptomics, mostly in cancer biomarkers. Projects include, but not limited to, algorithms for multi-level thresholding, non-linear dimensionality reduction, graph representation learning, graph neural networks, and others. Applications include protein-protein interaction and dynamics, transcriptomics, microRNA prediction, integrative genome-wide analysis, multi-omics data analysis, single-cell RNA-Seq data analysis, and discovery of cancer biomarkers.
Problems in protein-protein interaction involve discovering new domains and short-linear motifs related to the interactions between proteins and other molecules, and also those interactions and motifs related to the dynamics of the interactome, as well as Calmodulin-binding proteins. Problems in transcriptomics involve analysis of next generation sequencing data, including ChIP-seq and single-cell RNA-seq data for discovering biomarkers in different types of cancer, and the role of alternative splicing, protein interactions and pathways.
At the PhD level, I am looking for students who are strong on algorithm design and analysis, lineal algebra and probability, and willingness to learn on quickly changing topics in the foundations of machine learning, and applications in interactomics and transcriptomics data analysis, including ChIP-seq, RNA-seq data analysis, big genomic data analysis, protein-protein interaction, dynamics of proteins, and Calmodulin-binding proteins, among others. Prospective students must demonstrate independence and creativity in conducting research. Knowledge of Python, Matlab and/or R, and machine learning tools like Scikit-learn/TensorFlow is desirable. Knowledge of foundations of machine learning is a requirement, while bioinformatics is optional.
Notes: Please consider the following guidelines about funding. Note that these numbers are given as a guideline and for reference purposes only, and may change over time and/or be outdated by the time you read this page. Please consider the following notes before contacting me for a position.
At the Master's level, I am looking for enthusiastic, self-motivated, research-oriented students to work in the foundations and applications of machine learning and applications in protein-protein interaction, ChIP-seq/RNA-seq data analysis, alternative splicing, and identification of biomarkers in breast and prostate cancer, among others. The use of supervised and unsupervised machine learning techniques and/or statsitcial and visualization approaches is important.
Deep knowledge of Python, R and/or Matlab, and machine learning tools like Scikit-learn/TensorFlow (or serious willingness to learn) is required. Knowledge or willingness to learn machine learning/bioinformatics techniques is a requirement.
Notes: At present, positions for Master's are not open for Master's students who want to pursue the Co-op stream. Currently, only exceptional prospective students are being considered at the Master's level.
I am looking for enthusiastic, self-motivated undergraduate students who possess excellent analytical and programming skills, while being willing to accept challenges and engage in machine learning research problems in data analytics for genomics, transcriptomics, proteomics and interactomics data, with applications to biomarker discovery in cancer and other diseases. Feel free to contact me for more details about these projects.
Knowledge of Python, Script language, HTML, PhP, Joomla, R and/or Matlab, and machine learning tools like Scikit-learn/TensorFlow (or serious willingness to learn) is required). Willingness to learn machine learning techniques and fundamental concepts in bioinformatics, while improving their algorithm design and analysis skills is also a requirement. I normally have several short-term and mid-term projects in these fields. Feel free to contact me for more details or present your own ideas.