Tommi Suvitaival

Email:

tommi.suvitaival@alumni.aalto.fi

I completed my doctoral degree in November 2014, after which this page is no longer updated. For up-to-date information, please check my profiles elsewhere and contact via tommi.suvitaival@alumni.aalto.fi.

• My profile at Google Scholar
• My profile at LinkedIn

About Me

I worked at the Statistical Machine Learning and Bioinformatics Group, supervised by Prof. Samuel Kaski.

The topic of my research was Bayesian Multi-Way Models for Data Translation in Computational Biology. This included the development of machine learning methods for (1) finding similarities between humans and model organisms in terms of diseases and their treatments at the molecular level, and (2) the generalization of the outcome of novel treatments from model organisms to humans.

In my previous works, I developed methods for the analysis of high-dimensional metabolomic data arising from multiple sources. I was involved with the Tekes-funded Transcendo and Multibio projects, and the Academy of Finland-funded ChemBio project. I was a member of the FICS doctoral programme. In 2012, funded by the Finnish Foundation for Technology Promotion and FICS, I visited University of Glasgow to work with Dr. Simon Rogers.

Publications

• Stronger findings for metabolomics through Bayesian modeling of multiple peaks and compound correlations
  Tommi Suvitaival, Simon Rogers, and Samuel Kaski
  Bioinformatics, 30(17):i461-i467, 2014 (ECCB'14).
  (abstract, citation, HTML, implementation, PDF)
• Stronger findings from mass spectral data through multi-peak modeling
  Tommi Suvitaival, Simon Rogers, and Samuel Kaski
  BMC Bioinformatics, 15:208, 2014.
  (abstract, implementation, PDF)
  
• Cross-organism toxicogenomics with group factor analysis
  Tommi Suvitaival, Juuso A. Parkkinen, Seppo Virtanen, and Samuel Kaski
  Systems Biomedicine, 2:e29291, 2014.
  (abstract, implementation, PDF)
• Cross-species translation of multi-way biomarkers
  Tommi Suvitaival, Ilkka Huopaniemi, Matej Orešič, Samuel Kaski
  In Timo Honkela et al., editors, Artificial Neural Networks and Machine Learning - ICANN 2011, volume 6791 of Lecture Notes in Computer Science, pages 209-216. Springer Berlin / Heidelberg, 2011.
  (abstract, citation, PDF)
• Graphical multi-way models
  Ilkka Huopaniemi, Tommi Suvitaival, Matej Orešič, Samuel Kaski
  In José Balcázar et al., editors, Machine Learning and Knowledge Discovery in Databases, volume 6321 of Lecture Notes in Computer Science (ECML PKDD 2010), pages 538-553. Springer Berlin / Heidelberg.
  (abstract, citation, PDF)
• Multivariate multi-way analysis of multi-source data
  Ilkka Huopaniemi, Tommi Suvitaival, Janne Nikkilä, Matej Orešič, Samuel Kaski
  Bioinformatics, 26(12):i391-i398, (ISMB) 2010.
  (abstract, citation, HTML, PDF)
• Two-way analysis of high-dimensional collinear data
  Ilkka Huopaniemi, Tommi Suvitaival, Janne Nikkilä, Matej Orešič, Samuel Kaski
  Data Mining and Knowledge Discovery, 19(2):261-276, (ECML PKDD) 2009.
  (abstract and citation, PDF, talk)

Conference and workshop presentations

• Cross-organism prediction of drug hepatotoxicity by sparse group factor analysis
  Tommi Suvitaival, Juuso A. Parkkinen, Seppo Virtanen, Samuel Kaski
  In 12th Annual International Conference on Critical Assesment of Massive Data Analysis (CAMDA), 2013
  Extended abstract
  (citation, conference page, PDF, presentation slides)
• Predicting malt quality from barley gene expression
  Tommi Suvitaival, Annika Wilhelmson, Jussi Gillberg, Jari Rautio, Oona Rechardt, Alan Schulman, Jaakko Tanskanen, Ulla Holopainen, Esko Pajunen, Pekka Reinikainen, Anneli Ritala
  In 34th International Congress of the European Brewery Convention (EBC), 2013
  Poster
  (available upon request, conference page)
• Detecting similar high-dimensional responses to experimental factors from human and model organism
  Tommi Suvitaival, Ilkka Huopaniemi, Matej Orešič, Samuel Kaski
  In NIPS 2011 Workshop "From Statistical Genetics to Predictive Models in Personalized Medicine", 2011
  Extended abstract
  (PDF, talk, workshop page)
• Multi-way, multi-view learning
  Ilkka Huopaniemi, Tommi Suvitaival, Janne Nikkilä, Matej Orešič, Samuel Kaski
  In NIPS 2009 Workshop on Learning from Multiple Sources with Application to Robotics, 2009
  Extended abstract
  Presented by Ilkka Huopaniemi
  (citation, PDF, talk, workshop page)

Invited talks

• IDI Seminar
  Inference, Dynamics and Interaction group, University of Glasgow
  Probabilistic ANOVA-type analysis for mass-spectrometry peak data
  Tommi Suvitaival, Simon Rogers, Samuel Kaski
  December 2012
  (abstract, group webpage)
• QBIX Seminar
  Quantitative Biology and Bioinformatics group, VTT Technical Research Centre of Finland
  Cross-species translation of experiments
  Tommi Suvitaival, Matej Orešič, Samuel Kaski
  September 2011

Software

• PeakANOVA
  An R-package for inferring covariate effects from multiple mass spectral peaks
  (package)

• multiWayCCA
  An R-package for multivariate multi-way analysis of multi-source data
  (citation, package)

Theses

• Bayesian multi-way models for data translation in computational biology
  Tommi Suvitaival
  Supervisor: Samuel Kaski
  Doctoral Dissertation, Aalto University, 2014.
  (electronic dissertation, presentation slides, press releases in English and in Finnish)
• Bayesian two-way analysis of high-dimensional collinear metabolomics data
  Tommi Suvitaival
  Instructor: Ilkka Huopaniemi
  Supervisor: Samuel Kaski
  Master's Thesis, Helsinki University of Technology, 2009.
  (abstract and citation, database entry, PDF, presentation slides)
• Optiset mikrokaviteetit
  Tommi Suvitaival
  Supervisor: Jukka Tulkki
  Bachelor's Thesis, Helsinki University of Technology, 2008.