Tomasz  Arodz, Ph.D. profile photo

Tomasz Arodz, Ph.D.

Associate Professor, Graduate Program Director

Engineering East Hall, Room E4252, Richmond, VA, UNITED STATES

tarodz@vcu.edu

Dr. Arodz's research focuses on machine learning and bioinformatics

Social

Biography

Tomasz Arodz is an assistant professor in the Department of Computer Science at Virginia Commonwealth University. Dr. Arodz holds a Ph.D. in computer science from AGH University of Science and Technology in Krakow, Poland. He is a laureate of the Prime Minister of Poland Award for his Ph.D. dissertation. Dr. Arodz also holds a M.Sc. in biotechnology from Jagiellonian University in Krakow.

Industry Expertise

  • Computer Software
  • Education/Learning
  • Health and Wellness
  • Writing and Editing

Areas of Expertise

Machine Learning: Nonlinear Classification Methods That Incorporate Existing Knowledge Into TrainingSystems Biology: Integration of Prior Biological Knowledge and Multiple Sources of Data for Pathway DiscoveryComputational Biology: Analysis of Role of Protein Mutations in Evolution and DiseasePattern Recognition and Machine Learning in BiomedicineProtein EvolutionComplex Biological NetworksBioinformatics

Accomplishments

Prime Minister of Poland Award | professional

Laureate of the Award for Ph.D. Dissertation

2008-01-01

Foundation for Polish Science | professional

Laureate of the Young Researcher Stipend

2006-01-01

Education

Jagiellonian University

M.S., Biotechnology

2009

AGH University of Science and Technology

Ph.D., Computer Science

2007

AGH University of Science and Technology

M.S., Computer Science

2003

Media Appearances

To Relieve Holiday Stress, Techies Trot Out Artificial Intelligence

Style Weekly  print

2017-12-19

By now the journey to 2018 can feel more like a crawl than a mad dash. There's pressure to entertain family, reconnect with old friends and take that special someone on a memorable date. But a Richmond startup says artificial intelligence can solve the indecision over where to go and what to do. While some experts caution against placing exaggerated faith in artificial intelligence, early adopters are hoping for a more perfect holiday experience. . . . Just remember, if you're struggling to plan a not-so-silent night, don't give up on your gut, says Tom Arodz, another VCU professor who studies machine learning. "AI may learn to never recommend a symphony to heavy-metal lovers," Arodz says. "But just like with human instinct, it is often difficult to say why any particular recommendation is made."

view more

Selected Articles

Computational Science – ICCS 2008 | Lecture Notes on Computer Science

2008

view more
Ensemble of Linear Models for Predicting Drug Properties | Journal of Chemical Information Models

2006

We propose a new classification method for the prediction of drug properties, called random feature subset boosting for linear discriminant analysis (LDA). The main novelty of this method is the ability to overcome the problems with constructing ensembles of linear discriminant models based on generalized eigenvectors of covariance matrices. Such linear models are popular in building classification-based structure-activity relationships. The introduction of ensembles of LDA models allows for an analysis of more complex problems than by using single LDA, for example, those involving multiple mechanisms of action. Using four data sets, we show experimentally that the method is competitive with other recently studied chemoinformatic methods, including support vector machines and models based on decision trees. We present an easy scheme for interpreting the model despite its apparent sophistication. We also outline theoretical evidence as to why, contrary to the conventional AdaBoost ensemble algorithm, this method is able to increase the accuracy of LDA models.

view more
Computational Methods in Developing Quantitative Structure-Activity Relationships (QSAR): A Review | Combinatorial Chemistry & High Throughput Screening

2006

Virtual filtering and screening of combinatorial libraries have recently gained attention as methods complementing the high-throughput screening and combinatorial chemistry. These chemoinformatic techniques rely heavily on quantitative structure-activity relationship (QSAR) analysis, a field with established methodology and successful history. In this review, we discuss the computational methods for building QSAR models. We start with outlining their usefulness in high-throughput screening and identifying the general scheme of a QSAR model. Following, we focus on the methodologies in constructing three main components of QSAR model, namely the methods for describing the molecular structure of compounds, for selection of informative descriptors and for activity prediction. We present both the well-established methods as well as techniques recently introduced into the QSAR domain.

view more