The official site for workshop MCBI 2015

1st workshop on Matrix Computations for Biomedical Informatics

June 20th, 2015, Pavia, Italy

To be held in conjunction with 15th Conference on Artificial Intelligence in Medicine (AIME 2015)


In the last decade, advances in high-throughput technologies, growth of clinical data warehouses, and rapid accumulation of biomedical knowledge provided unprecedented opportunities and challenges to researchers in biomedical informatics. One distinct solution, to efficiently conduct big data analytics for biomedical problems, is the application of matrix computation and factorization methods such as non-negative matrix factorization, joint matrix factorization, tensor factorization, principal component analysis (PCA), and singular value decomposition (SVD). Compared to probabilistic and information theoretic approaches, matrix-based methods are fast, easy to understand and implement. In recent years, matrix-based methods have been successfully adapted to many challenges in biomedicine, such as drug repositioning, drug-target interactions, and electronic phenotyping. 

This workshop will cover the application of matrix computational techniques in dealing with massive, high-dimensional, and nonlinear-structured biomedical data. The objectives of this workshop are:
  1. Bring together leading researchers on many topic areas (e.g., data miners, computational biologists, and healthcare professionals) to assess the state-of-the-art, share ideas, and form collaborations.
  2. Present recent advances in algorithms and methods using matrix and their potential applications in biomedical informatics and identify killer applications and key industry drivers (where theories and applications meet).
  3. Exploring benchmark data from real-world applications for better evaluation of the techniques.

Topics of Interest

Topic areas for the workshop include (but are not limited to) the following:

Methods and algorithms:
  • Linear, quadratic and semi-definite programming
  • Sparse and probabilistic matrix factorization
  • Low-rank kernel methods for matrix factorization
  • Tensor analysis
  • Higher-order SVD (e.g., CP decomposition, Tucker decomposition)
  • Deep learning
  • Collaborative filtering and recommender systems
  • PCA and SVD for clustering and dimension reduction
  • Spectral graph clustering
Application areas:
  • Drug discovery
  • Computational biology and bioinformatics
  • Clinical informatics
  • Health informatics

Workshop Organizers

Riccardo Bellazzi, PhD
Professor, Bioengineering and Medical Informatics
University of Pavia

Jimeng Sun, PhD
Associate Professor, Computational Science and Engineering
Georgia Institute of Technology

Ping Zhang, PhD
Research Staff Member, Healthcare Analytics
IBM T. J. Watson Research Center

Note: for inquiries please send e-mail to

Program Committee

  • Nitesh Chawla, University of Notre Dame
  • Mohamed Ghalwash, Temple University
  • Mehmet Gönen, Oregon Health & Science University
  • Assaf Gottlieb, Stanford University
  • Joyce Ho, The University of Texas at Austin
  • Jianying Hu, IBM T. J. Watson Research Center
  • Samuel Kaski, Aalto University
  • Yashu Liu, Arizona State University
  • Robert Moskovitch, Columbia University
  • Zoran Obradovic, Temple University
  • Niels Peek, University of Manchester
  • Chandan K. Reddy, Wayne State University
  • Gregor Stiglic, University of Maribor
  • Zhaonan Sun, IBM T. J. Watson Research Center
  • Fei Wang, University of Connecticut
  • Christopher C. Yang, Drexel University
  • Hao Ye, U.S. Food and Drug Administration
  • Jieping Ye, University of Michigan
  • Marinka Žitnik, University of Ljubljana
  • Blaž Zupan, University of Ljubljana

Important Dates

Paper Submission: May 15th, 2015 (Extended)

Notification of Acceptance: May 20th, 2015

Camera Ready Paper Due: June 1st, 2015

Workshop: June 20th, 2015

Submission Information

All submissions must be made electronically at .

Papers submitted to this workshop must not have been accepted or be under review by another conference with a published proceedings or by a journal. The work may be either theoretical or applied.

The workshop accepts short papers (up to 10 pages) and extended abstracts (up to 3 pages). Papers and extended abstract should be formatted according to Springer's LNCS format (see or ). All submissions must have an abstract with a maximum of 150 words and a keyword list with no more than 5 keywords.

All submissions should clearly present the author information including the names of the authors, the affiliations and the emails.

Workshop Schedule

June 20, Saturday
9:00 - 9:15 Opening
  Welcome by Workshop Organizers and Self-Introduction
  Organizers: Riccardo Bellazzi, Jimeng Sun, and Ping Zhang
9:15 - 10:15 Invited Talk I (slides)
  Learning Latent Factor Models by Data Fusion
  Speakers: Marinka Zitnik and Blaz Zupan
10:15 - 10:35 Paper 1 (slides)
  A Collaborative Filtering Approach to Predict Patient Future Disease Risk from Electronic Health Records
  Riccardo Miotto, Li Li, and Joel T. Dudley
10:35 - 10:55 Paper 2 (slides)
  Factorization Machines as a Tool for Healthcare: Case Study on Type 2 Diabetes Detection
  Ioakeim Perros, and Jimeng Sun
10:55 - 11:15 Coffee Break
11:15 - 12:00 Invited Talk 2 (slides)
  Matrix Computation in Precision Health and Wellness
  Speaker: Joel Dudley
12:00 - 12:20 Paper 3 (slides)
  A Bayesian Approach to Matrix Factorization for Data Fusion
  Andrea Demartini, and Riccardo Bellazzi
12:20 - 13:05 Invited Talk 3
  Structured Regression in Biomedical Evolving Networks
  Speaker: Zoran Obradovic
13:05 - 14:15 Lunch Break
14:15 - 14:35 Paper 4 (slides)
  Matrix Tri-Factorization for miRNA-Gene Association Discovery in Acute Myeloid Leukemia
  Andrea Demartini, Simone Marini, Francesca Vitali, and Riccardo Bellazzi
14:35 - 14:55 Paper 5 (slides)
  Precision Medicine on Cancer Treatment: A Joint Matrix Factorization Approach
  Ping Zhang, Filippo Utro, Fei Wang, Jianying Hu
14:55 - 15:30 Open discussion and closing
15:30 - 16:00 Final coffee time and networking

Invited Talks

Invited Talk 1
Title: Learning Latent Factor Models by Data Fusion
Speakers: Marinka Zitnik and Blaz Zupan

Abstract: In science and technology it has become common to gather data that describe systems from different perspectives at different levels of granularity. This gives rise to data sets that are represented in different input spaces. A bottleneck that prevents us from better understanding a system as a whole is identifying the kind of knowledge that can be transferred between related data views, entities and tasks. In many heterogeneous data settings, there exists some correspondence among input dimensions of different input spaces. We use this observation in design of factor models that share latent data representation between heterogeneous input spaces, multiple types of features and related predictive tasks. We have developed an interesting and accurate data fusion approach for predictive modeling, which reduces or entirely eliminates feature engineering steps that were needed in the past when inferring prediction models from disparate data. Our algorithms are capable of retaining the relational structure of a data system during model inference, which turns out to be vital for good performance of data fusion. This data fusion approach has helped us to predict gene functions, forecast pharmacological actions of small chemicals, prioritize genes for further studies, mine disease associations, detect drug toxicity, regress cancer patient survival data, and, more recently, infer cancer gene networks from many potentially non-identical data distributions.

Bio: Blaz Zupan is professor of computer science at University of Ljubljana and visiting professor at Baylor College of Medicine in Houston. His research focuses on methods for data mining and applications in bioinformatics and systems biology. Marinka Zitnik is currently working towards her PhD in computer science at University of Ljubljana. Her research interests include machine learning, optimization and matrix analysis.

Invited Talk 2
Title: Matrix Computation in Precision Health and Wellness 
Speaker: Joel T Dudley

Abstract: This talk will discuss how matrix computation can be applied to diverse clinical and molecular data towards enabling precision wellness and improved understanding of disease and drug response. The speaker will also discuss emerging and future opportunities to apply matrix computation to wearable sensors and digital health data streams towards applications in precision health and wellness.

Bio: Joel T Dudley is a bioinformatics and genomics researcher with more than 10 years of professional experience studying the genomic basis of species evolution and human disease. He has published more than 38 peer-review research articles pertaining to personal genomics, genomic medicine, pharmacogenomics, drug discovery, bioinformatics, and evolutionary genomics. Joel is currently the Director of Bioinformatics and Assistant Professor of Genetics and Genomics Sciences at Mount Sinai School of Medicine in New York. Joel earned a B.S. in Microbiology from Arizona State University and a Ph.D. in Biomedical Informatics from Stanford University.

Invited Talk 3
Title: Structured Regression in Biomedical Evolving Networks 
Speaker: Zoran Obradovic

Abstract: Node attributes and links in biomedical networks often evolve over time and are inextricably dependent on each other. In addition, the evolving network is partially observed, multiple kinds of links exist among nodes and various nodes have different temporal dynamics.  In this talk we will present an overview of the results of our ongoing DARPA GRAPHS big data project aimed to address some of these challenges by developing a structured regression model, which we have applied to predict admission and mortality rate for many diseases at a large number of hospitals.

Bio: Zoran Obradovic is a L.H. Carnell Professor of Data Analytics at Temple University, Professor in the Department of Computer and Information Sciences with a secondary appointment in Statistics, and is the Director of the Center for Data Analytics and Biomedical Informatics. He is the executive editor at the journal on Statistical Analysis and Data Mining, which is the official publication of the American Statistical Association and is an editorial board member at eleven journals. He is the chair at the SIAM Activity Group on Data Mining and Analytics and was co-chair for 2013 and 2014 SIAM International Conference on Data Mining and was the program or track chair at many data mining and biomedical informatics conferences. His work is published in more than 300 articles and is cited about 15,000 times (H-index 48). For more details see