Dare to Think
Home >Research>Centre For Biotech Data Science

Centre for Biotech Data Science


  • Prof. dr. Shodhan Rao
  • Prof. dr. Wesley De Neve
  • Manvel Gasparyan
  • Homin Park
  • Utku Ozbulak
  • Esla Timothy Anzaku
  • Azimberdy Besya
  • Espoir Kabanga
  • Negin Harandi
  • Mena Markos
  • Yunseol Park
  • Anju Susan Anish

About Us

The Center for Biotech Data Science pursues the development of new mathematical and computational approaches for extracting knowledge from huge sets of biotech data (e.g., biological sequence data and biomedical imagery), paying attention to technical challenges such as
  • predictive analysis and visualization of biotech data;
  • complexity reduction and validation of data-driven models for biotechnical processes and systems; and
  • interpretability and robustness of data-driven models for biotechnical processes and systems.
The newly developed approaches have a wide variety of applications, ranging from cancer research and medical image diagnosis over drug development to plant phenotyping.

Useful links


Current research topics include:
  • stability, model reduction and parameter estimation of biochemical reaction networks;
  • ecological species interaction networks and metapopulation models;
  • validity conditions for quasi steady state approximations;
  • representation learning for biological sequences;
  • interpretability for biological sequence and biomedical image analysis;
  • deep machine learning for structural and functional genome annotation;
  • deep machine learning for 3-D object understanding;
  • 3-D phenotyping of rice plants via computer vision and machine learning;
  • uncertainty and out-of-distribution modeling for deep machine learning; and
  • adversariality in deep machine learning.


Mathematics is often described as the "queen of science" because it has played an active role in the development of science and it has also benefited from its involvement in science. Particularly in bioscience engineering, there are many topics that cannot be mastered without a solid background in mathematics. Some of these topics are stability analysis and control of bioprocess plants, synthetic biology, computational and systems biology, modeling of bio-systems and chemical networks. Consequently, in our BSc programmes of Environmental Technology, Food Technology and Molecular Biotechnology, the mathematical education is quite rigorous and is on par with mathematical courses for other engineering programs like electrical, civil and aerospace engineering around the world. The program involves 3 compulsory mathematics courses and the student is expected to have had a good secondary/high school training in mathematics in order to cope up with the level of mathematics at Ghent University Global Campus. The three courses of Mathematics are

Mathematics 1: Engineering Mathematics (Ba1)

This is a yearlong course split into two semesters. In the first semester, basic high school topics are treated in depth in order to prepare the student for university level mathematics. The topics dealt with in the first semester are trigonometry, 2-dimensional co-ordinate geometry including straight lines and circles, basic algebra, 1-variable differential and integral calculus. In the second semester, some special topics in 1-variable calculus including applications of differentiation and integration in geometry and physics are dealt with along with an introduction to linear algebra including systems of linear equations, matrices, determinants, eigenvalues and eigenvectors. The focus of the course is mainly on the development of scientific skills such as analytical reasoning, critical reflection and problem-solving capability.

Mathematics 2: Multivariable Calculus and Geometry (Ba2)

This course continues further from Mathematics 1 dealing mainly with 2-D and 3-D coordinate geometry including vectors and multivariable calculus as the name suggests. While some emphasis is placed on understanding theoretical concepts, the students are also encouraged to face and solve real-life application-based problems. The course also lays the foundation for the mathematics that the students will encounter in other third year process-based courses including Process Modelling & Control and Process Engineering.

Mathematics 3: Differential Equations (Ba2)

Since most bioprocesses are modelled using ordinary and partial differential equations, the course Mathematics 3 gives a strong foundation on these two types of differential equations and the analytical methods for solutions of the two types of differential equations. Since not all differential equations can be solved using analytical methods, the last one-third part of the course deals with numerical solution techniques for solving ordinary differential equations. The students are trained in using Matlab software for solving first order initial value problems. The course also includes a brief introduction to Laplace transforms and the concept of equilibria of differential equations and their stability, which are later also studied in depth in the course Process Modelling & Control.

Next to the pure mathematical courses, the Center for Biotech Data Science is also responsible for providing a strong background in applied mathematics, informatics, statistics, and physics through the courses:

Physics 1 and 2: Mechanics, Vibration, Waves, and Thermodynamics (Ba1)

Physics is the study of an enormous span of natural phenomena ranging from the large-scale galaxies to the sub-microscopic entities in their static or dynamic states. Physicists pursue a fundamental understanding of the physical universe whereas engineers apply scientific knowledge to design and develop structures, machines and products. At Ghent University Global Campus, the Physics 1 and 2 course is designed to stitch together the skills of physicist and engineer to enable a deeper understanding of the engineering fundamentals through a broader understanding of physics in an engineering context. This course is an intensive course of study that emphasizes analytical and problem-solving skills. Physics 1 and 2 is a yearlong course aimed at providing the students a thorough training in basic physics, with a focus on both basic principles and practical applications. It further aims to make the students familiar with the practical applications of mechanics in everyday life, to establish an understanding of the various states of matter, to gain a working understanding of both physical and chemical thermodynamics, to learn with respect to physical aspects how to calculate the energy transfer of processes. The syllabus for the course has been carefully crafted to cater to the needs of students majoring in molecular biotechnology, food technology and environment technology.

Informatics (Ba1)

Scientists and engineers are often confronted with time-consuming and repetitive tasks when having to process and analyze data, namely collecting information from websites, converting files from one format to another, and analyzing, summarizing and visualizing the information obtained. In addition, the exponential flow of newly incoming information requires present-day scientists and engineers to be able to automate these tasks, in order to speed up their daily job routines.
This course teaches students how to describe time-consuming and repetitive tasks in such a way that they can be performed automatically by a (network-based) computer system. To that end, the necessary skills for computer-based creative problem solving will be acquired through learning to work and think in (1) Python, a popular programming language, and (2) in UNIX, the workhorse operating system of science and engineering. The computer problems that need to be solved are taken from different scientific disciplines, including mathematics, biology, chemistry, physics, and computer science.

Process Modelling and Control (Ba3)

The first part of the course deals with modelling of biosystems encountered in environmental engineering, food technology, ecology, chemical engineering, biotechnology and process industry. Students are taught how to use Matlab Simulink toolbox in order to model and simulate biosystems. Since no standard techniques are available for the analysis of nonlinear systems which are commonly encountered in practice, the course also includes techniques for linearization of nonlinear systems. The second part of the course deals with analysis of impulse, step and frequency response of first order and second order linear systems. The third and the final part of the course deals with techniques for design of feedback control that ensures bounded-input bounded-output (BIBO) stability of the controlled system. This part also deals with control of dead-time systems which are commonly encountered in real life applications.

Probability and Statistics (Ba3)

Statistics is the science that collects, analyses, and interprets numerical data, with as goal to summarize the data (descriptive statistics) or draw conclusions from them (statistical inference). Nowadays, every scientific field is confronted with large amounts of data, and thus plays an ever-increasing role in, e.g., drug development, climate research, or food quality control.
In this course, students are first introduced to probabilistic and statistical concepts. They learn to perform statistical techniques and to correctly describe and interpret statistical data and output. They also learn to distinguish between haphazard effects on the one hand and scientifically significant results on the other hand. Focus is also placed on critically reading and evaluating results presented in scientific literature.
The second part of the course continues where process modelling left off, namely with the simulation of dynamical (bio)systems. Different methodologies are discussed for model simulation, parameter estimation, and sensitivity analysis in order to come to a final model selection.
All theory is illustrated with ample examples. The statistical software R is used throughout the course.

Bioinformatics (Ba3 – major Molecular Biotechnology)

The field of bioinformatics was born after biologists discovered how to sequence (digitize) DNA, raising the need for mathematical and computational techniques to decipher the language of DNA, RNA, and proteins. As a result, bioinformatics has become an important part of modern biology, often facilitating new insights and new (data-driven) approaches, driving further biological developments.
Primarily taking a computational point-of-view, this course aims at introducing students to the design, implementation, and analysis of standard algorithms in the field of bioinformatics, including exhaustive search algorithms, recursive algorithms, divide and-conquer algorithms, greedy algorithms, graph algorithms, dynamic programming algorithms, machine learning algorithms (shallow and deep), and randomized algorithms. These algorithms and related datastructures (e.g., lists, tuples, sets, dictionaries, graphs, hash tables, and trees) are studied in the context of problems like pattern matching, genome rearrangements, DNA sequencing, DNA sequence alignment, regulatory motif finding, genome annotation (structural and functional), and/or medical image analysis.

Bachelor dissertations

  • 2019-2020
    Yeji Bae – A Deep Learning Approach Towards Detecting and Locating Trypanosoma Parasites in Microscopy Images of Thick Blood Smears
    Jongdo Im – Effects of Diffusion on the Coexistence of Species under Intransitive Competition
    Taewoo Jung – Automatic Detection of Trypanosomosis in Thick Blood Smear Images Using Deep Learning
    Hanul Kang – An Investigation of Class Activation Mapping for Visualizing Deep Learning-based Brain Tumor Classification
    Younsoo Kang – Parameter Estimation for Chemical Reaction Networks from Experimental Data of Reaction Rates
    Hayoung Kim – Automated Early Detection of Diabetic Retinopathy in Retinal Fundus Photographs using Deep Learning
    Yunseol Park – Translation Initiation Site Prediction in Arabidopsis thaliana Using Synthetic Datasets and Black-box Models
    Heesoo Song – Computer-aided Diagnosis of Trypanosomiasis Using Unstained Microscopy Images and Deep Machine Learning
  • 2018-2019
    Siho Han – Manual Feature Extraction and Extreme Gradient Boosting for Splice Site Detection
    Jeongtek Kim – Generating synthetic genomic datasets for the validation of convolutional neural network models
    Pyeong Eun Kim – Loss Function Visualization for Encoder-Decoder Style Deep Learning Models Targeting Biomedical Image Segmentation
    Ju Hyung Lee – Deep learning for disease symptom segmentation in medical images
    Woojin Lee – Computer Vision to Measure Cell Lengths in Rice Coleoptiles
  • 2017-2018
    Chananchida Sang-aram – Computer Vision in Plant Phenotyping: A Case Study for Automated Analysis of Rice Seedlings


Tenured Academic Staff

Wesley De Neve
+82 32-626-4204
Shodhan Rao
+82 32-626-4203

Assisting Academic Staff

Esla Timothy Anzaku
+82 32-626-4319 eslatimothy.anzaku(at)ghent.ac.kr
Azimberdy Besya
+82 32-626-4354
Manvel Gasparyan
+82 32-626-4328 manvel.gasparyan(at)ghent.ac.kr
Negin Harandi
+82 32-626-4317 negin.harandi(at)ghent.ac.kr
Espoir Kabanga
+82 32-626-4306 espoir.kabanga(at)ghent.ac.kr
Utku Ozbulak
+82 32-626-4330 utku.ozbulak(at)ghent.ac.kr
Ho-Min Park
+82 32-626-4326 homin.park(at)ghent.ac.kr
Anju Susan Anish
+82-32-626-4318 Anjususan.Anish@ghent.ac.kr

Teaching Assistant

Mena Markos
+82 32-626-4355


Yunseol Park

Former members

Mijung Kim
Breght Vandenberghe
Bayer Crop Science
Jasper Zuallaert
Vlaams Instituut voor Biotechnologie (VIB)
Arnout Van Messem
University of Liege
Surender Kumar
Nathan Muyinda
Makerere University, Kampala, Uganda

Contact details

Center director

Arnout Van Messem


Ghent University Global Campus
#935, 119-5 Songdomunhwa-ro, Yeonsu-gu
Incheon 21985
South Korea