CIBB2018 will host the following Special Sessions:

COMPUTATIONAL METHODS FOR NEUROIMAGING ANALYSIS 

MACHINE LEARNING IN HEALTH INFORMATICS AND BIOLOGICAL SYSTEMS 

SOFT COMPUTING METHODS FOR CHARACTERIZING DISEASES FROM OMICS DATA 

ENGINEERING BIO-INTERFACES AND RUDIMENTARY CELLS AS A WAY TO DEVELOP SYNTHETIC BIOLOGY

MODELING AND SIMULATION METHODS FOR SYSTEMS BIOLOGY AND SYSTEMS MEDICINE

FAST AND EFFICIENT SOLUTIONS FOR COMPUTATIONAL INTELLIGENCE METHODS IN BIOINFORMATICS, SYSTEMS AND COMPUTATIONAL BIOLOGY

NETWORKING BIOSTATISTICS AND BIOINFORMATICS

MACHINE EXPLANATION – INTERPRETATION OF MACHINE LEARNING MODELS FOR MEDICINE AND BIOINFORMATICS 

---

COMPUTATIONAL METHODS FOR NEUROIMAGING ANALYSIS 

Aim and scope

There is an increasing need for the application of machine learning (ML) techniques which can perform image processing operations such as segmentation, coregistration, classification and dimensionality reduction in the field of neuroimaging. Although the manual approach often remains the golden standard in some tasks (like segmentation), ML can be utilised to automate and facilitate the work of researchers and clinicians. Frequently used techniques include support vector machines (SVMs) for classification problems, graph-based methods for brain network analysis and recently artificial neural networks (ANNs). 

Deep ANNs, i.e. deep learning, have proved to be very successful in computer vision tasks owing to the ability to automatically extract hierarchical descriptive features from input images. It has also been used in the medical and neuroimaging domains for automatic disease diagnosis, tissue segmentation and even synthetic image generation. The issue, however, is the relative sample paucity in typical neuroimaging datasets which leads to poor generalisation considering the high number of parameters employed in typical deep neural networks. Consequently, parameter- efficient design paradigms ought to be created. 

Another approach to investigate degeneration is the study and mapping of the neural connections in the brain known as the connectome. The connectome can be seen as a matrix representing all possible pairwise connections between different neural areas. Researchers study both the structural and functional connectivity in order to understand important brain patterns, such as how the connectome impacts the dynamics of disease spreading, ageing and learning. 

Topics of interest includes but are not limited to: 

• Machine learning techniques for segmentation, coregistration, classification or dimensionality reduction of neuroimages 


• Deep learning for neuroimaging analysis 


• Brain network analysis 


• Applications of graph theory to MRI and fMRI data 


• Applications of machine learning methodologies for neurodegenerative disease studies 


• Computational modelling and analysis of neuroimaging 


• Methods of analysis for structural or functional connectivity 


• Development of new neuroimaging tools

 

Session chairs

Tiago Azevedo, University of Cambridge, UK

Giovanna Maria Dimitri, University of Cambridge, UK

Pietro Liò, University of Cambridge, UK

Angela Serra, University of Salerno, Italy

Simeon Spasov, University of Cambridge, UK

MACHINE LEARNING IN HEALTH INFORMATICS AND BIOLOGICAL SYSTEMS 

Aim and scope

Machine learning has become a pivotal tool to analyze biomedical and biological datasets, especially in the Big Data era. In fact, machine learning algorithms can identify hidden relationships and structures in health care data, and even take advantage of them to make accurate predictions about similar or future data instances. For example, machine learning software has been able to predict the diagnosis of tumor patients just by processing patients’ clinical features, allowing scientists to save time and money compared to wet lab experiments. Computational researchers have also exploited machine learning to infer knowledge about patients by analyzing biological datasets, especially the ones featuring genetics and epigenomic traits. Data mining approaches applied to such datasets, in fact, can lead to relevant discoveries both to understand molecular biology and to gain new knowledge about patients’ diseases. 

Our special session on “Machine learning in health informatics and biological systems” aims at boosting these scienti c elds, calling for researchers able to show the potential and the advance of machine learning algorithms to make accurate computational predictions in health care datasets and in patient- oriented biological datasets. 

Topics of interest include, but are not limited to:

• ML methods applied to health care and biomedical datasets 


• ML methods applied to genetics and epigenomics datasets, to
understand the conditions of healthy and/or sick patients 


• ML methods applied to biological datasets to understand the underlying biomolecular scenario 


• ML software and tools in the health care and biological domain 


• Statistical models to analyze health care, biomedical, and biological datasets 


• Data mining applications in the health care and biological domain 


Session chairs

Davide Chicco, Princess Margaret Cancer Centre, Toronto, Ontario, Canada 


Marco Masseroli, Politecnico di Milano, Milan, Italy


Annalisa Barla, Università di Genova, Genoa, Italy 


Anne-Christin Hauschild, Krembil Research Institute, Toronto, Ontario, Canada

SOFT COMPUTING METHODS FOR CHARACTERIZING DISEASES FROM OMICS DATA 

Aim and scope

In modern biomedical research, high-throughput technologies, such as the next generation sequencing, produces huge data sets. High-throughput data are collected in the broad context of genomics, epigenomics, transcriptomics and proteomics. From these data, it is possible to explain the pathogenesis or predict the predisposition and/or the clinical outcome of several human diseases, among which psychiatric, cardiovascular, obesity, aetiology of a number of diseases such as cancer, schizophrenia, and Alzheimer, just to name a few. The identification of new strategies for processing and analyzing such kind of data is becoming more and more necessary since their large amount of data can sometimes represent a real obstacle to effectively identify the most relevant patterns and to build comprehensive models capable of explaining complex biological phenotypes. The aim of the special session is to host original papers and reviews on recent research advances and the state-of-the-art methods in the fields of Soft Computing, Machine Learning and Data Mining methodologies concerning with the processing of omics data in order to shed light about the relationship between genotype and disease-related phenotype. 

Topics of interest include, but are not limited to:

• Machine learning 


• Sparse Coding 


• Data Mining 


• Fuzzy and Neuro-Fuzzy Systems 


• Probabilistic and statistical modelling 


• OMICs in the context of genomics, epigenomics, transcriptomics and proteomics 


• Evaluation of protein folding and/or protein-ligand interactions (where ligands are 
proteins, DNA, RNA and small molecules), also in the context of genetic variation 


• Identification of potential gene regulatory elements (i.e., binding of transcription factors, 
miRNAs, etc.) 


• Analysis of common genetic variants (i.e., SNPs, HLA genotypes, microsatellites) 


• Analysis of experimental data from next-generation sequencing 


• Analysis of gene expression data 


• Biomedical applications 


Session chairs

Angelo Ciaramella, Università di Napoli Parthenope, Italy 

Giosuè Lo Bosco, Università di Palermo, Italy

Riccardo Rizzo, ICAR-CNR, Italy 

Antonino Staiano, Università di Napoli Parthenope, Italy


ENGINEERING BIO-INTERFACES AND RUDIMENTARY CELLS AS A WAY TO DEVELOP SYNTHETIC BIOLOGY

Aims and scope

The bioengineering has been fundamental in both regenerate medicine and the understanding of biochemical mechanisms involved in life appearance and maintenance. The aim of this special session is to bring together theoretical researchers interested in cutting-edge methods to address the challenges posed by the huge amount of data produced in omics sciences and in application to systems and synthetic biology and experimental researchers with interests on develop experimentally new approaches of synthetic biology for biomedical and biotechnological applications like implants, artificial organs, advanced medical systems, drug delivery systems and sensors. The track of this SS aims to present latest experimental advancements concerning synthetic biology. Relevant topics within this context include, but are not limited to:

• physical interactions between biological molecules, 

• effect of radiation and plasma in biological tissues,

• cell-nanomaterials interactions, 

• molecular aspects of membrane assembly and transport, 

• communication between cells, 

• biosensors at micro and nanoscales, 

• drug delivery systems, 

• liposomes and encapsulation of molecules, 

• synaptic transmission, 

• artificial organs and contractile systems.

Session chairs

Maria Raposo, Universidade Nova de Lisboa

Quirina Ferreira, Universidade de Lisboa

Paulo A. Ribeiro, Universidade Nova de Lisboa

Susana Sério, Universidade Nova de Lisboa

MODELING AND SIMULATION METHODS FOR SYSTEMS BIOLOGY AND SYSTEMS MEDICINE

Aim and scope

Systems Biology deals with the analysis of natural systems at different scales of complexity, by means of proper modeling frameworks and computational methods. Given that Systems Biology approaches are becoming well established, the challenge is now to apply the developed techniques towards the definition of personalized models in order to identify individually tailored drugs and treatments; i.e. to realize the Personalized Medicine paradigm. The scope of this special session is to bring together researchers involved in the development of methods applied to the fields of Systems Biology and Systems Medicine.

Topics of interest include, but are not limited to:

• analysis of robustness of cellular networks 


• biomedical model parameterization

• cancer progression models

• clinical image analysis

• emergent properties in complex biological systems 


• flux balance analysis 


• metabolic engineering 


• metabolic pathway analysis 


• model verification and refinement methods 


• models of neural activity

• multi¬scale modelling and simulation of biological systems 


• parameter estimation methods

• personalized models

• reverse engineering of reaction networks 


• software tools for systems biology 


• spatio¬temporal modelling and simulation of biological systems

 

Session chairs

Chiara Damiani, University of Milano-Bicocca, Italy

Marco S. Nobile, University of Milano-Bicocca, Italy

Riccardo Colombo, University of Milano-Bicocca, Italy

Giancarlo Mauri, University of Milano-Bicocca, Italy

Alex Graudenzi, University of Milano-Bicocca, Italy

Marzia Di Filippo, University of Milano-Bicocca, Italy

Dario Pescini, University of Milano-Bicocca, Italy

FAST AND EFFICIENT SOLUTIONS FOR COMPUTATIONAL INTELLIGENCE METHODS IN BIOINFORMATICS, SYSTEMS AND COMPUTATIONAL BIOLOGY

Aims and Scopes 

The aim of this special session is to bring together researchers involved in the definition, enhancement and application of computational intelligence and machine learning techniques accelerated by means of fast and efficient implementations. In particular, this session will focus on the challenges in the implementation of computational intelligence methods that exploit data parallelism, model parallelism, large-scale parameter searches, high performance computing solutions, etc. 

Topics of interest include, but are not limited to: 

●  Applications of machine learning exploiting HPC solutions 


●  Machine learning models, including deep learning, for large scale systems 


●  Enhancing the applicability of machine learning techniques in HPC 


●  Learning of large scale models 


●  Optimization methodologies for large scale models 


●  Training machine learning models on large datasets 


●  Tackling the problems of large datasets (e.g. noisy labels, missing data) 


●  Large scale machine learning applications 


●  Machine learning for Image analysis 


●  HPC solutions for Bioinformatics and Systems Biology 


●  Evolutionary techniques 


 

Session chairs

Stefano Beretta, University of Milano-Bicocca, Italy


Paolo Cazzaniga, University of Bergamo, Italy


Ivan Merelli, Institute for Biomedical Technologies, National Research Council, Italy 


NETWORKING BIOSTATISTICS AND BIOINFORMATICS

Aim and Scope 

Biostatistics and bioinformatics are considered and perceived as different disciplines, with the former being more associated with complex math and modeling issues and the latter dealing more with the development of faster and efficient algorithms within an informatics and engineering approach. In practice, they are strongly interrelated sharing common interest in learning from biological data and understanding complex biological processes.

The goal of the session is to encourage a “data driven” approach aimed at developing appropriate models that provide new insights into the biomedical problem.  Since, in the big data era, the biomedical data turns out to be complex and multivariate, robust and computationally efficient statistical tools are needed to investigate complex dependencies within data structure.

In this spirit, the special session will be devoted to both theoretical advances and applications of statistical methods for the analysis of high-dimensional genetic/omics data.

Topics of interest includes but are not limited to: 

• Expert Systems and Bayesian Networks

• Graphical models

• Multivariate techniques for dimensionality reduction

• Latent class (mixed) modelling

Session chairs 

Clelia Di Serio, Vita-Salute San Raffaele University, Milano, Italy

Cugnata Federica, Vita-Salute San Raffaele University, Milano, Italy

--------------------------

Tutorials and Special Session proposals: 25 March 2018 

Special Session proposals, including the session's title and scope, short CV of sessions chairs, preliminary list of at least 4, possibly more, potential authors are due by 25th March 2018. Proposals of special sessions will be evaluated as soon as they are submitted. A special session is expected to have at least 4 accepted papers. Please send proposals to cibb2018@campus.fct.unl.pt