19^th conference on
Computational Intelligence methods for Bioinformatics and Biostatistics

Authors are encouraged to submit a short paper (4-6 pages) outlining their original contributions within one of the main conference tracks (Bioinformatics, Biostatistics, and Medical Informatics) or one of the eleven special session tracks (topics and chairs detailed below). During the review process, papers may be reassigned to different tracks if deemed more suitable by the reviewers and chairs. Each paper will undergo the same rigorous peer review process, with a minimum of two reviewers. In cases of uncertainty or differing opinions, a third reviewer will provide additional evaluation.

Reviewers are tasked with assessing the submission's quality for potential oral presentation, suggesting minimal adjustments for the conference presentation, and identifying areas for potential expansion for extended submissions, due after the conference (Tentative date, October 2024). The aim is to facilitate authors in promptly initiating work on expanding their papers for consideration in LNCS or Journal supplement publications.

In October 2024, the program committee will reconvene to evaluate the significant revisions made to submitted papers. Together with the chairs, they will select papers to be invited for journal supplements, while the remaining papers will be published in the LNCI proceedings of the conference.

Paper awards

This year, we're organizing a best paper award. Details will follow, stay tuned! All accepted papers will be eligible for consideration. Authors of the winning paper will be awarded during the social dinner (or welcome reception) and the paper will be automatically selected for the submission to a journal supplement.

Key dates

Short paper templates

• Latex CIBB 2024
• Libre Office/Word CIBB 2024
• Overleaf

Main Research Tracks

• Bioinformatics

  Expand

Topics of interest include, but are not limited to:

• Applications of machine learning to bioinformatics or health datasets
• Data mining methods in biomedical contexts
• Artificial intelligence in biomedicine
• Next-generation sequencing bioalgorithms
• Multi-omics data analysis
• Statistical analysis of high-dimensional omics data
• Algorithms for alternative splicing analysis
• Methods for visualization of high-dimensional biomedical data
• Software tools for bioinformatics
• Methods for comparative genomics
• Computational tools for proteomics
• Simulation of biological systems and clinical populations
• Methods for the functional classification of genes
• Algorithms for molecular evolution and phylogenetic analysis
• Methods for unsupervised analysis, validation, and visualization of structures discovered in bio-molecular data
• Health informatics and medical informatics
• Biomedical and microscopy imaging
• Methods for the integration of clinical, genetic, or environmental data
• Heterogeneous data integration and data fusion
• Algorithms for pharmacogenomics
• Biomedical text mining and natural language processing
• Bayesian methods for medical and biological data
• Health big data analytics
• Data-driven approaches for patient stratification, and prognosis or onset prediction
• Process mining in healthcare
• Information retrieval, and temporal and spatial representation and reasoning in biomedicine
• Simulation models, software, and tools (clinical decision support systems, patient engagement support, visual analytics, solutions for assisted living, and telemedicine)
• Biomedical signal processing
• Explainable AI and clinical model interpretation
• Personalised medicine for diagnosis and prognosis
• Statistical methods for the analysis of clinical data
• Prediction of secondary and tertiary protein structures
• Advanced pathway enrichment analysis methods
• Mass spectrometry data analysis in proteomics
• Bio-molecular databases and data mining
• Mathematical modelling and automated reasoning on biological and synthetic systems
• Computational simulation of biological systems
• Methods and advances in systems biology
• Spatio-temporal analysis of synthetic and biological systems
• Network systems biology
• Models for cell populations and tissues
• Methods for the engineering of synthetic components
• Modelling and engineering of interacting synthetic and biological systems
• Software tools for bioinformatics, biostatistics, systems and synthetic biology
• Computational drug discovery
• Operational research in healthcare and bioinformatics

Chair

• Annalisa Occhipinti, Teesside University, UK

• Biostatistics

  Expand

Topics of interest include, but are not limited to:

• Statistical analysis of high-dimensional omics data
• Methods for comparative genomics
• Health informatics and medical informatics
• Bayesian methods for medical and biological data
• Health big data analytics
• Data-driven approaches for patient stratification, and prognosis or onset prediction
• Statistical methods for the analysis of clinical data
• Advanced pathway enrichment analysis methods

Chair

• Cheng Lu, Aalto University, Finland

• Medical Informatics

  Expand

Topics of interest include, but are not limited to:

• Artificial intelligence in biomedicine
• Health informatics and medical informatics
• Biomedical and microscopy imaging
• Methods for the integration of clinical, genetic, or environmental data
• Heterogeneous data integration and data fusion
• Biomedical text mining and natural language processing
• Health big data analytics
• Information retrieval, and temporal and spatial representation and reasoning in biomedicine
• Simulation models, software, and tools (clinical decision support systems, patient engagement support, visual analytics, solutions for assisted living, and telemedicine)
• Explainable AI and clinical model interpretation
• Personalised medicine for diagnosis and prognosis
• Process mining in healthcare
• Computational drug discovery
• Operational research in healthcare and bioinformatics

Chair

• Francesco Bardozzo, University of Salerno, Italy

Special session tracks

• Computational Intelligence in Personalized Medicine

  Expand

Increased life expectancies and the expectation of universal medical care provision in modern societies clash with the increasing costs of meeting those challenges. The promises of Personalized Medicine (PM) may become wishful thinking unless they deliver on cost efficiency. The most promising avenue to deliver on such efficiency is the use of data science approaches. The use of data-centred Computational Intelligence (CI) methods is becoming an important tool in healthcare and medical applications for providing enhanced diagnosis and prognosis tailored to the patient's characteristics and needs. Data-intensive assays, widespread sensorization and big data technologies enable the capturing and sharing of increasingly larger amounts of biomedical data, which need to be exploited through computational analysis in order to discover meaningful patterns in data. CI methods, including machine learning in general (and deep learning in particular) as well as other soft computing approaches are at the forefront of efficient complex medical and omics data analysis. In this special session, we call for new research on applications that, using CI approaches, can provide efficient solutions for the development of PM applications based on biomedical and bioinformatics data.

Topics of interest include, but are not limited to:

• Applications of personalized medicine based on CI methods
• Biomedical pattern recognition using machine learning for PM
• Data-intensive biomedical assays
• Biomedical data sharing and harmonization
• Regulation of CI-based medical devices Interpretable, explainable and transparent CI methods for PM

Chairs

• Caroline König, Universitat Politècnica de Catalunya, UPC Barcelona Tech, Spain
• Alfredo Vellido, Universitat Politècnica de Catalunya, UPC Barcelona Tech, Spain

• Natural language processing (NLP) and large language models (LLM) for unstructured data in health informatics

  Expand

Natural Language Processing (NLP) combines linguistics and computer science and empowers building Artificial Intelligence (AI) solutions able to comprehend, interpret, and generate human language. In recent years, it has had various applications also in medical applications. NLP impacts many clinical key areas such as clinical documentation and EHR analysis where it assists in automating the extraction of relevant information from clinical notes useful for diagnosis, drawing information on treatments and prescriptions, identifying adverse events, and summarising patient histories. NLP can also be combined with medical imaging technologies (with the use of Large Language Models for example) to extract information from radiology reports, pathology reports, and other imaging-related documents facilitating image interpretation, automating report generation, and improving communication between radiologists, pathologists, and other healthcare professionals. Furthermore, NLP also finds a place in health monitoring and surveillance where it can analyze text data from sources such as social media, online forums, and electronic health records to monitor public health trends, detect disease outbreaks, and track the spread of infectious diseases helping public health agencies and so that healthcare providers respond more effectively to emerging health threats. This session mainly focuses on exploring NLP and LLM models in the context of healthcare. The ability to extract information to interpret and analyse the history of the patients is critical to increasing the prediction on time of the diagnosis and recommendations to provide to medical staff, for this reason, NLP techniques can be created with this specific goal: to provide more information to be analysed by AI solutions. The goal is for artificial intelligence models to become a useful and reliable tool that helps in decisions and treatment of pathologies. Finally, the purpose of this special session is to bring together global professionals, industry leaders, and specialists involved in evaluating, creating, and using explainability methodologies in healthcare.

Topics of interest include, but are not limited to:

• ML/DL based Natural Language Processing applied to Clinical assessment, exams, and health processes
• Natural Language Inference in Diagnostics
• Natural Language inference in Clinical assessment
• Knowledge Extraction and Information Analysis
• Natural Language Generation
• Large Language Models applied to Healthcare fields

Chairs

• Lerina Aversano, University of Foggia, Department of Agricultural Science, Food, Natural Resources and Engineering, Italy
• Antonella Madau, University of Sannio, Engineering Departments, Italy
• Debora Montano, Regional Center Information Communication Technology (CeRICT), Italy
• Chiara Verdone, University of Sannio, Engineering Departments, Italy

• Informatics research in bioinformatics: contributions from the CINI-InfoLife network

  Expand

The national CINI (Consorzio Interuniversitario Nazionale di Informatica) InfoLife laboratory promotes networking initiatives among researchers with an informatics background who conduct relevant research in bioinformatics, and related topics, together with their international partners. Italy is an important source, and partner, in providing computational approaches for any aspect of the bioinformatic field, from the development of baseline specialized algorithms and data structures to the implementation of high-level data analysis and visualization. This special session, building on the success of last year's event at CIBB2023, aims to once again provide an insightful overview of current research and future perspectives in bioinformatics conducted by Italian research institutes of Informatics and their partners. In addition, we are pleased to announce that this year's session will also feature contributions from the National Biodiversity Future Center (NBFC).

Topics of interest include, but are not limited to:

• Computational transcriptomics and spatial transcriptomic data analysis
• Singe-cell omics
• Multi-omics data analysis and models
• Computational pangenomics
• High-performance computing for omics data
• Algorithms and data structures for bioinformatics
• Knowledge management in bioinformatics and medical informatics
• Drug development and pharmacovigilance
• Artificial intelligence and machine learning in bioinformatics
• Advanced technique for bio-medical content visualization
• Bio-inspired computing for bioinformatics
• Computational modeling and omics data

Chairs

• Vincenzo Bonnici, Department of Mathematical, Physical, and Computer Sciences, University of Parma, Italy
• Simone Pernice, Computer Science Department, University of Turin, Italy
• Giacomo Baruzzo, Department of Information Engineering, University of Padova, Italy
• Bruno Galuzzi, Institute of Bioimaging and Molecular Physiology (CNR-IBFM), Italy
• Mikele Milia, University of Padova, Italy
• Leonardo Pellegrina, Department of Information Engineering, University of Padova, Italy
• Roberto Pagliarini, Department of Mathematics, Computer Science and Physics, University of Udine, Italy

• Machine learning for structured data in clinical informatics and medical biology

  Expand

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 formulate accurate predictions about similar or future data instances. For example, machine learning software has been able to predict the diagnosis of oncological 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 aims at boosting these scientific fields, calling for researchers able to show the potential and the advances of machine learning algorithms, in making accurate computational predictions in health care datasets and in patient-oriented biological datasets.

Topics of interest include, but are not limited to:

• Machine learning methods applied to health care and biomedical datasets
• Machine learning methods applied to genetics and epigenomics datasets, to understand the conditions of healthy and/or sick patients
• Machine learning methods applied to biological datasets to understand the underlying biomolecular scenario
• Machine learning software and tools in the health care and biological domains
• Statistical models to analyze health care, biomedical, and biological datasets
• Data mining applications in the health care and biological domains

Chairs

• Davide Chicco, Università di Milano-Bicocca, Italy
• Giuseppe Jurman, Fondazione Bruno Kessler, Italy
• Giuseppe Agapito, Università Magna Graecia di Catanzaro, Italy
• Wei Liu, Fujian Agriculture and Forestry University, China
• Matthijs Warrens, Rijksuniversiteit Groningen, the Netherlands

• Advancements in Biological Network Analysis

  Expand

In biology, networks have become powerful models for understanding the intricate relationships between various molecular entities. With the proliferation of high-throughput biological data together with the latest advancements in spatial biology, the analysis of molecular networks has emerged as a central focus for bioinformatics research, allowing to facilitate the modelling of always more complex experiments. Networks offer a versatile framework for representing patterns of interaction across diverse biological systems, ranging from gene regulation to cellular signaling or cellular spatial organization. Co-expression, co-methylation, protein-protein interaction, and cell-cell interaction networks, among others, have become essential tools for deciphering the complexities of biological processes.

Topics of interest include, but are not limited to:

• Single-cell transcriptomics network modelling.
• Networks in spatial transcriptomics.
• Computational methods for constructing and analyzing biological networks.
• Multiomics data integration via network.
• Network-based approaches for studying gene regulation, protein-protein interactions, and signaling pathways.
• Applications of network analysis in disease research and drug discovery.

Chairs

• Annamaria Carissimo IAC/CNR Naples, Italy
• Dario Righelli Department of Electric Engineer and Technology Information, University of Naples Federico II, Naples, Italy
• Valeria Policastro University of Naples Federico II, Naples, Italy

• Uncertainty in deep learning applications

  Expand

To prevent wrong predictions of a Neural Network, we need to better understand and/or visualize the confidence of each individual prediction. For this reason, we ask the community, what happen if a model must predict an out-of-distribution sample in an open-world scenario? In other words, how a model defines a certain in-distribution (test data is assumed to be drawn from the training data), to detect an out-of-distribution event. In fact, a model can cause prediction failures due to its blindness and poor awareness. Moreover, it conveys high confident in its correctness, which can be problematic for wide range of applications, such as for healthcare applications. For instance, standard metrics for the evaluation of Deep Learning models measure overall model performance on a limit test dataset and provide no indication of the model confidence in the correctness of an individual prediction of new samples. That can result in prediction failure, when a model is faced with out-of-distribution data. Therefore, we should question our self. How can we detect and visualize unknown unknowns? The scope of this special session is to ask the research community how they measure out-of-distribution samples and how we can better predict out-of-distribution samples in the future.

Topics of interest include, but are not limited to:

• Prediction uncertainty in Health informatics
• Methods for the visualisation of out-of-distribution samples
• Out-of-distribution recognition
• Metrics for model evaluation and sample prediction
• Unknown sample prediction techniques
• Mathematical modelling of out-of-distribution recognition
• Open-set versus closed-set recognition
• Application of out-of-distribution recognition
• Explainable AI
• Methods for active learning

Chairs

• David Dannhauser, University of Naples (Federico II), Italy
• Pasquale Memmolo, Istituto di Scienze Applicate e Sistemi Intelligenti 'Eduardo Caianiello', Italy

• Statistical modelling and machine learning to support cancer research

  Expand

Statistical modelling (SM) and Machine learning (ML) are nowadays the main tools to improve the understanding the pathophysiological mechanisms underlying diseases, in particular in the area of cancer research. The aim of this session is to combine ML and statistical models to offers several capabilities in handling high-dimensional data and to provide clarity, simplicity and reliability in complex problems. Therefore, the approaches behind SM and ML is mandatory to comprehend the fundamental principles upon which it is possible to set up more complicated real-life systems. Moreover, the purpose of this session is to create a discussion for researchers in order to present new concepts for finding solutions to challenges in cancer research for prevention, early detection, prognosis and to support clinical decision making.

Chairs

• Antonella Iuliano, Department of Mathematics, Computer Science and Economics (DIMIE), University of Basilicata, Italy
• Monica Franzese, Istituto di Ricovero e Cura a Carattere Scientifico nell'area di ricerca della Diagnostica (IRCCS SYNLAB SDN), Naples, Italy

• Modeling and simulation methods for computational biology and systems medicine

  Expand

Computational biology is a field that involves the analysis of biological systems at various levels of complexity, using appropriate modeling frameworks and computational methods. With the advancement of computational biology approaches and modeling systems, the current challenge is to employ these techniques to define personalized models that identify tailored drugs and therapies, thus realizing the personalized medicine paradigm. The aim of this special session is to bring together researchers who are working on the development of methods and models applied in the fields of computational biology and systems medicine to facilitate the exchange of knowledge and ideas in these innovative and fundamental research areas. The workshop will be sponsored by InfoLife CINI National Laboratory (https://www.consorzio-cini.it/index.php/en/) and by the National Biodiversity Future Center (NBFC) (https://www.nbfc.it/).

Topics of interest include, but are not limited to:

• Parameterization and verification of biomedical models
• Modeling neural activity
• Individual-aware models to assess the impact of genetic variation on cellular regulatory network
• Cancer progression models
• Epidemiological models
• Multiscale models and simulation of biological systems
• Space-temporal models and simulation of biological systems
• Robustness of cellular networks
• Emergent properties in complex biological systems
• Metabolic and signaling pathways analysis and engineering
• Genetic variants impact on epigenetic elements
• Models for personalized and targeted therapies
• Patient classification and stratification
• Drug combination, repositioning and recommendation for personalized medicine
• Clinical data integration into systems biology models
• Single-cell and spatial transcriptomics analysis

Chairs

• Simone Avesani, University of Verona, Italy
• Marco Beccuti, University of Turin, Italy
• Vincenzo Bonnici, University of Parma, Italy
• Chiara Damiani, University of Milano-Bicocca, Italy
• Bruno Giovanni Galuzzi, CNR, Italy
• Rosalba Giugno, University of Verona, Italy
• Gospel Ozioma Nnadi, University of Verona, Italy
• Simone Pernice, University of Turin, Italy
• Michele Tebaldi, University of Verona, Italy
• Manuel Tognon, University of Verona, Italy
• Eva Viesi, University of Verona, Italy

• Translational medical informatics and data privacy protection

  Expand

With the development of large language models and their increasing application in the healthcare sector, the issues of translational medical informatics and data privacy protection have become particularly important. Large language models have shown great potential in processing and analyzing large-scale biomedical datasets to assist clinical decision-making and research. However, this also comes with the risk of sensitive health information leakage. Translational medical informatics is dedicated to transforming biomedical discoveries into practical clinical applications, involving a wide range of information types from genomic data to electronic health records. Therefore, implementing effective data privacy protection measures is key to ensuring personal information security, maintaining patient trust, and promoting scientific progress. In designing and applying large language models and other data analysis tools, data privacy must be considered from the outset, adopting a comprehensive strategy to protect personal privacy without hindering medical knowledge advancement. This includes, but is not limited to, the use of encryption technologies, anonymizing data, and implementing strict data access controls. Additionally, transparency and explainability are equally important in this process; researchers, clinicians, and ultimately the patients should be able to understand how data are processed and used in the decision-making process. To balance the needs of privacy protection with medical research and clinical applications, new technological and policy frameworks need to be developed.

Topics of interest include, but are not limited to:

• Application of Large Language Models in Translational Medical Informatics
• Data Privacy Protection in the Era of Large Language Models and Artificial Intelligence
• The Role of Artificial Intelligence in Disease Prediction and Prevention
• Improving Patient Experience and Treatment Outcomes with Big Data and Artificial Intelligence
• Interdisciplinary Integration and Innovative Applications of Large Language Models
• Genomic Medicine Informatics and Artificial Intelligence
• Large Models in Digital Medicine and Health Management
• Modern Hospital Management and Artificial Intelligence
• Translational Medical Informatics in Health Education and Talent Cultivation
• Digital Twin, Brain-Computer Interface, Metaverse, and Future Medicine

Chairs

• Bairong Shen, Sichuan University, China
• Silvana Quaglini, University of Pavia, Italy
• Mauro Giacomini, University of Genoa, Italy
• Gabriella Balestra, Politecnico di Torino, Italy
• Shuaicheng Li, City University of Hong Kong, Hong Kong

• Graph Neural Networks for Biological Data

  Expand

With their ability to capture structures and relationships in various domains, graphs are a powerful tool for real-world data analysis. Graph Neural Networks have been conceived to integrate graphs with the computational capability of neural architecture, and they have proven to be versatile models suitable for various computational problems. These include, but are not limited to, node classification, link prediction, and graph prediction. The adaptability of GNNs is particularly noteworthy, as they can handle information that does not adhere to traditional grid-like structures. This adaptability is a critical feature that sets GNNs apart and makes them powerful tools for supervised and unsupervised classification problems. Recently, by leveraging the power of deep learning, these models have become increasingly famous for their capability to represent and analyse biological data. With their ability to model complex interactions, they are well-suited, for instance, in the fields of protein structure prediction, drug discovery, gene expression analysis, sequence classification, and medical image processing. The main objective of this special session is to provide a forum for the presentation and discussion of original papers and the latest methods, including GNN, in the context of biological data processing.

Chairs

• Domenico Amato, University of Palermo, Department of Mathematics and Computer Science, Italy
• Salvatore Calderaro, University of Palermo, Department of Mathematics and Computer Science, Italy
• Filippo Vella, National Research Council of Italy, Institute for High Performance Computing and Networking, Italy

• Computational Structural Bioinformatics

  Expand

Structural Bioinformatics plays a crucial role in many fields such as macromolecule structure and function prediction, identification of potential drug targets, understanding protein-protein/DNA/RNA interactions, predicting the effect of mutations on macromolecule function, and studying the relationship between dynamics and function. The scope of this special session is to bring together researchers from various disciplinary backgrounds involved in structural bioinformatics of Proteins, RNAs and Complexes to facilitate the integration of different research areas. We welcome the presentation of preliminary ideas or results of ongoing active studies.

Topics of interest include, but are not limited to:

• Structure representation, prediction, and comparison
• Pattern recognition, clustering and classification
• Interaction and docking
• Sequence-structure functional relationships
• Molecular dynamic simulations
• Biomolecular graphics
• Coarse-grained modeling and simulations
• Data mining and machine learning of structural data
• Structure-based drug design
• Data mining and process mining applications in structural bioinformatics
• Artificial intelligence and machine learning in structural bioinformatics

Chairs

• Michela Quadrini, University of Camerino, Italy
• Luca Tesei, University of Camerino, Italy
• Alexander Miguel Monzon, University of Padua, Italy

Ready to submit?

Submission will be opened soon... stay tuned!