ICBRA 2024

Keynote Speaker

Prof. FangXiang Wu

University of Saskatchewan, Canada

Biography: Dr. FangXiang Wu is currently a full professor in the Departments of Computer Science, and the College of Engineering at the University of Saskatchewan. His research interests include Artificial Intelligence, Machine/Deep Learning, Computational Biology, Health Informatics, Medical Image Analytics, and Complex Network Analytics. Dr. Wu has published about 360 journal papers and more than 130 conference papers. His total google scholar citations are over 15300, h-index is 63. He is among top 2% world’s scientists ranked by Stanford University. Dr Wu is serving as the editorial board member of several international journals (including IEEE TCBB, Neurocomputing, etc.) and as the guest editor of numerous international journals, and as the program committee chair or member of many international conferences. He is an IEEE senior member and a recipient of many awards such as University of Saskatchewan Distinguished Research awards, IEEE BIBM Outstanding Service Awards, etc..

Speech title: "Artificial Intelligence for ASD Diagnosis"

Abstract: Autism Spectrum Disorder (ASD) is a common psychiatric disorder disease that typically causes impaired communication and compromised social interactions. Functional magnetic resonance imaging (fMRI) data is one of the common neuroimaging modalities for understanding human brain functionalities as well as the diagnosis and treatment of brain disorders. Artificial intelligence methods with functional magnetic resonance imaging (fMRI) are now providing the great opportunities for ASD diagnosis. In this talk, after brief introductions to ASD and machine learning, I present three machine learning models of our work in ASD image analysis, which include auto-encoder, semi-supervised autoencoder, and graph attention neural network based methods for ASD diagnosis.

Prof. Jan Gorodkin

University of Copenhagen, Denmark

Jan Gorodkin obtained his Ph.D. in Bioinformatics from Center for Biological Sequence analysis at the Technical University, Denmark. With outset in an awarded talent project grant from the national research council, he did a joint post doc at Aarhus University, Denmark and Washington University Medical School, St. Louis. He has since then been awarded numerous grants. He took up positions at the Royal Veterinary and Agricultural University (now University of Copenhagen), where he served as director of Center for non-coding RNA in Technology and Health, professor and head of the bioinformatics group in the Department of Veterinary and Animal Sciences. He has been the main driver in establishing the danish RNA society of which we served as president for 6 years. He has also served as associate editor in Bioinformatics and is currently a member of the editorial board. His research interests span from bioinformatics and computational biology of RNA structure and CRISPR to genome and omics analyses. His is research group has been involved in developing numerous computational tools as well as applying them in genome and transcriptome analysis.

Speech title: "Computational Strategies for Genome Editing Design with CRISPR"

Abstract: Genome editing concern engineering changes in the genome with applications ranging from optimization of yield in production microorganisms, crop and therapeutics. For this CRISPR (Clustered Regularly Interspaced Short Palindromic Repeats) in various variants have been established as the key tool. The CRISPR enzyme, such as Cas9 binds a guide RNA (gRNA) consisting of a 20 nucleotide spacer sequence which is complement to the DNA corresponding to where the cut is to be made. The remaining part of the gRNA sequence, the scaffolds is sequestered by the enzyme. When conducting a genome editing it can be for different purposes for example knock down of a gene or correction of disease causing genetic variant. Typically it will be possible to choose a gRNA among several other. The “design” is there a matter of gRNA selection and the goal is the select the gRNA which has the maximal editing efficiency on the on-target site while having minimum off-target activity, that is unintended cuts elsewhere in the genome. Here, I will present the our computational strategies to predict on and off-targets in human based on both a deep learning and binding energy models. The methodologies are also available as an integrated CRISPRon/off web resource available via http://rth.dk/resources/crispr.

Invited Speaker

Prof. Chanchal Mitra

University of Hyderabad

Chanchal Mitra did his Bachelors and Masters from the University of Calcutta and Ph.D. from the Tata Institute of Fundamental Research (University of Bombay). He did his post doctoral work at the State University of New York at Albany (The University at Albany), USA and also at the University of Lund, Sweden. His research interests are Bioinformatics, Computational Biology and Biosensors (enzyme based). He joined University of Hyderabad in 1985 as a lecturer and retired in 2015 as Professor of Biochemistry. He has supervised several Ph.D. students, project students and research associates. He has over 100 publications in peer reviewed journals. According to google scholar, he has citations 1272, h-index of 20 and i10-index of 31. He lives in Hyderabad, India (2023).

Speech title: "Traditional ANOVA and PCA used on the Same Diabestes Database"

Abstract: Genes responsible for Diabetes Mellitus (DM) are believed to be inherited from the Neanderthals (Homo neanderthalensis). Although commonly called a lifestyle disease, DM is widely prevalent in the PIMA (Akimel O'odham, Native American people are also known as the Pima) tribes of the US. On the other hand, diabetes is considered a rare condition in sub-saharan africa. The PIMA diabetes database is a small but comprehensive database of adult female patients with key relevant physiological parameters. In this study diabetes has been (rather arbitrarily) defined as the “... plasma glucose concentration of 200 mg/dl (11.1 mmol/l) or greater two hours following the ingestion of 75 gms of glucose” and we can immediately see that the definition ignores the basic metabolic status of the individual. We review the results of the PCA analysis and compare the results vis-a-vis the traditional ANOVA. We compare individual steps so that some meaningful insight can be gained.