To be added.
Previous Invited Speakers
Invited Speaker I
Prof. Leyi Wei
Prof. Leyi Wei is currently a full Professor at School of Software, Shandong University, China. His research interests include bioinformatics and artificial intelligence. He has published 100+ peer-reviewed papers, receiving 4000+ citations in Google Scholar with h-index=40. His work has been recognized through the reception of awards, including Highly Cited Researcher" in Cross-Field (Released by Clarivate Analytics, 2021), ACM SIGBIO Rising Star Award (2021), and many others. He is now serving as Associate Editor and the Editorial Board member for a number of well-known journals, such as Frontiers in Genetics, Methods, BMC Genomics, and Current Bioinformatics, etc.
Speech Title: "Accelerating Bioactive Peptide Discovery via Mutual Information-based Meta-learning"
Abstract: "Recently, machine learning methods have been developed to identify various peptide bio-activities. However, due to the lack of experimentally validated peptides, machine learning methods cannot provide a sufficiently trained model, easily resulting in poor generalizability. Furthermore, there is no generic computational framework to predict the bioactivities of different peptides. Thus, a natural question is whether we can use limited samples to build an effective predictive model for different kinds of peptides. To address this question, we propose Mutual Information Maximization Meta-Learning (MIMML), a novel meta-learning-based predictive model for bioactive peptide discovery. Using few samples from various functional peptides, MIMML can sufficiently learn the discriminative information amongst various functions and characterize functional differences. Experimental results show excellent performance of MIMML though using far fewer training samples as compared to the state-of-the-art methods. We also decipher the latent relationships among different kinds of functions to understand what meta-model learned to improve a specific task. In summary, this study is a pioneering work in the field of functional peptide mining and provides the first-of-its-kind solution for few-sample learning problems in biological sequence analysis, accelerating the new functional peptide discovery."
Invited Speaker II
Assoc. Prof. Shirley Weng In Siu
University of Saint Joseph
Shirley Weng In Siu is an Associate Professor at the University of Saint Joseph. She received her PhD in Natural Sciences from Saarland University (Germany) in 2010. Between 2012 and 2021, she was Assistant Professor in the Department of Computer and Information Sciences at the University of Macau and the head of the Computational Biology and Bioinformatics Laboratory. Her research focuses on computational drug discovery, biomolecular simulation, cheminformatics and machine learning. She pioneers the application of swarm intelligence and machine learning to solve problems in protein ligand docking, drug target identification, and prediction of biological activity and toxicity. She is interested in finding new chemical and biological agents with pharmaceutical potential. Shirley also has great interest in the biophysics of proteins, membranes and polymers. Using molecular dynamics simulations, she has studied the conformational dynamics and mode of action of peptides that are antimicrobial, anticancer, and neurotoxic. She has been involved in the development of membrane lipid force fields and more recently in the modelling of self-assembling monolayers on biochips. Shirley is the author/co-author of more than 60 peer-reviewed journal and conference papers.
Speech Title:"Sequence-based Machine Learning Approaches to Identify Anticancer Peptides"
Abstract: In recent years, with the vigorous development of machine learning algorithms (ML), more and more ML-based methods have been developed to facilitate the discovery of new anticancer peptides (ACPs) and drugs. In this talk, the machine learning workflow to develop ACP prediction models and the different numerical representations for peptide sequences will be explained. Then, the deep learning method called xDeep-AcPEP for predicting biological activity towards six tumor cells will be presented. I will show that multi-task learning is a good strategy to improve model performance by learning a common feature representation and latent relationship between subtasks. Moreover, as a step towards an interpretable model, I will discuss our attempt to correlate the prediction results with the input sequences, i.e., ask the model why it predicts what it predicts. It is believed that finding the most influential residue or subsequence for the predicted biological activity is the first question users might want the prediction model to answer.
Invited Speaker III
Dr. Faez Iqbal Khan
Xi’an Jiaotong-Liverpool University
Dr. Faez Iqbal Khan is an Assistant Professor of the Department of Biological Sciences at the Xi’an Jiaotong-Liverpool University. Dr. Khan received his Ph.D. degree in Computational Chemistry (Bioinformatics) from Durban University of Technology, South Africa. He received his B.Sc. and M.Sc. degrees in Biomedical Science and Bioinformatics. Dr. Khan carried out further research work and teaching at Rhodes University (South Africa), South China University of Technology, and the University of Electronic Science and Technology of China. His primary research focuses on Protein engineering, Protein folding, drug design and Protein dynamics. Dr. Khan established wide-ranging collaborations with BRICS countries and mentored several postgraduate students. He has authored over 70 publications in international peer-reviewed journals which are well cited.
Speech Title:"Potential Multi-target Inhibitors of SARS-CoV-2"
Abstract: Development of new drugs is a time taking and expensive process. Comprehensive efforts are being made globally towards the search of therapeutics against SARS-CoV-2. Several drugs such as remdesivir, favipiravir, ritonavir, and lopinavir have been included in the treatment regimen and shown effective results in several cases. Among the existing broad-spectrum antiviral drugs remdesivir is found to be more effective against SARS-CoV-2. Remdesivir has broad-spectrum antiviral action against many single-stranded RNA viruses including pathogenic SARS-CoV and Middle East respiratory syndrome coronavirus (MERS-CoV). We proposed that remdesivir strongly binds to membrane protein (Mprotein), RNA-Dependent RNA Polymerase (RDRP) and Main Protease (Mprotease) of SARS-CoV-2. It might show antiviral activity by inhibiting more than one target. Additionally, we identified the compounds fangchinoline and versicolactone C exhibiting strong binding to the target proteins with structural deformation of three structural proteins (N, S and M). The inhibitory effects of these compounds from this study against SARS-CoV-2 should be experimentally validated. Further, psilocybin-mushroom that contains the psychedelic compounds such as psilacetin, psilocin, and psilocybine were screened and found to be inhibitors of SARS-CoV-2 Mprotease. The psilacetin was found to inhibit human interleukin-6 receptors to reduce cytokine storm. The binding of psilacetin to Mprotease of SARS-CoV-2 and human interleukin-6 receptors changes the structural dynamics and Gibbs free energy patterns of proteins. These results suggested that psilocybin-mushroom could be utilized as viable potential chemotherapeutic agents for SARS-CoV-2.
25 December, 2022
Paper Acceptance Notification:
25 January, 2023
Camera-ready Paper Submission:
10 February, 2023
Conference Date: 26-28 May, 2023