Join us for the next DSPT Braga Meetup!
The preliminary agenda for the meetup is the following:
• 18:30-19:00: Welcome and get together
• 19:00-19:30: Talk 1: Large-scale data analysis for the characterization of human gene expression patterns - Pedro G. Ferreira @ U.Porto/i3s/INESCTEC
• 19:40-19:45: Group photo
• 19:45-20:15: Networking / Coffee Break
• 20:15-20:45: Talk 2: Deep Learning at work for Biotechnology applications - João Correia @ U.Minho and Paulo Vilaça @ Silicolife
• 20:50: Closing, hanging out and some beers
• 21:00: Dinner is optional but it might be an excellent opportunity for networking
This meetup is sponsored by Silicolife.
Thank you for the support!
Talk 1: Large-scale data analysis for the characterization of human gene expression patterns
Abstract: Biomedical data, including those generated from large-scale genomic projects, is growing at an unprecedented scale. These are valuable datasets that often provide important insights to understand cell biology and disease mechanisms. Advanced data analysis methods are an essential tool to extract value from this data. The Genotype-Tissue Expression project is one of the most exciting and large-scale projects on biomedical science. In this talk, I will talk about my experience in this project. I will then describe how we are using data science to characterize patterns of transcriptome variation across individuals and tissues and how these patterns associated with human traits.
Pedro G. Ferreira is an Assistant Professor at the Department of Computer Science, Faculty of Sciences of University of Porto and an affiliated researcher at i3s/ipatimup and at LIAAD-INESCTEC.
Graduated from the University of Minho, he was a Postdoctoral Fellow at the Center for Genomic Regulation (Barcelona) and at the Functional Population Genomics and Genetics of Complex Traits group (University of Geneva).
He was involved in several major international research consortia, and an active member of the GTEx consortium. His main research focus in the development of methods. In particular, he is interested in unraveling the role of genomics on the human health and disease.
Talk 2: Deep Learning at work for Biotechnology applications
Machine learning is becoming increasingly relevant in bioinformatics and chemoinformatics in recent years, providing valuable resources to the toolbox of all professionals in the fields of biology, biotechnology and biochemistry. Several methods, including traditional machine learning and more recent deep learning (DL) approaches have been developed and applied in different tasks related to the prediction of the function of biological sequences (DNA,proteins), but also in compound activity prediction and the new compound design. These approaches have allowed to automate the search for biologically active molecules with relevant properties, facilitating the posterior experimental validation.In this talk, we will discuss two research projects, Shikifactory100 and Deep Bio,collaborations of the University of Minho with the SilicoLife company, where DL is being used to address important tasks in Biotechnology, related with the computational optimization of the biological production of important compounds.We will address in more detail a case where we are using DL to generate new molecules with a given biological activity.
João Correia is a research fellow at the Centre of Biological Engineering (CEB),University of Minho in a grant that is part of the Shikifactory100 project where he is involved in the development of ML and DL-based tools for the identification and generation of new compounds with improved biological capabilities. He is also starting a Ph.D. involving the use of DL-based approaches for retrosynthesis and pathway design towards optimizing compound bioproduction. He holds a Bachelor’s degree in Bioengineering and a Master’s degree in Bioinformatics.
Paulo Vilaça from Silicolife