|
|
Biography |
|
|
BP has a background in Biotechnology and Bioinformatics from The Technical University of Denmark, DTU, and has been working in the Bioinformatics field for the last 13 years. He is a senior member of the Computational Biodiscovery group at the GLOBE institute, where he is utilizing his thorough experience in machine learning to advance projects that aim to decipher the medicinal potential of the Rainforest. BP brings in expertise in genomics and metagenomics and works extensively with Next Generation Sequencing data. He actively uses this expertise to start new collaborations with scientific groups from all over the world to expand the group's project portfolio with exciting projects within NGS, phage biology, rainforest biology, Supercomputing, and Machine Learning. His long term experience in teaching and previous position as Head of Studies from DTU, allowed him to develop excellent educational skills resulting in broad appreciation from former students. BP has within the last few years been running international mobile workshops in NGS, metagenomics, and bioinformatics in Brazil, China, Colombia, Egypt, India, Malaysia and at the Faroe Islands.
|
|
|
|
|
|
|
Abstract |
|
|
|
|
Artificial Intelligence in Phage Discovery |
|
|
|
|
|
Title: Artificial Intelligence in Phage Discovery.
Abstract: Phages are very abundant, but extremely diverse which therefore makes them difficult to detect and to make sense of. To date, a number of tools exist to detect phages and prophages, but most of them are based on and rely on sequence similarities to known phages and therefore have difficulties to identify novel phage sequences, thus essentially whilst valuable, by definition, and because of the way they work, they identify ‘more of the same’.
Artificial intelligence (AI) has been successfully used for a wide range of modern challenges where a lot of data exist – for example, it is used heavily in image classification, security, commerce and to makes sense of linguistic data. Today we have enough bacterial and phage genomic sequences to be able to apply similar - data-hungry - AI approach that is based not on sequence similarity but by identifying features of phages that differ from features present in bacteria.
To develop this project, a consortium of scientists from four Institutes - |
|
|
|
|