Computer Vision News - September 2021

2 Summary Deep Learning Research 4 “The way to succeed is to double your failure rate.” - Thomas J. Watson , pioneer in the development computing equipment for IBM Hi everyone! For people who took a summer break I hope that you enjoyed it; and for everyone else, keep going strong! Let’s begin with an inspirational quote that may shift your mood. Failure shouldn’t always be seen as an obstacle, but - when that’s possible - as a learning event to fight for adversities and create a new plan. Failure in experimentation or in science should be as well a motivator to try new ideas, explore what went wrong and better understand the problems. By looking closer into the problems, one may find more solutions . Microbiome An exact definition isn’t easy. The fact that in the terminology, “microbiota” (human- associated microbia) and “microbiome” (catalogue of microbes and their genes) are often used interchangeably, makes it even more complex. The topic for this month is a little bit different than usual; it’s taking a deep dive into microbiome data and how it is used for drug response predictions and disease diagnosis. Microbiome (and its research using bioinformatics techniques) is an important scientific area, which is really hot at the moment; both in the scientific sense but also in the entrepreneurship world, where many companies are investing in the field. Our microbiome is a great source of lot of information about us; A novel deep learning method for predictive modelling of microbiome data how we eat, we digest and even how we feel. Let’s dive into that! We are indebted to the authors of this paper (Ye Wang, Tathagata Bhattacharya, Yuchao Jiang, Xiao Qin, Yue Wang, Yunlong Liu, Andrew J Saykin, Li Chen) for allowing us to use their images. The paper was published in Briefings in Bioinformatics, 22(3), 2021, 1-14.