<html><head><meta http-equiv="Content-Type" content="text/html; charset=utf-8"></head><body style="word-wrap: break-word; -webkit-nbsp-mode: space; line-break: after-white-space;" class="">Dear colleague,<div class=""><br class=""><div class=""><div class="">The Summer School on Machine Learning in Drug Design will take place on August 20-22, 2018 in Leuven, Belgium. This Summer School will bring together the machine learning, chemoinformatics, and bioinformatics communities from academia and industry to tackle the challenges of complex data integration in drug design and discovery. </div><div class=""><br class=""></div><div class="">The complete program is available on the summer school web site: <a href="http://mldd.esat.kuleuven.be" class="">http://mldd.esat.kuleuven.be</a>. It is still possible to submit a late poster.</div><div class=""><br class=""></div><div class="">Please forward this announcement to members of your team and to interested colleagues. Apologies for multiple postings.</div><div class=""><div class=""><br class=""></div></div><div class="">Best regards,</div><div class=""><br class=""></div><div class="">Prof. Yves Moreau, University of Leuven<br class=""><br class="">Prof. Sepp Hochreiter, Johannes Kepler University of Linz<br class=""><br class="">Prof. Samuel Kaski, Aalto University</div><div class=""><br class=""></div><div class=""><br class=""></div><div class=""><br class=""></div><div class="">SCOPE<br class=""><br class="">The data sets amenable to mining for drug design are rapidly expanding. This holds not only for the volume of conventional annotation of chemicals (i.e., representations of their chemical structure and their activities in a growing set of validated assays). It also goes for less conventional data sources, such as cellular microscopy or gene expression profiles of chemicals acquired at high throughput. Powerful novel machine learning methods unleashed on these massive volumes of heterogeneous and rich, but noisy and biased data, hold the promise of better and safer drugs to address unmet medical needs. <br class=""><br class="">To deliver on that promise, the Summer School calls on the machine learning, big data analytics, cheminformatics and bioinformatics communities to join forces and strengthen collaborative work at the interface of their disciplines. The Summer School will bring together contributors from both academia and industry to foster interdisciplinary exchange in this area where the need for expertise is growing rapidly. Contributions will cover recent advances in chemogenomics, strategies for data fusion, and machine learning. <br class=""><br class="">INVITED SPEAKER PROGRAM<br class=""><br class=""><div class=""><div class="">* Djork-Arné Clevert (Bayer): Deep learning for proteochemometric modeling<br class=""></div><div class=""><br class=""></div><div class="">* Gerard van Westen (Leiden University): Combining cheminformatics and bioinformatics through deep learning<br class=""></div><div class=""><br class=""></div><div class="">* Gilles Marcou (University of Strasbourg): Chemical space modeling and visualization with Generative Topographic Maps<br class=""></div><div class=""><br class=""></div><div class="">* Günter Klambauer (JKU Linz): Boosting drug discovery with deep learning<br class=""></div><div class=""><br class=""></div><div class="">* Florian Nigsch (Novartis): From heterogeneous data to highly predictive models and their applications in early drug discovery<br class=""></div><div class=""><br class=""></div><div class="">* Daniel Reker (MIT): Machine learning for natural product target prediction and chemogenomic data compression</div><div class=""><br class=""></div><div class="">* Tim Becker (Harvard University): Machine learning and deep learning to predict drug-target activity from high-content imaging<br class=""></div><div class=""><br class=""></div><div class="">* Thomas Blaschke (AstraZeneca): The rise of deep learning in drug discovery</div></div></div><div class=""><div class=""><br class=""></div><div class="">* Val Gillet (University of Sheffield): Applications of machine learning in molecular design: learning from bioactivity and reaction databases</div><div class=""><br class=""></div></div><div class="">INTENDED AUDIENCE AND FORMAT<br class=""><br class="">The summer school is intended for academic and industry researchers in machine learning, chemoinformatics, or bioinformatics who are either currently working at the interface between these fields or want to expand their skills to link these three areas. The summer school is also intended as a bridge between academia and industry.</div><div class=""><br class=""></div><div class="">Complete program available at <a href="http://mldd.esat.kuleuven.be" class="">http://mldd.esat.kuleuven.be</a>.<br class=""><br class="">ABSTRACT SUBMISSION<br class=""><br class="">Participants are invited to submit abstracts for late posters (up to 250 words) before August 13, 2018. Abstracts will be available as a book of abstracts and online, but there will be no full proceedings.<br class=""><br class="">REGISTRATION AND FEE<br class=""><br class="">Registration fee (registration closes on August 13, 2018): €180 (including VAT)<br class=""><br class="">The fee covers participation to the meeting and includes coffee breaks and lunch (sandwich lunch). Oral and poster contributors also need to pay the registration fee.</div><div class=""><br class=""></div><div class="">VENUE<br class=""><br class="">The Summer School will be held at the Irish College, a beautifully restored historical building in the center of Leuven, Belgium.</div></div></div></body></html>