Prof. Anna Goldenberg, SickKids Research Institute and Department of Computer Science at University of Toronto, Toronto, Canada.

Prof. Julio Saez-Rodriguez, Joint Research Center for Computational Biolmedicine, RWTH-Aachen University, Germany and Visting Group Leader at EMBL-EBI, Cambridge, UK.

Prof. Fabian Theis, Institute of Computational Biology, Helmholtz Center Munich, Germany.

Program

08:30 – 08:40	Opening remarks
	Computational methods for emerging biotechnologies
08:40 – 09:30	Invited talk: Lineage estimation from single-cell RNAseq time-series – Fabian J. Theis. Abstract Single-cell technologies have gained popularity in developmental and stem cell biology because they allow resolving potential heterogeneities due to asynchronicity of differentiating cells. With technologies slowly becoming mature and cost-efficient, single cell profiles across multiple conditions e.g. time points and replicates are being generated. In this talk I will first show that by modeling the high-dimensional single cell state space as a diffusion process, we can visualize cell differentiation and estimate lineage formation using pseudotemporal ordering. By including information across multiple time points and if available replicates, we can then setup a model motivated by population dynamics but with continuous states that explains cell lineage transitions in real time beyond pseudotime. I will finish by briefly discussing algorithmic and computational challenges in upscaling to "big data" scRNAseq.
09:30 – 10:00	Coffee break + posters
10:00 – 10:25	Contributed talk: Transcriptome-wide splicing quantification in single cells. Yuanhua Huang and Guido Sanguinetti. [pdf] Paper on BioRXiv
10:25 – 10:50	Contributed talk: Gaussian processes for identifying branching dynamics in single cell data. Alexis Boukouvalas, James Hensman and Magnus Rattray. [pdf] Paper on BioRXiv
	New advances in Machine Learning for Systems Biology I
10:50 – 11:40	Invited talk: Data integration in computational biology and medicine: current progress and future directions – Anna Goldenberg. Abstract There is a great potential for machine learning to contribute to understanding and curing complex human diseases. Rapidly evolving biotechnologies are making it progressively easier to collect multiple and diverse genome-scale datasets to address clinical and biological questions. How do we take advantage of this extensive and heterogeneous data to help patients? In this talk I will introduce several very different biological and clinical questions that all call for data integration but a diverse set of machine learning approaches. First, I will mention Bayesian and discriminative approaches we developed for patient subtyping, then I will talk about identifying disease mechanisms using graphical models and finally, if time permits, I will talk about drug response prediction via deep learning. I will conclude this talk with a summary of ongoing work in data integration and outline new research directions in this area.
11:40 – 12:05	Contributed talk: Modeling post-treatment gene expression change with a deep generative model. Ladislav Rampášek, Daniel Hidru, Peter Smirnov, Benjamin Haibe-Kains and Anna Goldenberg. [pdf]
12:05 – 14:15	Lunch + posters
	New advances in Machine Learning for Systems Biology II
14:15 – 14:40	Contributed talk: Generative learning of dynamic structures using spanning arborescence sets. Anthony Coutant and Celine Rouveirol. [pdf]
	Medical applications
14:40 – 15:30	Invited talk: Understanding and predicting drug efficacy in cancer: from machine learning to biochemical models. Julio Saez-Rodriguez. Abstract Large-scale genomic studies are providing unprecedented insights into the molecular basis of cancer, but it remains challenging to leverage this information for the development and application of therapies. We have performed an integrated analysis of the molecular profiles of over 11,000 primary tumours and 1,000 cancer cell lines, along with the response of the cell lines to 265 anti-cancer compounds. This analysis finds alterations in tumours that can confer drug sensitivity or resistance, and sheds light on which data types are most informative to prioritize treatment. Integration of this data with various sources of prior knowledge, in particular signaling pathways and transcription factors, points at molecular processes involved in resistance mechanisms, and offer hypotheses for novel combination therapies. Our own analysis as well as the results of a crowdsourcing effort (DREAM challenge) reveals that prediction of drug efficacy is far from accurate, implying important limitations for personalised medicine. I will argue than an important aspect that needs to be further studied is the dynamics of signaling networks and how they response to drug treatment. I will show how applying logic models, trained with phosphoproteomic measurements upon perturbations, can further improve our understanding of the molecular basis of drug resistance, thereby providing new treatment opportunities not noticeable by static molecular characterisation.
15:30 – 15:55	Contributed talk: Kernelized rank learning for personalized drug recommendation. Xiao He, Lukas Folkman and Karsten Borgwardt. [pdf]
15:55 – 16:20	Contributed talk: Ask the doctor - Improving drug sensitivity predictions through active expert knowledge elicitation. Iiris Sundin, Tomi Peltola, Muntasir Mamun Majumder, Pedram Daee, Marta Soare, Homayun Afrabandpey, Caroline Heckman, Samuel Kaski and Pekka Marttinen. [pdf] Paper on arXiv
16:20 – 16:30	Closing remarks

List of accepted posters

• Pioneering topological methods for network-based drug-target prediction by exploiting a brain-network self-organization theory. Claudio Durán, Simone Daminelli, Josephine Thomas, Joachim Haupt, Michael Schroeder and Carlo Vittorio Cannistraci. [pdf]
• Kernelized rank learning for personalized drug recommendation. Xiao He, Lukas Folkman and Karsten Borgwardt. [pdf]
• MEMNAR: Finding mutually exclusive mutation sets through negative association rule mining. Iman Deznabi, Ahmet Alparslan Celik and Oznur Tastan. [pdf]
• Enlightening discriminative network functional modules behind Principal Component Analysis separation in differential-omic science studies. Sara Ciucci, Yan Ge, Claudio Duran, Alessandra Palladini, Víctor Jiménez Jiménez, Luisa María Martínez Sánchez, Yuting Wang, Susanne Sales, Andrej Shevchenko, Steven W. Poser, Maik Herbig, Oliver Otto, Andreas Androutsellis-Theotokis, Jochen Guck, Mathias J. Gerl and Carlo Vittorio Cannistraci. [pdf]
• A scalable algorithm for calibrating mathematical models of biochemical pathways using steady state perturbation response data. Tapesh Santra. [pdf]
• Ask the doctor - Improving drug sensitivity predictions through active expert knowledge elicitation. Iiris Sundin, Tomi Peltola, Muntasir Mamun Majumder, Pedram Daee, Marta Soare, Homayun Afrabandpey, Caroline Heckman, Samuel Kaski and Pekka Marttinen. [pdf]
• PAC Learning of Thomas Regulatory Networks from Time-Series Data. Arthur Carcano, François Fages, Jérémy Grignard and Sylvain Soliman. [pdf]
• Integrative concurrent analysis of multiple biological datasets by HALS-based multi-relational NMF. Oliver Mueller-Stricker and Lars Kaderali. [pdf]
• Robustness of modeling-based experiment retrieval to differences in measurement and preprocessing techniques. Pradeep Eranti, Paul Blomstedt and Samuel Kaski. [pdf]
• Partially ordered expression features improves survival prediction in cancer. Mustafa Buyukozkan, Halil Ibrahim Kuru and Oznur Tastan. [pdf]
• Fast imputation of summary statistics based on local LD structure. Matteo Togninalli, Damian Roqueiro and Karsten Borgwardt. [pdf]
• Gaussian processes for identifying branching dynamics in single cell data. Alexis Boukouvalas, James Hensman and Magnus Rattray. [pdf]
• Exploiting the structure of random forests for the detection of epistatic interactions. Corinna Lewis Schmalohr, Jan Großbach, Andreas Beyer and Mathieu Clément-Ziza. [pdf]
• Deep50: Web service for multi-task protein-ligand interaction prediction. Adam Arany, Jaak Simm and Yves Moreau. [pdf]
• Scaling up probabilistic pseudotime estimation with the GPLVM. Sumon Ahmed, Alexis Boukouvalas and Magnus Rattray. [pdf]
• Smart systems for model exploration with application in computational systems biology. Fredrik Wrede and Andreas Hellander. [pdf]
• TOPSPIN: a novel algorithm to predict treatment specific survival in cancer. Joske Ubels, Erik Van Beers, Pieter Sonneveld, Martin van Vliet and Jeroen de Ridder. [pdf]
• Knowledge-driven graph evolution (KDGE). Federico Tomasi, Margherita Squillario and Annalisa Barla. [pdf]
• FastCMH: Genome-wide genetic heterogeneity discovery with categorical covariates. Felipe Llinares-Lopez, Laetitia Papaxanthos, Dean Bodenham, Damian Roqueiro, COPDGene Investigators and Karsten Borgwardt. [pdf]
• easyGWAS: A cloud-based platform for comparing the results of genome-wide association studies. Dominik Grimm, Damian Roqueiro, Matteo Togninalli, EasyGWAS Consortium and Karsten Borgwardt. [pdf]