Machine Learning for Personalized Medicine

Felipe Llinares López

ETH Zürich, Switzerland

Machine Learning for biomarker discovery from heterogeneous data

ARTICLES

- Laetitia Papaxanthos*, Felipe Llinares-López*, Dean Bodenham and Karsten Borgwardt (*=equal contributions). Finding significant combinations of features in the presence of categorical covariates, Advances in Neural Information Processing Systems 29 (NIPS 2016), 2271-2279.

- Mahito Sugiyama, Felipe Llinares Lopez, Niklas Kasenburg, Karsten Borgwardt.
 Significant Subgraph Mining with Multiple Testing Correction,
 Proceedings of the 2015 SIAM International Conference on Data Mining. 2015, in press.

- Felipe Llinares-López, Dominik G. Grimm, Dean A. Bodenham, Udo Gieraths, Mahito Sugiyama, Beth Rowan, Karsten Borgwardt. Genome-wide detection of intervals of genetic heterogeneity associated with complex traits. Bioinformatics (2015) 31 (12):i240-i249.

- Llinares-López F, Sugiyama M, Papaxanthos L, Borgwardt KM. Fast and Memory-Efficient Significant Pattern Mining via Permutation Testing. Proceedings of the 21st ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD2015), 2015, 725-734. 

CODE

http://www.bsse.ethz.ch/mlcb/research/bioinformatics-and-computational-biology/sis.html

ORAL PRESENTATIONS

- Felipe Llinares-López, Dominik G. Grimm, Dean A. Bodenham, Udo Gieraths, Mahito Sugiyama, Beth Rowan, Karsten Borgwardt. Genome-wide detection of intervals of genetic heterogeneity associated with complex traits. ISMB conference 2015.

- Llinares-López F, Sugiyama M, Papaxanthos L, Borgwardt KM. Fast and Memory-Efficient Significant Pattern Mining via Permutation Testing. KDD conference 2015.

POSTERS

- Llinares-López F, Sugiyama M, Papaxanthos L, Borgwardt KM. Fast and Memory-Efficient Significant Pattern Mining via Permutation Testing. KDD conference 2015

- Llinares-López F*, Bodenham D*, Papaxanthos L*, Borgwardt KM. Detecting significant high-order associations between genotype and phenotype while conditioning on covariates. NIPS conference 2015 (* first authors)

- Felipe Llinares-López, Dominik G. Grimm, Dean A. Bodenham, Udo Gieraths, Mahito Sugiyama, Beth Rowan, Karsten Borgwardt. Genome-wide detection of intervals of genetic heterogeneity associated with complex traits.  CC-PM/MTB Retreat 2015, November 1st–3rd 2015, Kartause Ittingen, Switzerland

Meiwen Jia

Max Planck Society, Munich, Germany

High-throughput detection of higher-order epistasis using GPGPU computing methods

POSTER

Poster for 2nd ITN Machine learning for personalized medicine summer school in Paris, France, 18-26 Sep 2014

Menno Witteveen

ETH Zürich, Switzerland

Patient subtype discovery from heterogeneous datasets via unsupervised machine learning

ARTICLE

Roqueiro D*, Witteveen M*, Anttila V, Terwindt G, van den Maagdenberg A, Borgwardt K. In-silico phenotyping via co-training for improved phenotype prediction from genotype. Bioinformatics 2015, accepted.
(* equal first authors)

CODE

http://www.bsse.ethz.ch/mlcb/research/bioinformatics-and-computational-biology/co-training.html

ORAL PRESENTATION

Witteveen M. In silico phenotyping via co-.‐training for improved phenotype prediction from genotype. Retreat of the MTB graduate school, November 1st–3rd 2015, Kartause Ittingen, Switzerland

POSTER PRESENTATION

Roqueiro D*, Witteveen M*, Anttila V, Terwindt G, van den Maagdenberg A, Borgwardt K. In-silico phenotyping via co-training for improved phenotype prediction from genotype. Clinical Genomic Analysis Workshop, June 7, 2015, Haifa, Israel

(* equal first authors)

Victor Bellón

ARMINES, France

Adverse drug reaction discovery

ARTICLES

- Sieberts, S. K., Zhu, F., García-García, J., Stahl, E., Pratap, A., Pandey, G., … Mangravite, L. M. (2016). Crowdsourced assessment of common genetic contribution to predicting anti-TNF treatment response in rheumatoid arthritis. Nature Communications, 7, 12460. 

ORAL PRESENTATION AND CONFERENCE PUBLICATION

- Victor Bellon, Veronique Stoven, Chloe-Agathe Azencott. Multitask Feature Selection with Task Descriptors. Pacific Symposium on Biocomputing (PSB) 2016.

POSTERS

- Victor Bellón, Chloé-Agathe Azencott, Véronique Stoven, Olivier Collier, Azadeh Khaleghi, Valentina Boeva, Jean Philippe Vert. DREAM Rheumatoid Arthritis Responder Challenge 2014: Team Lucia 

- Víctor Bellón, Chloé-Agathe Azencott and Véronique Stoven. A Multiplicative Multitask Lasso approach with task descriptor variables. FEAST 2015: ICML Workshop on Features and Structures

Cristóbal Esteban

SIEMENS, Germany

Learning Decision Support for Personalized Medicine

ARTICLES

- Yang Y, Esteban C, Tresp V. Embedding Mapping Approaches for Tensor Factorization and Knowledge Graph Modelling. The Semantic Web. Latest Advances and New Domains. Volume 9678 of the series Lecture Notes in Computer Science pp 199-213, 2016.

- Esteban C, Staeck O, Baier S, Yang Y, Tresp V. Predicting Clinical Events by Combining Static and Dynamic Information Using Recurrent Neural Networks. Proceedings of 2016 IEEE International Conference on Helthcare Informartics 2016. IEEE. (Best paper nominee)

- Esteban C, Tresp V, Yang Y, Baier S, Krompaß D. Predicting the Co-Evolution of Event and Knowledge Graphs. Proceedings of IEEE International Conference on Information Fusion 2016.

- Cristóbal Esteban, Danilo Schmidt, Denis Krompaß, and Volker Tresp. Predicting Sequences of Clinical Events by using a Personalized Temporal Latent Embedding Model. Proceedings of the  IEEE International Conference on Healthcare Informatics  (ICHI), 2015.

- Denis Krompaß, Cristóbal Esteban, Volker Tresp, Martin Sedlmayr and Thomas Ganslandt. Exploiting Latent Embeddings of Nominal Clinical Data for Predicting Hospital Readmission. KI-Künstliche Intelligenz. 2015 Jun 1;29(2):153-9.

PREPRINTS

- Tresp V, Esteban C, Yang Y, Baier S, Krompaß D. Learning with Memory Embeddings. arXiv preprint arXiv:1511.07972. 2015 Nov 25.

POSTERS

- Cristóbal Esteban, Stephan Baier, Yinchong Yang, Danilo Schmidt, Denis Krompaß, and Volker Tresp. Representation Learning for Electronic Health Record Modeling. NIPS workshop on Machine Learning in Healthcare, 2015.

- Volker Tresp, Cristóbal Esteban, Yinchong Yang, Stephan Baier, and Denis Krompass. Learning with Memory Embeddings. NIPS workshop on Nonparametric Methods for Large Scale Representation Learning, 2015 (accepted). 

Max Zwießele

University of Sheffield, UK

Analysis and detection of differential isoform expression and splicing dysregulation events from RNA-seq data

ARTICLES

- Tapio Lönnberg, Valentine Svensson, Kylie R James, Daniel Fernandez-Ruiz, Ismail Sebina, Ruddy Montandon, Megan S F Soon, Lily G Fogg, Michael J T Stubbington, Frederik Otzen Bagger, Max Zwiessele, Neil Lawrence, Fernando Souza-Fonseca- Guimaraes, William R Heath, Oliver Billker, Oliver Stegle, Ashraful Haque, Sarah A Teichmann. Temporal mixture modelling of single-cell RNA-seq data resolves a CD4+ T cell fate bifurcation. bioRxiv 074971, 2016.

- Max Zwiessele, Neil Lawrence. Tilted Variational Bayes. bioRxiv 057778, 2016.

- James Hensman, Max Zwiessele, Neil Lawrence
. Tilted Variational Bayes. JMLR W&CP 33 : 356–364, 2014.

- Ricardo Andrade Pacheco, James Hensman, Max Zwiessele, Neil Lawrence
. Hybrid Discriminative-Generative Approach with Gaussian Processes. JMLR W&CP 33 : 47–56, 2014.

POSTER

- Max Zwiessele. Metric for Probabilistic Manifold Embeddings. Poster at MLPM Summerschool, MOSI, Manchester, UK 2015.

- Max Zwiessele. Probabilistic Dimensionality Reduction in Biological Applications. Poster at AISTATS, Reykjavic, Iceland 2014.

CODE

General implementations

You can find almost all of my code in the GPy package which can be found on Github (GPy).

IPython notebooks

For some IPython notebook examples and more explanation of the toolbox see GPy Notebooks. 

How-to view IPython notebooks

You can run the notebooks by visiting nbviewer and giving the address of the notebook in Github. For example try 

Coregionalized Regression Model

Daniel Urda Muñoz

Pharmatics, Edinburgh, UK

Development of Methods for Patient Group Stratification and Tailored Medical Interventions

Ramouna Fouladi

University of Liège, Belgium

An –omics integrated flexible framework for epistasis analysis, acknowledging interpretation capacity

ARTICLE

- Ramouna Fouladi, Kyrylo Bessonov, François Van Lishout, Kristel Van Steen. Model-Based Multifactor Dimensionality Reduction for Rare Variant Association Analysis. Human Heredity 2015; 79(3-4):157-67

ORAL PRESENTATIONS

- Ramouna Fouladi, Kyrylo Bessonov, François Van Lishout, Jason Moore, Kristel Van Steen. A novel integrated framework for rare variant analysis. Accepted for oral presentation in EMGM, Cologne, Germany, 1-2 April 2014

- Ramouna Fouladi, Kyrylo Bessonov, François Van Lishout, Jason Moore, Kristel Van Steen.  A novel gene-based analysis method based on MB-MDR. CSCDA 2014

POSTERS

- R. Fouladi, C. Schurmann, K. Bessonov, JP. Vert, R.J.F Loos, K. Van Steen. A novel gene-based analysis method based on MB-MDR,  ASHG 2015, Baltimore. 6-10 October 2015

- Ramouna Fouladi, Kyrylo Bessonov, François Van Lishout, Jason Moore, Kristel Van Steen. A novel integrated framework for large scale association analysis,  Accepted for poster presentation in Human Genome Meeting (HGM), Geneva, Switzerland, 27-30 April 2014

- Ramouna Fouladi, Kyrylo Bessonov, François Van Lishout, Jason Moore, Kristel Van Steen. A novel integrated framework for large scale omics association analysis, Accepted for poster presentation in International Genetic Epidemiology Society (IGES), Vienna, Austria, 28-30 August 2014

Yunlong Jiao

ARMINES, France

Robust molecular signatures for personalized medicine

ARTICLE

- Jiao Y, Korba A, Sibony E. Controlling the distance to a Kemeny consensus without computing it. Proceedings of The 33rd International Conference on Machine Learning (ICML-16), pp. 2971–2980, 2016.

- Jiao Y, Vert JP. The Kendall and Mallows Kernels for Permutations.
Technical Report, HAL-01279273, February 2016.

- Jiao Y and Vert JP. The Kendall and Mallows Kernels for Permutations. Proceedings of the 32nd International Conference on Machine Learning (ICML), JMLR: W&CP 37, 1935-1944, 2015.

- Eduati, F., Mangravite, L. M., Wang, T., Tang, H., Bare, J. C., Huang, R., ... & NIEHS-NCATS-UNC DREAM Toxicogenetics Collaboration. Prediction of human population responses to toxic compounds by a collaborative competition. Nature biotechnology, 2015.

ORAL PRESENTATIONS

- Bernard E, Scornet E, Jiao Y, Stoven V, Walter T, Vert J-P. Kernel bilinear regression for toxicogenetics. NIPS Workshop on Machine Learning in Computational Biology (MLCB), Lake Tahoe, Nevada, December 2013.

Yuanlong Liu

INSERM, France

Comparison of multi-marker methods to identify the genetics pathways underlying asthma

ARTICLES

- Y. Liu, M. Brossard, C. Sarnowski, A. Vaysse, M. Moffatt, P. Margaritte-Jeannin, F. Llinares-López, M.H. Dizier, M. Lathrop, W. Cookson, E. Bouzigon, F. Demenais. Network-assisted analysis of GWAS data identifies a functionally-relevant gene module for childhood-onset asthma. Scientific Reports (under review)

- Y. Liu, M. Brossard, D. Roqueiro, P. Margaritte-Jeannin, C. Sarnowski, E. Bouzigon, F. Demenais. SigMod: an exact and efficient method to identify a strongly interconnected disease-associated module in a gene network. Bioinformatics (under review)

ORAL PRESENTATION

- Y. Liu, M. Brossard, C. Sarnowski, P. Margaritte-Jeannin, F. Llinares, A. Vaysse, M.H. Dizier, E. Bouzigon, F. Demenais. Bring together Machine Learning and Statistical Genetics for Personalized Medicine. 14th annual congress of international drug discovery science and technology (invited talk), Nanjing, China, 16-19 Nov 2016

- Y. Liu, M. Brossard, C. Sarnowski, P. Margaritte-Jeannin, A. Vaysse, M.H. Dizier, E. Bouzigon, F. Demenais. Integrate network resources to optimize genetic association studies. European Society of Human Genetics annual meeting, Barcelona, Spain, 21-24 May 2016.

- Y. Liu, M. Brossard, C. Sarnowski, P. Margaritte-Jeannin, F. Llinares, A. Vaysse, M. H. Dizier, E. Bouzigon, F. Demenais, and GABRIEL asthma consortium. Integration of genome-wide association data and human protein interaction networks identifies a gene sub-network underlying childhood-onset asthma. American Society of Human Genetics annual meeting, Baltimore, USA, 6-10 Oct 2015.

- Y. Liu, M. Brossard, P. Margaritte-Jeannin, F. Llinares, C. Sarnowski1, L. Al-Shikhley, N. Lavielle, A. Vaysse, M.H. Dizier, E. Bouzigon, F. Demenais. Network-Assisted Investigation of Signals from Genome-Wide Association Studies in Childhood-onset Asthma. Capita Selecta in Complex Disease Analysis conference, Liège, Belgium, 24-26 Nov 2014.

POSTERS

- Myriam Brossard, Amaury Vaysse, Hamida Mohamdi, Yuanlong Liu, Eve Maubec, Pilar Galan, Marie-Françoise Avril, Mark Lathrop, Florence Demenais. Genetic analysis of the telomere interactome pinpoints new candidate genes for melanoma risk. Interational Genetic Epidimiology Society Annual Meeting, Toronto, Canada, 24-26 Oct  2016.

- Yuanlong Liu, Myriam Brossard, Damian Roqueiro , Patricia Margaritte-Jeannin, Chloé Sarnowski, Emmanuelle Bouzigon, Florence Demenais. A novel network method (SigMod) identifies a strongly interconnected gene module associated with childhood asthma. European Society of Human Genetics annual meeting, Barcelona, Spain, 21-24 May 2016.

- Y. Liu, M. Brossard, C. Sarnowski, P. Margaritte-Jeannin, F. Llinares, A. Vaysse, M.H. Dizier, E. Bouzigon, F. Demenais. Network-based analysis of GWAS data identifies agene sub-network underlying childhood-onset asthma. Interational Genetic Epidimiology Society Annual Meeting, Baltimore, USA, 4-6 Oct  2015.

- Liu Y et al. Pathways and Protein networks associated with asthma. Annual meeting of the French Doctoral School, Saint Malo, France, 20-22 Oct 2014.

CODE

- SigMod: an exact and efficient method to identify a strongly interconnected disease-associated module in gene connectome

- SigMod2: identify novel disease-associated modules closely connected to previously known disease genes

- fastCGP: a fast and powerful algorithm to compute gene-level P-values from Genome-Wide Association Studies through circular genomic permutation

Melanie Fernandez Pradier

University of Madrid, Spain

Stochastic modelling and graphical models for the analysis and prediction of phenotype interactions

ARTICLES

- M. F. Pradier, F. Perez-Cruz, O. Puig, and F. Milletti, Indian Buffet Process for Biomarker Discovery in Clinical Trials. To be submitted soon.

- M. F. Pradier, F. J. R. Ruiz and F. Perez-Cruz. Prior Design for Dependent Dirichlet Process: An Application to Marathon Modeling. Plos ONE, 2016

ORAL PRESENTATIONS (plus posters)

- M. F. Pradier,  S. Stark, S. Hyland, J. E. Vogt, G. Rätsch, and F. Perez-Cruz. Large-Scale Sentence Clustering from Electronic Health Records for Genetic Associations in Cancer. Paper + Spotlight Talk at Machine Learning for Computational Biology Workshop in Neural Information Processing Systems Conference 2015 (NIPS 2015). 

- Pradier MF, Vogt JE, Stark S, Karaletsos T, Perez-Cruz F and Rätsch G. Probabilistic Analysis of Genetic Associations with Clinical Features in Cancer. Presented as Spotlight talk at the 9th Annual Machine Learning Symposium at New York Academy of Sciences, New York 2015.

- Pradier MF, Moreno PG, Ruiz FJR, Valera I, Mollina-Bulla H, Perez-Cruz F. Map/Reduce Uncollapsed Gibbs Sampling for Bayesian Non Parametric Models. Spotlight Talk at Workshop in Software Engineering for Machine Learning at Neural Information Processing Systems Conference 2014 (NIPS2014).

POSTERS

- M. F. Pradier, T. Karaletsos,  S. Stark, J. E. Vogt, G. Rätsch, and F. Perez-Cruz. “Bayesian Poisson Factorization for Genetic Associations with Clinical Features in Cancer”, Accepted Abstract at Machine Learning for Healthcare Workshop in Neural Information Processing Systems Conference 2015 (NIPS 2015).

- M. F. Pradier, and F. Perez-Cruz. Infinite Mixture of Global Gaussian Processes. Paper at Bayesian Non-parametric: the Next Generation Workshop in Neural Information Processing Systems Conference (NIPS 2015).

- Pradier MF, Olmos PM, Perez-Cruz F. Lossy Source Compression of Multiple Gaussian Sources. European School of Information Theory 2013 (ESIT2013).

- Vogt JE, Pradier MF, Hyland S, Stark S, Lehmann K, Karaletsos T and Rätsch G. Clinical Notes, Sentence Clusters & Somatic Mutations. Poster at Workshop in Machine Learning for Clinical Data Analysis, Healthcare and Genomics at Neural Information Processing Systems Conference 2014 (NIPS2014).

- S. Stark, J. E. Vogt, M. F. Pradier, and G. Rätsch. Large-Scale Clustering of Sentences and Patients based on Electronic Health Records. Presented at the 9th Annual Machine Learning Symposium at New York Academy of Sciences, New York 2015.

AWARD

2015 Spotlight Talk Award for

Pradier MF, Vogt JE, Stark S, Karaletsos T, Perez-Cruz F and Rätsch G. Probabilistic Analysis of Genetic Associations with Clinical Features in Cancer. Presented at the 9th Annual Machine Learning Symposium at New York Academy of Sciences, New York 2015.

The Spotlight Talk Award recognized a series of the best oral research presentations delivered by early career investigators during the Symposium.

Cankut Cubuk

CIPF, Valencia, Spain

Modeling functional and regulatory modules using statistical and machine learning methods

ARTICLES

- Hidalgo MR, Cubuk C,  Amadoz A, Salavert F,  Carbonell-Caballero J, Dopazo J. High throughput estimation of functional cell activities reveals disease mechanisms and predicts relevant clinical outcomes. bioRxiv 076083, 2016.

- Salavert F, Hidalgo MR, Amadoz A, Cubuk C,  Medina I, Crespo D, Carbonell-Caballero J, Dopazo J. Actionable pathways: interactive discovery of therapeutic targets using signaling pathway models. Nucl. Acids Res. 2016;  doi: 10.1093/nar/gkw369

- Sanchez V, Cubuk C, Sebastián-Leon P, Carobbio S, Dopazo J, Vidal-Puig A, Bartolomucci A. Chronic subordination stress selectively downregulates the insulin signaling pathway in liver and skeletal muscle but not in adipose tissue of male mice. Stress: Int. J. Biol. Stress. 2016; doi: 10.3109/10253890.2016.1151491.

- Razzoli M, Frontini A, Gurney A, Mondini E, Cubuk C, Katz LS, Cero C, Bolan PJ, Dopazo J, Vidal-Puig A, Cinti S, Bartolomucci A. Stress-induced activation of brown adipose tissue prevents obesity in conditions of low adaptive thermogenesis. Molecular Metabolism 2015 (in press).
doi: 10.1016/j.molmet.2015.10.005.

- Alonso R, Salavert F, Garcia-Garcia F, Carbonell-Caballero J, Bleda M, Garcia-Alonso L, Sanchis-Juan A, Perez-Gil D, Marin-Garcia P, Sanchez R, Cubuk C, Hidalgo MR, Amadoz A, Hernansaiz-Ballesteros RD, Aleman A, Tarraga J, Montaner D, Medina I, Dopazo J. Babelomics 5.0: functional interpretation for new generations of genomic data. Nucleic Acids Research 2015; doi: 10.1093/nar/gkv384 

ORAL PRESENTATIONS

- Cankut Cubuk, Marta R. Hidalgo, Jose Carbonell-Caballero and Joaquín Dopazo. Signalling circuit activities as mechanism-based features to predict mode of action of chemicals. CAMDA 2015 Conference at ISMB/ECCB, Dublin

- Marta R. Hidalgo, Cankut Cubuk, Jose Carbonell-Caballero and Joaquín Dopazo. Functional hallmarks in clear cell renal cell carcinoma grade and stage progression revealed by changes in signalling circuit activities. CAMDA 2015 Conference at ISMB/ECCB, Dublin

POSTERS

Cankut Cubuk, Marta R. Hidalgo, Jose Carbonell-Caballero and Joaquin Dopazo. Identification of Key Metabolic Patterns of Cancer Using RNA-Seq Data. 4th Conference on Constraint-Based Reconstruction and Analysis (COBRA 2015)

Cankut Cubuk and Joaquin Dopazo. Constraining metabolic model with gene expression data to understand functional differences. MLPM Summer school, Institut Curie in Paris, France, Sep 2014.

Yi Zhong

MSKCC, USA

Functional annotation of genomic variation explaining phenotypes