Exascale Compound Activity Prediction Engine

Risultati finali

Workshop 2

Workshop for PRACE and/or QSAR community or similat

Factsheet 2

Factsheet for dissemination

Development report

Development report: Document describing the impact of the algorithmic developments on the industry challenges

Simulation report 3

Report: Node peformance simulation of D2.11

Simulation report 2

Report: Node performance simulation of D2.7

Simulation Report 1

Report: Node performance simulation of D2.3

Criteria report

Benchmarking criteria

Metamodel report

Document describing industry challenges and academic research initiatives, and overlap between different ML algorithms to guide building the meta-model

Final simulation and scalability report (4 and 2)

Report: Node performance simulation of D2.17, and scalability test

Factsheet 1

Factsheet for exploitation

Scalability report 1

Scalability test

Challenge report

Document describing challenges, data types and pipelines used in building Chemogenomics models

Report + Code 6

Code for Platt scaling and its integration with algorithms from earlier deliverables corresponding to Task 1.2.3.

Workflows report

Overview of developed methods and workflows

PublicCancer

Public cancer cell line datasets

Report + Code 4

Code for Exascale Bayesian Non-linear Multi-view Matrix Factorization and related documentation, deep learning code and related documentation version 3. Code for integration of unsupervised pre-processing and supervised learning, and related documentation. Code for Venn-Abers probabilistic predictors for large and imbalanced datasets

WebData

Web APIs for public datasets

Tox

Toxicology datasets

PublicBio

Public biological datasets

Social

Social media material

Website

Project website online

Pubblicazioni

Combination of Conformal Predictors for Classification

Autori: Paolo Toccaceli, Alexander Gammerman
Pubblicato in: Proceedings of Machine Learning Research: The Sixth Workshop on Conformal and Probabilistic Prediction and Applications, Numero 60, 2017, 2017, Pagina/e 39-61, ISSN 1938-7228
Editore: JMLR Inc. and Microtome Publishing (United States)

Nonparametric predictive distributions based on conformal prediction

Autori: Vladimir Vovk, Jieli Shen, Valery Manokhin, Min-ge Xie
Pubblicato in: Proceedings of Machine Learning Research Proceedings: The Sixth Workshop on Conformal and Probabilistic Prediction and Applications, Numero 60, 2017, 2017, Pagina/e 82-102, ISSN 1938-7228
Editore: JMLR Inc. and Microtome Publishing (United States)

Reverse Conformal Approach for On-line Experimental Design

Autori: Ilia Nouretdinov
Pubblicato in: Proceedings of Machine Learning Research: The Sixth Workshop on Conformal and Probabilistic Prediction and Applications, Numero 60, 2017, 2017, Pagina/e 185-192, ISSN 1938-7228
Editore: JMLR Inc. and Microtome Publishing (United States)

Improving Reliable Probabilistic Prediction by Using Additional Knowledge

Autori: Ilia Nouretdinov
Pubblicato in: Proceedings of Machine Learning Research: The Sixth Workshop on Conformal and Probabilistic Prediction and Applications, Numero 60, 2017, 2017, Pagina/e 193-200, ISSN 1938-7228
Editore: JMLR Inc. and Microtome Publishing (United States)

Machine Learning for Chemogenomics on HPC in the ExCAPE Project

Autori: Tom Vander Aa, Tom Ashby, Yves Vandriessche, Vojtech Cima, Stanislav Böhm, Jan Martinovic
Pubblicato in: INFOCOMP17, Numero June 25, 2017, 2017, Pagina/e 72 to 74, ISSN 2308-3484
Editore: IARIA

Inductive Conformal Martingales for Change-Point Detection

Autori: Denis Volkhonskiy, Evgeny Burnaev, Ilia Nouretdinov, Alexander Gammerman, Vladimir Vovk
Pubblicato in: Proceedings of Machine Learning Research Proceedings: The Sixth Workshop on Conformal and Probabilistic Prediction and Applications, Numero 60, 2017, 2017, Pagina/e 132-153, ISSN 1938-7228
Editore: JMLR Inc. and Microtome Publishing (United States)

Inductive Venn-Abers predictive distribution

Autori: Ilia Nouretdinov, Denis Volkhonskiy, Pitt Lim, Paolo Toccaceli, Alexander Gammerman
Pubblicato in: Proceedings of Machine Learning Research: The Seventh Workshop on Conformal and Probabilistic Prediction and Applications, Numero 91, 2018, 2018, Pagina/e 15-36, ISSN 1938-7228
Editore: JMLR Inc. and Microtome Publishing (United States)

Conformal predictive decision making

Autori: Vladimir Vovk, Claus Bendtsen
Pubblicato in: Proceedings of Machine Learning Research: The Seventh Workshop on Conformal and Probabilistic Prediction and Applications, Numero 91, 2018, 2018, Pagina/e 52-62, ISSN 1938-7228
Editore: JMLR Inc. and Microtome Publishing (United States)

Large-scale probabilistic non-linear matrix factorization for drug discovery

Autori: Xiangju Qin, Paul Blomstedt, Samuel Kaski
Pubblicato in: 3rd International workshop on biomedical informatics with optimization and machine learning, Numero 15th April, 2018, Pagina/e https://www.ijcai-boom.org/uploads/5/1/6/8/51680821/xiangju_qu.pdf
Editore: https://www.ijcai-boom.org/proceeding.html

Self-Normalizing Neural Networks

Autori: Günter Klambauer, Thomas Unterthiner, Andreas Mayr, Sepp Hochreiter
Pubblicato in: Advances in Neural Information Processing Systems 30 (NIPS 2017), Numero 4.12-9.12.2017, 2017, Pagina/e 971--980
Editore: Curran Associates, Inc.

HyperLoom - A Platform for Defining and Executing Scientific Pipelines in Distributed Environments

Autori: Vojtěch Cima, Stanislav Böhm, Jan Martinovič, Jiří Dvorský, Kateřina Janurová, Tom Vander Aa, Thomas J. Ashby, Vladimir Chupakhin
Pubblicato in: Proceedings of the 9th Workshop and 7th Workshop on Parallel Programming and RunTime Management Techniques for Manycore Architectures and Design Tools and Architectures for Multicore Embedded Computing Platforms - PARMA-DITAM '18, 2018, Pagina/e 1-6, ISBN 9781-450364447
Editore: ACM Press
DOI: 10.1145/3183767.3183768

Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)

Autori: Djork-Arne Clevert, Thomas Unterthiner, Sepp Hochreiter
Pubblicato in: CoRR, Numero abs/1511.07289, 2015, Pagina/e 1-14
Editore: International Conference on Learning Representations (ICLR) 2016

Speeding up Semantic Segmentation for Autonomous Driving

Autori: Michael Treml, José Arjona-Medina, Thomas Unterthiner, Rupesh Durgesh, Felix Friedmann, Peter Schuberth, Andreas Mayr, Martin Heusel, Markus Hofmarcher, Michael Widrich, Bernhard Nessler, Sepp Hochreiter
Pubblicato in: OpenReview, 2016, Pagina/e 1-7
Editore: Workshop on Machine Learning for Intelligent Transport Systems, Conference Neural Information Processing Systems Foundation (NIPS 2016)

Criteria of Efficiency for Conformal Prediction

Autori: Vladimir Vovk, Valentina Fedorova, Ilia Nouretdinov, Alexander Gammerman
Pubblicato in: COPA 2016: Conformal and Probabilistic Prediction with Applications, 2016, Pagina/e 23-39
Editore: Springer International Publishing
DOI: 10.1007/978-3-319-33395-3_2

Distributed Bayesian Probabilistic Matrix Factorization

Autori: Tom Vander Aa, Imen Chakroun, Tom Haber
Pubblicato in: 2016 IEEE International Conference on Cluster Computing (CLUSTER), 2016, Pagina/e 346-349, ISBN 978-1-5090-3653-0
Editore: IEEE
DOI: 10.1109/CLUSTER.2016.13

Universal Probability-Free Conformal Prediction

Autori: Vladimir Vovk, Dusko Pavlovic
Pubblicato in: COPA 2016: Conformal and Probabilistic Prediction with Applications, 2016, Pagina/e 40-47
Editore: Springer International Publishing
DOI: 10.1007/978-3-319-33395-3_3

Distributed Conformal Anomaly Detection

Autori: Ilia Nouretdinov
Pubblicato in: 2016 15th IEEE International Conference on Machine Learning and Applications (ICMLA), 2016, Pagina/e 253-258, ISBN 978-1-5090-6167-9
Editore: IEEE
DOI: 10.1109/ICMLA.2016.0049

Conformal Predictors for Compound Activity Prediction

Autori: Paolo Toccaceli, Ilia Nouretdinov, Alexander Gammerman
Pubblicato in: COPA 2016: Conformal and Probabilistic Prediction with Applications, 2016, Pagina/e 51-66
Editore: Springer International Publishing
DOI: 10.1007/978-3-319-33395-3_4

Self-Normalizing Neural Networks

Autori: Günter Klambauer, Thomas Unterthiner, Andreas Mayr, Sepp Hochreiter
Pubblicato in: ArXiv, Numero 8.6.2017, 2017
Editore: arXiv preprint arXiv:1706.02515

Distributed Bayesian Matrix Factorization with Limited Communication

Autori: Xiangju Qin, Paul Blomstedt, Eemeli Leppäaho, Pekka Parviainen, Samuel Kaski
Pubblicato in: arXiv, Numero 02 March 2017, 2017
Editore: Cornell University Library

SMURFF: a High-Performance Framework for Matrix Factorization

Autori: Tom Vander Aa and Tom Ashby
Pubblicato in: n/a, Numero n/a, 2018
Editore: EPCC

Exploratory Analysis of Multiple Data Sources with Group Factor

Autori: Eemeli Leppäaho, Muhammad Ammad-ud-din, Samuel Kaski
Pubblicato in: Journal of Machine Learning Research, Numero 18, 04-2017, 2017, Pagina/e 1-5, ISSN 1533-7928
Editore: JMLR Inc. and Microtome Publishing (United States)

Criteria of efficiency for set-valued classification

Autori: Vladimir Vovk, Ilia Nouretdinov, Valentina Fedorova, Ivan Petej, Alex Gammerman
Pubblicato in: Annals of Mathematics and Artificial Intelligence, Numero 81/1-2, 2017, Pagina/e 21-46, ISSN 1012-2443
Editore: Kluwer Academic Publishers
DOI: 10.1007/s10472-017-9540-3

The role of measurability in game-theoretic probability

Autori: Vladimir Vovk
Pubblicato in: Finance and Stochastics, Numero 21/3, 2017, Pagina/e 719-739, ISSN 0949-2984
Editore: Springer Verlag
DOI: 10.1007/s00780-017-0336-4

panelcn.MOPS: Copy-number detection in targeted NGS panel data for clinical diagnostics

Autori: Gundula Povysil, Antigoni Tzika, Julia Vogt, Verena Haunschmid, Ludwine Messiaen, Johannes Zschocke, Günter Klambauer, Sepp Hochreiter, Katharina Wimmer
Pubblicato in: Human Mutation, Numero 38/7, 2017, Pagina/e 889-897, ISSN 1059-7794
Editore: John Wiley & Sons Inc.
DOI: 10.1002/humu.23237

Universal probability-free prediction

Autori: Vladimir Vovk, Dusko Pavlovic
Pubblicato in: Annals of Mathematics and Artificial Intelligence, Numero 81/1-2, 2017, Pagina/e 47-70, ISSN 1012-2443
Editore: Kluwer Academic Publishers
DOI: 10.1007/s10472-017-9547-9

Ambit-SMIRKS: a software module for reaction representation, reaction search and structure transformation

Autori: Nikolay Kochev, Svetlana Avramova, Nina Jeliazkova
Pubblicato in: Journal of Cheminformatics, Numero 10/1, 2018, ISSN 1758-2946
Editore: Chemistry Central
DOI: 10.1186/s13321-018-0295-6

Conformal prediction of biological activity of chemical compounds

Autori: Paolo Toccaceli, Ilia Nouretdinov, Alexander Gammerman
Pubblicato in: Annals of Mathematics and Artificial Intelligence, Numero 81/1-2, 2017, Pagina/e 105-123, ISSN 1012-2443
Editore: Kluwer Academic Publishers
DOI: 10.1007/s10472-017-9556-8

Combination of inductive mondrian conformal predictors

Autori: Paolo Toccaceli, Alexander Gammerman
Pubblicato in: Machine Learning, 2018, ISSN 0885-6125
Editore: Kluwer Academic Publishers
DOI: 10.1007/s10994-018-5754-9

Nonparametric predictive distributions based on conformal prediction

Autori: Vladimir Vovk, Jieli Shen, Valery Manokhin, Min-ge Xie
Pubblicato in: Machine Learning, 2018, ISSN 0885-6125
Editore: Kluwer Academic Publishers
DOI: 10.1007/s10994-018-5755-8

Towards a Scalable Software Defined Network-on-Chip for Next Generation Cloud

Autori: Alberto Scionti, Somnath Mazumdar, Antoni Portero
Pubblicato in: Sensors, Numero 18/7, 2018, Pagina/e 2330, ISSN 1424-8220
Editore: Multidisciplinary Digital Publishing Institute (MDPI)
DOI: 10.3390/s18072330

Large-scale comparison of machine learning methods for drug target prediction on ChEMBL

Autori: Andreas Mayr, Günter Klambauer, Thomas Unterthiner, Marvin Steijaert, Jörg K. Wegner, Hugo Ceulemans, Djork-Arné Clevert, Sepp Hochreiter
Pubblicato in: Chemical Science, Numero 9/24, 2018, Pagina/e 5441-5451, ISSN 2041-6520
Editore: Royal Society of Chemistry
DOI: 10.1039/c8sc00148k

Validity and efficiency of conformal anomaly detection on big distributed data

Autori: Ilia Nouretdinov
Pubblicato in: Advances in Science, Technology and Engineering Systems Journal, Numero 2/3, 2017, Pagina/e 254-267, ISSN 2415-6698
Editore: ASTES Publishers
DOI: 10.25046/aj020335

Purely pathwise probability-free Ito integral

Autori: V. Vovk
Pubblicato in: Matematychni Studii, Numero 46/1, 2017, ISSN 1027-4634
Editore: the Lviv Mathematical Society
DOI: 10.15330/ms.46.1.96-110

Distributed Bayesian Probabilistic Matrix Factorization

Autori: Tom Vander Aa, Imen Chakroun, Tom Haber
Pubblicato in: Procedia Computer Science, Numero 108, 2017, Pagina/e 1030-1039, ISSN 1877-0509
Editore: Elsevier
DOI: 10.1016/j.procs.2017.05.009

SW-SGD: The Sliding Window Stochastic Gradient Descent Algorithm

Autori: Imen Chakroun, Tom Haber, Thomas J. Ashby
Pubblicato in: Procedia Computer Science, Numero 108, 2017, Pagina/e 2318-2322, ISSN 1877-0509
Editore: Elsevier
DOI: 10.1016/j.procs.2017.05.082

Improving Operational Intensity in Data Bound Markov Chain Monte Carlo

Autori: Balazs Nemeth, Tom Haber, Thomas J. Ashby, Wim Lamotte
Pubblicato in: Procedia Computer Science, Numero 108, 2017, Pagina/e 2348-2352, ISSN 1877-0509
Editore: Elsevier
DOI: 10.1016/j.procs.2017.05.024

Hypergraphical Conformal Predictors

Autori: Valentina Fedorova, Alex Gammerman, Ilia Nouretdinov, Vladimir Vovk
Pubblicato in: International Journal on Artificial Intelligence Tools, Numero 24/06, 2015, Pagina/e 1560003, ISSN 0218-2130
Editore: World Scientific Publishing Co
DOI: 10.1142/S0218213015600039

ExCAPE-DB: an integrated large scale dataset facilitating Big Data analysis in chemogenomics

Autori: Jiangming Sun, Nina Jeliazkova, Vladimir Chupakin, Jose-Felipe Golib-Dzib, Ola Engkvist, Lars Carlsson, Jörg Wegner, Hugo Ceulemans, Ivan Georgiev, Vedrin Jeliazkov, Nikolay Kochev, Thomas J. Ashby, Hongming Chen
Pubblicato in: Journal of Cheminformatics, Numero 9/1, 2017, ISSN 1758-2946
Editore: Chemistry Central
DOI: 10.1186/s13321-017-0203-5

HyperLoom Possibilities for Executing Scientific Workflows on the Cloud

Autori: Vojtech Cima, Stanislav Böhm, Jan Martinovič, Jiří Dvorský, Thomas J. Ashby, Vladimir Chupakhin
Pubblicato in: Complex, Intelligent, and Software Intensive Systems, Numero 611, 2018, Pagina/e 397-406, ISBN 978-3-319-61565-3
Editore: Springer International Publishing
DOI: 10.1007/978-3-319-61566-0_36

Application of Bioactivity Profile Based Fingerprints for Building Machine Learning Models

Autori: Noé Sturm, Jiangming Sun, Yves Vandriessche, Andreas Mayr, Günter Klambauer, Lars-Anders Carlson, Ola Engkvist, Hongming Chen
Pubblicato in: ChemRxiv, 2018, ISSN 2573-2293
Editore: American Chemical Society
DOI: 10.26434/chemrxiv.6969584.v1

È in corso la ricerca di dati su OpenAIRE...

Risultati finali

Pubblicazioni

Condividi questa pagina

Scarica