Data Talks

KNIME Spring Summit 2018 - Berlin

- - Hotel Berlin, Berlin - Lützowplatz 17, 10785 Berlin, Germany

Join us and other KNIME users for the 11th KNIME Spring Summit at Hotel Berlin, Berlin from March 5 - 9, 2018. Leading data scientists will be there to share how they use KNIME software for solving complex data problems across a variety of fields. We have an agenda filled with training courses, Summit sessions, and workshops with presenters from various companies, KNIME community members, our customers, and of course our very own KNIME team.


Overview – Courses – Agenda – Workshops – VenueRegistration



Overview – Courses – Agenda – Workshops – VenueRegistration

On March 5 - 6 we are offering several one day KNIME Training Courses that cover a variety of topics. Your Summit registration allows you to select either one or two of these full day training courses:

KNIME Training Courses: Monday, March 5, 2018:

  • Course M1: KNIME Analytics Platform for Beginners: From installation to utilization and everything in between. Presented by Iris Adä, KNIME. Berlin-Berlin 3
  • Course M2: Text Mining with KNIME Analytics Platform: Using the Textprocessing Extension. Presented by Roland Burger, KNIME. Room: Berlin-London
  • Course M3: KNIME Big Data Extensions: Data Mining with Apache Hive and Apache Spark. Presented by Björn Lohrmann, KNIME. Room: Berlin-Peking
  • Course M4: Advanced Analytics Methods with KNIME Analytics Platform. Presented by Stefan Weingaertner AdvancedAnalytics.Academy. Room: Berlin-Berlin 1

KNIME Training Courses: Tuesday, March 6, 2018:

  • Course T1: Advanced Users in KNIME Analytics Platform: Beyond the basics. Presented by Iris Adä, KNIME. Berlin-Berlin 3
  • Course T2: Text Mining with KNIME Analytics Platform: Using the Textprocessing Extension. Presented by Roland Burger, KNIME. Room: Berlin-London
  • Course T3: KNIME Big Data Extensions: Data Mining with Apache Hive and Apache Spark. Presented by Tobias Kötter, KNIME. Room: Berlin-Berlin 1
  • Course T4: IoT Analytics with KNIME Analytics Platform. Presented by Simon Steinacher & Stefan Weingaertner, AdvancedAnalytics.Academ. Room: Berlin-Sydney
  • Course T5: The Power of Random: Using Perturbation Experiments to Improve Model Accuracy and Interpretation. Presented by Dean Abbott, Abbott Analytics. Room: Berlin-Buenos Aires

Please use the Summit registration form below to register for one or two of these courses.

Node Development Crash Course & Developer Meeting

Tuesday, March 6, 1pm - 3:30pm: Node Development Crash Course. In this session we will show you everything you need to know in order to write your own nodes. Based on a simple KNIME node we will show you what classes are required and what methods must be implemented. All participants should know how to program Java and ideally also how to use the Eclipse SDK. Please bring your own computer with a current installation of Eclipse SDK.

Tuesday, March 6, 4pm - 5:30pm: Developer Meeting. This is an open session about all things, well, development! If there’s anything in particular you want to discuss, please email and we'll try to get it included in the agenda. The KNIME team will also provide an overview about important changes and news for developers. Topics we have on the list so far:

  • Nodepit (Philipp Katz, Daniel Esser, Jacobo Miranda Ackerman)

  • KNIME Node Archetype (Stefan Verhoeven)

  • Simple node creation (David Kolb, Marcel Wiedenmann)

These sessions will be held in the Berlin-Montreal room. Please indicate if you’ll be attending when completing your summit registration.

OverviewCourses – Agenda – Workshops – VenueRegistration

Wednesday, March 7th

9:00 - Registration and Light Breakfast

10:00 - Opening and KNIME Update

12:30 - Lunch

13:30 - Session 1

  • H2O in KNIME: Integrating High Performance Machine Learning, slides
    Jo-Fai Chow ( and Christian Dietz (KNIME)
  • KNIME in Action: The Monster Model Factory, slides, video
    Greg Landrum (KNIME)
  • Predictive Analytics of Hair Colorations
    Georg Knübel (Henkel Beauty Care) and Iris Adä (KNIME)

15:00 - Coffee Break

15:30 - Session 2

  • Blending Enterprise-BI, Data Science, and modern IT-Architecture - Lessons Learned
    Matthias Nolte (Berliner Sparkasse), slides
  • Smart Data Collaboration Hub
    Rainer Dürr and Gerrit Bungeroth (Landesbank Baden-Württemberg), slides
  • KNIME & Teacher Bots: From Workflows to Micro Services
    Kathrin Melcher, Vincenzo Tursi, Rosaria Silipo, Phil Winters (KNIME), slides, video

17:15 - End of Day 1

17:45 - Start of Shuttle Bus Transfer to Spindler & Klatt

19:00 - Summit Dinner at Spindler & Klatt

22:00 - Start of Return Shuttle Bus Transfer. Last bus is at 24:00

Thursday, March 8th

9:00 - Registration and Light Breakfast

9:30 - Parallel Track

Life Science. Session 3a Customer Intelligence. Session 3b
  • Deep Learning: From Mastering the Game of GO to Revolutionizing Microscopy, slides
    Florian Jug (MPI-CBG Dresden)
  • 3D-e-Chem: Structural Cheminformatics KNIME Workflows for Computer-aided Drug Discovery
    Chris de Graaf (VU University Amsterdam)
  • Guided Analytics in Action: KNIME Does Biology, slides
    Jeany Prinz (KNIME)
  • KNIME in Action: GDPR, Taking a Proactive Approach, slides
    Phil Winters (KNIME)
  • Predicting Probability of Debt Recovery, slides
    Elif Yigit Aycan and Mesrur Börü (Hayat Varlik)
  • Automating CRM, Marketing and Analytics with KNIME, slides
    Edvinas Subacius (Zecure Gaming)

11:00 - Coffee Break

11:30 - Parallel Track

Life Science. Session 4a Customer Intelligence. Session 4b
  • Integrated CADD Methods: A Cocktail of KNIME, Bash and Modeling Software, slides
    Loris Moretti (NuEvolution)
  • Exploring the Factory: Into the Guts of the Monster, slides video
    Greg Landrum, Daria Goldmann, Anna Martin (KNIME)
  • KNIME for 'Deterministic Analytics' by Business Users, slides
    Arne Beckhaus (Continental)
  • Advanced Job Analytics @ Daimler
    Julian Leweling (Daimler AG) and Christoph Becker (DYMATRIX)

12:30 - Lunch

13:30 - Session 5

  • Citizen Data Science Initiative at Seagate, slides
    Allan Luk and Eric Lin (Seagate)
  • Poster Introductions
    Phil Winters (KNIME)
  • Using Analytics to Help Make Things Better for Consumers, slides
    Ian Ferrell (Which?) and Christoph Hansmann (DYMATRIX)

15:00 - Coffee Break

15:30 - Session 6

  • Smart Industry 4.0 - Industrial Automation Goes Machine Learning Automation, slides
    Thomas Zipf (ContiTech Fluid Technology), Michael Wojtas (Leadec), Stefan Weingaertner (Datatroniq)
  • Recipe Conversion Stories from a Domesticated Chemist
    Elizabeth Wright

16:45 - Keynote

  • The Biggest 'Miss' In Predictive Modeling
    Dean Abbott (SmarterHQ)

17:30 - Poster Session with Open Bar and BRLO Beer Tasting

OverviewCoursesAgenda – Workshops – VenueRegistration

Our workshops take place on March 9 and are free of charge in combination with a KNIME Spring Summit registration. Below are some of the workshops on offer this year (we are regularly adding others). During the Summit you can select two workshops you would like to attend. The time slots are 9:30 AM - 11:00 AM and 11:30 AM - 1:00 PM and a final agenda will be available soon. The workshops will be followed by a buffet lunch to round off the Summit week

9:30AM - 11:00AM

de.NBI/CIBI Workshop: Analysis of Mass Spectrometry and Sequence Data with KNIME: Julianus Pfeuffer (Universität Tübingen), René Rahn (TU Berlin), Julian Uzkoreit (Universität Bochum), Alexander Fillbrunn (Universität Konstanz)
ROOM: Berlin-Peking

In cooperation with OpenMS from the University of Tübingen, SeqAn from the FU Berlin and PIA from the University of Bochum, this workshop will provide a brief introduction to the analysis of mass spectrometry and sequence data within KNIME. After a short introduction to each of the frameworks/tools and the underlying Generic KNIME Node creation, we will demonstrate how to utilize the tools provided by the corresponding KNIME plugins in order to build workflows that retrieve and analyze common life science data and use standard KNIME nodes to statistically analyze the results. The capabilities of the plugins will be shown on two workflows - one for label-free quantification of proteins and another for metagenomic profiling. The workflows will make use of recent developments in the deNBI-CIBI plugin including the new Docker export functionality. This workshop is recommended for users who are familiar with KNIME and who would like to learn more about using OpenMS, SeqAn and PIA to process data from life-sciences.


Random Forests and Gradient Boosted Trees in KNIME: Dean Abbott (SmarterHQ)
ROOM: Berlin-Berlin 1

This workshop will describe why Random Forests and Gradient Boosted Trees are so much more accurate than individual decision trees or even other ensemble approaches (such as Bagging). We will also look at examples of how to build them in KNIME, and provide practical warnings of how they can fail.


KNIME Big Data Workshop: Tobias Kötter and Björn Lohrmann (KNIME)
ROOM: Berlin-Berlin 3

The KNIME Big Data Workshop is designed to show you solutions for the three Vs of Big Data: Variety, Volume, and Velocity. The workshop will discuss the KNIME Big Data Connectors and in-database processing, advanced analytics powered by Apache Spark and MLlib with the KNIME Extension for Apache Spark, distributed and parallel execution of workflows. We will also discuss high performance scoring services on deployed models based on REST interfaces.


Guided Analytics in Action (Hands On!): Daria Goldmann and Jeany Prinz (KNIME)
ROOM: Berlin-London

After participating in this interactive workshop you'll be able to create your own guided analytics workflows, understand how to use them in KNIME Analytics Platform, and deploy them using the KNIME WebPortal. We'll do this "Learnathon" style which means after a brief introduction to the nodes and techniques used to create guided analytics workflows in KNIME, you will work in small teams to build real workflows. We'll provide some sample use cases for you to work on. This workshop is targeted at people who already have some KNIME expertise. You don’t need to be an expert, but you'll get more out of it if you aren’t a complete beginner. We plan on working with life science datasets but domain knowledge isn't required for the workshop - you'll be fine if you know KNIME.


KNIME Deep Learning Workshop: Adrian Nembach and Christian Dietz (KNIME)
ROOM: Berlin-Montreal

In the KNIME Deep Learning Workshop we will demonstrate the new KNIME Deep Learning capabilities, which were released with KNIME Analytics Platform 3.5. We will discuss how to create, fine-tune, and extend new or existing Keras models in KNIME Analytics Platform to solve a variety of analysis problems such as image or text classification and time-series analysis.


11:30AM - 1:00PM

3D-e-Chem: KNIME Structural Cheminformatics Workflows for Computer-Aided Drug Discovery: J. Kooistra (Vrije Universiteit Amsterdam), M. Vass (Vrije Universiteit Amsterdam), R. McGuire (Radboudumc, BioAxis Research), S. Verhoeven (Netherlands eScience Center), C. de Graaf (Vrije Universiteit Amsterdam/Heptares)
ROOM: Berlin-Montreal

The 3D-e-Chem KNIME nodes enable the integration of cheminformatics and bioinformatics tools for the analysis of structural protein-ligand interaction data and the design of flexible computer-aided drug design workflows. New chemical and biological data analytics tools and workflows have been developed that complement existing cheminformatics KNIME nodes to facilitate the efficient exploitation of structural and pharmacological protein-ligand interaction data from proteome-wide databases (e.g. ChEMBLdb and PDB), as well as customized information systems focused on e.g. G Protein-Coupled Receptors (GPCRdb) and protein kinases (KLIFS). The 3D-e-Chem KNIME node toolbox provides building blocks for the design of new approaches in i) structure-based bioactivity data mapping, ii) structure-based identification of scaffold replacement strategies for ligand design (PLANTS), iii) ligand-based target prediction (SEA/OCEAN), iv) protein sequence-based binding site identification and ligand repurposing (ss-TEA), and v) structure-based pharmacophore comparison for ligand repurposing across protein families (KRIPO/ Silicos-it). Preconfigured workflows facilitate the  efficient use of these 3D-e-Chem tools. The 3D-e-Chem session will provide a hands-on tutorial on the different tools and example workflows, and will offer participants the possibility to work on the design of their own computer-aided drug discovery workflows.


Random Forests and Gradient Boosted Trees in KNIME: Dean Abbott (SmarterHQ)
ROOM: Berlin-Berlin 1

This workshop will describe why Random Forests and Gradient Boosted Trees are so much more accurate than individual decision trees or even other ensemble approaches (such as Bagging). We will also look at examples of how to build them in KNIME, and provide practical warnings of how they can fail.


KNIME Text Mining Workshop: Kilian Thiel (KNIME)
ROOM: Berlin-Berlin 3

Floating through clouds of words, sailing down rivers of topics, entangled in networks of terms. In this workshop we will demonstrate various ways of visualizing unstructured textual data.


KNIME Image Processing Workshop: Simon Schmid and Martin Horn (KNIME)
ROOM: Berlin-Peking

The KNIME Image Processing Workshop provides a brief introduction into the analysis of images with KNIME Image Processing. We will walk through several use cases from various fields including BioImage Analysis and Classification with Deep Learning, Car Counting, and more. We will also provide a short overview of our current and future work. The workshop is recommended for users who are familiar with KNIME Analytics Platform and would like to learn more about KNIME Image Processing.


KNIME Server Workshop: Jon Fuller and Iris Adae (KNIME)
ROOM: Berlin-London

In the KNIME Server Workshop you’ll learn how to get the most out of KNIME Server. Learn how to effectively share workflows, data, and metanodes with colleagues, offload computationally intensive tasks to dedicated hardware, schedule tasks to run automatically,. You'll also learn about server administration managed by KNIME, and deploying analytics generated with KNIME Analytics Platform to end-users with KNIME WebPortal and KNIME Server REST API.


OverviewCourses – Agenda – Workshops – Venue – Registration

The Spring Summit will once again be held at Hotel Berlin, Berlin. They have a contingent of rooms reserved for attendees. When you reserve a room, please use this link for the group “KNIME SPRING SUMMIT 2018” to benefit from the special Summit rate which ensures you a Superior room, including breakfast. We advise booking your room early!


OverviewCoursesAgenda – Workshops – Venue – Registration


RDKit Nodes Development Crash Course

Presented by: Manuel Schwarze, Novartis Institutes of BioMedical Research

Time: Friday, March 9, 2018, 9.00 - 12:30. Room: Berlin-Bangkok

This workshop targets software developers with backgrounds in ChemInformatics and Java, who think about participating in RDKit Nodes Development. Information about this course can be found here.