One of the most time-consuming parts of any data analysis is curating the input data prior to any model building. This Knime workflow is fully documented and described and as such is an invaluable starting point.
A semi-automated procedure is made available to support scientists in data preparation for modelling purposes. The procedure address:
- Automatic chemical data retrieval (i.e., SMILES) from different, orthogonal web based databases, by using two different identifiers, i.e. chemical name and CAS registration number. Records were scored based on the coherence of information retrieved from different web sources.
- Data curation procedure performed to top scored records. The procedure includes removal of inorganic and organometallic compounds and mixtures, neutralization of salts, removal of duplicates, checking of tautomeric forms.
- Standardization of chemical structures yielding to ready-to-use data for the development of QSARs.
In many companies/institutions/universities new arrivals are presented with a variety of desktop tools with little or no advice on how to use them other than "pick it up as you along". This workshop is intended to provide expert tutorials to get you started and show what can be achieved with the software.
The tutorials will be given a series of outstanding experts Christian Lemmen (BioSolveIT), Akos Tarcsay (ChemAxon), Giovanna Tedesco (Cresset), Dan Ormsby (Dotmatics) Greg Landrum (Knime ) and Matt Segall (Optibrium), you will be able to install the software packages on you own laptops together with a license to allow you to use it for a limited period after the event.
Registration and full details are here.
What’s New in KNIME Analytics Platform 3.6.
- KNIME Deep Learning
- Constant Value Column Filter
- Numeric Outliers
- Column Expressions
- Git Nodes
- Call Workflow (Table Based)
- KNIME Server Connection
- Text Processing
- Usability Improvements
- Connect/Unconnect nodes using keyboard shortcuts
- Replacing and connecting nodes with node drop
- Node repository search
- Usability improvements in the KNIME Explorer
- Performance: Column Store (Preview)
- Making views beautiful: CSS changes
- KNIME Big Data Extensions
- Create Local Big Data Environment
- KNIME H2O Sparkling Water Integration
- Support for Apache Spark v2.3
- Big Data File Handling Nodes (Parquet/ORC)
- Spark PCA
- Spark Pivot
- Frequent Item Sets and Association Rules
- Create Spark Context via Livy
- Database Integration
- Apache Kafka Integration
Management (Client Preferences)
- Job View (Preview)
- Distributed Executors (Preview)
General release notes
JSON Path library update
- Java Snippet Bundle Imports
I suspect it will be the KNIME Deep learning that will catch the eye, the ability to set up deep learning models using drag and drop. Use regular Tensorflow models within KNIME Analytics Platform and seamlessly convert from Keras to Tensorflow for efficient network execution
The new Create Local Big Data Environment node creates a fully functional local big data environment including Apache Spark, Apache Hive and HDFS. It allows you to try out the nodes of the KNIME Big Data Extensions without a Hadoop cluster.
- New Date & Time integration
- Integration with the H2O machine learning library
- KNIME Personal Productivity now part of KNIME Analytics Platform
- Wrapped metanode composite view
- A new version of the Python integration
- Logistic Regression nodes are more scalable, faster, and support regularization
- Audio and speech recognition nodes
- New Cloud Connectors
Workflow tools have become increasingly popular Pipeline Pilot, Knime and Taverna and perhaps the best known. Most are desktop client based but some have a web page that allow users to run protocols that expert users have created.
Dotmatics Reaction Workflows (RW) is a web-based tool that allow users to build workflows from nodes that provide inputs and outputs or perform actions, including ones to perform reaction-, scaffold-, and transform-based enumeration, and it is all done within a web browser interface using drag and drop. I've been looking at reaction workflow for enumerating a potential library array.