EXTENDED COURSE

KNIME

Data-science workflows to build in KNIME without writing code — clean, join, analyse and visualise datasets by wiring nodes on a canvas. KNIME is free, runs on your desktop, and every workflow is reproducible and shareable as a portable recipe. This hands-on course takes you from installing the free Analytics Platform and running your first 2-node workflow, through reading the canvas (nodes, ports and traffic-light states), to building a real pipeline that joins and transforms messy lab exports, visualises them, and adds a machine-learning Learner / Predictor branch.

1Lessons5step-by-step, ~90 min each

Use and understand the node canvas

Build a real data workflow

2Cheat sheetcopy-ready expressions

3Examples5what people built

Dashboards & analytics1

KNIME Scientist AI-native SME

In the gallery

No-code ML classifier on tabular lab data

A workflow splits a labelled dataset, trains a Random Forest classifier using KNIME's learner nodes, evaluates it with a scorer, and deploys it as a local REST endpoint for batch prediction.

A working predictive model is built and validated without writing any code, and retraining is a one-click re-run.

Try it yourself

CSV Reader → Partitioning node (80/20) → Random Forest Learner → Random Forest Predictor → Scorer → ROC Curve node → KNIME Server REST endpoint (deploy).

Research & data tools3

KNIME Scientist

Course starter

Plate-reader CSV cleaning and statistics pipeline

A KNIME workflow reads raw plate-reader exports, removes outlier wells, normalises to controls, calculates mean and CV per condition, and writes a tidy results table plus a bar-chart figure.

A 45-minute manual Excel clean-up is replaced by a reproducible, one-click pipeline any lab member can run.

Try it yourself

CSV Reader → Missing Value node → Row Filter (remove flagged wells) → Math Formula (normalise to DMSO control) → GroupBy (mean, SD, CV per condition) → Box Plot node → Excel Writer.

KNIME Scientist

Course starter

Batch FASTA annotation with REST calls

Reads a multi-sequence FASTA, loops over each entry, queries the UniProt REST API for annotation, and assembles a flat table of sequences with GO terms, organism, and reviewed status.

Hundreds of sequences are annotated overnight without writing a single line of Python.

Try it yourself

File Reader (FASTA) → Chunk Loop Start → REST Client node (UniProt API, GET by accession) → JSON Path → Loop End → Column Appender → CSV Writer.

KNIME Scientist

Course starter

Clinical cohort data QC and reporting

Merges visit records from multiple CSV exports, checks for missing values and out-of-range measurements, flags anomalies, and produces a formatted QC report with per-site summaries.

Every data transfer is quality-checked consistently and a report is ready before the weekly data review call.

Try it yourself

Multiple CSV Readers → Joiner (merge on participant ID) → Missing Value node → Rule Engine (flag out-of-range) → GroupBy (QC stats per site) → Report Template node.

Forms, surveys & feedback1

KNIME Scientist AI-native SME

Course starter

Survey response cleaning and Likert summary

Ingests a raw Qualtrics export, recodes reversed items, filters incomplete responses, calculates composite scores, and outputs a publication-ready summary table with descriptive statistics.

Data cleaning that usually takes a day in SPSS or R is a reusable, auditable KNIME workflow.

Try it yourself

CSV Reader → Row Filter (completion threshold) → Math Formula (recode reversed items) → GroupBy (mean, SD per scale) → Normalizer → Data to Report node.