Why bet on a target
the data cannot pick?
A pharmaceutical company's public pipeline contains this line — “PHD inhibitors: treatment of inflammatory bowel disease and chronic kidney disease”. Yet query the public data and that target is not in the top 500 of the 7,629 targets linked to inflammatory bowel disease. The literature holds one paper.
Over these 20 lessons you query Open Targets, ChEMBL, ClinicalTrials.gov and PubMed yourself to measure where the target ranks, what is holding that rank up, and what evidence lives outside the table. Python runs right inside this page. There is nothing to install.
How you'll learn
The raw material is one line from a company's public pipeline. Starting from a line that names only a target, you recover the drug's code name, its trial phase, its size and its start date — from public data alone.
Not stand-in data. The actual responses from Open Targets, ChEMBL, ClinicalTrials.gov and PubMed, carried verbatim — with function names and JSON shapes identical to the live APIs.
You break the number “14th” into the parts it was built from. Take one part away and it becomes 400th. Reading a ranking and believing one are different acts.
The questions this course cannot answer are printed, as they are, in the final lesson. Never letting an invented number into a ranking — that is the rule here.