Drug Activity Data with ChEMBL Records at Multiple Confidence Levels

Three distinct sets of approved drugs are linked to ChEMBL bioactivity records across individual time intervals. The approved drug list originates from the DrugBank database. Each drug entry includes associated activity data categorized by varying levels of confidence.

Use Cases

• Train models to predict drug-target interactions based on time-series activity data.
• Benchmark drug repurposing algorithms using approved drugs from DrugBank.
• Analyze the relationship between activity confidence levels and experimental outcomes.

Strengths

• Drug entries are sourced from the authoritative DrugBank database.
• Activity data is associated with individual time intervals, providing temporal context.
• Data is stratified into three sets with varying confidence levels for analysis.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment.
• Last update date is unknown; freshness unverified.

Provenance

Source

DrugBank and ChEMBL databases.

Collection Method

Compilation and association of approved drugs with existing bioactivity records.