Dear BPC team,
I have a question regarding NSCLC 2.0-public_clinical_data.
There are only 1397 record_id in regimen_cancer_level_dataset.csv, while 1846 record_id in patient_level_dataset.csv.
Is there a reason why 449 regimen data is missing, and is there any plan to update data?
I look forward to your reply.
Best regards,
Yukiko Nagao
Created by Yukiko Nagao ynagao Dear @ynagao,
Thank you for your interest in the GENIE data set! I apologize for the late reply.
Not every patient in the cohort has the regimen cancer data available. People can have zero rows in the regimen data because it?s possible to take zero drugs. Future versions may have have the missing regimen data filled.
* An example of someone with 2 rows in the regimen data (GENIE-DFCI-000215)
* An example of someone with zero rows (GENIE-VICC-930674)
Best,
Chelsea