deepchem
Biophysical properties of the clinical-stage antibody landscape
http://www.pnas.org/content/114/5/944.full
Contains a large (by standards of field :-)) dataset of all antibodies tested in phase-2 or phase-3 clinical trials measured "criteria regarding the feasibility of their manufacture, stability in storage, and absence of off-target stickiness."
This could be a valuable dataset for benchmarking antibody algorithmic techniques.
"Great catch, @rbharath . This is a highly valuable reference. The PNAS dataset of 137 clinical-stage antibodies with $\approx12$ developability metrics (e.g., $\text{Tm}, \text{PSR}, \text{HIC}$) would be an excellent, high-value set for benchmarking our current $\text{ML}$ models. I propose we create a dedicated branch to integrate this data and compare our in silico predictions against the published experimental values to see how accurately we are predicting real-world developability risks."
