umich-aml/Simeonov2008

This curated dataset represents a subset of the high-throughput fluorescence screening data of 71,391 compunds reported in Simeonov et al., 2008. That study performed screening of the native fluorescence of the compounds to establish a baseline fluorescence threshold and determine which compounds may be more susceptible to false positives in due to their tendency to auto fluoresce at different wavelengths. The associated CIDs from assay IDs 587, 588, 590, 591, 592, 593, and 594 were retrieved using the PubChemR library to query the PubChem REST API in R. Here, only the sanitized SMILEs of active compounds found in more than one assay are reported with their chemical identifiers (SMILEs, InChI, InChIKey, and the sanitized SMILE).

To load into python:

# make sure huggingface module is installed
from datasets import load_dataset

ds = load_dataset("umich-aml/Simeonov2008")

Simeonov A, Jadhav A, Thomas CJ, Wang Y, Huang R, Southall NT, Shinn P, Smith J, Austin CP, Auld DS, Inglese J. Fluorescence spectroscopic profiling of compound libraries. J Med Chem. 2008 Apr 24;51(8):2363-71. DOI: 10.1021/jm701301m. Epub 2008 Mar 26. PMID: 18363325.