### WHAT DRIVES US

Knowledge about the chemical properties of small molecules is an essential feature to understand their behaviour within their environment. Scientists in academia and big pharma synthesize and screen millions of molecules to discover new chemical probes and drugs. Such molecules can enlarge our understanding of biology and provide treatments for severe diseases that cause millions of deaths every year. Many small molecules are not well characterized, and with the sheer number of available or synthesizable compounds, it seems unlikely that this will ever happen. Therefore,  ***the meaningful prediction of chemical properties of novel compounds will provide an essential tool to speed up research and allows us to focus more on the complex and often even less understood biology.***

### WHAT WE EXPECT FROM YOU

EU-OPENSCREEN ERIC and SLAS challenge you to develop a reliable algorithm that can predict the solubility of a small molecule, an essential feature of all biologically active compounds. 

#### WHAT WE PROVIDE

EU-OPENSCREEN ERIC provides a high-quality data set of experimentally measured aqueous solubility of about 100,000 small molecules which was produced at an EU-OPENSCREEN ERIC high throughput screening partner site. 70,000 of these molecules will be available for download on Kaggle, and the residual 30,000 compounds will be withheld for prediction. 

### Protocol used to measure solubility

Compounds were dispensed (50 nL from a 10 mM solution in DMSO) to the assay plates (Greiner, Ref: 781801) by employing an Echo550 dispenser. Amiodarone and Phenytoin were employed as assay controls
50 µL of PBS (pH=7.4) were added to each well to achieve a 10 µM concentration with a 0.1% of DMSO.
Plates were sealed and incubated at 37°C under gentle stirring for 2 h.
After the incubation plates were centrifuged for 20 sec at 200xg and the nephelometry was detected in a Nephelostar reader (BMG Labtech).
The entire screening was run in duplicates (N=2), but the duplicates were not in the same plates. Thus, the screening was carried out by assaying two identical plates with the compounds in the same location. This means that there were 352 compounds per plate in two identical plates for calculating the average and SD. The other wells were employed for blank measurements and controls. Data was analyzed by subtracting the nephelometry values observed in wells containing 0.1% DMSO. The solubility threshold for classifying compounds as high, medium and low solubility was fixed based on the average nephelometry values observed for phenytoin (high solubility) and amiodarone (medium-low solubility). Thus, the thresholds were fixed as follows:
High solubility: Nephelometry values lower than 50000
Medium solubility: Nephelometry values between 50000 and 100000
Low solubility: Nephelometry values higher than 100000

### Evaluation of models

Results will be evaluated using the Kappa coefficient calculated on the independent test set. The winner will receive the opportunity to present their winning algorithm in an SLAS journal, SLAS Discovery, and will be given the opportunity to present his/her research at the 2023 European SLAS conference in Brussels. 

### ACKNOWLEDGMENTS

We thank Prof. Dr. Mabel Loza and Dr. Jose Brea of the BioFarma Research group from the University of Santiago de Compostela for the preparation of the high-quality solubility data set.

We thank Dr. Andrea Zaliani from the Fraunhofer Institute for Translational Medicine and Pharmacology, Prof. Dr. Jing Tang and Wenyu Wang from the University of Helsinki for their expert input on data curation, scoring algorithms and role as competition judges.

We thank Dr. Julio Martin, Dr. Christian Parker, Jill Hronek, Kathy Daniels and Dr. Hannah Rosen from the SLAS and Dr. Wolfgang Fecke and Dr. Robert Harmel from EU-OPENSCREEN ERIC for organizing the competition.