Cystic fibrosis (CF) is a life-threatening recessive genetic disease caused by mutations in the gene encoding for the cystic fibrosis transmembrane conductance regulator (CFTR). With the discovery of Ivacaftor and Lumacaftor, it has been shown that administration of one or more small molecules can partially restore the CFTR function. Correctors are small molecules that enhance the amount of CFTR on the cell surface, while potentiators improve the gating function of the CFTR channel. Herein, we describe the discovery and optimization of a novel potentiator series. Scaffold hopping, focusing on retaining the different intramolecular contacts, was crucial in the whole discovery process to identify a novel series devoid of genotoxic liabilities. From this series, the clinical candidate GLPG2451 was selected based on its pharmacokinetic properties, allowing QD dosing and based on its low CYP induction potential.

When preparing training, validation and test sets for machine learning on molecular datasets, it is desirable to combine two requirements: 1) robustness, i.e. making a test set that is chemically dissimilar from the training set; 2) data balance, i.e. ensuring that the proportion of data points and the distribution of data labels (categorical) / data values (continuous) are as homogeneous as possible among the sets, for each individual property to model, while partitioning the overall set of compounds as required. Recent literature shows that meeting both these requirements simultaneously is sometimes very difficult. This is especially true for multi-task learning, but also for single-task learning if one aims to balance the distribution of data labels or values, too. In this work we present a method that resolves this issue by first carrying out a chemistry-guided clustering of the initial dataset to ensure the separation of chemical matter, and subsequently applying linear programming to select the lists of clusters that – once assembled into the final sets – result in the best possible data balance.

The methyl esters of L-tyrosine and D-(4-hydroxyphenyl)glycine were directly transformed into the corresponding 2-arylsulfonamido esters with arylsulfonyl chlorides, without protecting the phenolic hydroxy group. The reaction is conducted in a THF/DMF (8:1) mixture as solvent, and using lyophilized solid sodium carbonate as base. The N-arylsulfonylation takes place with good yields (62−85%) in a chemoselective fashion, without racemization of the stereogenic carbon centers. The DMF (2.6 mol/mol amino ester) specific-

No abstract

No abstract