High-Throughput Gene Expression Profiles to Define Drug Similarity and Predict Compound Activity

Abstract

By adding biological information, beyond the chemical properties and desired effect of a compound, uncharted compound areas and connections can be explored. In this study, we add transcriptional information for 31K compounds of Janssen's primary screening deck, using the HT L1000 platform and assess (a) the transcriptional connection score for generating compound similarities, (b) machine learning algorithms for generating target activity predictions, and (c) the scaffold hopping potential of the resulting hits. We demonstrate that the transcriptional connection score is best computed from the significant genes only and should be interpreted within its confidence interval for which we provide the stats. These guidelines help to reduce noise, increase reproducibility, and enable the separation of specific and promiscuous compounds. The added value of machine learning is demonstrated for the NR3C1 and HSP90 targets. Support Vector Machine models yielded balanced accuracy values ≥80% when the expression values from DDIT4 & SERPINE1 and TMEM97 & SPR were used to predict the NR3C1 and HSP90 activity, respectively. Combining both models resulted in 22 new and confirmed HSP90-independent NR3C1 inhibitors, providing two scaffolds (i.e., pyrimidine and pyrazolo-pyrimidine), which could potentially be of interest in the treatment of depression (i.e., inhibiting the glucocorticoid receptor (i.e., NR3C1), while leaving its chaperone, HSP90, unaffected). As such, the initial hit rate increased by a factor 300, as less, but more specific chemistry could be screened, based on the upfront computed activity predictions.

Exploring the Use of Compound-Induced Transcriptomic Data Generated From Cell Lines to Predict Compound Activity Toward Molecular Targets

“…GESs were produced for more than 20,000 compounds in 80 human cancer cell lines, tested at various concentration and exposition time. The large scale of this dataset allows the use of GESs in machine learning models for target prediction or drug repurposing (Lee et al, 2016;De Wolf et al, 2018).…”

Tales of 1,008 Small Molecules: Phenomic Profiling through Live-cell Imaging in a Panel of Reporter Cell Lines

“…In the last two decades, technological and analytical innovations in high-throughput microscopy and transcriptomics have enabled the large-scale phenomic profiling of small-molecule libraries [1][2][3][4][5][6][7][8]. These profiling approaches quantify the phenotypic response of cells to compound treatment by simultaneously measuring changes in hundreds or thousands of features, be they transcript levels assessed with gene expression technologies or the morphological characteristics of cells in a microscopy image.…”

Universal nature of drug treatment responses in drug-tissue-wide model-animal experiments using tensor decomposition-based unsupervised feature extraction

“…Kim et al [7] performed computational drug repositioning for gastric cancer using reversal gene expression profiles. Wolf et al [8] analyzed high-throughput gene expression profiles to define drug similarity and predict compound activity. Hodos et al [9] tried to fill missing observations of gene expression of cells treated with drugs by predicting cell-specific drug perturbation profiles using available expression data from related conditions.…”