Integrating High-Dimensional Transcriptomics and Image Analysis Tools into Early Safety Screening: Proof of Concept for a New Early Drug Development Strategy

Verbist, Bie; Verheyen, Geert R.; Vervoort, Liesbet; Crabbe, Marjolein; Beerens, D.; Bosmans, Cindy; Jaensch, Steffen; Osselaer, Steven; Talloen, Willem; Wyngaert, Ilse Van den; Hecke, Geert Van; Wuyts, D.; Goethem, Freddy Van; Göhlmann, Hinrich W. H.

doi:10.1021/acs.chemrestox.5b00103

Cited by 10 publications

(3 citation statements)

References 56 publications

(89 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…39 Given the advancements made in this article in combination with our strategic investment into generating L1000 profiles and target deconvolution strategies based on high content imaging, we are establishing the means to rapidly propose and test hypotheses for the likely mechanism underlying any biological activity that may be observed for Janssen's dark chemical matter. These capabilities provide the tools to unravel mechanistic insights into both the desired activities as well as any undesired activities 40 of the compounds we process through the Janssen drug discovery and development pipeline.…”

Section: Drug Similarity and Activity Predictionsmentioning

confidence: 99%

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

Wolf

Cougnaud²,

Hoorde³

et al. 2018

ASSAY and Drug Development Technologies

View full text Add to dashboard Cite

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.

show abstract

Section: Drug Similarity and Activity Predictionsmentioning

confidence: 99%

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

Wolf

Cougnaud²,

Hoorde³

et al. 2018

ASSAY and Drug Development Technologies

View full text Add to dashboard Cite

show abstract

“…Indeed, compound-induced transcriptional effects can be translated into ''gene signatures'' (i.e., set of differentially expressed genes characterizing the activity of a given compound, pathway, or disease), which can be used to discover new connections among compounds, pathways, and diseases. [2][3][4][5][6][7][8] To this end, Peck et al 9 developed a cost-effective transcriptional profiling methodology, in which up to 100 transcripts can be measured in HTS mode, combining multiplex ligation-mediated amplification with the Luminex FlexMap (Luminex, Austin, TX) optically addressed and barcoded microsphere, and flow cytometric detection technology. The combination of ligated-mediated amplification and an optically addressed microsphere and flow cytometric detection has since been extended to 978 gene transcripts.…”

Section: Introductionmentioning

confidence: 99%

Transcriptional Characterization of Compounds: Lessons Learned from the Public LINCS Data

Wolf

Bondt

Turner³

et al. 2016

ASSAY and Drug Development Technologies

View full text Add to dashboard Cite

The NIH-funded LINCS program has been initiated to generate a library of integrated, network-based, cellular signatures (LINCS). A novel high-throughput gene-expression profiling assay known as L1000 was the main technology used to generate more than a million transcriptional profiles. The profiles are based on the treatment of 14 cell lines with one of many perturbation agents of interest at a single concentration for 6 and 24 hours duration. In this study, we focus on the chemical compound treatments within the LINCS data set. The experimental variables available include number of replicates, cell lines, and time points. Our study reveals that compound characterization based on three cell lines at two time points results in more genes being affected than six cell lines at a single time point. Based on the available LINCS data, we conclude that the most optimal experimental design to characterize a large set of compounds is to test them in duplicate in three different cell lines. Our conclusions are constrained by the fact that the compounds were profiled at a single, relative high concentration, and the longer time point is likely to result in phenotypic rather than mechanistic effects being recorded.

show abstract

“…The focus on what assays to employ and how to use them differs among scientists and companies − as well as high-throughput approaches to prediction of the toxicity of environmental chemicals. , …”

mentioning

confidence: 99%

Toxicology Strategies for Drug Discovery - Present and Future: Introduction

Humphreys

Will

Guengerich

2016

Chem. Res. Toxicol.

View full text Add to dashboard Cite

Integrating High-Dimensional Transcriptomics and Image Analysis Tools into Early Safety Screening: Proof of Concept for a New Early Drug Development Strategy

Cited by 10 publications

References 56 publications

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

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

Transcriptional Characterization of Compounds: Lessons Learned from the Public LINCS Data

Toxicology Strategies for Drug Discovery - Present and Future: Introduction

Contact Info

Product

Resources

About