Using transcriptomics to guide lead optimization in drug discovery projects: Lessons learned from the QSTAR project

Abstract

The pharmaceutical industry is faced with steadily declining R&D efficiency which results in fewer drugs reaching the market despite increased investment. A major cause for this low efficiency is the failure of drug candidates in late-stage development owing to safety issues or previously undiscovered side-effects. We analyzed to what extent gene expression data can help to de-risk drug development in early phases by detecting the biological effects of compounds across disease areas, targets and scaffolds. For eight drug discovery projects within a global pharmaceutical company, gene expression data were informative and able to support go/no-go decisions. Our studies show that gene expression profiling can detect adverse effects of compounds, and is a valuable tool in early-stage drug discovery decision making.

DeepTox: Toxicity Prediction using Deep Learning

“…Feature-based approaches include (generalized) linear models (e.g., Luco and Ferretti, 1997;Sagardia et al, 2013), random forests, (e.g., Svetnik et al, 2003;Polishchuk et al, 2009), and scoring schemes based on naive Bayes (Bender et al, 2004;Xia et al, 2004). Choosing informative features for the task at hand is key in feature-based methods and requires deep insights into chemical and biological properties and processes (Verbist et al, 2015), such as interactions between molecules (e.g., ligand-target), reactions and enzymes involved, and metabolic modifications of the molecules. Similarity-based approaches, in contrast, require a proper similarity measure between two compounds.…”

Principal bicorrelation analysis: Unraveling associations between three data sources

“…In the present context QSAR requires two data sets: bioactivity (BA) readouts and chemical descriptors for all compounds. We will work within a new paradigm that extends QSAR by including a third data source: gene expression microarray measurements (GE), as it is believed that many drugs may act on the target indirectly by affecting the gene transcription process (Hochreiter et al, 2015;Feng et al, 2009;Searfoss et al, 2005). These microarray experiments are performed on cell lines relevant for the disease under study.…”

“…It is believed that relevant biological data on the various desired and undesired compound effects need to be acquired and integrated in the early stages of the research process. For example, compound-induced perturbations in transcriptomics networks have been used to understand the biology and mechanisms of action (Feng et al, 2009;Searfoss et al, 2005) and their utility in helping the decision making in compound selection has been evaluated in Hochreiter et al (2015). Instead of looking at one or two data sources at a time, data-integration methods aim at using all available data simultaneously so as to more efficiently extract the relevant information required for the decision making.…”

Antiviral Therapy

“…A set of cell lines were used by Verbist et al (2015) to test the effect of over 700 drug candidates on gene transcripts using a microarray readout. The focus was on a predetermined set of genes, some of which-if upregulated-could be toxic, while others-if upregulated-could be therapeutic.…”