Drug-induced adverse events prediction with the LINCS L1000 data

Wang, Zichen; Clark, Neil R.; Ma’ayan, Avi

doi:10.1093/bioinformatics/btw168

Cited by 165 publications

(208 citation statements)

References 42 publications

Supporting

Mentioning

206

Contrasting

Order By: Relevance

“…We found a substantially higher rate of positives in the list produced by a pathway‐level PDN approach: 54%, compared to 27% for the gene‐level approach, and 16% for randomly selected drugs. We also obtained up‐ and down‐regulated DEGs from the BarCode method (McCall et al , ; Table EV4), an approach that categorizes gene expression as on or off, and used these genes, as well as the standard DEG list to query the LINCS database (Wang et al , ), a greatly expanded version of CMap (Lamb et al , ). The lists of compounds expected to have a positive effect on sepsis mortality (i.e., up‐ and down‐regulated in adults compared to children) were also curated to assess the frequency of prior positive results in the literature.…”

Section: Resultsmentioning

confidence: 99%

The relative resistance of children to sepsis mortality: from pathways to drug candidates

Joachim

Altschuler

Hutchinson

et al. 2018

Molecular Systems Biology

View full text Add to dashboard Cite

Attempts to develop drugs that address sepsis based on leads developed in animal models have failed. We sought to identify leads based on human data by exploiting a natural experiment: the relative resistance of children to mortality from severe infections and sepsis. Using public datasets, we identified key differences in pathway activity (Pathprint) in blood transcriptome profiles of septic adults and children. To find drugs that could promote beneficial (child) pathways or inhibit harmful (adult) ones, we built an in silico pathway drug network (PDN) using expression correlation between drug, disease, and pathway gene signatures across 58,475 microarrays. Specific pathway clusters from children or adults were assessed for correlation with drug‐based signatures. Validation by literature curation and by direct testing in an endotoxemia model of murine sepsis of the most correlated drug candidates demonstrated that the Pathprint‐PDN methodology is more effective at generating positive drug leads than gene‐level methods (e.g., CMap). Pathway‐centric Pathprint‐PDN is a powerful new way to identify drug candidates for intervention against sepsis and provides direct insight into pathways that may determine survival.

show abstract

Section: Resultsmentioning

confidence: 99%

The relative resistance of children to sepsis mortality: from pathways to drug candidates

Joachim

Altschuler

Hutchinson

et al. 2018

Molecular Systems Biology

View full text Add to dashboard Cite

show abstract

“…Our experiments show that CS is a robust predictor of side effects. The base MLP model, which uses CS features as input, produces ∼11% macro-AUC and ∼2% micro-AUC improvement over the state-of-the-art results provided in [32], which uses both GEX (high quality) and CS features. The multi-modal neural network model, which uses CS, GEX and META features and uses summation in the fusion layer (MMNN.Sum) achieves 0.79 macro-AUC and 0.877 micro-AUC which is the best result among MLP based approaches.…”

Section: Introductionmentioning

confidence: 89%

“…and are not cell or condition (i.e., dosage) specific. To address this issue, Wang et al (2016) utilize the data from the LINCS L1000 project [32]. This project profiles gene expression changes in numerous human cell lines after treating them with a large number of drugs and small-molecule compounds.…”

Section: Introductionmentioning

confidence: 99%

“…This project profiles gene expression changes in numerous human cell lines after treating them with a large number of drugs and small-molecule compounds. By using the gene expression profiles of the treated cells, [32] provides the first comprehensive, unbiased, and cost-effective prediction of ADRs. The paper formulates the problem as a multi-label classification task.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

DeepSide: A Deep Learning Framework for Drug Side Effect Prediction

Uner

Cinbiş

Taştan

et al. 2019

Preprint

View full text Add to dashboard Cite

Drug failures due to unforeseen adverse effects at clinical trials pose health risks for the participants and lead to substantial financial losses. Side effect prediction algorithms have the potential to guide the drug design process. LINCS L1000 dataset provides a vast resource of cell line gene expression data perturbed by different drugs and creates a knowledge base for context specific features. The state-of-the-art approach that aims at using context specific information relies on only the highquality experiments in LINCS L1000 and discards a large portion of the experiments. In this study, our goal is to boost the prediction performance by utilizing this data to its full extent. We experiment with 5 deep learning architectures. We find that a multi-modal architecture produces the best predictive performance among multi-layer perceptron-based architectures when drug chemical structure (CS), and the full set of drug perturbed gene expression profiles (GEX) are used as modalities. Overall, we observe that the CS is more informative than the GEX. A convolutional neural network-based model that uses only SMILES string representation of the drugs achieves the best results and provides 13.0% macro-AUC and 3.1% micro-AUC improvements over the state-of-the-art. We also show that the model is able to predict side effect-drug pairs that are reported in the literature but was missing in the ground truth side effect dataset. DeepSide is available at

show abstract

“…3 This comprehensive profiling provided by L1000 is widely used in drug discovery and repurposing, largely facilitating large scale pharmacology analysis. 4,5 L1000 assay measures the expression of 978 landmark genes with The Luminex FlexMap 3D platform, which can identify 500 different bead color as tags for different genes. To measure all landmark genes within one scan, L1000 separately coupled two different gene barcodes to aliquots of the same bead color and mixed them with a ratio of 2:1.…”

Section: Introductionmentioning

confidence: 99%

A Bayesian approach to accurate and robust signature detection on LINCS L1000 data

Qiu

Lim

et al. 2019

Preprint

View full text Add to dashboard Cite

LINCS L1000 dataset produced by L1000 assay contains numerous cellular expression data induced by large sets of perturbagens. Although it provides invaluable resources for drug discovery as well as understanding of disease mechanisms, severe noise in the dataset makes the detection of reliable gene expression signals difficult. Existing methods for the peak deconvolution, either k-means based or Gaussian mixture model, cannot reliably recover the accurate expression level of genes in many cases, thereby limiting their robust applications in biomedical studies. Here, we have developed a novel Bayes' theory based deconvolution algorithm that gives unbiased likelihood estimations for peak positions and characterizes the peak with a probability based z-scores. Based on above algorithm, a pipeline is built to process raw data from L1000 assay into signatures that represent the features of perturbagen. The performance of the proposed new pipeline is rigorously evaluated using the similarity between bio-replicates and between drugs with shared targets. The results show that the new signature derived from the proposed algorithm gives a substantially more reliable and informative representation for perturbagens than existing methods. Thus, our new Bayesian-based peak deconvolution and z-score calculation method may significantly boost the performance of invaluable L1000 data in the down-stream applications such as drug repurposing, disease modeling, and gene function prediction.

show abstract

Drug-induced adverse events prediction with the LINCS L1000 data

Abstract: Supplementary data are available at Bioinformatics online.

Cited by 165 publications

References 42 publications

The relative resistance of children to sepsis mortality: from pathways to drug candidates

The relative resistance of children to sepsis mortality: from pathways to drug candidates

DeepSide: A Deep Learning Framework for Drug Side Effect Prediction

A Bayesian approach to accurate and robust signature detection on LINCS L1000 data

Contact Info

Product

Resources

About