Integration of human cell lines gene expression and chemical properties of drugs for Drug Induced Liver Injury prediction

Lesinski, Wojciech; Mnich, Krzysztof; Golińska, Agnieszka Kitlas; Rudnicki, Witold R.

doi:10.1186/s13062-020-00286-z

Cited by 5 publications

(6 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The DILI definition was based on FDA DILI classification (Chen et al, 2016). We obtained AUC = 0.74 using SuperLearner methodology (van der Laan et al, 2007) in our study (Lesiński et al, 2021). Similar results were obtained in Liu et al (2021).…”

Section: Introductionsupporting

confidence: 76%

“…In the final stage of the study, the results of the predictive models based on single data set were combined into a single model by means of the super learning approach. This methodology significantly improved our results in a previous DILI prediction study (CAMDA2019; Lesiński et al, 2021). This procedure includes verification of the results by cross-validation, hence entire modeling procedure described earlier had to be repeated multiple times within a cross-validation loop.…”

Section: Composite Modelsmentioning

confidence: 84%

See 1 more Smart Citation

Prediction of Alternative Drug-Induced Liver Injury Classifications Using Molecular Descriptors, Gene Expression Perturbation, and Toxicology Reports

2021

Self Cite

View full text Add to dashboard Cite

Motivation: Drug-induced liver injury (DILI) is one of the primary problems in drug development. Early prediction of DILI, based on the chemical properties of substances and experiments performed on cell lines, would bring a significant reduction in the cost of clinical trials and faster development of drugs. The current study aims to build predictive models of risk of DILI for chemical compounds using multiple sources of information.Methods: Using several supervised machine learning algorithms, we built predictive models for several alternative splits of compounds between DILI and non-DILI classes. To this end, we used chemical properties of the given compounds, their effects on gene expression levels in six human cell lines treated with them, as well as their toxicological profiles. First, we identified the most informative variables in all data sets. Then, these variables were used to build machine learning models. Finally, composite models were built with the Super Learner approach. All modeling was performed using multiple repeats of cross-validation for unbiased and precise estimates of performance.Results: With one exception, gene expression profiles of human cell lines were non-informative and resulted in random models. Toxicological reports were not useful for prediction of DILI. The best results were obtained for models discerning between harmless compounds and those for which any level of DILI was observed (AUC = 0.75). These models were built with Random Forest algorithm that used molecular descriptors.

show abstract

Section: Introductionsupporting

confidence: 76%

Section: Composite Modelsmentioning

confidence: 84%

Prediction of Alternative Drug-Induced Liver Injury Classifications Using Molecular Descriptors, Gene Expression Perturbation, and Toxicology Reports

2021

Self Cite

View full text Add to dashboard Cite

show abstract

“…The improper use of health products, such as prescription medicines, over-the-counter drugs and traditional Chinese medicines, can cause varying degrees of liver damage ( 27 ). The incidence of drug-induced liver injury (DILI) has been increasing in recent years ( 28 ).…”

Section: Discussionmentioning

confidence: 99%

FTY720 attenuates APAP‑induced liver injury via the JAK2/STAT3 signaling pathway

Kang

Pan

et al. 2022

Int J Mol Med

View full text Add to dashboard Cite

As the current clinical treatment of acetaminophen (APAP)-induced liver injury (AILI) has its limitations, new and effective treatment methods are required. Fingolimod (FTY720) is an immunosuppressive drug developed in recent years that has been shown to have a protective effect against ischemia/reperfusion liver injury. However, the role of FTY720 in AILI remains unclear. The aim of the present study was to determine whether FTY720 has a protective effect on AILI. AILI was induced using intraperitoneal injection of 300 mg/kg APAP in male C57BL/6J mice. Following APAP challenge, the mice were administered 5 mg/kg FTY720 for 30 min. Protein expression levels were measured using western blot analysis. Cell viability was examined using Cell Counting Kit-8 assays. mRNA levels were measured using reverse transcription-quantitative PCR. Inflammation levels were evaluated using immunohistochemistry. Cell death and reactive oxygen species levels were examined using immunofluorescence. Furthermore, laser scanning intravital microscopy was used to directly observe immune cell recruitment. APAP treatment increased the serum levels of alanine transaminase and aspartate transaminase at the 6- and 12-h time-points, suggesting liver tissue damage. However, FTY720 attenuated the liver injury induced by APAP by reducing the recruitment of immune cells and the release of pro-inflammatory cytokines and chemokines. FTY720 activated JAK2/STAT3 signaling and regulated the expression of BAX, BCL-2 and p65 to inhibit apoptosis and inflammation. In addition, compared with APAP treatment, the viability of primary hepatocytes treated with APAP and FTY720 was increased. Inhibition of JAK2/STAT3 signaling attenuated the protective, antioxidant effects of FTY720. In conclusion, FTY720 reduced liver injury by regulating the JAK2/STAT3 signaling pathway. This compound was capable of inhibiting oxidative stress to reduce hepatocyte death and the infiltration of neutrophils in the liver.

show abstract

“…The DILI classifications for this challenge also changed from binary to a most, less, ambiguous, and no-DILI concern which is in line with the FDA DILIrank dataset. Predictive model rates from multiple distinct approaches to this challenge in 2019 often yielded similar accuracy results around 0.70 (Aguirre-Plans et al, 2021;Lesiński et al, 2021;Liu et al, 2021). While it is difficult to make a direct comparison across the years of these challenges considering how the fundamental elements of predictive modeling, such as the data sources and classifications, have changed, the goal of the challenge has remained the same in modeling the risk of a drug to lead to liver injury in patients.…”

Section: Discussionmentioning

confidence: 99%

“…The CMap Drug Safety Challenge expanded in 2019 by including not only expression data from L1000 CMap but also by allowing a wide variety of external data sources that were incorporated into each study. Lesinski et al achieved their best predictive results by incorporating molecular drug properties along with the most informative variables from five of 13 cell line expression models via a super learner method (Lesiński et al, 2021). Including molecular property information improved their cell line models' accuracy up to 73% utilizing a random forest algorithm, which originally ranged from 55 to 61%.…”

Section: Introductionmentioning

confidence: 99%

Predicting Drug-Induced Liver Injury Using Machine Learning on a Diverse Set of Predictors

et al. 2021

View full text Add to dashboard Cite

A major challenge in drug development is safety and toxicity concerns due to drug side effects. One such side effect, drug-induced liver injury (DILI), is considered a primary factor in regulatory clearance. The Critical Assessment of Massive Data Analysis (CAMDA) 2020 CMap Drug Safety Challenge goal was to develop prediction models based on gene perturbation of six preselected cell-lines (CMap L1000), extended structural information (MOLD2), toxicity data (TOX21), and FDA reporting of adverse events (FAERS). Four types of DILI classes were targeted, including two clinically relevant scores and two control classifications, designed by the CAMDA organizers. The L1000 gene expression data had variable drug coverage across cell lines with only 247 out of 617 drugs in the study measured in all six cell types. We addressed this coverage issue by using Kru-Bor ranked merging to generate a singular drug expression signature across all six cell lines. These merged signatures were then narrowed down to the top and bottom 100, 250, 500, or 1,000 genes most perturbed by drug treatment. These signatures were subject to feature selection using Fisher’s exact test to identify genes predictive of DILI status. Models based solely on expression signatures had varying results for clinical DILI subtypes with an accuracy ranging from 0.49 to 0.67 and Matthews Correlation Coefficient (MCC) values ranging from -0.03 to 0.1. Models built using FAERS, MOLD2, and TOX21 also had similar results in predicting clinical DILI scores with accuracy ranging from 0.56 to 0.67 with MCC scores ranging from 0.12 to 0.36. To incorporate these various data types with expression-based models, we utilized soft, hard, and weighted ensemble voting methods using the top three performing models for each DILI classification. These voting models achieved a balanced accuracy up to 0.54 and 0.60 for the clinically relevant DILI subtypes. Overall, from our experiment, traditional machine learning approaches may not be optimal as a classification method for the current data.

show abstract

Integration of human cell lines gene expression and chemical properties of drugs for Drug Induced Liver Injury prediction

Cited by 5 publications

References 33 publications

Prediction of Alternative Drug-Induced Liver Injury Classifications Using Molecular Descriptors, Gene Expression Perturbation, and Toxicology Reports

Prediction of Alternative Drug-Induced Liver Injury Classifications Using Molecular Descriptors, Gene Expression Perturbation, and Toxicology Reports

FTY720 attenuates APAP‑induced liver injury via the JAK2/STAT3 signaling pathway

Predicting Drug-Induced Liver Injury Using Machine Learning on a Diverse Set of Predictors

Contact Info

Product

Resources

About