The impact of collapsing data on microarray analysis and DILI prediction

Pessiot, Jean-François; Wong, Pui Shan; Maruyama, Toru; Morioka, Ryoko; Aburatani, Sachiyo; Tanaka, Michihiro; Fujibuchi, Wataru

doi:10.4161/sysb.24255

Cited by 6 publications

(7 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For instance, and as averaged across folds of cross-validation, a subset of only about 300 genes was used for training the prediction models in the human in vitro study instead of the original 18,988 genes included by the FARMS 16 summarization. The solid performance of multiclassifier approach was not surprising 17,18 as several previous studies 19,20 on this data have already reported good results with single classification algorithms such as support vector machines or gradient boosting. In our case, the performance was boosted by both feature selection and classifier ensembling.…”

Section: Discussionsupporting

confidence: 54%

Matrix factorization-based data fusion for drug-induced liver injury prediction

Žitnik

Zupan

2014

Systems Biomedicine

View full text Add to dashboard Cite

Traditional studies of liver toxicity involve screening compounds through in vivo and in vitro tests. They need to distinguish between compounds that represent little or no health concern and those with the greatest likelihood to cause adverse effects in humans. High-throughput and toxicogenomic screening methods coupled with a plethora of circumstantial evidence provide a challenge for improved toxicity prediction and require appropriate computational methods that integrate various biological, chemical and toxicological data. We report on a data fusion approach for prediction of drug-induced liver injury potential in humans using microarray data from the Japanese Toxicogenomics Project (TGP) as provided for the contest by CAMDA 2013 Conference. Our aim was to investigate if the data from different TGP studies could be fused together to boost prediction accuracy. We were also interested if in vitro studies provided sufficient information to refrain from studies in animals. We show that our recently proposed matrix factorization-based data fusion provides an elegant computational framework for integration of the TGP and related data sets, 29 data sets in total. Fusion yields a high cross-validated accuracy (AUC of 0.819 for in vivo assays), which is above the accuracy of the established machine learning procedure of stacked classification with feature selection. Our data analysis shows that animal studies may be replaced with in vitro assays (AUC D 0.799) and that liver injury in humans can be predicted from animal data (AUC D 0.811). Our principal contribution is a demonstration that analysis of toxicogenomic data can substantially benefit from data fusion with directly and circumstantially related data sets.

show abstract

Section: Discussionsupporting

confidence: 54%

Matrix factorization-based data fusion for drug-induced liver injury prediction

Žitnik

Zupan

2014

Systems Biomedicine

View full text Add to dashboard Cite

show abstract

“…For instance, and as averaged across folds of crossvalidation, a subset of only about 300 genes was used for training the prediction models in the human in vitro study instead of the original 18,988 genes included by the FARMS 16 summarization. The solid performance of multi-classifier approach was not surprising 17,18 as several previous studies 19,20 on this data have already reported good results with single classification algorithms such as support vector machines or gradient boosting. In our case, the performance was boosted by both feature selection and classifier ensembling.…”

Section: Discussionsupporting

confidence: 53%

“…It is surprising that in vivo assays, which relied on an animal model, performed better than human assays, given the aim was to predict DILI potential in humans. However, Pessiot et al 19 similarly observed that using in vivo animal data was more informative than using in vitro human data. Their AUC scores obtained by a linear support vector machine classifier and inferred from separate toxicogenomic studies were surpassed by those reported by our fusion-based approach.…”

Section: Discussionmentioning

confidence: 99%

Survival regression by data fusion

Žitnik

Zupan

2014

Systems Biomedicine

View full text Add to dashboard Cite

Traditional studies of liver toxicity involve screening compounds through in vivo and in vitro tests. They need to distinguish between compounds that represent little or no health concern and those with the greatest likelihood to cause adverse effects in humans. high-throughput and toxicogenomic screening methods coupled with a plethora of circumstantial evidence provide a challenge for improved toxicity prediction and require appropriate computational methods that integrate various biological, chemical and toxicological data. We report on a data fusion approach for prediction of drug-induced liver injury potential in humans using microarray data from the Japanese Toxicogenomics Project (TGP) as provided for the contest by caMDa 2013 conference. Our aim was to investigate if the data from different TGP studies could be fused together to boost prediction accuracy. We were also interested if in vitro studies provided sufficient information to refrain from studies in animals. We show that our recently proposed matrix factorization-based data fusion provides an elegant computational framework for integration of the TGP and related data sets, 29 data sets in total. Fusion yields a high cross-validated accuracy (aUc of 0.819 for in vivo assays), which is above the accuracy of the established machine learning procedure of stacked classification with feature selection. Our data analysis shows that animal studies may be replaced with in vitro assays (aUc = 0.799) and that liver injury in humans can be predicted from animal data (aUc = 0.811). Our principal contribution is a demonstration that analysis of toxicogenomic data can substantially benefit from data fusion with directly and circumstantially related data sets.

show abstract

“…Over the past few years, DILI has significantly become one of the most concerning topics in drug discovery. − An up-to-date search on PubMed using the keyword “DILI” has indicated this research trend. Besides experimental approaches, − computational studies − on compounds causing DILI were also conducted to partially address the limitations of in vitro and in vivo experiments …”

Section: Introductionmentioning

confidence: 99%

Predicting Drug-Induced Liver Injury Using Convolutional Neural Network and Molecular Fingerprint-Embedded Features

Nguyen-Vo

Nguyen

et al. 2020

ACS Omega

View full text Add to dashboard Cite

As a critical issue in drug development and postmarketing safety surveillance, drug-induced liver injury (DILI) leads to failures in clinical trials as well as retractions of on-market approved drugs. Therefore, it is important to identify DILI compounds in the early-stages through in silico and in vivo studies. It is difficult using conventional safety testing methods, since the predictive power of most of the existing frameworks is insufficiently effective to address this pharmacological issue. In our study, we employ a natural language processing (NLP) inspired computational framework using convolutional neural networks and molecular fingerprint-embedded features. Our development set and independent test set have 1597 and 322 compounds, respectively. These samples were collected from previous studies and matched with established chemical databases for structural validity. Our study comes up with an average accuracy of 0.89, Matthews’s correlation coefficient (MCC) of 0.80, and an AUC of 0.96. Our results show a significant improvement in the AUC values compared to the recent best model with a boost of 6.67%, from 0.90 to 0.96. Also, based on our findings, molecular fingerprint-embedded featurizer is an effective molecular representation for future biological and biochemical studies besides the application of classic molecular fingerprints.

show abstract

The impact of collapsing data on microarray analysis and DILI prediction

Cited by 6 publications

References 22 publications

Matrix factorization-based data fusion for drug-induced liver injury prediction

Matrix factorization-based data fusion for drug-induced liver injury prediction

Survival regression by data fusion

Predicting Drug-Induced Liver Injury Using Convolutional Neural Network and Molecular Fingerprint-Embedded Features

Contact Info

Product

Resources

About