Cheminformatics Analysis of Assertions Mined from Literature That Describe Drug-Induced Liver Injury in Different Species
Open accessThe DOI matches its Crossref record; 28 of the 28 references it cites were found in a registry or an index.
Abstract
Drug-induced liver injury is one of the main causes of drug attrition. The ability to predict the liver effects of drug candidates from their chemical structures is critical to help guide experimental drug discovery projects toward safer medicines. In this study, we have compiled a data set of 951 compounds reported to produce a wide range of effects in the liver in different species, comprising humans, rodents, and nonrodents. The liver effects for this data set were obtained as assertional metadata, generated from MEDLINE abstracts using a unique combination of lexical and linguistic methods and ontological rules. We have analyzed this data set using conventional cheminformatics approaches and addressed several questions pertaining to cross-species concordance of liver effects, chemical determinants of liver effects in humans, and the prediction of whether a given compound is likely to cause a liver effect in humans. We found that the concordance of liver effects was relatively low (ca. 39-44%) between different species, raising the possibility that species specificity could depend on specific features of chemical structure. Compounds were clustered by their chemical similarity, and similar compounds were examined for the expected similarity of their species-dependent liver effect profiles. In most cases, similar profiles were observed for members of the same cluster, but some compounds appeared as outliers. The outliers were the subject of focused assertion regeneration from MEDLINE as well as other data sources. In some cases, additional biological assertions were identified, which were in line with expectations based on compounds' chemical similarities. The assertions were further converted to binary annotations of underlying chemicals (i.e., liver effect vs no liver effect), and binary quantitative structure-activity relationship (QSAR) models were generated to predict whether a compound would be expected to produce liver effects in humans. Despite the apparent heterogeneity of data, models have shown good predictive power assessed by external 5-fold cross-validation procedures. The external predictive power of binary QSAR models was further confirmed by their application to compounds that were retrieved or studied after the model was developed. To the best of our knowledge, this is the first study for chemical toxicity prediction that applied QSAR modeling and other cheminformatics techniques to observational data generated by the means of automated text mining with limited manual curation, opening up new opportunities for generating and modeling chemical toxicology data.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The check wasn’t confident either way, so it gives no verdict — never disputed.
In the citing paper
“Of note, the 4 references (comprising 6 studies) with sample sizes over 200 all fall within this category [68–71].”
From Animal to human translation: a systematic scoping review of reported concordance rates (2019) · cites this paper as [69]
Experimental — accuracy not yet measuredIn the citing paper
“However, the high structural diversity and complexity of nanomaterials typically lead to specific challenges,230 especially when it comes to the choice of molecular descriptors.”
From QSAR without borders (2020) · cites this paper as [230]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
The Nature of Statistical Learning Theory
Vapnik, V. N. (2000) · Springer eBooks · doi:10.1007/978-1-4757-3264-1 · Cited by 10,696
Concordance of the toxicity of pharmaceuticals in humans and in animals
Olson, H., Betton, G., Robinson, D., Thomas, K., Monro, A., Kolaja, G., Lilly, P., Sanders, J., Sipes, G., Bracken, W., et al. (2000) · Regulatory Toxicology and Pharmacology · doi:10.1006/rtph.2000.1399 · Cited by 2,050 · cited 2×
“However, recent experimental studies (4;27;28) support the concordance results (40–44”
ResultO’Brien, P. J., Irwin, W., Diaz, D., Howard-Cofield, E., Krejsa, C. M., Slaughter, M. R., Gao, B., Kaludercic, N., Angeline, A., Bernardi, P., et al. (2006) · Archives of Toxicology · doi:10.1007/s00204-006-0091-3 · Cited by 609 · cited 3×
“However, recent experimental studies (4;27;28) support the concordance results (40–44”
BackgroundResultCellular Imaging Predictions of Clinical Drug-Induced Liver Injury
Xu, J. J., Henstock, P. V., Dunn, M. C., Smith, A. R., Chabot, J. R., & de Graaf, D. (2008) · Toxicological Sciences · doi:10.1093/toxsci/kfn109 · Cited by 492
Abboud, G., & Kaplowitz, N. (2007) · Drug Safety · doi:10.2165/00002018-200730040-00001 · Cited by 479
Predictive QSAR Modeling Workflow, Model Applicability Domains, and Virtual Screening
Tropsha, A., & Golbraikh, A. (2007) · Current Pharmaceutical Design · doi:10.2174/138161207782794257 · Cited by 478 · cited 1×
“Best practices to derive and select the best models with high predictive abilities from a modeling set have been detailed elsewhere (26).”
BackgroundSelf-citationTetko, I. V., Sushko, I., Pandey, A. K., Zhu, H., Tropsha, A., Papa, E., Öberg, T., Todeschini, R., Fourches, D., & Varnek, A. (2008) · Journal of Chemical Information and Modeling · doi:10.1021/ci800151m · Cited by 416 · cited 1×
“2 out of these 11 compounds were found to fall outside of the models' domain of applicability (defined based on chemical similarity threshold in the descriptor space as described in (32;33).”
BackgroundSelf-citationKaplowitz, N. (2004) · Clinical Infectious Diseases · doi:10.1086/381446 · Cited by 402
Fung, M., Thornton, A., Mybeck, K., Wu, J. H.-H., Hornbuckle, K., & Muniz, E. (2001) · Drug Information Journal · doi:10.1177/009286150103500134 · Cited by 384
Combinatorial QSAR Modeling of Chemical Toxicants Tested against Tetrahymena pyriformis
Zhu, H., Tropsha, A., Fourches, D., Varnek, A., Papa, E., Gramatica, P., Öberg, T., Dao, P., Cherkasov, A., & Tetko, I. V. (2008) · Journal of Chemical Information and Modeling · doi:10.1021/ci700443v · Cited by 287 · cited 1×
“2 out of these 11 compounds were found to fall outside of the models' domain of applicability (defined based on chemical similarity threshold in the descriptor space as described in (32;33).”
BackgroundSelf-citation
Research works printed but not linked: 5
- Elferink MG Olinga P Draaisma AL Merema MT Bauerschmidt S Polman J Schoonen WG Groothuis GM Microarray analysis in rat liver slices correctly predicts in vivo hepatotoxicity Toxicol. Appl. Pharmacol 2008 229 3 300 309 18346771 · DOI
- Downs G Barnard J Clustering methods and their uses in computational chemistry Rev. Comp. Chem 2002 18 1 40
- Mercier D Clustering large datasets Electronic review - Linacre College 2003
- Olson H Betton G Robinson D Thomas K Monro A Kolaja G Lilly P Sanders J Sipes G Bracken W Dorato M Van DK Smith P Berger B Heller A Concordance of the toxicity of pharmaceuticals in humans and in animals Regul. Toxicol. Pharmacol 2000 32 1 56 67 11029269 · DOI · Paper page
- Todeschini R DRAGON for Windows (Software for Molecular Descriptor Calculations) 2006 Talete s. r. l Milan, Italy version 5.4
Cited by
Pires, D. E. V., Blundell, T. L., & Ascher, D. B. (2015) · Journal of Medicinal Chemistry · doi:10.1021/acs.jmedchem.5b00104 · Cited by 5,716
“Fluorine atom Count Integer Toxicophore [1-36]c Binary vector Pharmacophore countd Integer vector a Topological polar surface area(23).”
BackgroundadmetSAR: A Comprehensive Source and Free Tool for Assessment of Chemical ADMET Properties
Cheng, F., Li, W., Zhou, Y., Shen, J., Wu, Z., Liu, G., Lee, P. W., & Tang, Y. (2012) · Journal of Chemical Information and Modeling · doi:10.1021/ci300367a · Cited by 2,222
Best Practices for QSAR Model Development, Validation, and Exploitation
Tropsha, A. (2010) · Molecular Informatics · doi:10.1002/minf.201000061 · Cited by 2,024
Self-citationMuratov, E. N., Bajorath, J., Sheridan, R. P., Tetko, I. V., Filimonov, D., Poroikov, V., Oprea, T. I., Baskin, I. I., Varnek, A., Roitberg, A., et al. (2020) · Chemical Society Reviews · doi:10.1039/d0cs00098a · Cited by 913
Self-citationFourches, D., Muratov, E., & Tropsha, A. (2010) · Journal of Chemical Information and Modeling · doi:10.1021/ci100176x · Cited by 832
Self-citationFDA-approved drug labeling for the study of drug-induced liver injury
Chen, M., Vijay, V., Shi, Q., Liu, Z., Fang, H., & Tong, W. (2011) · Drug Discovery Today · doi:10.1016/j.drudis.2011.05.007 · Cited by 406
Quantitative Nanostructure−Activity Relationship Modeling
Fourches, D., Pu, D., Tassa, C., Weissleder, R., Shaw, S. Y., Mumper, R. J., & Tropsha, A. (2010) · ACS Nano · doi:10.1021/nn1013484 · Cited by 388
Self-citationAnimal to human translation: a systematic scoping review of reported concordance rates
Leenaars, C. H. C., Kouwenaar, C., Stafleu, F. R., Bleich, A., Ritskes-Hoitinga, M., De Vries, R. B. M., & Meijboom, F. L. B. (2019) · Journal of Translational Medicine · doi:10.1186/s12967-019-1976-2 · Cited by 314
“mined the literature to create a data set of 951 compounds with effects in the liver in different species [69].”
Information retrieval and text mining technologies for chemistry
Krallinger, M., Rabal, O., Lourenço, A., Oyarzabal, J., & Valencia, A. (2017) · Chemical Reviews · doi:10.1021/acs.chemrev.6b00851 · Cited by 281
Mechanisms of drug-induced liver injury: from bedside to bench
Tujios, S., & Fontana, R. J. (2011) · Nature Reviews Gastroenterology & Hepatology · doi:10.1038/nrgastro.2011.22 · Cited by 277
“Results of other pharmacoepidemiological studies have suggested that certain disease states (such as viral infections) and physiochemical properties of certain classes of drugs might increase the risk of idiosyncratic DILI”
BackgroundLagorce, D., Douguet, D., Miteva, M. A., & Villoutreix, B. O. (2017) · Scientific Reports · doi:10.1038/srep46277 · Cited by 266
“Some in silico predictive approaches have emerged with the MCASE program 107 or QSAR models 108,109 .”
MethodTran, T. T. V., Surya Wibowo, A., Tayara, H., & Chong, K. T. (2023) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.3c00200 · Cited by 226
Systematic reviews of animal models: methodology versus epistemology
Greek, R., & Menache, A. (2013) · International Journal of Medical Sciences · doi:10.7150/ijms.5529 · Cited by 207
“These examples could be easily multiplied (for example, see [85] [ [86] p67-74] [38, 87-93]).”
BackgroundAn analysis of the use of animal models in predicting human toxicology and drug safety
Bailey, J., Thew, M., & Balls, M. (2014) · Alternatives to Laboratory Animals · doi:10.1177/026119291404200306 · Cited by 182
In vitro platforms for evaluating liver toxicity
Bale, S. S., Vernetti, L., Senutovitch, N., Jindal, R., Hegde, M., Gough, A., McCarty, W. J., Bakan, A., Bhushan, A., Shun, T. Y., et al. (2014) · Experimental Biology and Medicine · doi:10.1177/1535370214531872 · Cited by 155
New Insights into Toxicity and Drug Testing
(2013) · InTech eBooks · doi:10.5772/55886 · Cited by 149
“[94] Ghosh A, Chakrabarti P, Roy P, Bhadury S,Nag T, Sarkar S.”
BackgroundMethodInfluentialComputational Models for Human and Animal Hepatotoxicity with a Global Application Scope
Mulliner, D., Schmidt, F., Stolte, M., Spirkl, H.-P., Czich, A., & Amberg, A. (2016) · Chemical Research in Toxicology · doi:10.1021/acs.chemrestox.5b00465 · Cited by 140
Toward Predictive Models for Drug-Induced Liver Injury in Humans: Are we There Yet?
Chen, M., Bisgin, H., Tong, L., Hong, H., Fang, H., Borlak, J., & Tong, W. (2014) · Biomarkers in Medicine · doi:10.2217/bmm.13.146 · Cited by 136
A Predictive Ligand-Based Bayesian Model for Human Drug-Induced Liver Injury
Ekins, S., Williams, A. J., & Xu, J. J. (2010) · Drug Metabolism and Disposition · doi:10.1124/dmd.110.035113 · Cited by 122
“We are aware of at least three studies that tackled predicting DILI using either LDA, ANN, OneR (Cruz-Monteagudo et al., 2007), SVM (Fourches et al., 2010) or structural alerts (Greene et al., 2010).”
BackgroundMethodAn In Silico Model for Predicting Drug-Induced Hepatotoxicity
He, S., Ye, T., Wang, R., Zhang, C., Zhang, X., Sun, G., & Sun, X. (2019) · International Journal of Molecular Sciences · doi:10.3390/ijms20081897 · Cited by 122
Metabolic activation in drug-induced liver injury
Leung, L., Kalgutkar, A. S., & Obach, R. S. (2012) · Drug Metabolism Reviews · doi:10.3109/03602532.2011.605791 · Cited by 118
“Qualitative and quantitative structure-activity relationships continue to be developed in an attempt to better forecast the potential for hepatotoxicity (Fourches et al., 2010; Greene et al., 2010).”
BackgroundApplications of Machine Learning Methods in Drug Toxicity Prediction
Zhang, L., Zhang, H., Ai, H., Hu, H., Li, S., Zhao, J., & Liu, H. (2018) · Current Topics in Medicinal Chemistry · doi:10.2174/1568026618666180727152557 · Cited by 113
Todeschini, R., Ballabio, D., & Grisoni, F. (2016) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.6b00277 · Cited by 117
Mixed learning algorithms and features ensemble in hepatotoxicity prediction
Liew, C. Y., Lim, Y. C., & Yap, C. W. (2011) · Journal of Computer-Aided Molecular Design · doi:10.1007/s10822-011-9468-3 · Cited by 115
Progress in computational toxicology
Ekins, S. (2013) · Journal of Pharmacological and Toxicological Methods · doi:10.1016/j.vascn.2013.12.003 · Cited by 108
In silico Prediction of Drug Induced Liver Toxicity Using Substructure Pattern Recognition Method
Zhang, C., Cheng, F., Li, W., Liu, G., Lee, P. W., & Tang, Y. (2016) · Molecular Informatics · doi:10.1002/minf.201500055 · Cited by 111
Discovery of Novel Antimalarial Compounds Enabled by QSAR-Based Virtual Screening
Zhang, L., Fourches, D., Sedykh, A., Zhu, H., Golbraikh, A., Ekins, S., Clark, J., Connelly, M. C., Sigal, M., Hodges, D., et al. (2013) · Journal of Chemical Information and Modeling · doi:10.1021/ci300421n · Cited by 101
Self-citationEfficiency of different measures for defining the applicability domain of classification models
Klingspohn, W., Mathea, M., ter Laak, A., Heinrich, N., & Baumann, K. (2017) · Journal of Cheminformatics · doi:10.1186/s13321-017-0230-2 · Cited by 115
“The performance of the different AD measures was also studied for different sets of structure descriptors (see a Number of data sets where the AD measure performs significantly better than chance based on the 95th percentile (α = 0.05) of the permutation test (see Additional file 1 for a description of the permutation…”
MethodInfluentialReview of machine learning and deep learning models for toxicity prediction
Guo, W., Liu, J., Dong, F., Song, M., Li, Z., Khan, M. K. H., Patterson, T. A., & Hong, H. (2023) · Experimental Biology and Medicine · doi:10.1177/15353702231209421 · Cited by 169
“120 The third approach is to search publications in the literature such as MEDLINE abstracts 135 and publications.”
BackgroundLiu, Z., Shi, Q., Ding, D., Kelly, R., Fang, H., & Tong, W. (2011) · PLoS Computational Biology · doi:10.1371/journal.pcbi.1002310 · Cited by 96
“Secondly, HepSE-based QSAR models were developed by using all 888 drugs in SIDER, which were highly predictive as compared to published models [14,18,19] and offered a robust translation of clinical observation (i.”
MethodComprehension of drug toxicity: Software and databases
Toropov, A. A., Toropova, A. P., Raška, I., Leszczyńska, D., & Leszczyński, J. (2013) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2013.11.013 · Cited by 96
Fourches, D., Pu, D., & Tropsha, A. (2011) · Combinatorial Chemistry & High Throughput Screening · doi:10.2174/138620711794728743 · Cited by 92
Self-citationPredicting drug-induced liver injury: The importance of data curation
Kotsampasakou, E., Montanari, F., & Ecker, G. F. (2017) · Toxicology · doi:10.1016/j.tox.2017.06.003 · Cited by 93
“Re-analyzing the dataset revealed, that for several co-occurring compounds, even labeled as DILI negatives by majority vote, the Fourches source (Fourches et al., 2010) was labeling them as positives.”
BackgroundText Mining for Drugs and Chemical Compounds: Methods, Tools and Applications
Vazquez, M., Krallinger, M., Leitner, F., & Valencia, A. (2011) · Molecular Informatics · doi:10.1002/minf.201100005 · Cited by 87
Hewitt, M., Enoch, S. J., Madden, J. C., Przybylak, K. R., & Cronin, M. T. D. (2013) · Critical Reviews in Toxicology · doi:10.3109/10408444.2013.811215 · Cited by 85
In silico models for drug-induced liver injury – current status
Przybylak, K. R., & Cronin, M. T. (2012) · Expert Opinion on Drug Metabolism & Toxicology · doi:10.1517/17425255.2012.648613 · Cited by 82
“Furthermore, the majority of in silico approaches predict a general hepatotoxicity endpoint [14,57,58,65,66,68,85] and only three methods considered more specific endpoints, mostly elevations of liver serum enzymes [67,69,87].”
BackgroundMethodInfluentialThe Nuremberg Code subverts human health and safety by requiring animal modeling
Greek, R., Pippus, A., & Hansen, L. A. (2012) · BMC Medical Ethics · doi:10.1186/1472-6939-13-16 · Cited by 78
“analyzed MEDLINE abstracts for 1061 compounds known to cause hepatotoxicity and discovered that the concordance between species was only 39-44% [123].”
BackgroundPredicting drug-induced liver injury in human with Naïve Bayes classifier approach
Zhang, H., Ding, L., Zou, Y. F., Hu, S., Huang, H.-G., Kong, W.-B., & Zhang, J. (2016) · Journal of Computer-Aided Molecular Design · doi:10.1007/s10822-016-9972-6 · Cited by 86
Zhu, X., & Kruhlak, N. L. (2014) · Toxicology · doi:10.1016/j.tox.2014.03.009 · Cited by 78
Constituents in Kava Extracts Potentially Involved in Hepatotoxicity: A Review
Olsen, L. R., Grillo, M. P., & Skonberg, C. (2011) · Chemical Research in Toxicology · doi:10.1021/tx100412m · Cited by 72
An analysis of the use of dogs in predicting human toxicology and drug safety
Bailey, J., Thew, M., & Balls, M. (2013) · Alternatives to Laboratory Animals · doi:10.1177/026119291304100504 · Cited by 71
Engineering Liver Microtissues for Disease Modeling and Regenerative Medicine
Huang, D. (., Gibeley, S. B., Xu, C., Xiao, Y., Celik, O., Ginsberg, H. N., & Leong, K. W. (2020) · Advanced Functional Materials · doi:10.1002/adfm.201909553 · Cited by 65
Per Aspera Ad Astra : Application of Simplex Qsar Approach in Antiviral Research
Muratov, E. N., Artemenko, A. G., Varlamova, E. V., Polischuk, P. G., Lozitsky, V. P., Fedchuk, A. S., Lozitska, R. L., Gridina, T. L., Koroleva, L. S., Sil’nikov, V. N., et al. (2010) · Future Medicinal Chemistry · doi:10.4155/fmc.10.194 · Cited by 64
Machine Learning Methods in Computational Toxicology
Baskin, I. I. (2018) · Methods in molecular biology · doi:10.1007/978-1-4939-7899-1_5 · Cited by 68
Vargas, H. M., Bass, A. S., Koerner, J. E., Matis‐Mitchell, S., Pugsley, M. K., Skinner, M. R., Burnham, M. P., Bridgland-Taylor, M. H., Pettit, S. D., & Valentin, J. (2015) · British Journal of Pharmacology · doi:10.1111/bph.13207 · Cited by 58
“The SIP has been used to evaluate hepatic adverse events (Fourches et al., 2010), and can evaluate other organ system findings, such as cardiovascular toxicity.”
MethodArtificial Intelligence-Driven Drug Toxicity Prediction: Advances, Challenges, and Future Directions
Zhang, R., Wen, H., Lin, Z., Li, B., & Zhou, X. (2025) · Toxics · doi:10.3390/toxics13070525 · Cited by 81
“The support vector machine (SVM) is a supervised learning algorithm based on the application of statistical theory [47], which is widely used in classification and regression problems.”
Myshkin, E., Brennan, R., Khasanova, T., Sitnik, T., Serebriyskaya, T., Litvinova, E., Guryanov, A., Nikolsky, Y., Nikolskaya, T., & Bureeva, S. V. (2012) · Chemical Biology & Drug Design · doi:10.1111/j.1747-0285.2012.01411.x · Cited by 56
“For general organ toxicity models such as 'Hepatotoxicity,' compounds associated with all liver pathologies were taken as positives.”
MethodInfluentialZhu, X., Sedykh, A., & Liu, S. (2014) · Journal of Applied Toxicology · doi:10.1002/jat.2879 · Cited by 48
“Most of them are associated with amine-derived fragments which is consistent with a previous observation (Fourches et al., 2010a).”
MethodResultJia, X., Wen, X., Russo, D. P., Aleksunes, L. M., & Zhu, H. (2022) · Journal of Hazardous Materials · doi:10.1016/j.jhazmat.2022.129193 · Cited by 49
A Bayesian neural network for toxicity prediction
Semenova, E., Williams, D. P., Afzal, A. M., & Lazic, S. E. (2020) · Computational Toxicology · doi:10.1016/j.comtox.2020.100133 · Cited by 57
Improved Detection of Drug-Induced Liver Injury by Integrating Predicted In Vivo and In Vitro Data
Seal, S., Williams, D. P., Hosseini-Gerami, L., Mahale, M., Carpenter, A. E., Spjuth, O., & Bender, A. (2024) · Chemical Research in Toxicology · doi:10.1021/acs.chemrestox.4c00015 · Cited by 63
Cañada, A., Capella-Gutiérrez, S., Rabal, O., Oyarzábal, J., Valencia, A., & Krallinger, M. (2017) · Nucleic Acids Research · doi:10.1093/nar/gkx462 · Cited by 53
“These consisted of co-mentions of concept-relationship-concept triplets (10) of compounds with terms related to hepatobiliary anatomy/pathology.”
BackgroundBassan, A., Alves, V. M., Amberg, A., Anger, L. T., Auerbach, S. S., Beilke, L. D., Bender, A., Cronin, M., Cross, K. P., Hsieh, J., et al. (2021) · Computational Toxicology · doi:10.1016/j.comtox.2021.100187 · Cited by 52
Steinmetz, F. P., Mellor, C. L., Meinl, T., & Cronin, M. (2015) · Molecular Informatics · doi:10.1002/minf.201400188 · Cited by 42
The development and application of in silico models for drug induced liver injury
Li, X., Chen, Y., Song, X., Zhang, Y., Li, H., & Zhao, Y. (2018) · RSC Advances · doi:10.1039/c7ra12957b · Cited by 41
Ghaderzadeh, M., Shalchian, A., Irajian, G., Sadeghsalehi, H., Bialvaei, A. Z., & Sabet, B. (2024) · Iranian Journal of Medical Microbiology · doi:10.30699/ijmm.18.3.135 · Cited by 42
Luo, M., Wang, X. S., Roth, B. L., Golbraikh, A., & Tropsha, A. (2014) · Journal of Chemical Information and Modeling · doi:10.1021/ci400460q · Cited by 37
Self-citationKotsampasakou, E., Brenner, S., Jäger, W. R., & Ecker, G. F. (2015) · Molecular Pharmaceutics · doi:10.1021/acs.molpharmaceut.5b00583 · Cited by 40
Gozalbes, R., & de Julián‐Ortiz, J. V. (2017) · International Journal of Quantitative Structure-Property Relationships · doi:10.4018/ijqspr.2018010101 · Cited by 46
Artificial Intelligence, Machine Learning, and Deep Learning in Real-Life Drug Design Cases
Müller, C., Rabal, O., & Gonzalez, C. D. (2021) · Methods in molecular biology · doi:10.1007/978-1-0716-1787-8_16 · Cited by 42
Computer-aided design of carbon nanotubes with the desired bioactivity and safety profiles
Fourches, D., Pu, D., Li, L., Zhou, H., Mu, Q., Su, G., Yan, B., & Tropsha, A. (2016) · Nanotoxicology · doi:10.3109/17435390.2015.1073397 · Cited by 37
“…neighbors – kNN (Zheng & Tropsha, 2000), random forest – RF (Breiman, 2001) and support vector machines – SVM (Cristianini & Shawe-Taylor, 2000)] and definitions of the model applicability domain were published elsewhere (Fourches et al., 2010a; Tropsha & Golbraikh, 2007; Zhu et al., 2008b).”
InfluentialSelf-citationFraser, K., Bruckner, D. M., & Dordick, J. S. (2018) · Chemical Research in Toxicology · doi:10.1021/acs.chemrestox.8b00054 · Cited by 50
Pizzo, F., Lombardo, A., Manganaro, A., & Benfenati, E. (2016) · Frontiers in Pharmacology · doi:10.3389/fphar.2016.00442 · Cited by 35
“In our combined dataset (950 compounds from (Fourches et al., 2010) and 491 from US FDA), we identified 191 duplicated compounds (16.7%).”
BackgroundMethodResultInfluentialMicrofluidic Cell Culture Platforms to Capture Hepatic Physiology and Complex Cellular Interactions
Bale, S. S., & Borenstein, J. T. (2018) · Drug Metabolism and Disposition · doi:10.1124/dmd.118.083055 · Cited by 37
“Current state-of-the-art techniques for assessing human-relevant hepatic responses include in vitro models, comprising either primary hepatocyte monocultures or cocultures in two-dimensional and three-dimensional (3D) formats (Fourches et al., 2010; Godoy et al., 2013; Lauschke et al., 2016).”
BackgroundZhao, L., Russo, D. P., Wang, W., Aleksunes, L. M., & Zhu, H. (2020) · Toxicological Sciences · doi:10.1093/toxsci/kfaa005 · Cited by 30
Alzheimer's disease biomarker discovery using in silico literature mining and clinical validation
Greco, I., Day, N., Riddoch-Contreras, J., Reed, J., Soininen, H., Kłoszewska, I., Tsolaki, M., Vellas, B., Spenger, C., Mecocci, P., et al. (2012) · Journal of Translational Medicine · doi:10.1186/1479-5876-10-217 · Cited by 31
“com/tag/sofia/ and [10]) and was powered by the broad vocabularies around Proteins, Observations and Tissues, to enable semantic consistency of all final assertions.”
BackgroundSelf-citationAnimal Models in an Age of Personalized Medicine
Greek, R., Menache, A., & Rice, M. J. (2011) · Personalized Medicine · doi:10.2217/pme.11.89 · Cited by 32
Challenges in mining the literature for chemical information
Gurulingappa, H., Mudi, A., Toldo, L., Hofmann‐Apitius, M., & Bhate, J. (2013) · RSC Advances · doi:10.1039/c3ra40787j · Cited by 32
Medicare spending and mortality rates of the elderly.
Hadley, J. (1988) · PubMed · Cited by 37
Pérez‐Castillo, Y., Lazar, C., Taminau, J., Froeyen, M., Cabrera‐Pérez, M. Á., & Nowé, A. (2012) · Journal of Chemical Information and Modeling · doi:10.1021/ci300146h · Cited by 28
In Silico Prediction of Drug-Induced Liver Injury Based on Adverse Drug Reaction Reports
Zhu, X., & Li, S. (2017) · Toxicological Sciences · doi:10.1093/toxsci/kfx099 · Cited by 28
“…using a variety of algorithms [eg, Bayesian modeling, support vector machine, and random forest (RF)] based on chemicals’ structural information (Chen et al., 2013; Ekins et al., 2010; Fourches et al., 2010; Liu et al., 2011; Mulliner et al., 2016; Rodgers et al., 2009; Zhang et al., 2016).”
BackgroundMethodThree-Level Hepatotoxicity Prediction System Based on Adverse Hepatic Effects
Liu, L., Fu, L., Zhang, J., Wei, H., Ye, W.-L., Deng, Z., Zhang, L., Cheng, Y., Ouyang, D., Cao, Q., et al. (2018) · Molecular Pharmaceutics · doi:10.1021/acs.molpharmaceut.8b01048 · Cited by 29
Sharma, G., Kumar, N., Sharma, C. S., Alqahtani, T., Tiruneh, Y. K., Sultana, S., Silva, G. V. R., Menezes, G. D. L., Zaki, M. E. A., & Oliveira, J. I. N. (2025) · Scientific Reports · doi:10.1038/s41598-025-86016-9 · Cited by 37
Characterisation of data resources forin silicomodelling: benchmark datasets for ADME properties
Przybylak, K. R., Madden, J. C., Covey‐Crump, E. M., Gibson, L., Barber, C., Patel, M. L., & Cronin, M. (2017) · Expert Opinion on Drug Metabolism & Toxicology · doi:10.1080/17425255.2017.1316449 · Cited by 28
“However, such data for ADME end points very often need to be extracted using appropriate data-retrieval techniques [17] and then collated and organized in a tabular format.”
MethodKhakpour, A., Ghiabi, S., Babaheydari, A. K., Mirahmadi, S. A., Baziyar, P., Heidari-Soureshjani, E., & Horestani, M. K. (2024) · Chemical Physics Impact · doi:10.1016/j.chphi.2024.100784 · Cited by 25
Waheed, Z. A., Seyedalipour, B., Colagar, A. H., & Baziyar, P. (2024) · Molecular Simulation · doi:10.1080/08927022.2024.2365377 · Cited by 25
“The toxicity potential parameter is based on the prediction of hepatotoxicity, Salmonella typhimurium/reverse mutation assay (AMES assay) and LD50 [95].”
Cheminformatics Modeling of Amine Solutions for Assessing their CO2Absorption Properties
Kuenemann, M. A., & Fourches, D. (2017) · Molecular Informatics · doi:10.1002/minf.201600143 · Cited by 28
Self-citationLarge-scale classification of P-glycoprotein inhibitors using SMILES-based descriptors
Prachayasittikul, V., Worachartcheewan, A., Toropova, A. P., Toropov, A. A., Schaduangrat, N., Prachayasittikul, V., & Nantasenamat, C. (2017) · SAR and QSAR in environmental research · doi:10.1080/1062936x.2016.1264468 · Cited by 23
“which aim to predict, in the form of Yes/No, various abilities, such as toxicity [102], fungicide”
BackgroundRecent Trends in Statistical QSAR Modeling of Environmental Chemical Toxicity
Tropsha, A. (2012) · Proceedings of the Fourth International Symposium on Polarization Phenomena in Nuclear Reactions · doi:10.1007/978-3-7643-8340-4_13 · Cited by 25
Self-citationAnimal Models in Drug Development
Greek, R. (2013) · InTech eBooks · doi:10.5772/53893 · Cited by 23
“evaluated animal human data for 1061 compounds known to cause hepatotoxicity in humans and found that the concordance or sensitivity among species was around 39-44%.[94] The positive and negative predictive values could not be calculated from the article but would be well below 0.”
BackgroundTraining Translators for Smart Drug Discovery
Skarke, C., & FitzGerald, G. A. (2010) · Science Translational Medicine · doi:10.1126/scitranslmed.3000890 · Cited by 24
QSAR analysis of poliovirus inhibition by dual combinations of antivirals
Muratov, E. N., Varlamova, E. V., Artemenko, A. G., Полищук, П. Г., Nikolaeva–Glomb, L., Galabov, A. S., & Kuz’min, V. Е. (2013) · Structural Chemistry · doi:10.1007/s11224-012-0195-8 · Cited by 23
Machine Learning Models for Predicting Liver Toxicity
Liu, J., Guo, W., Sakkiah, S., Ji, Z., Yavaş, G., Zou, W., Chen, M., Tong, W., Patterson, T. A., & Hong, H. (2022) · Methods in molecular biology · doi:10.1007/978-1-0716-1960-5_15 · Cited by 23
Arsito, P. N., Waiwut, P., Yenjai, C., Arthan, S., Monthakantirat, O., Nualkaew, N., Takomthong, P., & Boonyarat, C. (2023) · Heliyon · doi:10.1016/j.heliyon.2023.e21894 · Cited by 24
“The next parameter is the potential for toxicity based on the prediction of hepatotoxicity, AMES test, and LD50 [39].”
BackgroundComputational toxicology: a tool for all industries
Marchant, C. A. (2011) · Wiley Interdisciplinary Reviews Computational Molecular Science · doi:10.1002/wcms.100 · Cited by 20
“56 The particularly interesting feature of this study is that the data used to derive the models were automatically extracted from Medline abstracts using text mining techniques, thus by-passing the time-consuming step of manual data curation which precedes the model building process when suitable…”
MethodAsl, F. S. S., Malverdi, N., Kachouei, F. A., Zarei, F., Ghiabi, S., Baziyar, P., & Nabi‐Afjadi, M. (2025) · Frontiers in Chemistry · doi:10.3389/fchem.2025.1569777 · Cited by 20
Lamooki, F. M., Alami, F., Toupchi, F. M., Jalali, P., Banimahdidehkordi, A., Baziyar, P., Ghiabi, S., Heidari-Soureshjani, E., & Mirahmadi, S. A. (2025) · Results in Chemistry · doi:10.1016/j.rechem.2025.102484 · Cited by 20
Asl, F. S. S., Malverdi, N., Mojahedian, F., Baziyar, P., & Nabi‐Afjadi, M. (2025) · International Journal of Biological Macromolecules · doi:10.1016/j.ijbiomac.2025.141273 · Cited by 21
Bajželj, B., & Drgan, V. (2020) · Molecules · doi:10.3390/molecules25030481 · Cited by 18
“[14] developed QSAR models with support-vector machines (SVMs) for hepatotoxicity, with a dataset of 531 compounds (248 hepatotoxic, 283 non-hepatotoxic) acquired with text mining, and achieved accuracy from 55.”
MethodNew approach methodologies (NAMs) for drug-induced liver injury (DILI): Where are we now?
Shrimali, S., Chen, M., Li, D., & Tong, W. (2025) · Drug Discovery Today · doi:10.1016/j.drudis.2025.104452 · Cited by 19
Zhu, X., Xin, Y., & Chen, Q.-H. (2016) · SAR and QSAR in environmental research · doi:10.1080/1062936x.2016.1201142 · Cited by 17
“the available hepatotoxicity data can be categorized into four types: (1) post-market case reports [5–7]; (2) FDA-approved drug labelling [8]; (3) in vitro assays [9, 10]; and (4) metasearch data [11, 12].”
BackgroundIn Silico Models for Hepatotoxicity
Hewitt, M., & Przybylak, K. R. (2016) · Methods in molecular biology · doi:10.1007/978-1-4939-3609-0_11 · Cited by 18
Liu, X., Zheng, D., Zhong, Y., Xia, Z., Luo, H., & Weng, Z. (2020) · BioMed Research International · doi:10.1155/2020/4795140 · Cited by 24
“Second, many studies focused on drug structural features [9, 12, 21, 22], Hindawi BioMed Research International Volume 2020, Article ID 4795140, 10 pages https://doi.”
BackgroundHybrid non-animal modeling: A mechanistic approach to predict chemical hepatotoxicity
Chung, E., Wen, X., Jia, X., Ciallella, H. L., Aleksunes, L. M., & Zhu, H. (2024) · Journal of Hazardous Materials · doi:10.1016/j.jhazmat.2024.134297 · Cited by 16
Lorin, S., Rajaraman, D., Selvam, S., Ramakrishnan, J., Kumaradhas, P., Nagaraj, K., & Kaliyaperumal, R. (2024) · Zeitschrift für Physikalische Chemie · doi:10.1515/zpch-2023-0397 · Cited by 15
Rathman, J. F., Yang, C., Ribeiro, J. V., Mostrąg, A., Thakkar, S., Tong, W., Hobocienski, B., Sacher, O., Magdziarz, T., & Bienfait, B. (2020) · Chemical Research in Toxicology · doi:10.1021/acs.chemrestox.0c00423 · Cited by 13
Schmidt, F. (2019) · Elsevier eBooks · doi:10.1016/b978-0-12-801238-3.11534-x · Cited by 13
McMillan, J., Bester, M. J., & Apostolides, Z. (2025) · In Silico Pharmacology · doi:10.1007/s40203-025-00324-6 · Cited by 15
“The hepatotoxicity was pre - dicted by comparing the chemical structure of the selected compounds to the compounds in the dataset (Fourches et al. 2010).”
Arcanjo, D. D. R., Mafud, A. C., Vasconcelos, A. G., da Silva‐Filho, J. C., do Amaral, M. P. D. M., Brito, L. M., Bemquerer, M. P., Kückelhaus, S. A. S., Plácido, A., Delerue-Matos, C. M., et al. (2016) · International Journal of Peptide Research and Therapeutics · doi:10.1007/s10989-016-9564-2 · Cited by 12
“If the compound is related with at least one liver pathological or physiological event, the prediction returns positive result (Fourches et al. 2010; Pires et al. 2015b).”
QSAR classification of metabolic activation of chemicals into covalently reactive species
Liew, C. Y., Pan, C., Tan, A., Ang, K. X. M., & Yap, C. W. (2012) · Molecular Diversity · doi:10.1007/s11030-012-9364-3 · Cited by 12
Metadata
- Authors
- Fourches, D., Barnes, J. C., Day, N. C., Bradley, P., Reed, J. Z., & Tropsha, A.
- Affiliations
- University of North Carolina at Chapel Hill (US)
- Corresponding author
- Tropsha, Alexander
- Venue
- Chemical Research in Toxicology
- Publisher
- American Chemical Society (ACS)
- Published
- 2009-12-16
- Volume
- 23
- Issue
- 1
- Pages
- 171-183
- ISSN
- 0893-228X (ISSN-L)
- 1520-5010
- PMC
- PMC2850112
- OpenAlex
- W2090773565
- Cited by
- 162
- References
- 28
- Citations by year
- 2026: 9 · 2025: 16 · 2024: 15 · 2023: 13 · 2022: 3 · 2021: 4 · 2020: 7 · 2019: 9 · 2018: 7 · 2017: 11 · 2016: 11 · 2015: 8 · 2014: 7 · 2013: 12 · 2012: 9
- FWCI
- 9.08
- Type
- journal article
- Language
- en
- Open access
- green
- www.ncbi.nlm.nih.gov
- Locations
- Chemical Research in Toxicology (publishedVersion)
- PubMed (publishedVersion)
- Europe PMC (PubMed Central) (acceptedVersion)
- PubMed Central (acceptedVersion)
- Carolina Digital Repository (University of North Carolina at Chapel Hill) (submittedVersion)
- UNC Libraries
- Funders
- National Institutes of Health
- National Institute of General Medical Sciences (R21GM076059)
- Topics
- Life Sciences › Pharmacology, Toxicology and Pharmaceutics › Drug Discovery › Computational Drug Discovery Methods
- Life Sciences › Pharmacology, Toxicology and Pharmaceutics › Pharmacology › Drug-Induced Hepatotoxicity and Protection
- Health Sciences › Medicine › Health Informatics › Biomedical Text Mining and Ontologies
- Keywords
- drug-induced liver injury, hepatotoxicity prediction, chemical toxicity prediction, MEDLINE abstracts, drug attrition, structure-activity relationship
- MeSH terms
- Animals, Humans, Models, Chemical, Molecular Conformation, Cluster Analysis, Databases, Factual, MEDLINE, Quantitative Structure-Activity Relationship, Mice, Chemical and Drug Induced Liver Injury
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.