Comparative Study of Multitask Toxicity Modeling on a Broad Chemical Space
Open accessAbstract
Acute toxicity is one of the most challenging properties to predict purely with computational methods due to its direct relationship to biological interactions. Moreover, toxicity can be represented by different end points: it can be measured for different species using different types of administration, etc., and it is questionable if the knowledge transfer between end points is possible. We performed a comparative study of prediction multitask toxicity for a broad chemical space using different descriptors and modeling algorithms and applied multitask learning for a large toxicity data set extracted from the Registry of Toxic Effects of Chemical Substances (RTECS). We demonstrated that multitask modeling provides significant improvement over single-output models and other machine learning methods. Our research reveals that multitask learning can be very useful to improve the quality of acute toxicity modeling and raises a discussion about the usage of multitask approaches for regulation purposes. Our MultiTox models are freely available in OCHEM platform ( ochem.eu/multitox ) under CC-BY-NC license.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Cites
Breiman, L. (2001) · Machine Learning · doi:10.1023/a:1010933404324 · Cited by 133,538 · cited 1× · see citing works
“52 This method has been heavily used in chemoinformatics for the last decade before the rise of deep learning due to a long list of advantages, particularly the performance of modelling, the speed of computation, and the ability to use default parameters or parameters with minimal tuning.”
Method(2014) · Cited by 33,419 · see citing works
(2008) · Journal of Machine Learning Research · Cited by 33,051 · see citing works
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate ShiftPreprint
Ioffe, S. (2024) · arXiv (Cornell University) · doi:10.57702/o9raffed · Cited by 15,273 · see citing works
Extended-Connectivity Fingerprints
Rogers, D. O. W., & Hahn, M. (2010) · Journal of Chemical Information and Modeling · doi:10.1021/ci100050t · Cited by 7,597 · cited 1× · see citing works
“OEstate descriptors which are based on electrostatic properties of atoms and bonds CDK2 (3D) 43 Chemistry development kit descriptors, version 2.0 Morgan fingerprints 38,39 Morgan (circular) fingerprints of radius two (which corresponds to ECFP4 38 ) calculated by RDKit.”
MethodInfluentialPubChem Substance and Compound databases
Kim, S., Thiessen, P. A., Bolton, E. E., Chen, J., Fu, G., Gindulyte, A., Han, L., He, J., He, S., Shoemaker, B. A., et al. (2016) · Nucleic Acids Research · doi:10.1093/nar/gkv951 · Cited by 5,436 · cited 1× · see citing works
“Since the structures of organic compounds are not presented in the database, we extracted them from PubChem 25 using Chemical Abstract Structure (CAS) registration numbers.”
MethodGolbraikh, A., & Tropsha, A. (2002) · Journal of Molecular Graphics and Modelling · doi:10.1016/s1093-3263(01)00123-1 · Cited by 3,735 · cited 1× · see citing works
“56 To combat with this problem and estimate the statistical performance in a robust way a 5-fold cross-validation routine has been carried out for all models in this study.”
MethodRandom Forest: A Classification and Regression Tool for Compound Classification and QSAR Modeling
Svetnik, V., Liaw, A. I., Tong, C., Culberson, J. C., Sheridan, R. P., & Feuston, B. P. (2003) · Journal of Chemical Information and Computer Sciences · doi:10.1021/ci034160g · Cited by 3,613 · see citing works
Morgan, H. L. (1965) · Journal of Chemical Documentation · doi:10.1021/c160017a018 · Cited by 1,716 · cited 1× · see citing works
“OEstate descriptors which are based on electrostatic properties of atoms and bonds CDK2 (3D) 43 Chemistry development kit descriptors, version 2.0 Morgan fingerprints 38,39 Morgan (circular) fingerprints of radius two (which corresponds to ECFP4 38 ) calculated by RDKit.”
MethodInfluentialEstimation of clinical trial success rates and related parameters
Wong, C. H., Siah, K. W., & Lo, A. W. (2019) · Biostatistics · doi:10.1093/biostatistics/kxx069 · Cited by 1,585 · see citing works
The ChEMBL bioactivity database: an update
Bento, A. P., Gaulton, A., Hersey, A., Bellis, L. J., Chambers, J. K., Davies, M., Krüger, F. A., Light, Y., Mak, L., McGlinchey, S., et al. (2013) · Nucleic Acids Research · doi:10.1093/nar/gkt1031 · Cited by 1,487 · cited 1× · see citing works
“Some examples of the open source databases are the TOXNET database 9 and DSSTox, 10 which includes Tox21 high throughput data and CheMBL 11 database containing approximately 15 million of bioactivities.”
MethodThe Chemistry Development Kit (CDK): An Open-Source Java Library for Chemo- and Bioinformatics
Steinbeck, C., Han, Y., Kühn, S., Horlacher, O., Luttmann, E., & Willighagen, E. (2003) · Journal of Chemical Information and Computer Sciences · doi:10.1021/ci025584y · Cited by 1,111 · see citing works
Inglese, J., Auld, D. S., Jadhav, A., Johnson, R. L., Simeonov, A. M., Yasgar, A., Zheng, W., & Austin, C. P. (2006) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.0604348103 · Cited by 794 · see citing works
Hall, L. H., & Kier, L. B. (1995) · Journal of Chemical Information and Computer Sciences · doi:10.1021/ci00028a014 · Cited by 770 · see citing works
ProTox: a web server for the in silico prediction of rodent oral toxicity
Drwal, M. N., Banerjee, P., Dunkel, M., Wettig, M. R., & Preißner, R. (2014) · Nucleic Acids Research · doi:10.1093/nar/gku401 · Cited by 742 · cited 1× · see citing works
“The ProTox web-server is another tool for prediction of acute toxicity and other types of toxicity, 15 which utilizes a nearest neighbor approach combined with fingerprint similarity assessment.”
MethodSushko, I., Novotarskyi, S., Körner, R., Pandey, A. K., Rupp, M., Teetz, W., Brandmaier, S., Abdelaziz, A., Prokopenko, V. V., Tanchuk, V. Y., et al. (2011) · Journal of Computer-Aided Molecular Design · doi:10.1007/s10822-011-9440-2 · Cited by 684 · cited 4× · see citing works
“It should be noted that OCHEM develops a new model on each validation step without using any information about the test compounds, which are only predicted following model developments.”
MethodInfluentialSelf-citationApplication of Associative Neural Networks for Prediction of Lipophilicity in ALOGPS 2.1 Program
Tetko, I. V., & Tanchuk, V. Y. (2002) · Journal of Chemical Information and Computer Sciences · doi:10.1021/ci025515j · Cited by 618 · cited 2× · see citing works
“CODE program Inductive (3D) 34 Descriptors based on inductive and steric effects of atoms Chemaxon (3D) A subset of descriptors calculated by Chemaxon (www.chemaxon.com) module in OCHEM Mera and Mesry (3D) 35 3D descriptors of molecules GSFrag 35 Descriptors calculated by GSFRAG program (the occurrence numbers of certa…”
MethodSelf-citationExtreme Gradient Boosting as a Method for Quantitative Structure–Activity Relationships
Sheridan, R. P., Wang, W. M., Liaw, A., Ma, J., & Gifford, E. M. (2016) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.6b00591 · Cited by 544 · cited 2× · see citing works
“This result is not surprising, and it confirmed observations of previous studies 48,59 that the efficiency of these methods is similar.”
MethodResultMachine learning methods in chemoinformatics
Mitchell, J. B. O. (2014) · Wiley Interdisciplinary Reviews Computational Molecular Science · doi:10.1002/wcms.1183 · Cited by 470 · cited 1× · see citing works
“49 The idea is close to chemical paradigm that similar compounds have lookalike properties.”
BackgroundEstimation of Aqueous Solubility of Chemical Compounds Using E-State Indices
Tetko, I. V., Tanchuk, V. Y., Kasheva, T. N., & Villa, A. E. P. (2001) · Journal of Chemical Information and Computer Sciences · doi:10.1021/ci000392t · Cited by 331 · see citing works
Self-citationSushko, I., Salmina, E. S., Potemkin, V., Poda, G. I., & Tetko, I. V. (2012) · Journal of Chemical Information and Modeling · doi:10.1021/ci300245q · Cited by 265 · see citing works
Self-citationZhang, L., Ai, H., Chen, W., Yin, Z., Hu, H., Zhu, J., Zhao, J. H., Zhao, Q., & Liu, H. (2017) · Scientific Reports · doi:10.1038/s41598-017-02365-0 · Cited by 255 · cited 1× · see citing works
“This result is not surprising, and it confirmed observations of previous studies 48,59 that the efficiency of these methods is similar.”
ResultDemystifying Multitask Deep Neural Networks for Quantitative Structure–Activity Relationships
Xu, Y., Ma, J., Liaw, A., Sheridan, R. P., & Svetnik, V. (2017) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.7b00087 · Cited by 238 · cited 1× · see citing works
“Previous studies 58 pointed out that the efficiency of multi-task modelling depends on correlations between targets.”
BackgroundThe US Federal Tox21 Program: A strategic and operational plan for continued leadership
Thomas, R. (2018) · ALTEX · doi:10.14573/altex.1803011 · Cited by 229 · see citing works
ISIDA - Platform for Virtual Screening Based on Fragment and Pharmacophoric Descriptors
Varnek, A. A., Fourches, D., Horvath, D., Klimchuk, O., Gaudin, C., Vayer, P., Solov’ev, V. P., Hoonakker, F., Tetko, I. V., & Marcou, G. (2008) · Current Computer - Aided Drug Design · doi:10.2174/157340908785747465 · Cited by 213 · see citing works
Self-citationDistributed structure-searchable toxicity (DSSTox) public database network: a proposal
Richard, A. M., & Williams-DeVane, C. (2002) · Mutation research. Fundamental and molecular mechanisms of mutagenesis · doi:10.1016/s0027-5107(01)00289-5 · Cited by 170 · cited 1× · see citing works
“Some examples of the open source databases are the TOXNET database 9 and DSSTox, 10 which includes Tox21 high throughput data and CheMBL 11 database containing approximately 15 million of bioactivities.”
MethodHierarchical QSAR technology based on the Simplex representation of molecular structure
Kuz’min, V. Е., Artemenko, A. G., & Muratov, E. N. (2008) · Journal of Computer-Aided Molecular Design · doi:10.1007/s10822-008-9179-6 · Cited by 153 · see citing works
Neural Network Studies. 4. Introduction to Associative Neural Networks
Tetko, I. V. (2002) · Journal of Chemical Information and Computer Sciences · doi:10.1021/ci010379o · Cited by 150 · see citing works
Self-citationDevelopment of structure–activity relationship for metal oxide nanoparticles
Liu, R., Zhang, H. Y., Ji, Z., Ralló, R., Xia, T., Chang, C. H., Nel, A. E., & Cohen, Y. (2013) · Nanoscale · doi:10.1039/c3nr01533e · Cited by 139 · cited 1× · see citing works
“There is a number of models constructed for a narrow class of chemical compound 16–18 or the certain model organism, 19,20 however, the applicability domain of such models is limited.”
BackgroundKauffman, G. W., & Jurs, P. C. (2001) · Journal of Chemical Information and Computer Sciences · doi:10.1021/ci010073h · Cited by 126 · see citing works
BIGCHEM: Challenges and Opportunities for Big Data Analysis in Chemistry
Tetko, I. V., Engkvist, O., Koch, U., Reymond, J., & Chen, H. (2016) · Molecular Informatics · doi:10.1002/minf.201600073 · Cited by 124 · cited 1× · see citing works
“In the same time, we are at the beginning of a “big data” time 62 in chemistry and biology The appearance of these data promotes development of powerful multi-task models that could significantly increase quality of models for individual end-points.”
BackgroundSelf-citationMasand, V. H., & Rastija, V. (2017) · Chemometrics and Intelligent Laboratory Systems · doi:10.1016/j.chemolab.2017.08.003 · Cited by 120 · see citing works
Auerbach, S. S., Shah, R., Mav, D., Smith, C. S., Walker, N. J., Vallant, M. K., Boorman, G. A., & Irwin, R. D. (2009) · Toxicology and Applied Pharmacology · doi:10.1016/j.taap.2009.11.021 · Cited by 100 · see citing works
Pogodin, P. V., Lagunin, A. A., Filimonov, D. A., & Poroikov, V. (2015) · SAR and QSAR in environmental research · doi:10.1080/1062936x.2015.1078407 · Cited by 91 · see citing works
Predictive Toxicology: Benchmarking Molecular Descriptors and Statistical Methods
Feng, J., Lurati, L., Ouyang, H., Robinson, T., Wang, Y., Yuan, S., & Young, S. S. (2003) · Journal of Chemical Information and Computer Sciences · doi:10.1021/ci034032s · Cited by 86 · see citing works
Varnek, A., Gaudin, C., Marcou, G., Baskin, I., Pandey, A. K., & Tetko, I. V. (2009) · Journal of Chemical Information and Modeling · doi:10.1021/ci8002914 · Cited by 86 · cited 1× · see citing works
“It was shown that the Feature Net approach can achieve better accuracy than single-task learning 61 and can provide models with similar accuracy to MT models.”
MethodSelf-citationA Survey of Multi‐task Learning Methods in Chemoinformatics
Sosnin, S., Vashurina, M., Withnall, M., Karpov, P., Fedorov, M. V., & Tetko, I. V. (2018) · Molecular Informatics · doi:10.1002/minf.201800108 · Cited by 82 · cited 1× · see citing works
“21 In this study we have addressed this question by using multi-task learning 22–24 with state of the art machine learning methods.”
MethodSelf-citationeMolTox: prediction of molecular toxicity with confidence
Ji, C., Svensson, F., Zoufir, A., & Bender, A. (2018) · Bioinformatics · doi:10.1093/bioinformatics/bty135 · Cited by 73 · cited 1× · see citing works
“The EMolTox web-service 14 predicts different types of toxicity using random forests and conformational prediction as measure of confidence and simultaneously visualizes the ToxAlert substructures on the molecular graph.”
MethodPrinciples for 3D/4D QSAR classification of drugs
Potemkin, V., & Grishina, M. (2008) · Drug Discovery Today · doi:10.1016/j.drudis.2008.07.006 · Cited by 69 · see citing works
Alden, C. L., Lynn, A., Bourdeau, A., Morton, D., Sistare, F. D., Kadambi, V. J., & Silverman, L. (2011) · Veterinary Pathology · doi:10.1177/0300985811400445 · Cited by 69 · see citing works
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 62 · see citing works
Toxicity-Indicating Structural Patterns
von Korff, M., & Sander, T. (2006) · Journal of Chemical Information and Modeling · doi:10.1021/ci050358k · Cited by 61 · see citing works
Cell- and biomarker-based assays for predicting nephrotoxicity
Huang, J. X., Blaskovich, M. A. T., & Cooper, M. A. (2014) · Expert Opinion on Drug Metabolism & Toxicology · doi:10.1517/17425255.2014.967681 · Cited by 46 · cited 1× · see citing works
“7 However, due to their biological complexity, the in vitro tests do not also always provide a reliable estimation of the in vivo toxicity because human cell-based data used in in vivo testing may not take into account the general systemic toxicity for the whole organism.”
BackgroundCherkasov, A. (2005) · International Journal of Molecular Sciences · doi:10.3390/i6010063 · Cited by 39 · see citing works
Wang, Y., Zheng, M., Xiao, J., Lu, Y., Wang, F., Lu, J., Luo, X., Zhu, W., Jiang, H., & Chen, K. (2010) · SAR and QSAR in environmental research · doi:10.1080/1062936x.2010.502300 · Cited by 38 · cited 1× · see citing works
“There is a number of models constructed for a narrow class of chemical compound 16–18 or the certain model organism, 19,20 however, the applicability domain of such models is limited.”
BackgroundToxCast EPA <i>in Vitro</i> to <i>in Vivo</i> Challenge: Insight into the Rank-I Model
Novotarskyi, S., Abdelaziz, A., Sushko, Y., Körner, R., Vogt, J., & Tetko, I. V. (2016) · Chemical Research in Toxicology · doi:10.1021/acs.chemrestox.5b00481 · Cited by 34 · cited 1× · see citing works
“55 We constructed consensus models by averaging of the predictions of top five individual models.”
MethodSelf-citationLi, X., Zhang, Y., Chen, H., Li, H., & Zhao, Y. (2017) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.7b00476 · Cited by 34 · cited 1× · see citing works
“There is a number of models constructed for a narrow class of chemical compound 16–18 or the certain model organism, 19,20 however, the applicability domain of such models is limited.”
BackgroundComputer‐aided prediction of toxicity with substructure pattern and random forest
Cao, D., Yang, Y., Zhao, J., Yan, J., Shao, L., Hu, Q., Xu, Q., & Liang, Y. (2012) · Journal of Chemometrics · doi:10.1002/cem.1416 · Cited by 30 · see citing works
Exploring QSTR analysis of the toxicity of phenols and thiophenols using machine learning methods
Asadollahi-Baboli, M. (2012) · Environmental Toxicology and Pharmacology · doi:10.1016/j.etap.2012.09.003 · Cited by 26 · see citing works
Chemical risk analysis: A practical Handbook, 2000
Grossel, S. S. (2001) · Journal of Loss Prevention in the Process Industries · doi:10.1016/s0950-4230(01)00007-9 · Cited by 20 · see citing works
Nomen Est Omen: Quantitative Prediction of Molecular Properties Directly from IUPAC Names
Thormann, M., Vidal, D., Almstetter, M., & Pons, M. (2007) · The Open Applied Informatics Journal · doi:10.2174/1874136300701010028 · Cited by 17 · see citing works
Prediction of hERG Potassium Channel Blockade Using kNN‐QSAR and Local Lazy Regression Methods
Gunturi, S. B., Archana, K., Khandelwal, A., & Ramamurthi, N. (2008) · QSAR & Combinatorial Science · doi:10.1002/qsar.200810072 · Cited by 16 · cited 1× · see citing works
“50,51 Random Forest: this method uses the set (forest) of the simple classifiers or regressors, namely decision trees.”
MethodFesting, M. F. W. (2014) · PLoS ONE · doi:10.1371/journal.pone.0112955 · Cited by 8 · see citing works
Application of spectrophores™ to map vendor chemical space using self-organising maps
Thijs, G., Langenaeker, W., & Winter, H. L. D. (2011) · Journal of Cheminformatics · doi:10.1186/1758-2946-3-s1-p7 · Cited by 8 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Muratov, 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 · see citing works
Self-citationJiang, D., Wu, Z., Hsieh, C.-Y., Chen, G., Liao, B., Wang, Z., Shen, C., Cao, D., Wu, J., & Hou, T. (2021) · Journal of Cheminformatics · doi:10.1186/s13321-020-00479-8 · Cited by 664 · see citing works
Artificial intelligence in drug discovery: recent advances and future perspectives
Jiménez-Luna, J., Grisoni, F., Weskamp, N., & Schneider, G. (2021) · Expert Opinion on Drug Discovery · doi:10.1080/17460441.2021.1909567 · Cited by 464 · see citing works
“As drug discovery is a multiparameter optimization challenge [36], multitask learning might make more efficient use of correlated data in common scenarios where the entirety of a molecular library is not exhaustively tested on all endpoints of interest, and without the need for prior imputation.”
BackgroundTransformer-CNN: Swiss knife for QSAR modeling and interpretation
Karpov, P., Godin, G., & Tetko, I. V. (2020) · Journal of Cheminformatics · doi:10.1186/s13321-020-00423-w · Cited by 261 · see citing works
“These descriptors were analysed by the same methods as used in the previous work, i.e., LibSVM [57], Random Forest [58], XGBoost [59] as well as by Associative Neural Networks (ASNN) [60] and Deep Neural Networks [61].”
MethodSelf-citationHemmerich, J., & Ecker, G. F. (2020) · Wiley Interdisciplinary Reviews Computational Molecular Science · doi:10.1002/wcms.1475 · Cited by 169 · see citing works
“The application so far was done for modeling of acute toxicity, 134,141 reactivity, 142 and ADME-Tox properties.”
BackgroundSeal, S., Mahale, M., García-Ortegón, M., Joshi, C. K., Hosseini-Gerami, L., Beatson, A., Greenig, M., Shekhar, M., Patra, A., Weis, C., et al. (2025) · Chemical Research in Toxicology · doi:10.1021/acs.chemrestox.5c00033 · Cited by 159 · see citing works
Inductive transfer learning for molecular activity prediction: Next-Gen QSAR Models with MolPMoFiT
Li, X., & Fourches, D. (2020) · Journal of Cheminformatics · doi:10.1186/s13321-020-00430-x · Cited by 145 · see citing works
Jeong, J., & Choi, J. (2022) · Environmental Science & Technology · doi:10.1021/acs.est.1c07413 · Cited by 147 · see citing works
Advances in Artificial Intelligence (AI)-assisted approaches in drug screening
Singh, S., Gupta, H., Sharma, P., & Sahi, S. (2023) · Artificial Intelligence Chemistry · doi:10.1016/j.aichem.2023.100039 · Cited by 144 · see citing works
Amorim, A. M. B., Piochi, L. F., Gaspar, A. T., Preto, A. J., Rosário-Ferreira, N., & Moreira, I. S. (2024) · Chemical Research in Toxicology · doi:10.1021/acs.chemrestox.3c00352 · Cited by 132 · see citing works
Sharma, B., Chenthamarakshan, V., Dhurandhar, A., Pereira, S., Hendler, J., Dordick, J. S., & Das, P. (2023) · Scientific Reports · doi:10.1038/s41598-023-31169-8 · Cited by 122 · see citing works
Jain, S., Siramshetty, V. B., Alves, V. M., Muratov, E. N., Kleinstreuer, N., Tropsha, A., Nicklaus, M. C., Simeonov, A. M., & Zakharov, A. V. (2021) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.0c01164 · Cited by 114 · see citing works
TOXRIC: a comprehensive database of toxicological data and benchmarks
Wu, L., Yan, B., Han, J., Li, R., Xiao, J., He, S., & Bo, X. (2022) · Nucleic Acids Research · doi:10.1093/nar/gkac1074 · Cited by 102 · see citing works
“All the sources are commonly used for toxicity prediction (28–33).”
graphDelta: MPNN Scoring Function for the Affinity Prediction of Protein–Ligand Complexes
Karlov, D. S., Sosnin, S., Fedorov, M. V., & Popov, P. A. (2020) · ACS Omega · doi:10.1021/acsomega.9b04162 · Cited by 99 · see citing works
Self-citationMachine Learning in Drug Discovery
Klambauer, G., Hochreiter, S., & Rarey, M. (2019) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.9b00136 · Cited by 91 · see citing works
A Survey of Multi‐task Learning Methods in Chemoinformatics
Sosnin, S., Vashurina, M., Withnall, M., Karpov, P., Fedorov, M. V., & Tetko, I. V. (2018) · Molecular Informatics · doi:10.1002/minf.201800108 · Cited by 82 · see citing works
Self-citationTransformers enable accurate prediction of acute and chronic chemical toxicity in aquatic organisms
Gustavsson, M., Käll, S., Svedberg, P., Inda-Diaz, J. S., Molander, S., Coria, J., Backhaus, T., & Kristiansson, E. (2024) · Science Advances · doi:10.1126/sciadv.adk6669 · Cited by 82 · see citing works
Benchmarking machine learning methods for modeling physical properties of ionic liquids
Baskin, I. I., Epshtein, A., & Ein‐Eli, Y. (2022) · Journal of Molecular Liquids · doi:10.1016/j.molliq.2022.118616 · Cited by 72 · see citing works
Wu, L., Huang, R., Tetko, I. V., Xia, Z., Xu, J., & Tong, W. (2021) · Chemical Research in Toxicology · doi:10.1021/acs.chemrestox.0c00373 · Cited by 72 · see citing works
“For neural networks, we deployed a 3-Layer neural-network (MLP-3), 7-Layer neural-network (DNN 19 ), Associative Neural Network (ASNN-MTL) 29 , and a Multi-task Learning version of the 7-Layer Neural-network (DNN-MTL) 19 .”
BackgroundMethodSelf-citationA review on the recent applications of deep learning in predictive drug toxicological studies
Sinha, K., Ghosh, N., & Sil, P. C. (2023) · Chemical Research in Toxicology · doi:10.1021/acs.chemrestox.2c00375 · Cited by 64 · see citing works
User-friendly and industry-integrated AI for medicinal chemists and pharmaceuticals
Kapustina, O., Burmakina, P., Gubina, N., Serov, N., & Vinogradov, V. V. (2024) · Artificial Intelligence Chemistry · doi:10.1016/j.aichem.2024.100072 · Cited by 56 · see citing works
Uncertainty-Informed Deep Transfer Learning of Perfluoroalkyl and Polyfluoroalkyl Substance Toxicity
Feinstein, J., Sivaraman, G., Picel, K., Peters, B., Vázquez‐Mayagoitia, Á., Ramanathan, A., MacDonell, M. M., Foster, I. T., & Yan, E. (2021) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.1c01204 · Cited by 58 · see citing works
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 47 · see citing works
Predictive Models for Human Organ Toxicity Based on In Vitro Bioactivity Data and Chemical Structure
Xu, T., Ngan, D. K., Ye, L., Xia, M., Xie, H. Q., Zhao, B., Simeonov, A. M., & Huang, R. (2020) · Chemical Research in Toxicology · doi:10.1021/acs.chemrestox.9b00305 · Cited by 44 · see citing works
Kim, D., & Choi, J. (2025) · Toxicology · doi:10.1016/j.tox.2025.154230 · Cited by 46 · see citing works
Small data, big challenges: Machine- and deep-learning strategies for data-limited drug discovery
Pallikkavaliyaveetil, N., & Chandrasekaran, S. (2025) · Advanced Drug Delivery Reviews · doi:10.1016/j.addr.2025.115762 · Cited by 41 · see citing works
Simplex representation of molecular structure as universal QSAR/QSPR tool
Kuz’min, V. Е., Artemenko, A. G., Ognichenko, L. N., Hromov, A. I., Kosinskaya, A. P., Stelmakh, S. I., Sessions, Z. L., & Muratov, E. N. (2021) · Structural Chemistry · doi:10.1007/s11224-021-01793-z · Cited by 46 · see citing works
Deep neural network model for highly accurate prediction of BODIPYs absorption
Ksenofontov, A. A., Lukanov, M. M., Bocharov, P. S., Березин, М. Б., & Tetko, I. V. (2021) · Spectrochimica Acta Part A Molecular and Biomolecular Spectroscopy · doi:10.1016/j.saa.2021.120577 · Cited by 38 · see citing works
Self-citationXu, Y. (2021) · Methods in molecular biology · doi:10.1007/978-1-0716-1787-8_10 · Cited by 37 · see citing works
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 37 · see citing works
Machine learning models for phase transition and decomposition temperature of ionic liquids
Makarov, D. M., Fadeeva, Y. A., Shmukler, L. E., & Tetko, I. V. (2022) · Journal of Molecular Liquids · doi:10.1016/j.molliq.2022.120247 · Cited by 35 · see citing works
Self-citationDaghighi, A., Casañola‐Martín, G. M., Iduoku, K., Kušić, H., González‐Díaz, H., & Rasulev, B. (2024) · Environmental Science & Technology · doi:10.1021/acs.est.4c01017 · Cited by 34 · see citing works
de Lomana, M. G., Zapata, P. A. M., & Montanari, F. (2023) · Chemical Research in Toxicology · doi:10.1021/acs.chemrestox.3c00086 · Cited by 34 · see citing works
“44 − 46 Here, multi-task models were trained on the mechanistic datasets alone (including five tasks; see Multi-Task Model Development section) or in combination with two datasets of pseudolabeled data for the overall and membrane potential endpoints.”
Ksenofontov, A. A., Lukanov, M. M., & Bocharov, P. S. (2022) · Spectrochimica Acta Part A Molecular and Biomolecular Spectroscopy · doi:10.1016/j.saa.2022.121442 · Cited by 31 · see citing works
Recommender Systems in Antiviral Drug Discovery
Sosnina, E. A., Sosnin, S., Nikitina, A. A., Nazarov, I., Osolodkin, D. I., & Fedorov, M. V. (2020) · ACS Omega · doi:10.1021/acsomega.0c00857 · Cited by 27 · see citing works
Self-citationMultitask CapsNet: An Imbalanced Data Deep Learning Method for Predicting Toxicants
Wang, Y., Wang, B., Jiang, J., Guo, J., Lai, J., Lian, X., & Wu, J. (2021) · ACS Omega · doi:10.1021/acsomega.1c03842 · Cited by 24 · see citing works
Halder, A. K., & Cordeiro, M. N. D. S. (2021) · Biomolecules · doi:10.3390/biom11111670 · Cited by 25 · see citing works
Banerjee, A., & Roy, K. (2023) · Environmental Science Processes & Impacts · doi:10.1039/d3em00322a · Cited by 24 · see citing works
Collado, A. A., Carrasco‐Velar, R., García‐Pedrajas, N., & García, G. C. (2020) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.0c00908 · Cited by 22 · see citing works
Deep Learning in Environmental Toxicology: Current Progress and Open Challenges
Tan, H., Jin, J., Fang, C., Zhang, Y., Chang, B., Zhang, X., Yu, H., & Shi, W. F. (2023) · ACS ES&T Water · doi:10.1021/acsestwater.3c00152 · Cited by 21 · see citing works
Hunklinger, A., Hartog, P. B. R., Šícho, M., Godin, G., & Tetko, I. V. (2024) · SLAS DISCOVERY · doi:10.1016/j.slasd.2024.01.005 · Cited by 21 · see citing works
“The machine learning methods based on descriptors included Deep Neural Network (DNN) [35] and CatBoost [36].”
BackgroundMethodSelf-citationLu, J., Wu, L., Li, R., Wan, M., Yang, J., Zan, P., Bai, H., He, S., & Bo, X. (2025) · Nature Communications · doi:10.1038/s41467-025-60989-7 · Cited by 21 · see citing works
Bichan, N. G., Ovchenkova, E. N., Ksenofontov, A. A., Mozgova, V. A., Сергеевич, Г. М., Вадимовна, Ч. У., Shelaev, I. V., & Lomova, T. N. (2022) · Dyes and Pigments · doi:10.1016/j.dyepig.2022.110470 · Cited by 20 · see citing works
Boulaamane, Y., Jangid, K., Britel, M. R., & Maurady, A. (2023) · Molecular Diversity · doi:10.1007/s11030-023-10691-x · Cited by 17 · see citing works
“4B, t-SNE analysis was used to compare molecules by their structural features based on RDkit’s Morgan fingerprints [63].”
Analysis of the benefits of imputation models over traditional QSAR models for toxicity prediction
Walter, M., Allen, L. N., de León, A. D. L. V., Webb, S. J., & Gillet, V. J. (2022) · Journal of Cheminformatics · doi:10.1186/s13321-022-00611-w · Cited by 20 · see citing works
“…using solely predicted activities as features in the test set, we found no consistent improvements over single task models (for MCC and ROC-AUC as metric), which is in contrast to previous reports on FNs [7, 8] and on the related approach using predicted bioactivity profiles by Norinder et al. [9].”
ResultAccurate prediction of 11 B NMR chemical shift of BODIPYs via machine learning
Ksenofontov, A. A., Isaev, Y. I., Lukanov, M. M., Makarov, D. M., Eventova, V. A., Anatolevich, K. I., & Berezin, M. B. (2023) · Physical Chemistry Chemical Physics · doi:10.1039/d3cp00253e · Cited by 19 · see citing works
HyperPCM: Robust Task-Conditioned Modeling of Drug–Target Interactions
Svensson, E., Hoedt, P.-J., Hochreiter, S., & Klambauer, G. (2024) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.3c01417 · Cited by 20 · see citing works
Interpreting Neural Network Models for Toxicity Prediction by Extracting Learned Chemical Features
Walter, M., Webb, S. J., & Gillet, V. J. (2024) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.4c00127 · Cited by 21 · see citing works
Cheminformatics Explorations of Natural Products
Prieto-Martínez, F. D., Norinder, U., & Medina‐Franco, J. L. (2019) · Fortschritte der Chemie Organischer Naturstoffe/Fortschritte der Chemie organischer Naturstoffe/Progress in the chemistry of organic natural products · doi:10.1007/978-3-030-14632-0_1 · Cited by 19 · see citing works
Generalizable, fast, and accurate DeepQSPR with fastprop
Burns, J. W., & Green, W. H. (2025) · Journal of Cheminformatics · doi:10.1186/s13321-025-01013-4 · Cited by 20 · see citing works
“One simple but incredibly computationally expensive approach is to use delta learning, which artificially increases dataset size by generating all possible pairs of molecules from the available data (thus squaring the size of the dataset).”
Semenyuta, I. V., Trush, M. M., Kovalishyn, V., Rogalsky, S. P., Hodyna, D. M., Karpov, P., Xia, Z., Tetko, I. V., & Metelytsia, L. O. (2021) · International Journal of Molecular Sciences · doi:10.3390/ijms22020563 · Cited by 17 · see citing works
“The next analysis was to examine the toxic effects of the studied ILs using the OCHEM published models against in vivo toxicity [27] and Ames test [28].”
MethodSelf-citationHalder, A. K., Moura, A. S., & Cordeiro, M. N. D. S. (2023) · The Science of The Total Environment · doi:10.1016/j.scitotenv.2023.164337 · Cited by 15 · see citing works
Makarov, D. M., Ksenofontov, A. A., & Budkov, Y. A. (2025) · Chemical Research in Toxicology · doi:10.1021/acs.chemrestox.4c00421 · Cited by 14 · see citing works
Viljanen, M., Minnema, J., Wassenaar, P. N. H., Rorije, E., & Peijnenburg, W. J. G. M. (2023) · SAR and QSAR in environmental research · doi:10.1080/1062936x.2023.2254225 · Cited by 14 · see citing works
Shkil, D. O., Muhamedzhanova, A. A., Petrov, P. I., Скорб, Е. В., Aliev, T. A., Steshin, I., Tumanov, A. V., Kislinskiy, A. S., & Fedorov, M. V. (2024) · Molecules · doi:10.3390/molecules29081826 · Cited by 13 · see citing works
“The comparison was carried out with the metrics of the multitask model of a fully connected neural network, the architecture of which was considered in an earlier publication by Sosnin et al. [43], and the metrics with five-fold cross-validation were presented on Syntelly’s website [44].”
MethodSelf-citationPrediction of Combined Sorbent and Catalyst Materials for SE-SMR, Using QSPR and Multitask Learning
Nkulikiyinka, P., Wagland, S. T., Manovic, V. M., & Clough, P. T. (2022) · Industrial & Engineering Chemistry Research · doi:10.1021/acs.iecr.2c00971 · Cited by 10 · see citing works
Co‐model for chemical toxicity prediction based on multi‐task deep learning
Li, Y. Y., Chen, L., Pu, C., Zang, C., Yan, Y., Chen, Y., Zhang, Y., & Liu, H. (2023) · Molecular Informatics · doi:10.1002/minf.202200257 · Cited by 11 · see citing works
Improvement of multi-task learning by data enrichment: application for drug discovery
Sosnina, E. A., Sosnin, S., & Fedorov, M. V. (2023) · Journal of Computer-Aided Molecular Design · doi:10.1007/s10822-023-00500-w · Cited by 10 · see citing works
“Toxicity data can also be collected based on different toxicity endpoints such as investigated organisms or administration methods [4, 5].”
BackgroundSelf-citationMultitask Modeling with Confidence Using Matrix Factorization and Conformal Prediction
Norinder, U., & Svensson, F. (2019) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.9b00027 · Cited by 10 · see citing works
Identification of Potential Insect Growth Inhibitor against Aedes aegypti: A Bioinformatics Approach
da Costa, G. V., Neto, M. F. A., Silva, A. K. P. D., de Sá, E. M. F., Cancela, L. C. F., Vega, J. S., Lobato, C. M., Zuliani, J. P., Espejo-Román, J. M., Rosa, J. M. C., et al. (2022) · International Journal of Molecular Sciences · doi:10.3390/ijms23158218 · Cited by 9 · see citing works
Umemori, Y., D, K. H. M., Sakamoto, S., Kageyama, M., & Iijima, T. (2022) · SAR and QSAR in environmental research · doi:10.1080/1062936x.2022.2149619 · Cited by 9 · see citing works
“It has been reported that the other experimental data (source domain) used for this multi-task learning should be correlated with the experimental data (target domain) to be predicted [31,32].”
BackgroundQSAR investigation of acute toxicity of organic compounds during oral administration to mice
Tinkov, O. V., Grigorev, V. Y., Полищук, П. Г., Yarkov, A. V., & Raevsky, O. A. (2019) · Biomeditsinskaya Khimiya · doi:10.18097/pbmc20196502123 · Cited by 9 · see citing works
Multi-task multi-view and iterative error-correcting random forest for acute toxicity prediction
Gao, J., Wu, L., Lin, G., Zou, J., Yan, B., Liu, K., He, S., & Bo, X. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.126972 · Cited by 8 · see citing works
Lancia, P., Louazzani, M., Gros, L., Ginestar, J., Fioravanzo, E., & Baleydier, A. (2025) · Chemical Research in Toxicology · doi:10.1021/acs.chemrestox.4c00534 · Cited by 8 · see citing works
Drug efficacy and toxicity prediction: an innovative application of transcriptomic data
Xia, X. (2020) · Cell Biology and Toxicology · doi:10.1007/s10565-020-09552-2 · Cited by 8 · see citing works
Joint Virtual Special Issue on Computational Toxicology
Tetko, I. V., & Tropsha, A. (2020) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.0c00140 · Cited by 8 · see citing works
Self-citationpH-dependent solubility prediction for optimized drug absorption and compound uptake by plants
Bonin, A., Montanari, F., Niederführ, S., & Göller, A. H. (2023) · Journal of Computer-Aided Molecular Design · doi:10.1007/s10822-023-00496-3 · Cited by 7 · see citing works
“[36] pH was implemented as one-hot encoding in a single-task approach.”
MethodKim, J., Lee, S., Jung, D., Kim, H. Y., Lee, J.-I., Seo, M., Kim, S., Choi, J., Yu, W., & Cho, H. (2025) · Journal of Hazardous Materials · doi:10.1016/j.jhazmat.2025.137650 · Cited by 6 · see citing works
In Silico Prediction of Toxicological and Pharmacokinetic Characteristics of Medicinal Compounds
Vassiliev, P. M., Golubeva, A. V., Королева, А. Р., Perfilev, M. A., & Kochetkov, A. N. (2023) · Safety and Risk of Pharmacotherapy · doi:10.30895/2312-7821-2023-11-4-390-408 · Cited by 5 · see citing works
Modelling In vitro Mutagenicity Using Multi-Task Deep Learning and REACH Data
Karamertzanis, P. G., Rasenberg, M., Shah, I., & Patlewicz, G. Y. (2025) · Chemical Research in Toxicology · doi:10.1021/acs.chemrestox.5c00152 · Cited by 7 · see citing works
AI and machine learning in pharmaceutical formulation and manufacturing of personalized medicines
Gupta, A., Vaidya, K., & Boehnke, N. (2024) · Elsevier eBooks · doi:10.1016/b978-0-323-91819-0.00006-3 · Cited by 5 · see citing works
Socio-economic aspects of the introduction of artificial intelligence technologies
Fedorov, M. V. (2023) · Journal of Digital Economy Research · doi:10.24833/14511791-2023-1-6-60 · Cited by 4 · see citing works
Self-citationMachine learning for biomaterials design
Xia, X., Leng, T., Garcı́a, A. J., & de la Fuente‐Núñez, C. (2026) · Nature Reviews Bioengineering · doi:10.1038/s44222-026-00476-w · Cited by 8 · see citing works
SangsterLogP - the largest publicly available dataset of logP values
Cirino, T., Caron, G., Ermondi, G., Charochkina, L. L., & Tetko, I. V. (2026) · Scientific Data · doi:10.1038/s41597-026-07357-2 · Cited by 3 · see citing works
“Amid descriptor-based methods, we selected a combination of an extended set of Estate descriptors 26 with DNN 27 and OSMORDRED 28 descriptors with CatBoost 29 .”
Self-citationNoga, M., & Jurowski, K. (2025) · Chemico-Biological Interactions · doi:10.1016/j.cbi.2025.111623 · Cited by 2 · see citing works
Explainable Artificial Intelligence in Drug Discovery
Geevarghese, A. V. (2024) · Computational intelligence methods and applications · doi:10.1007/978-981-97-3705-5_6 · Cited by 2 · see citing works
HT_PREDICT: a machine learning-based computational open-source tool for screening HDAC6 inhibitors
Tinkov, O. V., Осипов, В. Н., Колотаев, А. В., Khachatryan, D. S., & Grigorev, V. Y. (2024) · SAR and QSAR in environmental research · doi:10.1080/1062936x.2024.2371155 · Cited by 2 · see citing works
“As is seen from the data in Table 6, the best developed model has comparable coefficients of determination Q 2 after 5-fold internal cross validation with the models proposed earlier [23,42,43].”
Highly Accurate Filters to Flag Frequent Hitters in AlphaScreen Assays by Suggesting their Mechanism
Ghosh, D., Koch, U., Hadian, K., Sattler, M., & Tetko, I. V. (2021) · Molecular Informatics · doi:10.1002/minf.202100151 · Cited by 2 · see citing works
Self-citationHodyna, D. M., Kovalishyn, V., Brazhko, O. A., & Metelytsia, L. O. (2025) · Bioactivities · doi:10.47352/bioactivities.2963-654x.278 · Cited by 1 · see citing works
Empirical and physics-based calculations of physical-chemical properties
Ratkova, E. L., Abramov, Y. A., Baskin, I. I., Livingstone, D. J., Xia, J., & Tetko, I. V. (2025) · Elsevier eBooks · doi:10.1016/b978-0-443-29808-0.00058-3 · Cited by 1 · see citing works
Self-citationCerimagic, T., Sosnin, S. D., & Ecker, G. F. (2026) · Digital Discovery · doi:10.1039/d5dd00536a · Cited by 2 · see citing works
Self-citationPatlewicz, G. Y., Friedman, K. P., Houck, K. A., Zhang, L., Huang, R., Xia, M., Brown, J., & Simmons, S. O. (2023) · Computational Toxicology · doi:10.1016/j.comtox.2023.100271 · Cited by 1 · see citing works
HDAC2 SCAN: An Expert System for Virtual Screening of Histone Deacetylase 2 Inhibitors
Tinkov, O. V., Grigoreva, L. D., & Grigorev, V. Y. (2023) · Russian Journal of General Chemistry · doi:10.1134/s1070363223150021 · Cited by 1 · see citing works
Beyond Chemical 1D knowledge using TransformersPreprint
van Deursen, R., Tetko, I. V., & Godin, G. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.01027 · Cited by 1 · see citing works
Self-citationAnalysis and Modelling of False Positives in GPCR Assays
Ghosh, D., Tetko, I. V., Klebl, B., Nußbaumer, P., & Koch, U. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-30493-5_71
Self-citationAbdelalim, M. (2022) · ChemRxiv · doi:10.26434/chemrxiv-2022-090pf
Elaleem, M. A. (2022) · ChemRxiv · doi:10.26434/chemrxiv-2022-090pf-v2
Rule-based model for interpretable acute toxicity prediction
Zhong, J., Ren, W., & Sun, Z. (2023) · International Conference on Computer Vision and Data Mining (ICCVDM) · doi:10.1117/12.2660032
Benzocaine-N-acylindoline conjugates: synthesis and antiviral activity against Coxsackievirus B3
Volobueva, A. S., Андреевич, Ш. А., Mikhalski, M. G., Panova, V. A., Barkhatova, D. D., Korshunova, E., Ivanovskiy, S. A., Zarubaev, V. V., & Baykov, S. V. (2024) · Medicinal Chemistry Research · doi:10.1007/s00044-024-03191-6
“It was chosen here due to its resistance to pleconaril – well studied capsid binder inhibitor, and it is important to address existing a Data were obtained using synthelly.ru [30, 41, 42] resistance of CVB3 to pleconaril in antiviral studies [32].”
Jiang, D., Wu, Z., Hsieh, C., Chen, G., Liao, B., Wang, Z., Shen, C., Cao, D., Wu, J., & Hou, T. (2021) · Figshare · doi:10.6084/m9.figshare.14053377
Jiang, D., Wu, Z., Hsieh, C., Chen, G., Liao, B., Wang, Z., Shen, C., Cao, D., Wu, J., & Hou, T. (2021) · Figshare · doi:10.6084/m9.figshare.14053374
Balancing Imbalanced Toxicity Models: Using MolBERT with Focal Loss
Masood, M. A., Samuel Kaski, A., Ceulemans, H., Herman, D., & Heinonen, M. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72381-0_8
Multi-Task Cascade Forest Framework for Predicting Acute Toxicity across Species
Liu, K., Li, R., Wu, L., Yang, J., Han, J., He, S., Bo, X., & Gao, J. (2025) · Research · doi:10.34133/research.1046
“The first 5 methods, MT-DNN [ 9 ], MT-GCNN [ 17 ], DLCA [ 10 ], ConsenA [ 11 ], and ConsenB [ 11 ], were derived from recently published studies on MSATP modeling.”
InfluentialJiang, D., Wu, Z., HSIEH, C., Chen, G., Liao, B., Wang, Z., Shen, C., Cao, D., Wu, J., & Hou, T. (2021) · Figshare · doi:10.6084/m9.figshare.14053380
Walter, M., Allen, L. N., de León, A. D. L. V., Webb, S. J., & Gillet, V. J. (2022) · Figshare · doi:10.6084/m9.figshare.20025047
Comparison of Different Models for Toxicity Prediction using AI
Galav, R. K., Thakur, S. N., Angaitkar, P., Gupta, A., Kumbhare, A., & Kumarrao, S. (2025) · International Conference on Artificial Intelligence for Innovations in Healthcare Industries (ICAIIHI) · doi:10.1109/icaiihi67124.2025.11403297
“Comparative studies have illustrated that multitask and hybrid strategies enhance generalizability across wide chemical spaces [14].”
InfluentialUnlocking structure–property relationships in organic dyes with machine learning and statistics
Wu, H., Yang, Z., Jiang, H., Yuan, Q., Zhao, L., Tan, R., Dong, L., Lu, C., Tan, L., Zhang, G., et al. (2026) · AIChE Journal · doi:10.1002/aic.70318
Audebrand, A., Brogi, S., Tezeren, M., Tafi, A., Ocak, O. H., Koyuncu, H., Tetko, I. V., Désaubry, L., & Nebigil, C. G. (2026) · British Journal of Pharmacology · doi:10.1111/bph.70394
“Toxicological and pharmacokinetic properties of IS20, IS37 and IS39 were predicted using QSAR models implemented in the Online Chemical Data-base and Modelling Environment (OCHEM) platform (Sosnin et al., 2019).”
Self-citationHan, T., Wang, J., Zhao, Y., Lin, Y., Yu, L., He, S., Zan, P., & Bo, X. (2026) · Molecules · doi:10.3390/molecules31071144
“Subsequent studies [15,16] systematically benchmarked multi-task toxicity prediction across broad chemical spaces, varying both molecular descriptors and algorithmic frameworks.”
Quantitative Spatial Analysis of PFAS in Nine Biological Tissues from Mouse via MALDI-TIMS-MSI
Nikolopoulou, V., Stem, A. D., Alayyoub, M., Vasiliou, V., & Aalizadeh, R. (2026) · Environmental Science & Technology · doi:10.1021/acs.est.5c14803
- Authors
- Sosnin, S., Karlov, D., Tetko, I. V., & Fedorov, M. V.
- Affiliations
- Skolkovo Institute of Science and Technology (RU)
- Helmholtz Munich (DE)
- Corresponding author
- Tetko, Igor V.
- Fedorov, Maxim V.
- Venue
- Journal of Chemical Information and Modeling
- Publisher
- American Chemical Society (ACS)
- Published
- 2018-12-27
- Volume
- 59
- Issue
- 3
- Pages
- 1062-1072
- ISSN
- 1549-9596 (ISSN-L)
- 1549-960X
- OpenAlex
- W2907473220
- Cited by
- 102
- References
- 54
- Citations by year
- 2026: 11 · 2025: 15 · 2024: 13 · 2023: 18 · 2022: 13 · 2021: 14 · 2020: 12 · 2019: 5 · 2018: 1
- FWCI
- 6.36
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by-nc
- Locations
- Journal of Chemical Information and Modeling (publishedVersion, cc-by-nc)
- PubMed (publishedVersion)
- Site cant be reached (submittedVersion, other-oa)
- PuSH - Publication Server of Helmholtz Zentrum München (submittedVersion)
- Funders
- Russian Science Foundation (14-43-00024)
- Topics
- Physical Sciences › Computer Science › Computational Theory and Mathematics › Computational Drug Discovery Methods
- Physical Sciences › Materials Science › Materials Chemistry › Machine Learning in Materials Science
- Physical Sciences › Chemistry › Physical and Theoretical Chemistry › History and advancements in chemistry
- Keywords
- acute toxicity prediction, multi-task learning, toxicity modeling, molecular descriptors, chemical safety regulation
- MeSH terms
- Deep Learning, Animals, Models, Theoretical, Endpoint Determination, Toxicity Tests, Acute
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
