Abstract
Thousands of molecular descriptors (1D to 4D) can be generated and used as features to model quantitative structure–activity or toxicity relationship (QSAR or QSTR) for chemical toxicity prediction. This often results in models that suffer from the “curse of dimensionality”, a problem that can occur in machine learning practice when too many features are employed to train a model. Here we discuss different methods of eliminating redundant and irrelevant features to enhance prediction performance, increase interpretability, and reduce computational complexity. Several feature selection and extraction methods are summarized along with their strengths and shortcomings. We also highlight some commonly overlooked challenges such as algorithm instability and selection bias while offering possible solutions.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsAbbreviations
- 1D:
-
One-dimensional
- 2D:
-
Two-dimensional
- 3D:
-
Three-dimensional
- 4D:
-
Four-dimensional
- ACO:
-
Ant colony optimization
- ECFP:
-
Extended connectivity fingerprints
- GA:
-
Genetic algorithm
- KPCA:
-
Kernel principal component analysis
- LASSO:
-
Least absolute shrinkage and selection operator
- LDA:
-
Linear discriminant analysis
- LOOCV:
-
Leave-one-out cross-validation
- MACCS:
-
Molecular access system
- MDS:
-
Multi-dimensional scaling
- PCA:
-
Principal component analysis
- PSO:
-
Particle swarm optimization
- QSAR:
-
Quantitative structure–activity relationship
- QSTR:
-
Quantitative structure–toxicity relationship
- RFE:
-
Recursive feature elimination
- SA:
-
Simulated annealing
- SAR:
-
Structure–activity relationship
- SFFS:
-
Sequential floating forward selection
- SFS:
-
Sequential forward selection
- STR:
-
Structure–toxicity relationship
- SVM:
-
Support vector machine
- Tox21:
-
Toxicology in the twenty-first century
- t-SNE:
-
t-Distributed stochastic neighbor embedding
References
Lavecchia A (2015) Machine-learning approaches in drug discovery: methods and applications. Drug Discov Today 20(3):318–331
Raies AB, Bajic VB (2016) In silico toxicology: computational methods for the prediction of chemical toxicity. Wiley Interdiscip Rev Comput Mol Sci 6(2):147–172
Greene N, Pennie W (2015) Computational toxicology, friend or foe? Toxicol Res 4(5):1159–1172
Kruhlak NL, Benz RD, Zhou H, Colatsky TJ (2012) (Q)SAR modeling and safety assessment in regulatory review. Clin Pharmacol Ther 91(3):529–534
Tropsha A (2010) Best practices for QSAR model development, validation, and exploitation. Mol Inform 29(6–7):476–488
Yang H, Sun L, Li W, Liu G, Tang Y (2018) In silico prediction of chemical toxicity for drug design using machine learning methods and structural alerts. Front Chem 6:30. https://doi.org/10.3389/fchem.2018.00030
Danishuddin Khan AU (2016) Descriptors and their selection methods in QSAR analysis: paradigm for drug design. Drug Discov Today 21(8):1291–1302
Leach AR, Gillet VJ (2007) Molecular descriptors. An introduction to chemoinformatics. Springer, Dordrecht, pp 53–74
Todeschini R, Consonni V (2000) Handbook of molecular descriptors. Wiley-VCH, Weinheim
Duan J, Dixon SL, Lowrie JF, Sherman W (2010) Analysis and comparison of 2D fingerprints: insights into database screening performance using eight fingerprint methods. J Mol Graph Model 29(2):157–170
National Institutes of Health (2009) PubChem substructure fingerprint. ftp://ftp.ncbi.nlm.nih.gov/pubchem/specifications/pubchem_fingerprints.txt. Accessed 10 Oct 2018
Rogers D, Hahn M (2010) Extended-connectivity fingerprints. J Chem Inf Model 50(5):742–754
Huang R, Xia M, Nguyen D-T et al (2016) Tox21Challenge to build predictive models of nuclear receptor and stress response pathways as mediated by exposure to environmental chemicals and drugs. Front Environ Sci 3:85. https://doi.org/10.3389/fenvs.2015.00085
Mayr A, Klambauer G, Unterthiner T, Hochreiter S (2016) DeepTox: toxicity prediction using deep learning. Front Environ Sci 3:80. https://doi.org/10.3389/fenvs.2015.00080
Subramanian J, Simon R (2013) Overfitting in prediction models—Is it a problem only in high dimensions? Contemp Clin Trials 36(2):636–641
Clarke R, Ressom HW, Wang A et al (2008) The properties of high-dimensional data spaces: implications for exploring gene and protein expression data. Nat Rev Cancer 8(1):37–49
Hinton GE, Salakhutdinov RR (2006) Reducing the dimensionality of data with neural networks. Science 313(5786):504–507
Ang JC, Mirzal A, Haron H, Hamed HNA (2016) Supervised, unsupervised, and semi-supervised feature selection: a review on gene selection. IEEE/ACM Trans Comput Biol Bioinform 13(5):971–989
Merkwirth C, Mauser H, Schulz-Gasch T, Roche O, Martin Stahl A, Lengauer T (2004) Ensemble methods for classification in cheminformatics. J Chem Inf Comput Sci 44(6):1971–1978
Venkatraman V, Dalby AR, Yang ZR (2004) Evaluation of mutual information and genetic programming for feature selection in QSAR. J Chem Inf Comput Sci 44(5):1686–1692
Bajorath J (2001) Selected concepts and investigations in compound classification, molecular descriptor analysis, and virtual screening. J Chem Inf Comput Sci 41(2):233–245
Goodarzi M, Dejaegher B, Heyden YV (2012) Feature selection methods in QSAR studies. J AOAC Int 95(3):636–651
Shahlaei M (2013) Descriptor selection methods in quantitative structure—activity relationship studies: a review study. Chem Rev 113(10):8093–8103
Bellman R (2016) Adaptive control processes: a guided tour. Princeton University Press, New Jersey
Chandrashekar G, Sahin F (2014) A survey on feature selection methods. Comput Electr Eng 40(1):16–28
Van Der Maaten L, Postma E, Van Den Herik J (2009) Dimensionality reduction: a comparative review. J Mach Learn Res 10:66–71
Cai J, Luo J, Wang S, Yang S (2018) Feature selection in machine learning: a new perspective. Neurocomputing 300:70–79
Tang J, Alelyani S, Liu H (2014) Feature selection for classification: a review. In: Aggarwal CC (ed) Data classification: algorithms and applications, 1st edn. CRC Press, Boca Raton, pp 37–64
Johnstone IM, Titterington DM (2009) Statistical challenges of high-dimensional data. Philos Trans A Math Phys Eng Sci 367(1906):4237–4253
Zhu X, Wu X (2004) Class noise versus attribute noise: a quantitative study. Artif Intell Rev 22(3): 177 –210
Kohonen T (1982) Self-organized formation of topologically correct feature maps. Biol Cybern 43(1):59–69
Sheikhpour R, Sarram MA, Gharaghani S, Chahooki MAZ (2017) A survey on semi-supervised feature selection methods. Pattern Recognit 64:141–158
Dy JG, Brodley CE (2004) Feature selection for unsupervised learning. J Mach Learn Res 5:845–889
Guyon I, Elisseeff A (2003) An introduction to variable and feature selection. J Mach Learn Res 3:1157–1182
Solorio-Fernandez S, Martinez-Trinidad JF, Carrasco-Ochoa JA, and Zhang Y-Q (2012) Hybrid feature selection method for biomedical datasets. In: 2012 IEEE symposium on computational intelligence in bioinformatics and computational biology (CIBCB), San Diego, 9–12 May 2012
Hsu H-H, Hsieh C-W, Lu M-D (2011) Hybrid feature selection by combining filters and wrappers. Expert Syst Appl 38(7):8144–8150
Guan D, Yuan W, Lee YK, Najeebullah K, Rasel MK (2014) A review of ensemble learning based feature selection. IETE Tech Rev 31(3):190–198
Brahim AB, Limam M (2017) Ensemble feature selection for high dimensional data: a new method and a comparative study. Adv Data Anal Classif 12(4):937–952
Seijo-Pardo B, Porto-Díaz I, Bolón-Canedo V, Alonso-Betanzos A (2017) Ensemble feature selection: homogeneous and heterogeneous approaches. Knowl Based Syst 118:124–139
Janecek A, Gansterer W, Demel M, Ecker G (2008) On the relationship between feature selection and classification accuracy. Proc Mach Learn Res 4:90–105
Hira ZM, Gillies DF (2015) A review of feature selection and feature extraction methods applied on microarray data. Adv Bioinformatics. https://doi.org/10.1155/2015/198363
Rajarshi G, Jurs PC (2004) Development of linear, ensemble, and nonlinear models for the prediction and interpretation of the biological activity of a set of PDGFR inhibitors. J Chem Inf Comput Sci 44(6):2179–2189
Guo G, Neagu D, Cronin MTD (2005) A study on feature selection for toxicity prediction. In: Wang L, Jin Y (eds) Fuzzy systems and knowledge discovery. Springer, Heidelberg, pp 31–34
Newby D, Freitas AA, Ghafourian T (2012) Pre-processing feature selection for improved C&RT models for oral absorption. J Chem Inf Model 53(10):2730–2742
Pudil P, Novovičová J, Kittler J (1994) Floating search methods in feature selection. Pattern Recognit Lett 15(11):1119–1125
Brendel M, Zaccarelli R, Devillers L (2010) A quick sequential forward floating feature selection algorithm for emotion detection from speech. In: INTERSPEECH-2010, Chiba, 26–30 September 2010
Kennedy J, Eberhart R (1995) Particle swarm optimization. In: Proceedings of ICNN’95—international conference on neural networks, Perth, 27 November–1 December 1995
Goldberg DE (1989) Genetic algorithms in search, optimization, and machine learning. Addison-Wesley Longman Publishing Co., Inc, Boston
Revathy N, Balasubramanian R (2012) GA-SVM Wrapper approach for gene banking and classificaiton using expressions of very few genes. J Theor Appl Inf Technol 40(2):113–119
Shen Q, Jiang J-H, Tao J et al (2005) Modified ant colony optimization algorithm for variable selection in QSAR modeling: QSAR studies of cyclooxygenase inhibitors. J Chem Inf Model 45(4):1024–1029
Jain D, Singh V (2018) Feature selection and classification systems for chronic disease prediction: a review. Egypt Informatics J 19(3):179–189
Osman H, Ghafari M, Nierstrasz O (2017) Automatic feature selection by regularization to improve bug prediction accuracy. In: 2017 IEEE workshop on machine learning techniques for software quality evaluation (MaLTeSQuE), Klagenfurt, 21 February 2017
Reddy AS, Kumar S, Garg R (2010) Hybrid-genetic algorithm based descriptor optimization and QSAR models for predicting the biological activity of tipranavir analogs for HIV protease inhibition. J Mol Graph Model 28(8):852–862
Dutta D, Guha R, Wild D, Chen T (2007) Ensemble feature selection: consistent descriptor subsets for multiple QSAR models. J Chem Inf Model 47(3):989–997
Zhu X-W, Xin Y-J, Ge H-L (2015) Recursive random forests enable better predictive performance and model interpretation than variable selection by LASSO. J Chem Inf Model 55(4):736–746
Lauria A, Ippolito M, Almerico AM. (2009) Combined use of PCA and QSAR/QSPR to predict the drugs mechanism of action. An application to the NCI ACAM database. QSAR Comb Sci 28(4):387–395
Yoo C, Shahlaei M (2018) The applications of PCA in QSAR studies: a case study on CCR5 antagonists. Chem Biol Drug Des 91(1):137–152
Klepsch F, Vasanthanathan P, Ecker GF (2014) Ligand and structure-based classification models for prediction of P-glycoprotein inhibitors. J Chem Inf Model 54(1):218–229
Hemmateenejad B, Miri R, Jafarpour M, Tabarzad M, Foroumadi A (2006) Multiple linear regression and principal component analysis-based prediction of the anti-tuberculosis activity of some 2-aryl-1,3,4-Thiadiazole derivatives. QSAR Comb Sci 25(1):56–66
Manikandan G, Abirami S (2018) A survey on feature selection and extraction techniques for high-dimensional microarray datasets. In: Anouncia SM, Wiil UK (eds) Knowledge computing and its applications. Springer, Singapore, pp 311–333
Reverter F, Vegas E, Oller JM (2014) Kernel-PCA data integration with enhanced interpretability. BMC Syst Biol 8(2):S6
Wang Q (2012) Kernel principal component analysis and its applications in face recognition and active shape models. https://arxiv.org/abs/1207.3538. Accessed 10 October 2018
Baldi P (2012) Autoencoders, unsupervised learning, and deep architectures. In: Proceedings of ICML workshop on unsupervised and transfer learning, Bellevue, 2 July 2012
Goh GB, Hodas NO, Vishnu A (2017) Deep learning for computational chemistry. J Comput Chem 38(16):1291–1307
Chandra B, Sharma RK (2015) Exploring autoencoders for unsupervised feature selection. In: 2015 international joint conference on neural networks (IJCNN), Killarney, 12–17 July 2015
Blaschke T, Olivecrona M, Engkvist O, Bajorath J, Chen H (2018) Application of generative autoencoder in de novo molecular design. Mol Inform 37(1–2):1700123
Burgoon LD (2017) Autoencoder predicting estrogenic chemical substances (APECS): an improved approach for screening potentially estrogenic chemicals using in vitro assays and deep learning. Comput Toxicol 2:45–49
Ye J, Ji S (2009) Discriminant analysis for dimensionality reduction: an overview of recent developments. In: Boulgouris NV, Plataniotis KN, Micheli-Tzanakou E (eds) Biometrics: theory, methods, and applications. IEEE Press, Piscataway, pp 1–20
Yan H, Dai Y (2011) The comparison of five discriminant methods. In: 2011 International conference on management and service science, Wuhan, 12–14 August
Ren YY, Zhou LC, Yang L, Liu PY, Zhao BW, Liu HX (2016) Predicting the aquatic toxicity mode of action using logistic regression and linear discriminant analysis. SAR QSAR Environ Res 27(9):721–746
van der Maaten L, Hinton G (2008) Visualizing data using t-SNE. J Mach Learn Res 9:2579–2605
Borg I, Groenen PJF (2005) Modern Multidimensional Scaling, 2nd edn. Springer Science + Business Media Inc, New York
Belkin M, Niyogi P (2003) Laplacian eigenmaps for dimensionality reduction and data representation. Neural Comput 15(6):1373–1396
Tenenbaum JB, de Silva V, Langford JC (2000) A global geometric framework for nonlinear dimensionality reduction. Science 290(5500):2319–2323
Izenman AJ (2012) Introduction to manifold learning. Wiley Interdiscip Rev Comput Stat 4(5):439–446
Kalousis A, Prados J, Hilario M (2007) Stability of feature selection algorithms: a study on high-dimensional spaces. Knowl Inf Syst 12(1):95–116
Alelyani S, Liu H, Wang L (2011) The effect of the characteristics of the dataset on the selection stability. In: 2011 IEEE 23rd international conference on tools with artificial intelligence, Boca Raton, 7–9 November 2011
Yang P, Zhou BB, Yang JY-H, Zomaya AY (2013) Stability of feature selection algorithms and ensemble feature selection methods in bioinformatics. In: Elloumi M, Zomaya AY (eds) Biological knowledge discovery handbook: preprocessing, mining, and postprocessing of biological data. John Wiley & Sons Inc, Hoboken, pp 333–352
Yang P, Ho JW, Yang Y, Zhou BB (2011) Gene-gene interaction filtering with ensemble of filters. BMC Bioinformatics 12:S10. https://doi.org/10.1186/1471-2105-12-S1-S10
Yang F, Mao KZ (2011) Robust feature selection for microarray data based on multicriterion fusion. IEEE/ACM Trans Comput Biol Bioinforma 8(4):1080–1092
Abeel T, Helleputte T, Van de Peer Y, Dupont P, Saeys Y (2010) Robust biomarker identification for cancer diagnosis with ensemble feature selection methods. Bioinformatics 26(3):392–398
Hastie T, Tibshirani R, Friedman J (2009) The elements of statistical learning, 2nd edn. Springer-Verlag, New York
Ambroise C, McLachlan GJ (2002) Selection bias in gene extraction on the basis of microarray gene-expression data. Proc Natl Acad Sci U S A 99(10):6562–6566
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this chapter
Cite this chapter
Idakwo, G., Luttrell IV, J., Chen, M., Hong, H., Gong, P., Zhang, C. (2019). A Review of Feature Reduction Methods for QSAR-Based Toxicity Prediction. In: Hong, H. (eds) Advances in Computational Toxicology. Challenges and Advances in Computational Chemistry and Physics, vol 30. Springer, Cham. https://doi.org/10.1007/978-3-030-16443-0_7
Download citation
DOI: https://doi.org/10.1007/978-3-030-16443-0_7
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-16442-3
Online ISBN: 978-3-030-16443-0
eBook Packages: Chemistry and Materials ScienceChemistry and Material Science (R0)