Mining environmental chemicals with boosted trees
Pages 1082 - 1089
Abstract
In response to scientific reports and legislative actions, the United States Environmental Protection Agency (EPA) launched an Endocrine Disruptor Screening Program (EDSP). The overarching aim of this program is to develop novel analytical and computational tools and methods for the detection of environmental chemicals causing aberrations in estrogen, androgen, or thyroid hormone systems. As a result of this program, over 700 diverse environmental chemicals have been tested in in vitro and in vivo assays and deposited into public databases. In this work, machine learning classifiers were developed to predict putative disruptors of the human sodium/iodide symporter that plays a crucial role in the biosynthesis of thyroid hormones. Two powerful ensemble algorithms, Random forest and eXtreme Gradient Boosting Tree, were trained with EDSP experimental data and evaluated by repeated cross-validation as well as by retrospective validation. Within its applicability domain, Boosted Tree classifier achieved high performance and discriminated between inhibitors and noninhibitors with an accuracy of 87%, precision of 85% and recall of 63%. Additionally, 98 inhibitors were also predicted among 1,741 human endogenous and exogenous metabolites, including approved oral drugs. Further experimental studies will be needed to validate these predictions and elucidate the mechanism of interactions.
References
[1]
2014. Fortification of food-grade salt with iodine for the prevention and control of iodine deficiency disorders - Guideline. Technical Report. World Health Organization.
[2]
2019. Endocrine Disruption. https://www.epa.gov/endocrine-disruption.
[3]
M. Biciková, R. Hampl, M. Hill, S. Stanická, J. Tallová, and K. Vondra. 2003. Steroids, Sex Hormone-Binding Globulin, Homocysteine, Selected Hormones and Markers of Lipid and Carbohydrate Metabolism in Patients with Severe Hypothyroidism and Their Changes Following Thyroid Hormone Supplementation. Clinical chemistry and laboratory medicine: CCLM/FESCC 41 (04 2003), 284--92.
[4]
L. Breiman. 1996. Bagging Predictors. Machine Learning 24, 2 (1996), 123--140.
[5]
L. Breiman. 2001. Random Forests. Machine Learning 45, 1 (2001), 5--32.
[6]
J. Brossaud, V. Pallet, and J.-B. Corcuff. 2017. Vitamin A, endocrine tissues and hormones: Interplay and interactions. Endocrine Connections 6 (07 2017), EC-17.
[7]
E.C. Chen, N. Khuri, X. Liang, A. Stecula, H.C. Chien, S.W. Yee, Y. Huang, A. Sali, and K.M. Giacomini. 2017. Discovery of Competitive and Noncompetitive Ligands of the Organic Cation Transporter 1 (OCT1; SLC22A1). Journal of Medicinal Chemistry 60, 7 (2017), 2685--2696.
[8]
T. Chen and C. Guestrin. 2016. XGBoost: A Scalable Tree Boosting System. In Proceedings of the 22Nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD 2016). ACM, New York, NY, USA, 785--794.
[9]
G.A. Dai, O. Orlie Levy, and N. Carrasco. 1996. Cloning and characterization of the thyroid iodide transporter. Nature 379 (1996), 458--460.
[10]
E. Darrouzet, S. Lindenthal, D. Marcellin, J.L. Pellequer, and T. Pourcher. 2014. The sodium/iodide symporter: state of the art of its molecular characterization. Biochimica et biophysica acta 1838 (2014), 244--53.
[11]
T. De Bruyn, G. J. P. van Westen, A. P. IJzerman, B. Stieger, P. de Witte, P. F. Augustijns, and P. P. Annaert. 2013. Structure-Based Identification of OATP1B1/3 Inhibitors. Molecular Pharmacology 83, 6 (2013), 1257--1267.
[12]
S. De Coster and N.A. van Larebeke. 2012. Endocrine-Disrupting Chemicals: Associated Disorders and Mechanisms of Action. Journal of environmental and public health 713696 (2012).
[13]
O. Dohán, C. Portulano, C. Basquin, A. Reyna-Neyra, L. M. Amzel, and N. Carrasco. 2007. The Na+/I- symporter (NIS) mediates electroneutral active transport of the environmental pollutant perchlorate. Proceedings of the National Academy of Sciences 104, 51 (2007), 20250--20255.
[14]
H. Dragos, M. Gilles, and V. Alexandre. 2009. Predicting the predictability: a unified approach to the applicability domain problem of QSAR models. J Chem Inf Model 49 (2009), 1762--1776.
[15]
S. Ferrari, P. Fallahi, A. Antonelli, and S. Benvenga. 2017. Environmental Issues in Thyroid Diseases. 8, 50 (2017).
[16]
Y. Freund and R. E. Schapire. 1996. Experiments with a New Boosting Algorithm. In Proceedings of the Thirteenth International Conference on Machine Learning (ICML 1996). Morgan Kaufmann, 148--156.
[17]
Y. Freund and R. E. Schapire. 1997. A Decision-Theoretic Generalization of OnLine Learning and an Application to Boosting. J. Comput. Syst. Sci. 55, 1 (1997), 119--139.
[18]
J. H. Friedman. 2000. Greedy Function Approximation: A Gradient Boosting Machine. Annals of Statistics 29 (2000), 1189--1232.
[19]
J. H. Friedman, T. Hastie, and R. Tibshirani. 1998. Additive Logistic Regression: a Statistical View of Boosting. Annals of Statistics 28 (1998), 337--407.
[20]
D.R. Hallinger, A.S. Murr, A.R. Buckalew, S. Simmons, T.E. Stoker, and S.C. Laws. 2017. Development of a screening approach to detect thyroid disrupting chemicals that inhibit the human sodium iodide symporter (NIS). Toxicology in vitro 40 (2017), 66--78.
[21]
J.A. Hanley and B.J. McNeil. 1982. The meaning and use of the area under a receiver operating characteristic (roc) curve. Radiology 143, 1 (1982), 29--36.
[22]
S. Hertz, A. Roberts, J.H. Means, and R.D. Evans. 1940. Radioactive iodine as an indicator in thyroid physiology. Journal of Pharmacology and Experimental Therapeutics 128 (1940), 565--76.
[23]
M.W. Hornung, P.A. Kosian, J.T. Haselman, J.J. Korte, K. Challis, C. Macherla, E. Nevalainen, and S.J. Degitz. 2015. In Vitro, Ex Vivo, and In Vivo Determination of Thyroid Hormone Modulating Activity of Benzothiazoles. Toxicological sciences 146, 2 (2015), 254--64.
[24]
J.J. Irwin, D. Duan, H. Torosyan, and et al. 2015. An Aggregation Advisor for Ligand Discovery. Journal of Medicinal Chemistry 58, 17 (2015), 7076--7087.
[25]
S. Jain and G.F. Ecker. 2019. Experimental Cholestasis Research. Methods in Molecular Biology. Humana Press, New York, Chapter In Silico Approaches to Predict Drug-Transporter Interaction Profiles: Data Mining, Model Generation, and Link to Cholestasis.
[26]
H. W. Josephs. 1952. The carotenemia of hypothyroidism. The Journal of Pediatrics 41 (1952), 784 -- 791. Issue 6.
[27]
M. Karlgren, A. Vildhede, U. Norinder, J.R. Wisniewski, E. Kimoto, Y. Lai, U. Haglund, and P. Artursson. 2012. Classification of inhibitors of hepatic organic anion transporting polypeptides (OATPs): Influence of protein expression on drug-drug interactions. Journal of Medicinal Chemistry 55, 10 (2012), 4740--4763.
[28]
N. Khuri and S. Deshmukh. 2018. Machine Learning for Classification of Inhibitors of Hepatic Drug Transporters. In 17th IEEE International Conference on Machine Learning and Applications. 181--186.
[29]
N. Khuri, A.A. Zur, M.B. Wittwer, L. Lin, S.W. Yee, A. Sali, and K.M. Giacomini. 2017. Computational Discovery and Experimental Validation of Inhibitors of the Human Intestinal Transporter OATP2B1. Journal of Chemical Information Modeling 57, 6 (2017), 1402--1413.
[30]
S. Kim, J. Chen, T. Cheng, A. Gindulyte, J. He, S. He, Q. Li, B.A. Shoemaker, P.A. Thiessen, B. Yu, L. Zaslavsky, J. Zhang, and E.E. Bolton. 2019. PubChem 2019 update: improved access to chemical data. Nucleic Acids Research 47, D1 (2019), D1102--1109.
[31]
S. Kim, P. Thiessen, E. Bolton, and S. Bryant. 2015. PUG-SOAP and PUG-REST: web services for programmatic access to chemical information in PubChem. Nucleic acids research 43 (04 2015).
[32]
B.A. Knight, B.M. Shields, X. He, E.N. Pearce, L.E. Braverman, R. Sturley, and B. Vaidya. 2018. Effect of perchlorate and thiocyanate exposure on thyroid function of pregnant women from South-West England: a cohort study. Thyroid research 11, 9 (2018).
[33]
M Kuhn. 2008. Building Predictive Models in R Using the caret Package. Journal of Statistical Software 26 (01 2008), 1--26.
[34]
J.R. Landis and G.G. Koch. 1977. The Measurement of Observer Agreement for Categorical Data. Biometrics 33, 1 (1977), 159--174.
[35]
N. Lecat-Guillet, G. Merer, R. Lopez, T. Pourcher, B. Rousseau, and Y. Ambroise. 2008. Small-Molecule Inhibitors of Sodium Iodide Symporter Function. ChemBioChem 9, 6 (2008), 889--895.
[36]
W. Li, J.P. Nicola, L.M. Amzel, and N. Carrasco. 2013. Asn441 plays a key role in folding and function of the Na+/I- symporter (NIS). FASEB Journal 27, 8 (2013), 3229--38.
[37]
S. Lindenthal, N. Lecat-Guillet, A. Ondo-Mendez, Y. Ambroise, B. Rousseau, and T. Pourcher. 2009. Characterization of small-molecule inhibitors of the sodium iodide symporter. Journal of Endocrinology 200, 3 (2009), 357--365.
[38]
F. Maqbool, S. Mostafalou, H. Bahadar, and M. Abdollahi. 2016. Review of endocrine disorders associated with environmental toxicants and possible involved mechanisms. Life sciences 145 (2016), 265--73.
[39]
M. Martin, R. Geysels, V. Peyret, E. Barquero, A. Masini-Repiso, and J. Nicola. 2018. Implications of Na+/I- Symporter Transport to the Plasma Membrane for Thyroid Hormonogenesis and Radioiodide Therapy. Journal of the Endocrine Society 3 (12 2018), 222--234.
[40]
M. Martins da Silva, S. Alvi, C.F.L. Gonçalves, A.P. Santos-Silva, F.D. Faiva-Melo, M.L. de Freitas, R.S. Fortunato, L. Miranda-Alves, and A.C.F. Ferreira. 2018. Bisphenol A increases hydrogen peroxide generation by thyrocytes both in vivo and in vitro. Endocrine connections 7, 11 (2018), 1196--1207.
[41]
P. Matsson and C. Bergström. 2015. Computational modeling to predict the functions and impact of drug transporters. In Silico Pharmacology 3 (12 2015).
[42]
F. M. McRobb, I. Kufareva, and R. Abagyan. 2014. In Silico Identification and Pharmacological Evaluation of Novel Endocrine Disrupting Chemicals That Act via the Ligand-Binding Domain of the Estrogen Receptor alpha. Toxicological Sciences 141, 1 (2014), 188--197.
[43]
A. Natekin and A. Knoll. 2013. Gradient boosting machines, a tutorial. Frontiers in Neurorobotics 7 (2013), 1--21.
[44]
S.M. Park and V.K. Chatterjee. 2005. Genetics of congenital hypothyroidism. Journal of Medical Genetics 42 (2005), 379--89.
[45]
V. Paroder, J.P. Nicola, C.S. Ginter, and N. Carrasco. 2013. The iodide-transport-defect-causing mutation R124H: a delta-amino group at position 124 is critical for maturation and trafficking of the Na+/I- symporter. Journal of Cell Science 126 (2013), 3305--13.
[46]
V. Paroder, J. P. Nicola, C. S. Ginter, and N. Carrasco. 2013. The iodide-transport-defect-causing mutation R124H: a Δ-amino group at position 124 is critical for maturation and trafficking of the Na+/I- symporter. Journal of cell science 126, 15 (2013), 3305--3313.
[47]
E.N. Pearce, M. Andersson, and M. Zimmermann. 2013. Global iodine nutrition: Where do we stand in 2013? Thyroid: official journal of the American Thyroid Association 23, 5 (2013), 523--8.
[48]
C. Portulano, M. Paroder-Belenitsky, and N. Carrasco. 2014. The Na+/I- Symporter (NIS): Mechanism and Medical Impact. Endocrine Reviews 35, 1 (02 2014), 106--149.
[49]
S. Ravera, A. Reyna-Neyra, G. Ferrandino, L. M. Amzel, and N. Carrasco. 2017. The Sodium/Iodide Symporter (NIS): Molecular Physiology and Preclinical and Clinical Applications. Annual Review of Physiology 79, 1 (2017), 261--289.
[50]
S. Ravera, A. Reyna-Neyra, G. Ferrandino, Amzel M., and Carrasco N. 2017. The Sodium/Iodide Symporter (NIS): Molecular Physiology and Preclinical and Clinical Applications. Annual Review Physiology 79 (2017), 261--289.
[51]
P. Romanski and L. Kotthoff. [n. d.]. FSelector: Selecting Attributes. https://cran.r-project.org/web/packages/FSelector/index.html
[52]
A. Schlessinger, M. A. Welch, H. van Vlijmen, K. Korzekwa, P. W. Swaan, and P. Matsson. 2018. Molecular Modeling of Drug - Transporter Interactions - An International Transporter Consortium Perspective. Clinical Pharmacology & Therapeutics 104, 5 (2018), 818--835.
[53]
F. Scinicariello, H. Murray, L. Smith, S.B. Wilbur, and B.A. Fowler. 2005. Genetic Factors That Might Lead to Different Responses in Individuals Exposed to Perchlorate. Environmental health perspectives 113, 11 (2005), 1479--84.
[54]
S.M. Seidlin, L.D. Marinelli, and E. Oshry. 1946. Radioactive iodine therapy: effect on functioning metastases of adenocarcinoma of the thyroid. JAMA 132 (1946), 838--47.
[55]
R.P. Sheridan. 2012. Three useful dimensions for domain applicability in qsar models using random forest. J Chem Inf Model 52 (2012), 814--823.
[56]
U.H. Tazebay, I. Wapnir, O. Levy, O. Dohán, L.S. Zuckier, Q. H. Zhao, and et. al. 2000. The mammary gland iodide transporter is expressed during lactation and in breast cancer. Nature Medicine 6 (2000), 871--878.
[57]
N. Tran, L. Valenín-Blasini, B. C. Blount, C. G. McCuistion, M. S. Fenton, E. Gin, A. Salem, and J. M. Hershman. 2008. Thyroid-stimulating hormone increases active transport of perchlorate into thyroid cells. American Journal of Physiology-Endocrinology and Metabolism 294, 4 (2008), E802--E806.
[58]
F. Veltri and K. Poppe. 2018. Variables Contributing to Thyroid (Dys) Function in Pregnant Women: More than Thyroid Antibodies? European thyroid journal 7, 3 (2018), 120--128.
[59]
J. Wang, D.R. Hallinger, A. S. Murr, A.R. Buckalew, R.R. Lougee, A.M. Richard, S.C. Laws, and T. E. Stoker. 2019. High-throughput screening and chemotype-enrichment analysis of ToxCast phase II chemicals evaluated for human sodium-iodide symporter (NIS) inhibition. Environment International 126 (2019), 377--386.
[60]
J. Wang, D. R. Hallinger, A. S. Murr, A. R. Buckalew, S. O. Simmons, S. C. Laws, and T. E. Stoker. 2018. High-Throughput Screening and Quantitative Chemical Ranking for Sodium-Iodide Symporter Inhibitors in ToxCast Phase I Chemical Library. Environmental Science & Technology 52, 9 (2018), 5417--5426.
[61]
I. L. Wapnir, M. Van De Rijn, N. Kent, P.S. Amenta, W. Kelly, M. Kelli, R.S. Greco, O. Dohán, and N. Carrasco. 2003. Immunohistochemical profile of the sodium/iodide symporter in thyroid, breast, and other carcinomas using high density tissue microarrays and conventional sections. Journal of Clinical Endocrinology and Metabolism 88, 4 (1 4 2003), 1880--1888.
[62]
S. A. Wildman and Gordon M. C. 1999. Prediction of Physicochemical Parameters by Atomic Contributions. Journal of Chemical Information and Computer Sciences 39 (1999), 868--873.
[63]
M.-E. Willemin and A. Lumen. 2019. Characterization of the modes of action and dose-response relationship for thiocyanate on the thyroid hormone levels in rats using a computational approach. Toxicology and Applied Pharmacology 365 (02 2019), 84--100.
[64]
C. E. Willett, P. L. Bishop, and K. M. Sullivan. 2011. Application of an Integrated Testing Strategy to the U.S. EPA Endocrine Disruptor Screening Program. Toxicological Sciences 123, 1 (06 2011), 15--25.
[65]
D.S. Wishart, T. Jewison, A.C. Guo, M. Wilson, and C. et al. Knox. 2013. HMDB 3.0 - The Human Metabolome Database in 2013. Nucleic Acids Research 41, D1 (2013), D801--D807.
[66]
M. Wittwer, A. Zur, N. Khuri, Y. Kido, A. Kosaka, X. Zhang, K.M. Morrissey, A. Sali, Y. Huang, and K.M. Giacomini. 2012. Discovery of selective multidrug and toxin extrusion transporter 1 (MATE1, SLC47A1) inhibitors through prescription drug profiling and computational modeling. Journal of Medicinal Chemistry 56, 3 (2012), 781--795.
[67]
C. W. Yap. 2011. PaDEL-Descriptor: An Open Source Software to Calculate Molecular Descriptors and Fingerprints. Journal of computational chemistry 32 (05 2011), 1466--74.
[68]
B. Yu, P. A. Thiessen, S. Kim, T. Cheng, and E. E. Bolton. 2018. An update on PUG-REST: RESTful interface for programmatic access to PubChem. Nucleic Acids Research 46, W1 (2018), W563--W570.
[69]
R. T. Zoeller, T. R. Brown, L. L. Doan, A. C. Gore, N. E. Skakkebaek, A. M. Soto, T. J. Woodruff, and F. S. Vom Saal. 2012. Endocrine-Disrupting Chemicals and Public Health Protection: A Statement of Principles from The Endocrine Society. Endocrinology 153, 9 (2012), 4097--4110.
Index Terms
- Mining environmental chemicals with boosted trees
Recommendations
A Novel Prediction Method of ATP Binding Residues from Protein Primary Sequence
Advances in Neural Networks – ISNN 2019AbstractATP is an important nucleotide that provides energy for biological activities in cells. Correctly identifying the protein-ATP binding site is helpful for protein function annotations and new drug development. With the innovation of machine ...
Mining connections between chemicals, proteins, and diseases extracted from Medline annotations
The biomedical literature is an important source of information about the biological activity and effects of chemicals. We present an application that extracts terms indicating biological activity of chemicals from Medline records, associates them with ...
CAPTURE: Comprehensive anti-cancer peptide predictor with a unique amino acid sequence encoder
AbstractAnticancer peptides (ACPs) key properties including bioactivity, high efficacy, low toxicity, and lack of drug resistance make them ideal candidates for cancer therapies. To deeply explore the potential of ACPs and accelerate development of ...
Graphical abstractDisplay Omitted
Highlights- Detailed analysis of existing anti-cancer peptides predictors, sequence encoders and benchmark datasets.
- A powerful encoder for transforming peptides sequences into statistical vectors.
- Intrinsic and extrinsic performance ...
Comments
Information & Contributors
Information
Published In
March 2020
2348 pages
ISBN:9781450368667
DOI:10.1145/3341105
- Conference Chairs:
- Chih-Cheng Hung,
- Tomas Cerny,
- Program Chairs:
- Dongwan Shin,
- Alessio Bechini
Copyright © 2020 ACM.
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]
Sponsors
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 30 March 2020
Check for updates
Author Tags
Qualifiers
- Research-article
Conference
SAC '20
Sponsor:
SAC '20: The 35th ACM/SIGAPP Symposium on Applied Computing
March 30 - April 3, 2020
Brno, Czech Republic
Acceptance Rates
Overall Acceptance Rate 1,650 of 6,669 submissions, 25%
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 114Total Downloads
- Downloads (Last 12 months)11
- Downloads (Last 6 weeks)1
Reflects downloads up to 30 Aug 2024
Other Metrics
Citations
Cited By
View allView Options
Get Access
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in