112
P. Gong et al.
ically, our approach addresses several challenges in model development for toxicity
prediction and quantification: (1) what properties and features of the ligand-target
biomacromolecule (e.g., receptor and enzyme protein) interactions should be taken
into consideration; (2) how to capture such dynamic interactions and incorporate
them into QSAR modeling; (3) how to characterize chemical toxicities beyond binary
classes (toxic/non-toxic) for the purpose of lead optimization, mechanism elucidation and analogue prioritization; (4) how to handle the commonly encountered class
imbalance problem in chemical classification; and (5) how to develop novel machine
learning (e.g., deep learning) approaches that include solid theoretical foundation
and advanced optimization techniques for rapid and accurate quantitative toxicity
prediction. We anticipate finding interdisciplinary solutions for these challenges in
the course of developing the TsTKb. We believe the fully developed TsTKb will significantly advance in silico-based predictive toxicology and provide a new powerful
toolbox for regulators, the chemical industry and relevant academic communities.
References
1. Sachana M, Hargreaves AJ (2018) Toxicological testing. In vivo and in vitro models. In: Gupta
RC (ed) Veterinary toxicology: basic and clinical principles, 3rd edn. Elsevier, London, UK,
pp 145–161
2. Eisenbrand G, Pool-Zobel B, Baker V et al (2002) Methods of in vitro toxicology. Food Chem
Toxicol 40:193–236. https://doi.org/10.1016/S0278-6915(01)00118-1
3. Jain AK, Singh D, Dubey K et al (2018) Models and methods for in vitro toxicity. In: Dhawan,
Alok; Kwon S (ed) In vitro toxicology, 1st ed. Elsevier, London, UK, pp 45–65
4. Parthasarathi R, Dhawan A (2018) In silico approaches for predictive toxicology. In: Dhawan,
Alok; Kwon S (ed) In vitro toxicology, 1st ed. Elsevier, London, UK, pp 91–109
5. Stokes WS (2015) Animals and the 3Rs in toxicology research and testing: The way forward.
Hum Exp Toxicol 34:1297–1303. https://doi.org/10.1177/0960327115598410
6. United States Code (2014) Animal Welfare Act: Title 7, Chapter 54, Sections 2131–2159
7. Code of Federal Regulations (2014) Title 9: animals and animal products; Chapter I, subchapter
A—animal welfare (Parts 1–4)
8. Knudsen TB, Keller DA, Sander M et al (2015) FutureTox II: In vitro data and in silico models
for predictive toxicology. Toxicol Sci 143:256–267. https://doi.org/10.1093/toxsci/kfu234
9. European Union (2010) Directive 2010/63/EU of the European parliament and of the council
of 22 September 2010 on the protection of animals used for scientific purposes
10. European Union (2006) Regulation (EC) No 1907/2006—Registration, evaluation, authorisation and restriction of chemicals (REACH)
11. European Union (2009) Regulation (EC) no 1223/2009 of the european parliament and of the
council of 30 November 2009 on cosmetic products
12. Elmore SA, Ryan AM, Wood CE et al (2014) FutureTox II: contemporary concepts in toxicology: pathways to prediction. In vitro and in silico models for predictive toxicology. Toxicol
Pathol 42:940–942. https://doi.org/10.1177/0192623314537135
13. National Research Council (2007) Toxicity testing in the 21st century: a vision and a strategy.
National Academies Press, Washington, D.C.
14. Collins FS, Gray GM, Bucher JR (2008) Toxicology. Transforming environmental health protection. Science 319:906–907. https://doi.org/10.1126/science.1154619
15. Stokes WS (2014) Validation and regulatory acceptance of toxicological testing methods and
strategies. In: Hayes AW, Kruger CL (eds) Hayes’ principles and methods of toxicology, 6th
edn. CRC Press, Boca Raton, pp 1103–1128
P. Gong et al.
ically, our approach addresses several challenges in model development for toxicity
prediction and quantification: (1) what properties and features of the ligand-target
biomacromolecule (e.g., receptor and enzyme protein) interactions should be taken
into consideration; (2) how to capture such dynamic interactions and incorporate
them into QSAR modeling; (3) how to characterize chemical toxicities beyond binary
classes (toxic/non-toxic) for the purpose of lead optimization, mechanism elucidation and analogue prioritization; (4) how to handle the commonly encountered class
imbalance problem in chemical classification; and (5) how to develop novel machine
learning (e.g., deep learning) approaches that include solid theoretical foundation
and advanced optimization techniques for rapid and accurate quantitative toxicity
prediction. We anticipate finding interdisciplinary solutions for these challenges in
the course of developing the TsTKb. We believe the fully developed TsTKb will significantly advance in silico-based predictive toxicology and provide a new powerful
toolbox for regulators, the chemical industry and relevant academic communities.
References
1. Sachana M, Hargreaves AJ (2018) Toxicological testing. In vivo and in vitro models. In: Gupta
RC (ed) Veterinary toxicology: basic and clinical principles, 3rd edn. Elsevier, London, UK,
pp 145–161
2. Eisenbrand G, Pool-Zobel B, Baker V et al (2002) Methods of in vitro toxicology. Food Chem
Toxicol 40:193–236. https://doi.org/10.1016/S0278-6915(01)00118-1
3. Jain AK, Singh D, Dubey K et al (2018) Models and methods for in vitro toxicity. In: Dhawan,
Alok; Kwon S (ed) In vitro toxicology, 1st ed. Elsevier, London, UK, pp 45–65
4. Parthasarathi R, Dhawan A (2018) In silico approaches for predictive toxicology. In: Dhawan,
Alok; Kwon S (ed) In vitro toxicology, 1st ed. Elsevier, London, UK, pp 91–109
5. Stokes WS (2015) Animals and the 3Rs in toxicology research and testing: The way forward.
Hum Exp Toxicol 34:1297–1303. https://doi.org/10.1177/0960327115598410
6. United States Code (2014) Animal Welfare Act: Title 7, Chapter 54, Sections 2131–2159
7. Code of Federal Regulations (2014) Title 9: animals and animal products; Chapter I, subchapter
A—animal welfare (Parts 1–4)
8. Knudsen TB, Keller DA, Sander M et al (2015) FutureTox II: In vitro data and in silico models
for predictive toxicology. Toxicol Sci 143:256–267. https://doi.org/10.1093/toxsci/kfu234
9. European Union (2010) Directive 2010/63/EU of the European parliament and of the council
of 22 September 2010 on the protection of animals used for scientific purposes
10. European Union (2006) Regulation (EC) No 1907/2006—Registration, evaluation, authorisation and restriction of chemicals (REACH)
11. European Union (2009) Regulation (EC) no 1223/2009 of the european parliament and of the
council of 30 November 2009 on cosmetic products
12. Elmore SA, Ryan AM, Wood CE et al (2014) FutureTox II: contemporary concepts in toxicology: pathways to prediction. In vitro and in silico models for predictive toxicology. Toxicol
Pathol 42:940–942. https://doi.org/10.1177/0192623314537135
13. National Research Council (2007) Toxicity testing in the 21st century: a vision and a strategy.
National Academies Press, Washington, D.C.
14. Collins FS, Gray GM, Bucher JR (2008) Toxicology. Transforming environmental health protection. Science 319:906–907. https://doi.org/10.1126/science.1154619
15. Stokes WS (2014) Validation and regulatory acceptance of toxicological testing methods and
strategies. In: Hayes AW, Kruger CL (eds) Hayes’ principles and methods of toxicology, 6th
edn. CRC Press, Boca Raton, pp 1103–1128