Abstract
Integrating human knowledge into neural networks has the potential to improve their robustness and interpretability. We have developed a novel approach to integrate knowledge from ontologies into the structure of a Transformer network which we call ontology pre-training: we train the network to predict membership in ontology classes as a way to embed the structure of the ontology into the network, and subsequently fine-tune the network for the particular prediction task. We apply this approach to a case study in predicting the potential toxicity of a small molecule based on its molecular structure, a challenging task for machine learning in life sciences chemistry. Our approach improves on the state of the art, and moreover has several additional benefits. First, we are able to show that the model learns to focus attention on more meaningful chemical groups when making predictions with ontology pre-training than without, paving a path towards greater robustness and interpretability. Second, the training time is reduced after ontology pre-training, indicating that the model is better placed to learn what matters for toxicity prediction with the ontology pre-training than without. This strategy has general applicability as a neuro-symbolic approach to embed meaningful semantics into neural networks.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
van Bekkum, M., de Boer, M., van Harmelen, F., Meyer-Vitali, A., Teije, A.T.: Modular design patterns for hybrid learning and reasoning systems. Appl. Intell. 51(9), 6528–6546 (2021)
Cavasotto, C.N., Scardino, V.: Machine learning toxicity prediction: latest advances by toxicity end point. ACS Omega 7(51), 47536–47546 (2022). https://doi.org/10.1021/acsomega.2c05693
Chen, J., Hu, P., Jimenez-Ruiz, E., Holter, O.M., Antonyrajah, D., Horrocks, I.: OWL2Vec*: embedding of OWL ontologies. Mach. Learn. 110(7), 1813–1845 (2021). https://doi.org/10.1007/s10994-021-05997-6
Chen, J., Si, Y.-W., Un, C.-W., Siu, S.W.I.: Chemical toxicity prediction based on semi-supervised learning and graph convolutional neural network. J. Cheminform. 13(1), 1–16 (2021). https://doi.org/10.1186/s13321-021-00570-8
Chithrananda, S., Grand, G., Ramsundar, B.: Chemberta: large-scale self-supervised pretraining for molecular property prediction. arXiv preprint arXiv:2010.09885 (2020)
Clark, K., Luong, M.T., Le, Q.V., Manning, C.D.: Electra: pre-training text encoders as discriminators rather than generators. arXiv preprint arXiv:2003.10555 (2020)
Devlin, J., Chang, M., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Burstein, J., Doran, C., Solorio, T. (eds.) NAACL-HLT 2019, Minneapolis, MN, USA, 2–7 June 2019, Volume 1 (Long and Short Papers), pp. 4171–4186. Association for Computational Linguistics (2019). https://doi.org/10.18653/v1/n19-1423
Flügel, S., Glauer, M., Neuhaus, F., Hastings, J.: When one logic is not enough: integrating first-order annotations in OWL ontologies. Semant. Web J. (2023). http://www.semantic-web-journal.net/content/when-one-logic-not-enough-integrating-first-order-annotations-owl-ontologies
Glauer, M., Memariani, A., Neuhaus, F., Mossakowski, T., Hastings, J.: Interpretable Ontology Extension in Chemistry. Semant. Web J. (2022). https://doi.org/10.5281/ZENODO.6023497. https://zenodo.org/record/6023497
Hastings, J.: Primer on ontologies. In: Dessimoz, C., Škunca, N. (eds.) The Gene Ontology Handbook. MMB, vol. 1446, pp. 3–13. Springer, New York (2017). https://doi.org/10.1007/978-1-4939-3743-1_1
Hastings, J., Glauer, M., Memariani, A., Neuhaus, F., Mossakowski, T.: Learning chemistry: exploring the suitability of machine learning for the task of structure-based chemical ontology classification. J. Cheminform. 13(23) (2021). https://doi.org/10.21203/rs.3.rs-107431/v1
Hastings, J., et al.: ChEBI in 2016: improved services and an expanding collection of metabolites. Nucleic Acids Res. 44(D1), D1214–D1219 (2016). https://doi.org/10.1093/nar/gkv1031
Huang, R., et al.: 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 (2016). https://www.frontiersin.org/articles/10.3389/fenvs.2015.00085
Idakwo, G.: Structure-activity relationship-based chemical classification of highly imbalanced Tox21 datasets. J. Cheminform. 12(1), 1–19 (2020)
Jiang, J., Wang, R., Wei, G.W.: GGL-Tox: geometric graph learning for toxicity prediction. J. Chem. Inf. Model. 61(4), 1691–1700 (2021). https://doi.org/10.1021/acs.jcim.0c01294
Jumper, J., et al.: Highly accurate protein structure prediction with AlphaFold. Nature 1–11 (2021). https://doi.org/10.1038/s41586-021-03819-2. https://www.nature.com/articles/s41586-021-03819-2
Kulmanov, M., Hoehndorf, R.: DeepPheno: predicting single gene loss-of-function phenotypes using an ontology-aware hierarchical classifier. PLoS Comput. Biol. 16(11) (2020). https://doi.org/10.1371/journal.pcbi.1008453
Mayr, A., Klambauer, G., Unterthiner, T., Hochreiter, S.: DeepTox: toxicity prediction using deep learning. Front. Environ. Sci. 3 (2016). https://www.frontiersin.org/articles/10.3389/fenvs.2015.00080
Neuhaus, F., Hastings, J.: Ontology development is consensus creation, not (merely) representation. Appl. Ontol. 17(4), 495–513 (2022). https://doi.org/10.3233/AO-220273
Peng, Y., Zhang, Z., Jiang, Q., Guan, J., Zhou, S.: TOP: a deep mixture representation learning method for boosting molecular toxicity prediction. Methods 179, 55–64 (2020). https://doi.org/10.1016/j.ymeth.2020.05.013. https://www.sciencedirect.com/science/article/pii/S1046202320300888
Riegel, R., et al.: Logical neural networks. arXiv preprint arXiv:2006.13155 (2020)
Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models (2022)
von Rueden, L., et al.: Informed machine learning - a taxonomy and survey of integrating prior knowledge into learning systems. IEEE Trans. Knowl. Data Eng. 35(1), 614–633 (2021). https://doi.org/10.1109/TKDE.2021.3079836
Sahoo, S.S., et al.: Ontology-based feature engineering in machine learning workflows for heterogeneous epilepsy patient records. Sci. Rep. 12(1), 19430 (2022). https://doi.org/10.1038/s41598-022-23101-3. https://www.nature.com/articles/s41598-022-23101-3
Sayers, E.: PubChem: An Entrez Database of Small Molecules. NLM Tech. Bull. 2005 Jan-Feb(342:e2) (2005)
Smaili, F.Z., Gao, X., Hoehndorf, R.: OPA2Vec: combining formal and informal content of biomedical ontologies to improve similarity-based prediction. Bioinformatics 35(12), 2133–2140 (2019). https://doi.org/10.1093/bioinformatics/bty933. https://academic.oup.com/bioinformatics/article/35/12/2133/5165380
Vig, J., Madani, A., Varshney, L.R., Xiong, C., Socher, R., Rajani, N.F.: BERTology Meets Biology: Interpreting Attention in Protein Language Models. arXiv:2006.15222 (2021). http://arxiv.org/abs/2006.15222
Weininger, D.: SMILES, a chemical language and information system. 1. Introduction to methodology and encoding rules. J. Chem. Inf. Comput. Sci. 28(1), 31–36 (1988). https://doi.org/10.1021/ci00057a005
Wu, Z., et al.: Moleculenet: a benchmark for molecular machine learning. Chem. Sci. 9(2), 513–530 (2018)
Yang, H., Sun, L., Li, W., Liu, G., Tang, Y.: In silico prediction of chemical toxicity for drug design using machine learning methods and structural alerts. Front. Chem. 6 (2018). https://www.frontiersin.org/articles/10.3389/fchem.2018.00030
Zha, Y., et al.: Ontology-aware deep learning enables ultrafast and interpretable source tracking among sub-million microbial community samples from hundreds of niches. Genome Med. 14(1), 43 (2022). https://doi.org/10.1186/s13073-022-01047-5
Zhang, N., et al.: Ontoprotein: protein pretraining with gene ontology embedding. In: The Tenth International Conference on Learning Representations, ICLR 2022, Virtual Event, 25–29 April 2022. OpenReview.net (2022). https://openreview.net/forum?id=yfe1VMYAXa4
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Glauer, M., Neuhaus, F., Mossakowski, T., Hastings, J. (2023). Ontology Pre-training for Poison Prediction. In: Seipel, D., Steen, A. (eds) KI 2023: Advances in Artificial Intelligence. KI 2023. Lecture Notes in Computer Science(), vol 14236. Springer, Cham. https://doi.org/10.1007/978-3-031-42608-7_4
Download citation
DOI: https://doi.org/10.1007/978-3-031-42608-7_4
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-42607-0
Online ISBN: 978-3-031-42608-7
eBook Packages: Computer ScienceComputer Science (R0)