Papers
Topics
Authors
Recent
Search
2000 character limit reached

Predicting Side Effect of Drug Molecules using Recurrent Neural Networks

Published 17 May 2023 in q-bio.QM and cs.LG | (2305.10473v2)

Abstract: Identification and verification of molecular properties such as side effects is one of the most important and time-consuming steps in the process of molecule synthesis. For example, failure to identify side effects before submission to regulatory groups can cost millions of dollars and months of additional research to the companies. Failure to identify side effects during the regulatory review can also cost lives. The complexity and expense of this task have made it a candidate for a machine learning-based solution. Prior approaches rely on complex model designs and excessive parameter counts for side effect predictions. We believe reliance on complex models only shifts the difficulty away from chemists rather than alleviating the issue. Implementing large models is also expensive without prior access to high-performance computers. We propose a heuristic approach that allows for the utilization of simple neural networks, specifically the recurrent neural network, with a 98+% reduction in the number of required parameters compared to available LLMs while still obtaining near identical results as top-performing models.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (35)
  1. K. Yang et al., “Analyzing learned molecular representations for property prediction,” Journal of chemical information and modeling, vol. 59, no. 8, pp. 3370–3388, 2019.
  2. O. Wieder et al., “A compact review of molecular property prediction with graph neural networks,” Drug Discovery Today: Technologies, vol. 37, pp. 1–12, 2020.
  3. T. Lengauer et al., “Novel technologies for virtual screening,” Drug discovery today, vol. 9, no. 1, pp. 27–34, 2004.
  4. C. Merkwirth et al., “Automatic generation of complementary descriptors with molecular graph networks,” Journal of chemical information and modeling, vol. 45, no. 5, pp. 1159–1168, 2005.
  5. W. Hu et al., “Strategies for pre-training graph neural networks,” arXiv preprint arXiv:1905.12265, 2019.
  6. Z. Wu et al., “A comprehensive survey on graph neural networks,” IEEE transactions on neural networks and learning systems, vol. 32, no. 1, pp. 4–24, 2020.
  7. Mayr et al., “Large-scale comparison of machine learning methods for drug target prediction on chembl,” Chemical science, vol. 9, no. 24, pp. 5441–5451, 2018.
  8. R. Taylor et al., “Galactica: A large language model for science,” arXiv preprint arXiv:2211.09085, 2022.
  9. Wu et al., “Moleculenet: a benchmark for molecular machine learning,” Chemical science, vol. 9, no. 2, pp. 513–530, 2018.
  10. M. Kuhn et al., “The sider database of drugs and side effects,” Nucleic acids research, vol. 44, no. D1, pp. D1075–D1079, 2016.
  11. Subramanian et al., “Computational modeling of β𝛽\betaitalic_β-secretase 1 (bace-1) inhibitors using ligand based approaches,” Journal of chemical information and modeling, vol. 56, no. 10, pp. 1936–1949, 2016.
  12. Martins et al., “A bayesian approach to in silico blood-brain barrier penetration modeling,” Journal of chemical information and modeling, vol. 52, no. 6, pp. 1686–1697, 2012.
  13. Rohrer et al., “Maximum unbiased validation (muv) data sets for virtual screening based on pubchem bioactivity data,” Journal of chemical information and modeling, vol. 49, no. 2, pp. 169–184, 2009.
  14. D. Weininger, “Smiles, a chemical language and information system. 1. introduction to methodology and encoding rules,” Journal of chemical information and computer sciences, vol. 28, no. 1, pp. 31–36, 1988.
  15. M. Krenn et al., “Self-referencing embedded strings (selfies): A 100% robust molecular string representation,” Machine Learning: Science and Technology, vol. 1, no. 4, p. 045024, 2020.
  16. J. L. Elman, “Finding structure in time,” Cognitive science, vol. 14, no. 2, pp. 179–211, 1990.
  17. Cho et al., “Learning phrase representations using rnn encoder-decoder for statistical machine translation,” arXiv preprint arXiv:1406.1078, 2014.
  18. Rong et al., “Self-supervised graph transformer on large-scale molecular data,” Advances in Neural Information Processing Systems, vol. 33, pp. 12 559–12 571, 2020.
  19. Devlin et al., “Bert: Pre-training of deep bidirectional transformers for language understanding,” arXiv preprint arXiv:1810.04805, 2018.
  20. Radford et al., “Improving language understanding by generative pre-training,” 2018.
  21. Wang et al., “Smiles-bert: large scale unsupervised pre-training for molecular property prediction,” in Proceedings of the 10th ACM international conference on bioinformatics, computational biology and health informatics, 2019, pp. 429–436.
  22. Sterling et al., “Zinc 15–ligand discovery for everyone,” Journal of chemical information and modeling, vol. 55, no. 11, pp. 2324–2337, 2015.
  23. Gaulton et al., “Chembl: a large-scale bioactivity database for drug discovery,” Nucleic acids research, vol. 40, no. D1, pp. D1100–D1107, 2012.
  24. Fang et al., “Chemrl-gem: Geometry enhanced molecular representation learning for property prediction,” arXiv preprint arXiv:2106.06130, 2021.
  25. Zhang et al., “Litegem: Lite geometry enhanced molecular representation learning for quantum property prediction,” arXiv preprint arXiv:2106.14494, 2021.
  26. Vaswani et al., “Attention is all you need,” Advances in neural information processing systems, vol. 30, 2017.
  27. Hochreiter et al., “Long short-term memory,” Neural computation, vol. 9, no. 8, pp. 1735–1780, 1997.
  28. X. Yao et al., “A novel independent rnn approach to classification of seizures against non-seizures,” arXiv preprint arXiv:1903.09326, 2019.
  29. W. Yin et al., “Comparative study of cnn and rnn for natural language processing,” arXiv preprint arXiv:1702.01923, 2017.
  30. Maas et al., “Rectifier nonlinearities improve neural network acoustic models,” in Proc. icml, vol. 30, no. 1.   Atlanta, Georgia, USA, 2013, p. 3.
  31. Xu et al., “Empirical evaluation of rectified activations in convolutional network,” arXiv preprint arXiv:1505.00853, 2015.
  32. Gal et al., “A theoretically grounded application of dropout in recurrent neural networks,” Advances in neural information processing systems, vol. 29, 2016.
  33. Zhou et al., “Uni-mol: A universal 3d molecular representation learning framework,” 2023.
  34. Hanley et al., “The meaning and use of the area under a receiver operating characteristic (roc) curve.” Radiology, vol. 143, no. 1, pp. 29–36, 1982, pMID: 7063747. [Online]. Available: https://doi.org/10.1148/radiology.143.1.7063747
  35. Saito et al., “The precision-recall plot is more informative than the roc plot when evaluating binary classifiers on imbalanced datasets,” PloS one, vol. 10, no. 3, p. e0118432, 2015.

Summary

No one has generated a summary of this paper yet.

Sign Up to Summarize

Paper to Video (Beta)

No one has generated a video about this paper yet.

Sign Up to Generate All Videos Subscribe on YouTube

Whiteboard

No one has generated a whiteboard explanation for this paper yet.

Sign Up to Generate

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

Generate Now

Continue Learning

We haven't generated follow-up questions for this paper yet.

Generate Now