Theoretical and applied potential of artificial intelligence and machine learning in analysing molecular data

Abstract

Bu makale, moleküler analizde yapay zeka (AI) ve makine öğreniminin (ML) teorik potansiyelini ve uygulamalarını incelemektedir. YZ ve makine öğrenimi teknikleri, kimyasal ve biyolojik süreçlerin doğruluğunu hızlandırmaya ve iyileştirmeye olanak tanır. Özellikle, bu yöntemler moleküllerin kimyasal yapısını, biyolojik aktivitesini ve protein yapısını tahmin etmek için kullanılır. Bu makalede, moleküler dinamik simülasyonları, spektroskopi ve kemoinformatik verileri gibi çeşitli veri türlerinin yapay zeka ve makine öğrenimi algoritmaları ile nasıl işlenebileceği tartışılmaktadır. Ayrıca derin öğrenme algoritmalarının moleküler temsiller, ilaç tasarımı ve protein yapısı tahmini gibi alanlardaki devrim niteliğindeki katkıları vurgulanmaktadır. Kimyasal reaksiyonların tahmini ve optimizasyonunda takviyeli öğrenme ve grafik tabanlı modellerin etkinliği de tartışılmaktadır. Sonuç olarak, AI ve ML'nin moleküler analizlerde kullanımının gelecekte daha geniş bilimsel ve endüstriyel araştırma alanlarına yayılması beklenmektedir.

Keywords

• Yapay Zeka (AI)
• Makine Öğrenimi (ML)
• Moleküler Analiz
• Derin Öğrenme
• Kimyasal Reaksiyonlar

Theoretical and applied potential of artificial intelligence and machine learning in analysing molecular data

Abstract

This article examines the theoretical potential and applications of artificial intelligence (AI) and machine learning (ML) in molecular analysis. AI and ML techniques allow accelerating and improving the accuracy of chemical and biological processes. In particular, these methods are used to predict the chemical structure, biological activity and protein structure of molecules. In this article, we discuss how various data types such as molecular dynamics simulations, spectroscopy and cheminformatics data can be processed with AI and ML algorithms. It also highlights the revolutionary contributions of deep learning algorithms in areas such as molecular representations, drug design and protein structure prediction. The effectiveness of reinforcement learning and graph-based models in the prediction and optimization of chemical reactions is also discussed. In conclusion, the use of AI and ML in molecular analyses is expected to expand into broader areas of scientific and industrial research in the future.

Keywords

• Artificial Intelligence (AI)
• Machine Learning (ML)
• Molecular Analysis
• Deep Learning
• Chemical Reactions

References

1. S. Russell, P. Norvig, Artificial Intelligence: A Modern Approach (4th ed.), 2021, USA, Pearson.
2. I. Goodfellow, Y. Bengio, A. Courville, Deep Learning, 2016, USA, MIT Press.
3. K.P. Murphy, Machine Learning: A Probabilistic Perspective, 2012, USA, MIT Press.
4. D. Ramírez, Computational methods applied to rational drug design, Open Med Chem J, 10, 2016, 7–20.
5. Y. LeCun, Y. Bengio, G. Hinton, Deep learning, Nature, 521(7553), 2015, 436–444.
6. A.M. Turing, Computing machinery and intelligence, Mind, 59(236), 1950, 433–460.
7. A.L. Samuel, Some studies in machine learning using the game of checkers, IBM J Res Dev, 3(3), 1959, 210–229.
8. T.M. Mitchell, Machine Learning, 1997, USA, McGraw-Hill.

9. A. Krizhevsky, I. Sutskever, G.E. Hinton, ImageNet classification with deep convolutional neural networks, Adv Neural Inf Process Syst, 25, 2012, 1097–1105.
10. C. Cortes, V. Vapnik, Support-vector networks, Mach Learn, 20(3), 1995, 273–297.
11. L. Breiman, Random forests, Mach Learn, 45(1), 2001, 5–32.
12. M.I. Jordan, T.M. Mitchell, Machine learning: Trends, perspectives, and prospects, Science, 349(6245), 2015, 255–260.
13. D.A. Skoog, D.M. West, F.J. Holler, S.R. Crouch, Fundamentals of Analytical Chemistry (9th ed.), 2013, USA, Cengage Learning.
14. H.A. Duran-Limon, A. Chavoya, M. Hernández-Ochoa, The role of machine learning in big data analytics: Current practices and challenges, Development Methodologies for Big Data Analytics Systems, Editors: M. Mora, F. Wang, J. Marx Gomez, H. Duran-Limon, 2024, USA, Springer, 15–28.
15. Y. Oshima, T. Haruki, K. Koizumi, S. Yonezawa, A. Taketani, M. Kadowaki, S. Saito, Practices, potential, and perspectives for detecting predisease using Raman spectroscopy, Int J Mol Sci, 24(15), 2023, 12170.
16. T. Darden, D. York, L. Pedersen, Particle mesh Ewald: An N-log(N) method for Ewald sums in large systems, J Chem Phys, 98(12), 1993, 10089–10092.
17. M. Rupp, A. Tkatchenko, K.R. Müller, O.A. von Lilienfeld, Fast and accurate modeling of molecular atomization energies with machine learning, Phys Rev Lett, 108(5), 2012, 058301.
18. K. Schütt, F. Arbabzadah, S. Chmiela, et al., Quantum-chemical insights from deep tensor neural networks, Nat Commun, 8, 2017, 13890.
19. F.K. Brown, Chemoinformatics: What is it and how does it impact drug discovery, Annu Rep Med Chem, 33, 1998, 375–384.
20. D. Rogers, M. Hahn, Extended-connectivity fingerprints, J Chem Inf Model, 50(5), 2010, 742–754.
21. G. Schneider, Virtual screening: An endless staircase?, Nat Rev Drug Discov, 9(4), 2010, 273–276.
22. S. Hua, Z. Sun, Support vector machine approach for protein subcellular localization prediction, Bioinformatics, 17(8), 2001, 721–728.
23. B. Schölkopf, A.J. Smola, Learning with Kernels: Support Vector Machines, Regularization, Optimization, and Beyond, 2002, USA, MIT Press.
24. W.S. Noble, What is a support vector machine?, Nat Biotechnol, 24(12), 2006, 1565–1567.
25. V. Svetnik, A. Liaw, C. Tong, T. Wang, Random forest: A classification and regression tool for compound classification and QSAR modeling, J Chem Inf Comput Sci, 43(6), 2003, 1947–1958.
26. T. Hastie, R. Tibshirani, J. Friedman, The Elements of Statistical Learning: Data Mining, Inference, and Prediction (2nd ed.), 2009, USA, Springer.
27. M. Cherti, B. Kégl, A.O. Kazakçi, De novo drug design using deep generative models: An empirical study, International Conference on Learning Representations, Toulon, France, 2017.
28. M. Karakaplan, F.M. Avcu, Classification of some chemical drugs by genetic algorithm and deep neural network hybrid method, Concurr Comput Pract Exp, 33, 2021, e6242.
29. O. Ronneberger, P. Fischer, T. Brox, U-Net: Convolutional networks for biomedical image segmentation, International Conference on Medical Image Computing and Computer-Assisted Intervention, 2015, 234–241.
30. A.W. Senior, R. Evans, J. Jumper, et al., Improved protein structure prediction using potentials from deep learning, Nature, 577(7792), 2020, 706–710.
31. R.S. Sutton, A.G. Barto, Reinforcement Learning: An Introduction, 2018, USA, MIT Press.
32. M. Popova, O. Isayev, A. Tropsha, Deep reinforcement learning for de novo drug design, Sci Adv, 4(7), 2018, eaap7885.
33. J. Gilmer, S.S. Schoenholz, P.F. Riley, O. Vinyals, G.E. Dahl, Neural message passing for quantum chemistry, Proc Int Conf Mach Learn, 34, 2017, 1263–1272.
34. R. Xia, S. Kais, Quantum machine learning for electronic structure calculations, Nat Commun, 9, 2018, 4195.
35. F. Ghasemi, A. Mehridehnavi, A. Pérez-Garrido, H. Pérez-Sánchez, Neural network and deep-learning algorithms used in QSAR studies: Merits and drawbacks, Drug Discov Today, 23(10), 2018, 1784–1790.
36. A. Zhavoronkov, Y.A. Ivanenkov, A. Aliper, et al., Deep learning enables rapid identification of potent DDR1 kinase inhibitors, Nat Biotechnol, 37, 2019, 1038–1040.
37. B. Sanchez-Lengeling, A. Aspuru-Guzik, Inverse molecular design using machine learning: Generative models for matter engineering, Science, 361(6400), 2018, 360–365.
38. J. Behler, M. Parrinello, Generalized neural-network representation of high-dimensional potential-energy surfaces, Phys Rev Lett, 98(14), 2007, 146401.
39. F. Noé, A. Tkatchenko, K.R. Müller, C. Clementi, Machine learning for molecular simulation, Annu Rev Phys Chem, 71, 2020, 361–390.
40. M.H. Segler, M. Preuss, M.P. Waller, Planning chemical syntheses with deep neural networks and symbolic AI, Nature, 555(7698), 2018, 604–610.
41. C.W. Coley, R. Barzilay, T.S. Jaakkola, W.H. Green, K.F. Jensen, Prediction of organic reaction outcomes using machine learning, ACS Cent Sci, 3(5), 2017, 434–443.
42. O.A. von Lilienfeld, K.R. Müller, A. Tkatchenko, Exploring chemical compound space with quantum-based machine learning, Nat Rev Chem, 4, 2020, 347–358.
43. R. Gómez-Bombarelli, J. Aguilera-Iparraguirre, T. Hirzel, et al., Design of efficient molecular organic light-emitting diodes by a high-throughput virtual screening and experimental approach, Nat Mater, 15, 2016, 1120–1127.