Comparative Analysis of Optuna-Optimized 1D and 2D CNNs for Protein Secondary Structure Prediction

Annisa Rizqiana; Triando Hamonangan Saragih; Muhammad Itqan Mazdadi; Irwan Budiman; Adryan Maulana Saputra

doi:10.35882/jeeemi.v8i4.1878

Annisa Rizqiana Department of Computer Science, Lambung Mangkurat University, Banjarbaru, Indonesia https://orcid.org/0009-0009-1318-261X
Triando Hamonangan Saragih Department of Computer Science, Lambung Mangkurat University, Banjarbaru, Indonesia https://orcid.org/0000-0003-4346-3323
Muhammad Itqan Mazdadi Department of Computer Science, Lambung Mangkurat University, Banjarbaru, Indonesia https://orcid.org/0000-0002-8710-4616
Irwan Budiman Department of Computer Science, Lambung Mangkurat University, Banjarbaru, Indonesia https://orcid.org/0000-0002-0514-7429
Adryan Maulana Saputra Department of Computer Science, Lambung Mangkurat University, Banjarbaru, Indonesia

DOI: https://doi.org/10.35882/jeeemi.v8i4.1878

Abstract

Protein secondary structure prediction (PSSP) is a fundamental task in bioinformatics, yet traditional experimental methods remain costly and time-consuming. While Convolutional Neural Networks (CNNs) offer efficient computational alternatives, systematic comparisons between 1D and 2D CNN topologies remain limited. Furthermore, conventional hyperparameter tuning in existing models relies on manual trial-and-error, introducing human bias and trapping networks in suboptimal performance thresholds. This study aims to evaluate the effectiveness of 1D and 2D CNN architectures for PSSP and systematically investigate the impact of automated hyperparameter optimization on both model performance and training efficiency. The proposed framework integrates standalone 1D and 2D CNN topologies with an automated hyperparameter optimization pipeline using Optuna based on the Tree-structured Parzen Estimator. Models are trained on the benchmark CullPDB dataset and rigorously evaluated via cross-dataset testing on the independent, non-redundant CB513 benchmark. The primary contributions include a standalone comparative analysis between 1D and 2D CNN topologies, the elimination of human bias via automated tuning, and a comprehensive feature efficiency analysis highlighting the trade-offs between computational representation and predictive accuracy. Experimental results show that all configurations achieve high overall performance with accuracies exceeding 81% and AUC values above 94%. Specifically, the CNN 1D + Optuna configuration yields the highest precision of 0.4409 and an F1-score of 0.4454, effectively capturing local sequential motifs. Conversely, the CNN 2D + Optuna configuration excels in extracting spatial inter-residue relationships, delivering the highest AUC of 0.9493 and the lowest cross-entropy loss of 0.0114. Additionally, Optuna dramatically accelerates training efficiency, reducing convergence iterations by up to 66% (from epoch 24 down to 8 for the 2D model). In conclusion, automated optimization eliminates manual bias and enhances training efficiency, revealing that the choice between 1D and 2D topologies should be strategically guided by the precise needs of downstream biological applications.

Downloads

Download data is not yet available.

References

N. Ajomiwe, M. Boland, S. Phongthai, M. Bagiyal, J. Singh, and L. Kaur, “Protein Nutrition: Understanding Structure, Digestibility, and Bioavailability for Optimal Health,” Foods, vol. 13, no. 11, p. 1771, Jun. 2024, doi: 10.3390/foods13111771.

O. S. Zakharov, A. V. Rudik, D. A. Filimonov, and A. A. Lagunin, “Prediction of Protein Secondary Structures Based on Substructural Descriptors of Molecular Fragments,” Int. J. Mol. Sci., vol. 25, no. 23, p. 12525, Dec. 2024, doi: 10.3390/ijms252312525.

J. Zhang, J. Qian, Q. Zou, F. Zhou, and L. Kurgan, “Recent Advances in Computational Prediction of Secondary and Supersecondary Structures from Protein Sequences,” in Methods in Molecular Biology, vol. 2870, Humana Press, 2024, pp. 1–19. doi: 10.1007/978-1-0716-4213-9_1.

J. H. Wat et al., “Sequence-Specific Protein Secondary-Structure Assignment with Isotope Reverse-Labeled Amide I Spectroscopy,” J. Phys. Chem. B, vol. 129, no. 46, pp. 11959–11968, Nov. 2025, doi: 10.1021/acs.jpcb.5c06200.

N. Fatima Ali, S. Khan, and S. Zahid, “A critical address to advancements and challenges in computational strategies for structural prediction of protein in recent past,” Comput. Biol. Chem., vol. 117, Art. No. 108430, Aug. 2025, doi: 10.1016/j.compbiolchem.2025.108430.

H. M. Afify, M. B. Abdelhalim, M. S. Mabrouk, and A. Y. Sayed, “Protein secondary structure prediction (PSSP) using different machine algorithms,” Egyptian Journal of Medical Human Genetics, vol. 22, no. 1, Art. no. 54, Jun. 2021, doi: 10.1186/s43042-021-00173-w.

B. Huang et al., “Protein Structure Prediction: Challenges, Advances, and the Shift of Research Paradigms,” Genomics Proteomics Bioinformatics, vol. 21, no. 5, p. 913, Oct. 2023, doi: 10.1016/j.gpb.2022.11.014.

Y. Qin, Z. Chen, Y. Peng, Y. Xiao, T. Zhong, and X. Yu, “Deep learning methods for protein structure prediction,” MedComm - Future Medicine, vol. 3, no. 3, p. e96, Sep. 2024, doi: 10.1002/mef2.96.

Y. Zhao and Y. Liu, “OCLSTM: Optimized convolutional and long short-term memory neural network model for protein secondary structure prediction,” PLoS One, vol. 16, no. 2, p. e0245982, Feb. 2021, doi: 10.1371/journal.pone.0245982.

Y. Chen, G. Chen, and C. Y. C. Chen, “PSSP-MFFNet: A Multifeature Fusion Network for Protein Secondary Structure Prediction,” ACS Omega, vol. 9, no. 5, p. 5985, Feb. 2024, doi: 10.1021/acsomega.3c10230.

Y. N. H. Al-Shameri, İ. Kösesoy, H. Gündüz, and Ö. F. Yılmaz, “Scalable and Efficient Protein Secondary Structure Prediction Using Autoencoder-Reduced ProtBERT Embeddings,” Applied Sciences, vol. 15, no. 13, Art. no. 7112, Jun. 2025, doi: 10.3390/app15137112.

R. R. Ema, A. Khatun, M. A. Hossain, M. R. Akhond, N. Hossain, and M. Y. Arafat, “Protein Secondary Structure Prediction using Hybrid Recurrent Neural Networks,” Journal of Computer Science, vol. 18, no. 7, pp. 599–611, Jul. 2022, doi: 10.3844/jcssp.2022.599.611.

A. Rizqiana and Afiahayati, “N-Grams Modeling for Protein Secondary Structure Prediction: Exploring Local Features and Optimal CNN Parameters,” BIO Web Conf., vol. 75, p. 01008, Nov. 2023, doi: 10.1051/bioconf/20237501008.

J. Cheng, Y. Liu, and Y. Ma, “Protein secondary structure prediction based on integration of CNN and LSTM model,” J. Vis. Commun. Image Represent., vol. 71, p. 102844, Aug. 2020, doi: 10.1016/j.jvcir.2020.102844.

V. M. Sutanto, Z. I. Sukma, and A. Afiahayati, “Predicting Secondary Structure of Protein Using Hybrid of Convolutional Neural Network and Support Vector Machine,” International Journal of Intelligent Engineering and Systems, vol. 14, no. 1, p. 232-243, Feb. 2021, doi: 10.22266/ijies2021.0228.23.

B. Dong et al., “SERT-StructNet: Protein secondary structure prediction method based on multi-factor hybrid deep model,” Comput. Struct. Biotechnol. J., vol. 23, pp. 1364–1375, Dec. 2024, doi: 10.1016/j.csbj.2024.03.018.

V. Bongirwar and A. S. Mokhade, “A Hybrid Bidirectional Long Short-Term Memory and Bidirectional Gated Recurrent Unit Architecture for Protein Secondary Structure Prediction,” IEEE Access, vol. 12, pp. 115346–115355, 2024, doi: 10.1109/access.2024.3444468.

L. Zhao, J. Li, W. Zhan, X. Jiang, and B. Zhang, “Prediction of protein secondary structure by the improved TCN-BiLSTM-MHA model with knowledge distillation,” Sci. Rep., vol. 14, no. 1, p. 16488, Dec. 2024, doi: 10.1038/s41598-024-67403-0.

T. Wu, W. Cheng, and J. Cheng, “Improving Protein Secondary Structure Prediction by Deep Language Models and Transformer Networks,” Methods Mol. Biol., vol. 2867, pp. 43–53, 2025, doi: 10.1007/978-1-0716-4196-5_3.

D. P. Ismi, R. Pulungan, and Afiahayati, “Deep learning for protein secondary structure prediction: Pre and post-AlphaFold,” Comput. Struct. Biotechnol. J., vol. 20, pp. 6271–6286, Jan. 2022, doi: 10.1016/j.csbj.2022.11.012.

L. Zhao, J. Li, B. Zhang, and X. Jiang, “Combining knowledge distillation and neural networks to predict protein secondary structure,” Scientific Reports, vol. 15, no. 1, Art. no. 32031, Aug. 2025, doi: 10.1038/s41598-025-17513-0.

M. A. K. Raiaan et al., “A systematic review of hyperparameter optimization techniques in Convolutional Neural Networks,” Decision Analytics Journal, vol. 11, p. 100470, Jun. 2024, doi: 10.1016/j.dajour.2024.100470.

P. Srinivas and R. Katarya, “hyOPTXg: OPTUNA hyper-parameter optimization framework for predicting cardiovascular disease using XGBoost,” Biomed. Signal Process. Control, vol. 73, p. 103456, Mar. 2022, doi: 10.1016/j.bspc.2021.103456.

A. Khalifa, F. Ben Said, and Y. H. Kacem, “Optuna-Optimized Meta-Learner and Ensemble Learning Models for Student Performance Prediction,” Procedia Comput. Sci., vol. 270, pp. 1826–1835, Jan. 2025, doi: 10.1016/j.procs.2025.09.303.

Y. Guo, J. Wu, H. Ma, S. Wang, and J. Huang, “Deep Ensemble Learning with Atrous Spatial Pyramid Networks for Protein Secondary Structure Prediction,” Biomolecules, vol. 12, no. 6, Art. no. 774, Jun. 2022, doi: 10.3390/biom12060774.

L. Yuan, Y. Ma, and Y. Liu, “Ensemble deep learning models for protein secondary structure prediction using bidirectional temporal convolution and bidirectional long short-term memory,” Front. Bioeng. Biotechnol., vol. 11, p. 1051268, Feb. 2023, doi: 10.3389/fbioe.2023.1051268.

X. Jin, L. Guo, Q. Jiang, N. Wu, and S. Yao, “Prediction of protein secondary structure based on an improved channel attention and multiscale convolution module,” Front. Bioeng. Biotechnol., vol. 10, p. 901018, Jul. 2022, doi: 10.3389/fbioe.2022.901018.

J. Cheng, Y. Xu, and Y. Zhao, “Prediction of protein secondary structure based on deep residual convolutional neural network,” Biotechnology & Biotechnological Equipment, vol. 35, no. 1, pp. 1881–1890, 2021, doi: 10.1080/13102818.2022.2026815.

Y. Kim and J. Kwon, “AttSec: protein secondary structure prediction by capturing local patterns from attention map,” BMC Bioinformatics, vol. 24, no. 1, Art. no. 183, May 2023, doi: 10.1186/s12859-023-05310-3.

V. Bongirwar and A. S. Mokhade, “An improved multi-scale convolutional neural network with gated recurrent neural network model for protein secondary structure prediction,” Neural Comput. Appl., vol. 36, no. 24, pp. 15063–15074, Aug. 2024, doi: 10.1007/s00521-024-09822-8.

L. Cheng et al., “RECNN: A Novel Deep Learning Model to Predict 8-state Protein Secondary Structure,” Communications in Computer and Information Science, vol. 2387 CCIS, pp. 172–181, 2025, doi: 10.1007/978-981-96-1907-8_17.

W. Alanazi, D. Meng, and G. Pollastri, “Porter 6: Protein Secondary Structure Prediction by Leveraging Pre-Trained Language Models (PLMs),” International Journal of Molecular Sciences, vol. 26, no. 1, p. 130, Dec. 2024, doi: 10.3390/ijms26010130.

L. Sharma, A. Deepak, A. Ranjan, and G. Krishnasamy, “A novel hybrid CNN and BiGRU-Attention based deep learning model for protein function prediction,” Stat. Appl. Genet. Mol. Biol., vol. 22, no. 1, Jan. 2023, doi: 10.1515/sagmb-2022-0057, PMID: 37658681.

M. Zubair et al., “A Deep Learning Approach for Prediction of Protein Secondary Structure,” Computers, Materials & Continua, vol. 72, no. 2, pp. 3705–3718, Mar. 2022, doi: 10.32604/cmc.2022.026408.

S. Alsenan, I. Al-Turaiki, M. Aldayel, and M. Tounsi, “Role of Optimization in RNA-Protein-Binding Prediction,” Curr. Issues Mol. Biol., vol. 46, no. 2, pp. 1360–1373, Feb. 2024, doi: 10.3390/cimb46020087.

J. Zhou and O. G. Troyanskaya, “Deep Supervised and Convolutional Generative Stochastic Network for Protein Secondary Structure Prediction,” in Proceedings of The 31st International Conference on Machine Learning (ICML), vol. 2, 2014, pp. 745-753.

Y. Gao, Y. Zhao, Y. Ma, and Y. Liu, “Prediction of Protein Secondary Structure Based on WS-BiLSTM Model,” Symmetry 2022, Vol. 14, Page 89, vol. 14, no. 1, p. 89, Jan. 2022, doi: 10.3390/sym14010089.

Q. Wang et al., “Prior knowledge facilitates low homologous protein secondary structure prediction with DSM distillation,” Bioinformatics, vol. 38, no. 14, pp. 3574–3581, Jul. 2022, doi: 10.1093/bioinformatics/btac351.

S. M. Shahid, S. Ko, and S. Kwon, “Performance Comparison of 1D and 2D Convolutional Neural Networks for Real-Time Classification of Time Series Sensor Data,” International Conference on Information Networking, vol. 2022-January, pp. 507–511, 2022, doi: 10.1109/icoin53446.2022.9687284.

S. Sasaoka et al., “Comparative study of 1D and 2D convolutional neural network models with attribution analysis for gravitational wave detection from compact binary coalescences,” Physical Review D, vol. 109, no. 4, p. 043011, Feb. 2024, doi: 10.1103/physrevd.109.043011.

Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner, “Gradient-based learning applied to document recognition,” Proceedings of the IEEE, vol. 86, no. 11, pp. 2278–2323, 1998, doi: 10.1109/5.726791.

V. Nair and G. E. Hinton, “Rectified Linear Units Improve Restricted Boltzmann Machines,” in Proceedings of the 27th International Conference on Machine Learning (ICML), pp. 807-814, June. 2010.

N. Srivastava, G. Hinton, A. Krizhevsky, I. Sutskever, and R. Salakhutdinov, “Dropout: A Simple Way to Prevent Neural Networks from Overfitting,” Journal of Machine Learning Research, vol. 15, pp. 1929–1958, 2014.

I. Goodfellow, Y. Bengio, and A. Courville, “Deep Feedforward Network,” in Deep Learning, MIT Press, pp. 164–220, 2016. [Online]. Available: https://www.deeplearningbook.org/contents/mlp.html

T. Akiba, S. Sano, T. Yanase, T. Ohta, and M. Koyama, “Optuna: A Next-generation Hyperparameter Optimization Framework,” Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 2623–2631, Jul. 2019, doi: 10.1145/3292500.3330701.

N. Parekh, A. Sen, P. Rajasekaran, J. D. D. Jayaseeli, and P. Robert, “Network Intrusion Detection System Using Optuna,” Proceedings of 5th International Conference on IoT Based Control Networks and Intelligent Systems, ICICNIS 2024, pp. 312–318, 2024, doi: 10.1109/icicnis64247.2024.10823298.

J. Bergstra, R. Bardenet, Y. Bengio, and B. Kégl, “Algorithms for Hyper-Parameter Optimization,” in Advances in Neural Information Processing Systems (NeurIPS), vol. 24, pp. 2546-2554, 2011.

F. Pedregosa, G. Varoquaux, A. Gramfort, V. Michel, B. Thirion, O. Grisel, M. Blondel, P. Prettenhofer, R. Weiss, V. Dubourg, J. Vanderplas, A. Passos, D. Cournapeau, M. Brucher, M. Perrot, and E. Duchesnay, "Scikit-learn: Machine learning in Python," Journal of Machine Learning Research, vol. 12, pp. 2825–2830, 2011. [Online]. Available: http://scikit-learn.sourceforge.net.

M. Sokolova and G. Lapalme, “A systematic analysis of performance measures for classification tasks,” Inf. Process. Manag., vol. 45, no. 4, pp. 427–437, Jul. 2009, doi: 10.1016/j.ipm.2009.03.002.

T. Fawcett, “An introduction to ROC analysis,” Pattern Recognit. Lett., vol. 27, no. 8, pp. 861–874, Jun. 2006, doi: 10.1016/j.patrec.2005.10.010.

T. G. Dietterich, “Approximate Statistical Tests for Comparing Supervised Classification Learning Algorithms,” Neural Comput., vol. 10, no. 7, pp. 1895–1923, Oct. 1998, doi: 10.1162/089976698300017197.

B. Zhang, J. Li, and Q. Lü, “Prediction of 8-state protein secondary structures by a novel deep learning architecture,” BMC Bioinformatics, vol. 19, no. 1, pp. 1–13, 2018, doi: 10.1186/s12859-018-2280-5.

P. Kumar, S. Bankapur, and N. Patil, “An enhanced protein secondary structure prediction using deep learning framework on hybrid profile based features,” Appl. Soft Comput., vol. 86, p. 105926, Jan. 2020, doi: 10.1016/j.asoc.2019.105926.

S. Geethu and E. R. Vimina, “Protein Secondary Structure Prediction Using Cascaded Feature Learning Model,” Appl. Soft Comput., vol. 140, p. 110242, Jun. 2023, doi: 10.1016/j.asoc.2023.110242.

Z. Li and Y. Yu, “Protein Secondary Structure Prediction Using Cascaded Convolutional and Recurrent Neural Networks,” in Proceedings of the 25th International Joint Conference on Artificial Intelligence (IJCAI-16), vol. 2016-January, pp. 2560–2567, Apr. 2016.

I. Drori et al., “High Quality Prediction of Protein Q8 Secondary Structure by Diverse Neural Network Architectures,” in 32nd Conference on Neural Information Processing Systems (NIPS 2018), Nov. 2018, arXiv preprint: 1811.07143.

Y. Lu, “Protein Secondary Structure Prediction Using Convolutional Bidirectional GRU,” Journal of Mathematics Research, vol. 16, no. 4, p. p11, Aug. 2024, doi: 10.5539/jmr.v16n4p11.

Z. Lyu, Z. Wang, F. Luo, J. Shuai, and Y. Huang, “Protein Secondary Structure Prediction With a Reductive Deep Learning Method,” Front. Bioeng. Biotechnol., vol. 9, p. 687426, Jun. 2021, doi: 10.3389/fbioe.2021.687426.