Applied Chemical Engineering

Deep learning approach for secondary structure prediction of Pseudomonas aeruginosa –Quorum sensing repressor

Saravanan K

Department of Physics, AVS Engineering College, Salem, Tamilnadu 636003, India

Sivakumar S

Department of Physics, Government Arts College (Autonomous), Salem, Tamilnadu 636007, India

Marimuthu T

Department of Computer Science and Engineering, School of Computing, Kalasalingam Academy of Research and Education (Deemed to be University), Krishnankoil, Tamilnadu 626126, India

Palanisamy P.N

Department of Electronics and Communication Engineering, Mahendra College of Engineering, Salem, Tamilnadu 636106, India

Sangeetha B

Department of Electrical and Electronics Engineering, AVS Engineering College, Salem, Tamilnadu 636003, India

Sangeetha P

Department of Physics, Sona College of Technology, Salem, Tamilnadu 636005, India

DOI: https://doi.org/10.59429/ace.v8i1.5588

Keywords: pseudomonas aeruginosa; quorum-sensing repressor; secondary structure prediction; UNet; bacterial proteins

---

Abstract

Accurate prediction of Protein Secondary Structure (PSS) plays a crucial role in understanding the functional mechanisms of proteins. This study focuses on predicting the secondary structure of the quorum-sensing control repressor protein (QscR) using a UNet based deep learning model. The UNet architecture, known for its exceptional performance is adapted to predict structural features of proteins by learning from sequence based data. The proposed model was trained and validated using benchmark protein datasets to ensure generalizability and accuracy. Comparative analysis with traditional approaches demonstrated that the UNet model achieved superior performance in terms of prediction accuracy and computational efficiency. The findings suggest that the UNet model is a robust tool for SS prediction and can provide deeper insights into quorum-sensing mechanisms, aiding in the design of novel antibacterial strategies.

---

References

[1]. Hondoh, T., Kato, A., Yokoyama, S. and Kuroda, Y. Computer‐aided NMR assay for detecting natively folded structural domains. Protein science, 2006; 15(4), pp.871-883.

[2]. Shi, Q., Chen, W., Huang, S., Jin, F., Dong, Y., Wang, Y. and Xue, Z. DNN-Dom: predicting protein domain boundary from sequence alone by deep neural network. Bioinformatics, 2019;35(24), pp.5128-5136.

[3]. Zheng, W., Zhou, X., Wuyun, Q., Pearce, R., Li, Y. and Zhang, Y. FUpred: detecting protein domains through deep-learning-based contact map prediction. Bioinformatics, 2020;36(12), pp.3749-3757.

[4]. Guo, Z., Hou, J. and Cheng, J. DNSS2: Improved ab initio protein secondary structure prediction using advanced deep learning architectures. Proteins: Structure, Function, and Bioinformatics, 2021;89(2), pp.207-217.

[5]. Wu, T., Guo, Z., Hou, J. and Cheng, J. DeepDist: real-value inter-residue distance prediction with deep residual convolutional network. BMC bioinformatics, 2021; 22, pp.1-17.

[6]. Zhou, Y., Tan, K., Shen, X., He, Z. and Zheng, H, March. A Protein Structure Prediction Approach Leveraging Transformer and CNN Integration. In 2024 7th International Conference on Advanced Algorithms and Control Engineering (ICAACE), 2024;(pp. 749-753). IEEE.

[7]. Cheng, J., Liu, Y. and Ma, Y. Protein secondary structure prediction based on integration of CNN and LSTM model. Journal of Visual Communication and Image Representation, 2020;71, p.102844.

[8]. Geethu, S. and Vimina, E.R. Protein secondary structure prediction using cascaded feature learning model. Applied Soft Computing, 2023; 140, p.110242.

[9]. Senior, A.W., Evans, R., Jumper, J., Kirkpatrick, J., Sifre, L., Green, T., Qin, C., Žídek, A., Nelson, A.W., Bridgland, A. and Penedones, H. Improved protein structure prediction using potentials from deep learning. Nature, 2020; 577(7792), pp.706-710.

[10]. Roy, R.S., Quadir, F., Soltanikazemi, E. and Cheng, J. A deep dilated convolutional residual network for predicting interchain contacts of protein homodimers. Bioinformatics, 2022; 38(7), pp.1904-1910.

[11]. Jin, X., Guo, L., Jiang, Q., Wu, N. and Yao, S., 2022. Prediction of protein secondary structure based on an improved channel attention and multiscale convolution module. Frontiers in Bioengineering and Biotechnology, 10, p.901018.

[12]. Dong, B., Liu, Z., Xu, D., Hou, C., Dong, G., Zhang, T. and Wang, G., 2024. SERT-StructNet: Protein secondary structure prediction method based on multi-factor hybrid deep model. Computational and Structural Biotechnology Journal, 23, pp.1364-1375.

[13]. Dai, W., 2025. A Survey of Deep Learning Methods in Protein Bioinformatics and its Impact on Protein Design. arXiv preprint arXiv:2501.01477.

[14]. Ismi, D.P. and Pulungan, R. Deep learning for protein secondary structure prediction: Pre and post-AlphaFold. Computational and structural biotechnology journal, 2022;20, pp.6271-6286.

[15]. Stapor, K., Kotowski, K., Smolarczyk, T. and Roterman, I. Lightweight ProteinUnet2 network for protein secondary structure prediction: a step towards proper evaluation. BMC bioinformatics, 2022; 23(1), p.100.

[16]. Mahmud, S., Guo, Z., Quadir, F., Liu, J. and Cheng, J. Multi-head attention-based u-nets for predicting protein domain boundaries using 1d sequence features and 2d distance maps. BMC bioinformatics, 2022; 23(1), p.283.

[17]. Kabsch, W. and Sander, C., 1983. Dictionary of protein secondary structure: pattern recognition of hydrogen‐bonded and geometrical features. Biopolymers: Original Research on Biomolecules, 22(12), pp.2577-2637.

[18]. Heinig M, Frishman D. STRIDE: a web server for secondary structure assignment from known atomic coordinates of proteins. Nucleic acids research. 2004 Jul 1;32(suppl_2):W500-2.