ERAP1 plays a pivotal role in processing antigenic peptides for presentation on major histocompatibility complex (MHC) class I molecules (Li et al. [1]). Disruptions in ERAP1 expression or function have been associated with a range of diseases, including cancer. Recent investigations have unveiled ERAP1's potential involvement in regulating tumor cell growth and immune evasion in cancers like lung cancer, melanoma, and breast cancer (Stratikos et al. [2]). Inhibiting ERAP1 activity has emerged as a promising therapeutic approach for combating these types of cancers (Bufalieri et al. [3]).The dataset used for this study comprises diverse proteins, representing various protein families. Among these, ERAP1 is a member of the aminopeptidase M1 family. This research is centered around the utilization of ERAPNet to identify Endoplasmic Reticulum Aminopeptidase 1 (ERAP1) within cancer cells. Both Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) models were used and trained using TensorFlow, a deep learning framework. During the training process, optimizations were undertaken to fine-tune the models' parameters and weights, enhancing their proficiency in detecting ERAP1 within the samples. The models underwent post-training evaluation using a testing dataset. Their accuracy was assessed using metrics including precision, recall, and the F1 score. Additionally, confusion matrices were generated to provide insight into the models' performance concerning the detection of ERAP1 protein. This evaluation process ensures reliability in the models' predictive capabilities.

Chloe Cheng. Deciphering ERAP1 in Cancer: Machine Learning for Protein Detection and Therapeutic Implications. Academic Journal of Computing & Information Science (2024), Vol. 7, Issue 8: 1-8. https://doi.org/10.25236/AJCIS.2024.070801.

[1] Li, Lenong, et al. “ERAP1 Enzyme-Mediated Trimming and Structural Analyses of MHC I–Bound Precursor Peptides Yield Novel Insights into Antigen Processing and Presentation.” The Journal of Biological Chemistry, vol. 294, no. 49, Dec. 2019, pp. 18534–44. PubMed Central, https://doi.org/10.1074/jbc.RA119.010102.

[2] Stratikos, Efstratios, et al. “A Role for Naturally Occurring Alleles of Endoplasmic Reticulum Aminopeptidases in Tumor Immunity and Cancer Pre-Disposition.” Frontiers in Oncology, vol. 4, Dec. 2014. Frontiers, https://doi.org/10.3389/fonc.2014.00363.

[3] Bufalieri, Francesca, et al. “ERAP1 Promotes Hedgehog-Dependent Tumorigenesis by Controlling USP47-Mediated Degradation of ΒTrCP.” Nature Communications, vol. 10, no. 1, 24 July 2019, www.ncbi.nlm.nih.gov/pmc/articles/PMC6656771/, https://doi.org/10.1038/s41467-019-11093-0.

[4] Seffernick, Justin T., and Steffen Lindert. “Hybrid Methods for Combined Experimental and Computational Determination of Protein Structure.” The Journal of Chemical Physics, vol. 153, no. 24, 28 Dec. 2020, www.ncbi.nlm.nih.gov/pmc/articles/PMC7773420/, https://doi.org/10.1063/5.0026025.

[5] Li Z , Miao Q , Yan F ,et al.Machine Learning in Quantitative Protein–peptide Affinity Prediction: Implications for Therapeutic Peptide Design[J].Current Drug Metabolism, 2019.DOI: 10.2174/ 1389200219666181012151944.

[6] Kufareva, Irina, and Ruben Abagyan. “Methods of Protein Structure Comparison.” Methods in Molecular Biology (Clifton, N.J.), vol. 857, 2012, p. 231. www.ncbi.nlm.nih.gov, https://doi.org/ 10. 1007/978-1-61779-588-6_10.

[7] PDB, RCSB. “PDB101: Learn: Guide to Understanding PDB Data: Methods for Determining Structure.” RCSB: PDB-101, 2016, pdb101.rcsb.org/learn/guide-to-understanding-pdb-data/methods-for-determining-structure. 

[8] Li, Yang, et al. “Robust and Accurate Prediction of Protein–Protein Interactions by Exploiting Evolutionary Information.” Scientific Reports, vol. 11, no. 1, 19 Aug. 2021, p. 16910, www.nature.com/articles/s41598-021-96265-z, https://doi.org/10.1038/s41598-021-96265-z.

[9] Xia, Yuhao, et al. “Multi-Domain and Complex Protein Structure Prediction Using Inter-Domain Interactions from Deep Learning.” Communications Biology, vol. 6, no. 1, 1 Dec. 2023, https://doi.org/10.1038/s42003-023-05610-7.

[10] Su T , Hasan S M S , Nahab F B ,et al.Abstract TMP98: Identifying Stroke Patients At Risk For Atrial Fibrillation Using Electronic Health Record Data And Machine Learning[J].Stroke, 2023, 54(Suppl_1):ATMP98-ATMP98.DOI:10.1161/str.54.suppl_1.TMP98.

[11] Bagaria, Anurag, et al. “Protein Structure Validation by Generalized Linear Model Root-Mean-Square Deviation Prediction.” Protein Science: A Publication of the Protein Society, vol. 21, no. 2, Feb. 2012, pp. 229–38. PubMed, https://doi.org/10.1002/pro.2007.