Inteligencia artificial avanzada en la investigación de piARNs y proteínas similares a PIWI: Una revisión sistemática de RNN, LSTM y técnicas computacionales emergentes

Introduction. PIWI-interacting RNAs are small non-coding RNAs involved in gene regulation and transposable element repression, emerging as critical biomarkers and therapeutic targets in oncology. Advances in artificial intelligence, such as recurrent neural networks, long short-term memory networks, and graph convolutional networks, offer significant improvements in piRNA detection.Objectives. To evaluate the performance of AI models, including RNNs, LSTMs, and GCNs, in detecting piRNAs and their implications for cancer diagnostics and prognosis.Materials and methods. A systematic review of 24 studies was conducted across PubMed, ScienceDirect, Scopus, and Web of Science, focusing on AI-based approaches for piRNA detection. Inclusion criteria were original articles published in English or Spanish using AI models in clinical or experimental settings. Performance metrics such as accuracy, sensitivity, and specificity were analyzed.Results. LSTM models achieved the highest overall accuracy (92.3%), followed by GCN (91.4%), SVM (88%), and RNN (85.7%). Sensitivity and specificity were also highest in LSTM (94% and 91%, respectively). GCN showed superior performance in identifying piRNA-disease associations with complex datasets. SVM models were effective in smaller datasets but demonstrated scalability limitations.Conclusion. AI models, especially LSTM and GCN, significantly enhance piRNA detection, supporting their application in cancer diagnostics and personalized medicine. Future studies should refine these models, address dataset biases, and explore their integration into clinical workflows.