Improved Prediction Model of Protein Lysine Crotonylation Sites Using Bidirectional Recurrent Neural Networks.

Histone lysine crotonylation (Kcr) is a post-translational modification of histone proteins that is involved in the regulation of gene transcription, acute and chronic kidney injury, spermatogenesis, depression, cancer, and so forth. The identification of Kcr sites in proteins is important for characterizing and regulating primary biological mechanisms. The use of computational approaches such as machine learning and deep learning algorithms have emerged in recent years as the traditional wet-lab experiments are time-consuming and costly. We propose as part of this study a deep learning model based on a recurrent neural network (RNN) termed as Sohoko-Kcr for the prediction of Kcr sites. Through the embedded encoding of the peptide sequences, we investigate the efficiency of RNN-based models such as long short-term memory (LSTM), bidirectional LSTM (BiLSTM), and bidirectional gated recurrent unit (BiGRU) networks using cross-validation and independent tests. We also established the comparison between Sohoko-Kcr and other published tools to verify the efficiency of our model based on 3-fold, 5-fold, and 10-fold cross-validations using independent set tests. The results then show that the BiGRU model has consistently displayed outstanding performance and computational efficiency. Based on the proposed model, a webserver called Sohoko-Kcr was deployed for free use and is accessible at https://sohoko-research-9uu23.ondigitalocean.app.

Using infrared imaging and deep learning in fit-checking of respiratory protective devices among healthcare professionals.

AIMS: This study aimed to investigate the application of infrared thermal imaging and adopt deep learning to detect air leakage for determining the fitness of respirators during fit-checks. BACKGROUND: The outbreak of Covid-19 virus constitutes a public health crisis with substantial resultant morbidities and mortalities; has exerted profound impacts. METHODS: This was a prospective observational study, employing a non-probability sampling method on a convenience sample to recruit the participants and followed the Strengthening the Reporting of Observational Studies in Epidemiology statement guidelines. RESULTS: The use of infrared thermal imaging identified air leakage points as a disruption to the facial thermal pattern distribution at (a) front of face; (b) right lateral of the face; (c) left lateral of the face; (d) top of the facemask with the head facing down; and (e) bottom of the facemask with the head facing up. Results also indicated that artificial intelligence tools and the proliferation of deep learning have the potential to detect the location of air leakage locations. CONCLUSION: The use of infrared thermal imaging provides evidence of the feasibility and applicability of infrared thermal imaging techniques in detecting air leakage for individuals wearing respirators. CLINICAL RELEVANCE: The use of infrared thermal technology can serve a potential role in complement fit-checking of respiratory protective devices and offers promising practical utility in determining the fitness of respirators for nurses at the frontline to protect against the air-borne viruses.