A New Floating Piezoelectric Microphone for Fully Implantable Cochlear Implants in Middle Ear.

OBJECTIVE: Our team designed a long-lasting, well-sealed microphone, which uses laser welding and vacuum packaging technology. This study examined the sensitivity and effectiveness of this new floating piezoelectric microphone (NFPM) designed for totally implantable cochlear implants (TICIs) in animal experiments and intraoperative testing. METHODS: Different NFPM frequency responses from 0.25 to 10 kHz at 90 dB SPL were analyzed using in vivo testing of cats and human patients. The NFPM was tested in different positions that were clamped to the ossicular chains or placed in the tympanic cavity of cats and human patients. Two volunteers' long incus foot and four cats' malleus neck of the ossicular chain were clamped with the NSFM. The output electrical signals from different locations were recorded, analyzed, and compared. The NFPM was removed after the test without causing any damage to the middle-ear structure of the cats. Intraoperative tests of the NFPM were performed during the cochlear implant surgery and the cochlear implant surgery was completed after all tests. RESULTS: Compared with the results in the tympanic cavity, the NFPM could detect the vibration from the ossicular chain more sensitively in cat experiments and intraoperative testing. We also found that the signal output level of the NFPM decreased as the acoustic stimulation strength decreased in the intraoperative testing. CONCLUSION: The NFPM is effective in the intraoperative testing, making it feasible as an implantable middle-ear microphone for TICIs. LEVEL OF EVIDENCE: 4 Laryngoscope, 134:937-944, 2024.

Signal-3L 3.0: Improving Signal Peptide Prediction through Combining Attention Deep Learning with Window-Based Scoring.

Signal peptides play an important role in guiding and transferring transmembrane proteins and secreted proteins. In recent years, with the explosive growth of protein sequences, computationally predicting signal peptides and their cleavage sites from protein sequences is highly desired. In this work, we present an improved approach, Signal-3L 3.0, for signal peptide recognition and cleavage-site prediction using a 3-layer hybrid method of integrating deep learning algorithms and window-based scoring. There are three main components in the Signal-3L 3.0 prediction engine: (1) a deep bidirectional long short-term memory (Bi-LSTM) network with a soft self-attention learns abstract features from sequences to determine whether a query protein contains a signal peptide; (2) the statistics propensity window-based cleavage site screening method is applied to generate the set of candidate cleavage sites; (3) the prediction of a conditional random field with a hybrid convolutional neural network (CNN) and Bi-LSTM is fused with the window-based score for identifying the final unique cleavage site. Experimental results on the benchmark datasets show that the new deep learning-driven Signal-3L 3.0 yields promising performance. The online server of Signal-3L 3.0 is available at http://www.csbio.sjtu.edu.cn/bioinf/Signal-3L/.

Topology Prediction Improvement of α-helical Transmembrane Proteins Through Helix-tail Modeling and Multiscale Deep Learning Fusion.

Transmembrane proteins (TMPs) play important roles in many biological processes, such as cell recognition and communication. Their structures are crucial for revealing complex functions but are hard to obtain. A variety of computational algorithms have been proposed to fill the gap by predicting structures from primary sequences. In this study, we mainly focus on α-helical TMP and develop a multiscale deep learning pipeline, MemBrain 3.0, to improve topology prediction. This new protocol includes two submodules. The first module is transmembrane helix (TMH) prediction, which features the capability of accurately predicting TMH with the tail part through the incorporation of tail modeling. The prediction engine contains a multiscale deep learning model and a dynamic threshold strategy. The deep learning model is comprised of a small-scale residue-based residual neural network and a large-scale entire-sequence-based residual neural network. Dynamic threshold strategy is designed to binarize the raw prediction scores and solve the under-split problem. The second module is orientation prediction, which consists of a support vector machine (SVM) classifier and a new Max-Min assignment (MMA) strategy. One typical merit of MemBrain 3.0 is the decision mode composed of the dynamic threshold strategy and the MMA strategy, which makes it more effective for hard TMHs, such as half-TMH, back-to-back TMH, and long-TMH. Systematic experiments have demonstrated the efficacy of the new model, which is available at: www.csbio.sjtu.edu.cn/bioinf/MemBrain/.