Advancing the accuracy of SARS-CoV-2 phosphorylation site detection via meta-learning approach.

The worldwide appearance of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has generated significant concern and posed a considerable challenge to global health. Phosphorylation is a common post-translational modification that affects many vital cellular functions and is closely associated with SARS-CoV-2 infection. Precise identification of phosphorylation sites could provide more in-depth insight into the processes underlying SARS-CoV-2 infection and help alleviate the continuing COVID-19 crisis. Currently, available computational tools for predicting these sites lack accuracy and effectiveness. In this study, we designed an innovative meta-learning model, Meta-Learning for Serine/Threonine Phosphorylation (MeL-STPhos), to precisely identify protein phosphorylation sites. We initially performed a comprehensive assessment of 29 unique sequence-derived features, establishing prediction models for each using 14 renowned machine learning methods, ranging from traditional classifiers to advanced deep learning algorithms. We then selected the most effective model for each feature by integrating the predicted values. Rigorous feature selection strategies were employed to identify the optimal base models and classifier(s) for each cell-specific dataset. To the best of our knowledge, this is the first study to report two cell-specific models and a generic model for phosphorylation site prediction by utilizing an extensive range of sequence-derived features and machine learning algorithms. Extensive cross-validation and independent testing revealed that MeL-STPhos surpasses existing state-of-the-art tools for phosphorylation site prediction. We also developed a publicly accessible platform at https://balalab-skku.org/MeL-STPhos. We believe that MeL-STPhos will serve as a valuable tool for accelerating the discovery of serine/threonine phosphorylation sites and elucidating their role in post-translational regulation.

ADP-Fuse: A novel two-layer machine learning predictor to identify antidiabetic peptides and diabetes types using multiview information.

Diabetes mellitus has become a major public health concern associated with high mortality and reduced life expectancy and can cause blindness, heart attacks, kidney failure, lower limb amputations, and strokes. A new generation of antidiabetic peptides (ADPs) that act on ß-cells or T-cells to regulate insulin production is being developed to alleviate the effects of diabetes. However, the lack of effective peptide-mining tools has hampered the discovery of these promising drugs. Hence, novel computational tools need to be developed urgently. In this study, we present ADP-Fuse, a novel two-layer prediction framework capable of accurately identifying ADPs or non-ADPs and categorizing them into type 1 and type 2 ADPs. First, we comprehensively evaluated 22 peptide sequence-derived features coupled with eight notable machine learning algorithms. Subsequently, the most suitable feature descriptors and classifiers for both layers were identified. The output of these single-feature models, embedded with multiview information, was trained with an appropriate classifier to provide the final prediction. Comprehensive cross-validation and independent tests substantiate that ADP-Fuse surpasses single-feature models and the feature fusion approach for the prediction of ADPs and their types. In addition, the SHapley Additive exPlanation method was used to elucidate the contributions of individual features to the prediction of ADPs and their types. Finally, a user-friendly web server for ADP-Fuse was developed and made publicly accessible (https://balalab-skku.org/ADP-Fuse), enabling the swift screening and identification of novel ADPs and their types. This framework is expected to contribute significantly to antidiabetic peptide identification.

An exploratory simulation study and prediction model on human brain behavior and activity using an integration of deep neural network and biosensor Rabi antenna.

The plasmonic antenna probe is constructed using a silver rod embedded in a modified Mach-Zehnder interferometer (MZI) ad-drop filter. Rabi antennas are formed when space-time control reaches two levels of system oscillation and can be used as human brain sensor probes. Photonic neural networks are designed using brain-Rabi antenna communication, and transmissions are connected via neurons. Communication signals are carried by electron spin (up and down) and adjustable Rabi frequency. Hidden variables and deep brain signals can be obtained by external detection. A Rabi antenna has been developed by simulation using computer simulation technology (CST) software. Additionally, a communication device has been developed that uses the Optiwave program with Finite-Difference Time-Domain (OptiFDTD). The output signal is plotted using the MATLAB program with the parameters of the OptiFDTD simulation results. The proposed antenna oscillates in the frequency range of 192 THz to 202 THz with a maximum gain of 22.4 dBi. The sensitivity of the sensor is calculated along with the result of electron spin and applied to form a human brain connection. Moreover, intelligent machine learning algorithms are proposed to identify high-quality transmissions and predict the behavior of transmissions in the near future. During the process, a root mean square error (RMSE) of 2.3332(±0.2338) was obtained. Finally, it can be said that our proposed model can efficiently predict human mind, thoughts, behavior as well as action/reaction, which can be greatly helpful in the diagnosis of various neuro-degenerative/psychological diseases (such as Alzheimer's, dementia, etc.) and for security purposes.

DrugormerDTI: Drug Graphormer for drug-target interaction prediction.

Drug-target interactions (DTI) prediction is a crucial task in drug discovery. Existing computational methods accelerate the drug discovery in this respect. However, most of them suffer from low feature representation ability, significantly affecting the predictive performance. To address the problem, we propose a novel neural network architecture named DrugormerDTI, which uses Graph Transformer to learn both sequential and topological information through the input molecule graph and Resudual2vec to learn the underlying relation between residues from proteins. By conducting ablation experiments, we verify the importance of each part of the DrugormerDTI. We also demonstrate the good feature extraction and expression capabilities of our model via comparing the mapping results of the attention layer and molecular docking results. Experimental results show that our proposed model performs better than baseline methods on four benchmarks. We demonstrate that the introduction of Graph Transformer and the design of residue are appropriate for drug-target prediction.

Multiband Rabi antenna using nest microstrip add-drop filter (NMADF) for relativistic sensing applications.

A microstrip circuit is designed, constructed, and tested based on the nest microstrip add-drop filters (NMADF). The multi-level system oscillation is generated by the wave-particle behaviors of AC driven along the microstrip ring circular path. The continuous successive filtering is applied via the device input port. The higher-order harmonic oscillations can be filtered, from which the two-level system known as a Rabi oscillation is achieved. The outside microstrip ring energy is coupled to the inside rings, from which the multiband Rabi oscillations can be formed within the inner rings. The resonant Rabi frequencies can be applied for multi-sensing probes. The relationship between electron density and Rabi oscillation frequency of each microstrip ring output can be obtained and used for multi-sensing probe applications. The relativistic sensing probe can be obtained by the warp speed electron distribution at the resonant Rabi frequency respecting the resonant ring radii. These are available for relativistic sensing probe usage. The obtained experimental results have shown that there are 3-center Rabi frequencies obtained, which can be used for 3-sensing probes simultaneously. The sensing probe speeds of 1.1c, 1.4c, and 1.5c are obtained using the microstrip ring radii of 14.20, 20.12, and 34.49 mm, respectively. The best sensor sensitivity of 1.30 ms is achieved. The relativistic sensing platform can be used for many applications.

Pretoria: An effective computational approach for accurate and high-throughput identification of CD8+ t-cell epitopes of eukaryotic pathogens.

T-cells recognize antigenic epitopes present on major histocompatibility complex (MHC) molecules, triggering an adaptive immune response in the host. T-cell epitope (TCE) identification is challenging because of the extensive number of undetermined proteins found in eukaryotic pathogens, as well as MHC polymorphisms. In addition, conventional experimental approaches for TCE identification are time-consuming and expensive. Thus, computational approaches that can accurately and rapidly identify CD8+ T-cell epitopes (TCEs) of eukaryotic pathogens based solely on sequence information may facilitate the discovery of novel CD8+ TCEs in a cost-effective manner. Here, Pretoria (Predictor of CD8+ TCEs of eukaryotic pathogens) is proposed as the first stack-based approach for accurate and large-scale identification of CD8+ TCEs of eukaryotic pathogens. In particular, Pretoria enabled the extraction and exploration of crucial information embedded in CD8+ TCEs by employing a comprehensive set of 12 well-known feature descriptors extracted from multiple groups, including physicochemical properties, composition-transition-distribution, pseudo-amino acid composition, and amino acid composition. These feature descriptors were then utilized to construct a pool of 144 different machine learning (ML)-based classifiers based on 12 popular ML algorithms. Finally, the feature selection method was used to effectively determine the important ML classifiers for the construction of our stacked model. The experimental results indicated that Pretoria is an accurate and effective computational approach for CD8+ TCE prediction; it was superior to several conventional ML classifiers and the existing method in terms of the independent test, with an accuracy of 0.866, MCC of 0.732, and AUC of 0.921. Additionally, to maximize user convenience for high-throughput identification of CD8+ TCEs of eukaryotic pathogens, a user-friendly web server of Pretoria (http://pmlabstack.pythonanywhere.com/Pretoria) was developed and made freely available.

Fruit-CoV: An efficient vision-based framework for speedy detection and diagnosis of SARS-CoV-2 infections through recorded cough sounds.

COVID-19 is an infectious disease caused by the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). This deadly virus has spread worldwide, leading to a global pandemic since March 2020. A recent variant of SARS-CoV-2 named Delta is intractably contagious and responsible for more than four million deaths globally. Therefore, developing an efficient self-testing service for SARS-CoV-2 at home is vital. In this study, a two-stage vision-based framework, namely Fruit-CoV, is introduced for detecting SARS-CoV-2 infections through recorded cough sounds. Specifically, audio signals are converted into Log-Mel spectrograms, and the EfficientNet-V2 network is used to extract their visual features in the first stage. In the second stage, 14 convolutional layers extracted from the large-scale Pretrained Audio Neural Networks for audio pattern recognition (PANNs) and the Wavegram-Log-Mel-CNN are employed to aggregate feature representations of the Log-Mel spectrograms and the waveform. Finally, the combined features are used to train a binary classifier. In this study, a dataset provided by the AICovidVN 115M Challenge is employed for evaluation. It includes 7,371 recorded cough sounds collected throughout Vietnam, India, and Switzerland. Experimental results indicate that the proposed model achieves an Area Under the Receiver Operating Characteristic Curve (AUC) score of 92.8% and ranks first on the final leaderboard of the AICovidVN 115M Challenge. Our code is publicly available.

H2Opred: a robust and efficient hybrid deep learning model for predicting 2'-O-methylation sites in human RNA.

2'-O-methylation (2OM) is the most common post-transcriptional modification of RNA. It plays a crucial role in RNA splicing, RNA stability and innate immunity. Despite advances in high-throughput detection, the chemical stability of 2OM makes it difficult to detect and map in messenger RNA. Therefore, bioinformatics tools have been developed using machine learning (ML) algorithms to identify 2OM sites. These tools have made significant progress, but their performances remain unsatisfactory and need further improvement. In this study, we introduced H2Opred, a novel hybrid deep learning (HDL) model for accurately identifying 2OM sites in human RNA. Notably, this is the first application of HDL in developing four nucleotide-specific models [adenine (A2OM), cytosine (C2OM), guanine (G2OM) and uracil (U2OM)] as well as a generic model (N2OM). H2Opred incorporated both stacked 1D convolutional neural network (1D-CNN) blocks and stacked attention-based bidirectional gated recurrent unit (Bi-GRU-Att) blocks. 1D-CNN blocks learned effective feature representations from 14 conventional descriptors, while Bi-GRU-Att blocks learned feature representations from five natural language processing-based embeddings extracted from RNA sequences. H2Opred integrated these feature representations to make the final prediction. Rigorous cross-validation analysis demonstrated that H2Opred consistently outperforms conventional ML-based single-feature models on five different datasets. Moreover, the generic model of H2Opred demonstrated a remarkable performance on both training and testing datasets, significantly outperforming the existing predictor and other four nucleotide-specific H2Opred models. To enhance accessibility and usability, we have deployed a user-friendly web server for H2Opred, accessible at https://balalab-skku.org/H2Opred/. This platform will serve as an invaluable tool for accurately predicting 2OM sites within human RNA, thereby facilitating broader applications in relevant research endeavors.

Zoning the suitability of the western Mekong Delta for paddy rice cultivation and aquaculture under current and future environmental conditions.

Ca Mau and Kien Giang, the two provinces of the Mekong Delta bordering the Gulf of Thailand, are facing major environmental challenges affecting the agriculture and aquaculture sectors upon which many livelihoods in this region depend on. This study maps the suitability of these two provinces for paddy rice cultivation and shrimp farming according to soil characteristics and current and future environmental conditions for variables found to significantly influence the yield of those two sectors, i.e., the level of saltwater intrusion, water availability for rainfed agriculture, and the length of the growing period. Future environmental conditions were simulated using the MIKE 11 hydrodynamic model forced by four hydrodynamic scenarios, each one representing different extents of saltwater intrusion during both the dry and rainy seasons, while also considering the availability of water resources for rainfed agriculture. The suitability zoning was performed using a GIS-based analytic hierarchy process (AHP) approach, resulting in the categorisation of the land according to four suitability levels for each sector. The analysis reveals that paddy rice cultivation will become more suitable to Kien Giang province while shrimp farming will be more suitable to Ca Mau province if the simulated future environmental conditions materialise. A suitability analysis is essential for optimal utilisation of the land. The approach presented in this study will inform the regional economic development master plan and provide guidance to other delta regions experiencing severe environmental changes and wishing to consider potential future climatic and sea level changes, and their associated impacts, in their land use planning.

A deep learning approach for detecting drill bit failures from a small sound dataset.

Monitoring the conditions of machines is vital in the manufacturing industry. Early detection of faulty components in machines for stopping and repairing the failed components can minimize the downtime of the machine. In this article, we present a method for detecting failures in drill machines using drill sounds in Valmet AB, a company in Sundsvall, Sweden that supplies equipment and processes for the production of pulp, paper, and biofuels. The drill dataset includes two classes: anomalous sounds and normal sounds. Detecting drill failure effectively remains a challenge due to the following reasons. The waveform of drill sound is complex and short for detection. Furthermore, in realistic soundscapes, both sounds and noise exist simultaneously. Besides, the balanced dataset is small to apply state-of-the-art deep learning techniques. Due to these aforementioned difficulties, sound augmentation methods were applied to increase the number of sounds in the dataset. In this study, a convolutional neural network (CNN) was combined with a long-short-term memory (LSTM) to extract features from log-Mel spectrograms and to learn global representations of two classes. A leaky rectified linear unit (Leaky ReLU) was utilized as the activation function for the proposed CNN instead of the ReLU. Moreover, an attention mechanism was deployed at the frame level after the LSTM layer to pay attention to the anomaly in sounds. As a result, the proposed method reached an overall accuracy of 92.62% to classify two classes of machine sounds on Valmet's dataset. In addition, an extensive experiment on another drilling dataset with short sounds yielded 97.47% accuracy. With multiple classes and long-duration sounds, an experiment utilizing the publicly available UrbanSound8K dataset obtains 91.45%. Extensive experiments on our dataset as well as publicly available datasets confirm the efficacy and robustness of our proposed method. For reproducing and deploying the proposed system, an open-source repository is publicly available at https://github.com/thanhtran1965/DrillFailureDetection_SciRep2022 .

Improving ligand-ranking of AutoDock Vina by changing the empirical parameters.

AutoDock Vina (Vina) achieved a very high docking-success rate, p^ , but give a rather low correlation coefficient, R , for binding affinity with respect to experiments. This low correlation can be an obstacle for ranking of ligand-binding affinity, which is the main objective of docking simulations. In this context, we evaluated the dependence of Vina R coefficient upon its empirical parameters. R is affected more by changing the gauss2 and rotation than other terms. The docking-success rate p^ is sensitive to the alterations of the gauss1, gauss2, repulsion, and hydrogen bond parameters. Based on our benchmarks, the parameter set1 has been suggested to be the most optimal. The testing study over 800 complexes indicated that the modified Vina provided higher correlation with experiment Rset1=0.556±0.025 compared with RDefault=0.493±0.028 obtained by the original Vina and RVina1.2=0.503±0.029 by Vina version 1.2. Besides, the modified Vina can be also applied more widely, giving R≥0.500 for 32/48 targets, compared with the default package, giving R≥0.500 for 31/48 targets. In addition, validation calculations for 1036 complexes obtained from version 2019 of PDBbind refined structures showed that the set1 of parameters gave higher correlation coefficient ( Rset1=0.617±0.017 ) than the default package ( RDefault=0.543±0.020 ) and Vina version 1.2 ( RVina1.2=0.540±0.020 ). The version of Vina with set1 of parameters can be downloaded at https://github.com/sontungngo/mvina. The outcomes would enhance the ranking of ligand-binding affinity using Autodock Vina.