Search

In the synthetic laboratory, researchers typically rely on nuclear magnetic resonance (NMR) spectra to elucidate structures of synthesized products and confirm whether they match the desired target compounds. As chemical synthesis technology evolves toward intelligence and continuity, efficient computer-assisted structure elucidation (CASE) techniques are required to replace time-consuming manual analysis and provide the necessary speed. However, current CASE methods typically aim to derive precise chemical structures from spectroscopic data, yet they suffer from drawbacks such as low accuracy, high computational cost, and reliance on chemical libraries. In meticulously designed chemical synthesis reactions, researchers prioritize confirming the attainment of the target product based on NMR spectra, rather than focusing on identifying the specific product obtained. For this purpose, we innovatively developed a binary classification model, termed as MatCS, to directly predict the relationship between NMR spectra image (including 1 H NMR and 13 C NMR) and the molecular structure of the target compound. After evaluating various feature extraction methods, MatCS employs a combination of the Graph Attention Networks and Graph Convolutional Networks to learn the structural features of molecular graphs and the pretrained ResNet101 network with a Convolutional Block Attention Module to extract features from NMR spectra images. The results show that on a challenging Test sim data set, which poses difficulty in distinguishing spectra of similar molecular structures, MatCS achieves comprehensive evaluation metrics with an F1-score of 0.81 and an AUC value of 0.87. Simultaneously, it exhibited commendable performance on an external SDBS data set containing experimental NMR spectra, showcasing substantial potential for structural verification tasks in real automated chemical synthesis.

Protein function annotation has been one of the longstanding issues in biological sciences, and various computational methods have been developed. However, the existing methods suffer from a serious long-tail problem, with a large number of GO families containing few annotated proteins. Herein, an innovative strategy named AnnoPRO was therefore constructed by enabling sequence-based multi-scale protein representation, dual-path protein encoding using pre-training, and function annotation by long short-term memory-based decoding. A variety of case studies based on different benchmarks were conducted, which confirmed the superior performance of AnnoPRO among available methods. Source code and models have been made freely available at: https://github.com/idrblab/AnnoPRO and https://zenodo.org/records/10012272., (© 2024. The Author(s).)

Interest in macrocycles as potential therapeutic agents has increased rapidly. Macrocyclization of bioactive acyclic molecules provides a potential avenue to yield novel chemical scaffolds, which can contribute to the improvement of the biological activity and physicochemical properties of these molecules. In this study, we propose a computational macrocyclization method based on Transformer architecture (which we name Macformer). Leveraging deep learning, Macformer explores the vast chemical space of macrocyclic analogues of a given acyclic molecule by adding diverse linkers compatible with the acyclic molecule. Macformer can efficiently learn the implicit relationships between acyclic and macrocyclic structures represented as SMILES strings and generate plenty of macrocycles with chemical diversity and structural novelty. In data augmentation scenarios using both internal ChEMBL and external ZINC test datasets, Macformer display excellent performance and generalisability. We showcase the utility of Macformer when combined with molecular docking simulations and wet lab based experimental validation, by applying it to the prospective design of macrocyclic JAK2 inhibitors., (© 2023. The Author(s).)

Bioinformatic annotation of protein function is essential but extremely sophisticated, which asks for extensive efforts to develop effective prediction method. However, the existing methods tend to amplify the representativeness of the families with large number of proteins by misclassifying the proteins in the families with small number of proteins. That is to say, the ability of the existing methods to annotate proteins in the 'rare classes' remains limited. Herein, a new protein function annotation strategy, PFmulDL, integrating multiple deep learning methods, was thus constructed. First, the recurrent neural network was integrated, for the first time, with the convolutional neural network to facilitate the function annotation. Second, a transfer learning method was introduced to the model construction for further improving the prediction performances. Third, based on the latest data of Gene Ontology, the newly constructed model could annotate the largest number of protein families comparing with the existing methods. Finally, this newly constructed model was found capable of significantly elevating the prediction performance for the 'rare classes' without sacrificing that for the 'major classes'. All in all, due to the emerging requirements on improving the prediction performance for the proteins in 'rare classes', this new strategy would become an essential complement to the existing methods for protein function prediction. All the models and source codes are freely available and open to all users at: https://github.com/idrblab/PFmulDL., (Copyright © 2022. Published by Elsevier Ltd.)

De novo drug design is the process of generating novel lead compounds with desirable pharmacological and physiochemical properties. The application of deep learning (DL) in de novo drug design has become a hot topic, and many DL-based approaches have been developed for molecular generation tasks. Generally, these approaches were developed as per four frameworks: recurrent neural networks; encoder-decoder; reinforcement learning; and generative adversarial networks. In this review, we first introduced the molecular representation and assessment metrics used in DL-based de novo drug design. Then, we summarized the features of each architecture. Finally, the potential challenges and future directions of DL-based molecular generation were prospected., Competing Interests: Conflict of interest statement Nothing declared., (Copyright © 2021 Elsevier Ltd. All rights reserved.)

During the drug discovery and design process, the acid–base dissociation constant (p K a) of a molecule is critically emphasized due to its crucial role in influencing the ADMET (absorption, distribution, metabolism, excretion, and toxicity) properties and biological activity. However, the experimental determination of p K a values is often laborious and complex. Moreover, existing prediction methods exhibit limitations in both the quantity and quality of the training data, as well as in their capacity to handle the complex structural and physicochemical properties of compounds, consequently impeding accuracy and generalization. Therefore, developing a method that can quickly and accurately predict molecular p K a values will to some extent help the structural modification of molecules, and thus assist the development process of new drugs. In this study, we developed a cutting-edge p K a prediction model named GR-p K a (Graph Retention p K a), leveraging a message-passing neural network and employing a multi-fidelity learning strategy to accurately predict molecular p K a values. The GR-p K a model incorporates five quantum mechanical properties related to molecular thermodynamics and dynamics as key features to characterize molecules. Notably, we originally introduced the novel retention mechanism into the message-passing phase, which significantly improves the model's ability to capture and update molecular information. Our GR-p K a model outperforms several state-of-the-art models in predicting macro-p K a values, achieving impressive results with a low mean absolute error of 0.490 and root mean square error of 0.588, and a high R 2 of 0.937 on the SAMPL7 dataset. [ABSTRACT FROM AUTHOR]

Protein structure prediction is a longstanding issue crucial for identifying new drug targets and providing a mechanistic understanding of protein functions. To enhance the progress in this field, a spectrum of computational methodologies has been cultivated. AlphaFold2 has exhibited exceptional precision in predicting wild-type protein structures, with performance exceeding that of other methods. However, predicting the structures of missense mutant proteins using AlphaFold2 remains challenging due to the intricate and substantial structural alterations caused by minor sequence variations in the mutant proteins. Molecular dynamics (MD) has been validated for precisely capturing changes in amino acid interactions attributed to protein mutations. Therefore, for the first time, a strategy entitled ' MoDAFold ' was proposed to improve the accuracy and reliability of missense mutant protein structure prediction by combining AlphaFold2 with MD. Multiple case studies have confirmed the superior performance of MoDAFold compared to other methods, particularly AlphaFold2. [ABSTRACT FROM AUTHOR]

Recent studies have shown that multichannel narrow-band speech separation achieves remarkable performance, while most successful deep learning-based studies directly work on the full-band spectrum of speech. Motivated by these two different but complementary trends, this paper proposes a multidimensional attention fusion network (MAF-Net) to automatically exploit and fuse narrow-band and full-band speech separation information, aiming at enhancing the performance of multichannel speech separation in a reverberation environment. Specifically, it extracts effective narrow-band and full-band information from three dimensions, temporal, spatial and channel, and dynamically integrates them through a feature fusion mechanism. First, the narrow-band feature extractor (NBFE) collects temporal information frame by frame to model context dependency, and it takes multichannel mixed signals of one frequency as input and generates a narrow-band feature map. Then, the multidimensional attention fusion module (MAFM) is proposed to adaptively fuse narrow-band and full-band information from spatial and channel dimensions. Finally, the arrangement of attention modules within the MAFM is designed to maximize the utilization of spatial and channel attention features, including the parallel MAFM (P-MAFM) and sequential MAFM (S-MAFM). Experimental results demonstrate that our proposed method outperforms other advanced methods. [ABSTRACT FROM AUTHOR]

In recent years, many studies have illustrated the significant role that non-coding RNA (ncRNA) plays in biological activities, in which lncRNA, miRNA and especially their interactions have been proved to affect many biological processes. Some in silico methods have been proposed and applied to identify novel lncRNA–miRNA interactions (LMIs), but there are still imperfections in their RNA representation and information extraction approaches, which imply there is still room for further improving their performances. Meanwhile, only a few of them are accessible at present, which limits their practical applications. The construction of a new tool for LMI prediction is thus imperative for the better understanding of their relevant biological mechanisms. This study proposed a novel method, ncRNAInter, for LMI prediction. A comprehensive strategy for RNA representation and an optimized deep learning algorithm of graph neural network were utilized in this study. ncRNAInter was robust and showed better performance of 26.7% higher Matthews correlation coefficient than existing reputable methods for human LMI prediction. In addition, ncRNAInter proved its universal applicability in dealing with LMIs from various species and successfully identified novel LMIs associated with various diseases, which further verified its effectiveness and usability. All source code and datasets are freely available at https://github.com/idrblab/ncRNAInter. [ABSTRACT FROM AUTHOR]

Recently, deep learning (DL)-based de novo drug design represents a new trend in pharmaceutical research, and numerous DL-based methods have been developed for the generation of novel compounds with desired properties. However, a comprehensive understanding of the advantages and disadvantages of these methods is still lacking. In this study, the performances of different generative models were evaluated by analyzing the properties of the generated molecules in different scenarios, such as goal-directed (rediscovery, optimization and scaffold hopping of active compounds) and target-specific (generation of novel compounds for a given target) tasks. In overall, the DL-based models have significant advantages over the baseline models built by the traditional methods in learning the physicochemical property distributions of the training sets and may be more suitable for target-specific tasks. However, both the baselines and DL-based generative models cannot fully exploit the scaffolds of the training sets, and the molecules generated by the DL-based methods even have lower scaffold diversity than those generated by the traditional models. Moreover, our assessment illustrates that the DL-based methods do not exhibit obvious advantages over the genetic algorithm-based baselines in goal-directed tasks. We believe that our study provides valuable guidance for the effective use of generative models in de novo drug design. [ABSTRACT FROM AUTHOR]

Drug metabolism research plays a key role in the discovery and development of drugs. Based on the discovery of drug metabolites, new chemical entities can be identified and potential safety hazards caused by reactive or toxic metabolites can be minimized. Nowadays, computational methods are usually complementary tools for experiments. However, current metabolites prediction methods tend to have high false positive rates with low accuracy and are usually only used for specific enzyme systems. In order to overcome this difficulty, a method was developed in this paper by first establishing a database with broad coverage of SMARTS-coded metabolic reaction rule, and then extracting the molecular fingerprints of compounds to construct a classification model based on deep learning algorithms. The metabolic reaction rule database we built can supplement chemically reasonable negative reaction examples. Based on deep learning algorithms, the model could determine which reaction types are more likely to occur than the others. In the test set, our method can achieve the accuracy of 70% (Top-10), which is significantly higher than that of random guess and the rule-based method SyGMa. The results demonstrated that our method has a certain predictive ability and application value. [ABSTRACT FROM AUTHOR]

Data biases such as class imbalance and label noise always exist in large-scale datasets in real-world. These problems bring huge challenges to deep learning methods. Some previous works adopted loss re-weighting, sample re-weighting, or data-dependent regularization to mitigate the influence of these training biases. But these methods usually pay more attention to class imbalance problem when both the class imbalance and label noise exist in training set simultaneously. These methods may overfit noisy labels, which leads to a great degradation in performance. In this paper, we propose a gradient-aware learning method for the combination of the two biases. During the training process, we update only a part of crucial parameters regularly and rectify the update direction of the rest redundant parameters. This update rule is conducted both in the encoder and classifier of the deep network to decouple label noise and class imbalance implicitly. The experimental results verify the effectiveness of the proposed method on synthetic and real-world data biases. [ABSTRACT FROM AUTHOR]

• A CGAN model is proposed for film cooling effectiveness downstream of a semi-sphere vortex generator prediction using a few parameters. • The CGAN model shows good accuracy and robustness compared with other methods. • An optimization workflow is developed to obtain the optimal parameters. • The film cooling effectiveness is greatly improved when compared with the baseline case. Film cooling has shown great potential in protecting hot section of high-pressure turbine from melting down. A counter-rotating vortex pair (CVP) is produced downstream of the cooling hole and reduces the lateral diffusion of the jet. To enhance the film cooling effectiveness, a semi-sphere vortex generator (SVG) is proposed to be installed downstream of the cooling hole. To optimize the performance of the semi-sphere vortex generator, it is necessary to predict the dimensionless temperature distribution accurately using surrogate models. Conventional surrogate models in the literature usually predict the lateral-averaged temperature distribution. In the current study, a conditional generative adversarial neural network (CGAN) model is developed to build the non-linear and high-dimensional mapping between the input parameters and the surface temperature distribution downstream of the SVG. The computational Fluid Dynamics (CFD) method was utilized to provide the training data. With rigorously testing and validation, it is found that the model shows high robustness and accuracy. Integrated with this low cost deep learning model, an optimization framework based on the sparrow search algorithm (SSA) was established to adjust and search the optimal parameters of SVG. The optimized design features a vortex pair rotating in the reverse direction of the CVP. The film cooling effectiveness is greatly improved when compared with the configuration without SVG. It is proved that the attempt of introducing machine learning to optimize the parameters of SVG is successful. [ABSTRACT FROM AUTHOR]

• A first study to investigate the auscultation characteristics of covid-19. • To grading diagnose covid-19 based on auscultation with deep learning algorithms. • Three CNN models in classifying auscultation of covid-19 achieve superior performance. • Unidimensional raw data prevents complex pre-processing & manual feature extraction. Research on automatic auscultation diagnosis of COVID-19 has not yet been developed. We therefore aimed to engineer a deep learning approach for the automated grading diagnosis of COVID-19 by pulmonary auscultation analysis. 172 confirmed cases of COVID-19 in Tongji Hospital were divided into moderate, severe and critical group. Pulmonary auscultation were recorded in 6-10 sites per patient through 3M littmann stethoscope and the data were transferred to computer to construct the dataset. Convolutional neural network (CNN) were designed to generate classifications of the auscultation. F1 score, the area under the curve (AUC) of the receiver operating characteristic curve, sensitivity and specificity were quantified. Another 45 normal patients were served as control group. There are about 56.52%, 59.46% and 78.85% abnormal auscultation in the moderate, severe and critical groups respectively. The model showed promising performance with an averaged F1 scores (0.9938 95% CI 0.9923–0.9952), AUC ROC score (0.9999 95% CI 0.9998–1.0000), sensitivity (0.9938 95% CI 0.9910–0.9965) and specificity (0.9979 95% CI 0.9970–0.9988) in identifying the COVID-19 patients among normal, moderate, severe and critical group. It is capable in identifying crackles, wheezes, phlegm sounds with an averaged F1 scores (0.9475 95% CI 0.9440–0.9508), AUC ROC score (0.9762 95% CI 0.9848–0.9865), sensitivity (0.9482 95% CI 0.9393–0.9578) and specificity (0.9835 95% CI 0.9806–0.9863). Our model is accurate and efficient in automatically diagnosing COVID-19 according to different categories, laying a promising foundation for AI-enabled auscultation diagnosing systems for lung diseases in clinical applications. [ABSTRACT FROM AUTHOR]