Prediction of antioxidant peptides using a quantitative structure-activity relationship predictor (AnOxPP) based on bidirectional long short-term memory neural network and interpretable amino acid descriptors.

Antioxidant peptides can protect against free radical-mediated diseases, especially food-derived antioxidant peptides are considered as potential competitors among synthetic antioxidants due to their safety, high activity and abundant sources. However, wet experimental methods can not meet the need for effectively screening and clearly elucidating the structure-activity relationship of antioxidant peptides. Therefore, it is particularly important to build a reliable prediction platform for antioxidant peptides. In this work, we developed a platform, AnOxPP, for prediction of antioxidant peptides using the bidirectional long short-term memory (BiLSTM) neural network. The sequence characteristics of peptides were converted into feature codes based on amino acid descriptors (AADs). Our results showed that the feature conversion ability of the combined-AADs optimized by the forward feature selection method was more accurate than that of the single-AADs. Especially, the model trained by the optimal descriptor SDPZ27 significantly outperformed the existing predictor on two independent test sets (Accuracy = 0.967 and 0.819, respectively). The SDPZ27-based AnOxPP learned four key structure-activity features of antioxidant peptides, with the following importance as steric properties > hydrophobic properties > electronic properties > hydrogen bond contributions. AnOxPP is a valuable tool for screening and design of peptide drugs, and the web-server is accessible at http://www.cqudfbp.net/AnOxPP/index.jsp.

Insight into the Structure-Odor Relationship of Molecules: A Computational Study Based on Deep Learning.

Molecules with pleasant odors, unacceptable odors, and even serious toxicity are closely related to human social life. It is impractical to identify the odors of molecules in large quantities (particularly hazardous odors) using experimental methods. Computer-aided methods have currently attracted increasing attention for the prediction of molecular odors. Here, through models based on multilayer perceptron (MLP) and physicochemical descriptors (MLP-Des), MLP and molecular fingerprint, and convolutional neural network (CNN), we conduct the two-class prediction of odor/no odor, fruity/no odor, floral/no odor, and woody/no odor, and the multi-class prediction of fruity/flowery/woody/no odor on our newly refined molecular odor datasets. We show that three kinds of predictors can robustly predict molecular odors. The MLP-Des model not only exhibits the best prediction results (the AUC values are 0.99 and 0.86 for the two- and multi-classification models, respectively) but can also well reflect the characteristics of the structure-odor relationship of molecules. The CNN model takes 2D molecular images as input and can automatically extract the structural features related to molecular odors. The proposed models are of great help for the prediction of molecular odorants, understanding the underlying relationship between chemical structure and odor perception, and the discovery of new odorous and/or hazardous molecules.

DFBP: a comprehensive database of food-derived bioactive peptides for peptidomics research.

MOTIVATION: Food-derived bioactive peptides (FBPs) have demonstrated their significance in pharmaceuticals, diets and nutraceuticals, benefiting public health and global ecology. While significant efforts have been made to discover FBPs and to elucidate the underlying bioactivity mechanisms, there is lack of a systemic study of sequence-structure-activity relationship of FBPs in a large dataset. RESULTS: Here, we construct a database of food-derived bioactive peptides (DFBP), containing a total of 6276 peptide entries in 31 types from different sources. Further, we develop a series of analysis tools for function discovery/repurposing, traceability, multifunctional bioactive exploration and physiochemical property assessment of peptides. Finally, we apply this database and data-mining techniques to discover new FBPs as potential drugs for cardiovascular diseases. The DFBP serves as a useful platform for not only the fundamental understanding of sequence-structure-activity of FBPs but also the design, discovery, and repurposing of peptide-based drugs, vaccines, materials and food ingredients. AVAILABILITY AND IMPLEMENTATION: DFBP service can be accessed freely via http://www.cqudfbp.net/. All data are incorporated into the article and its online supplementary material. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Prediction of bitterant and sweetener using structure-taste relationship models based on an artificial neural network.

Identifying the taste characteristics of molecules is essential for the expansion of their application in health foods and drugs. It is time-consuming and consumable to identify the taste characteristics of a large number of compounds through experiments. To date, computational methods have become an important technique for identifying molecular taste. In this work, bitterant/non-bitterant, sweetener/non-sweetener, and bitterant/sweetener are predicted using three structure-taste relationship models based on the convolutional neural networks (CNN), multi-layer perceptron (MLP)-Descriptor, and MLP-Fingerprint. The results showed that all three models have unique characteristics in the prediction of bitterant/non-bitterant, sweetener/non-sweetener, and bitterant/sweetener. For the prediction of bitterant/non-bitterant, sweetener/non-sweetener, and bitterant/sweetener, the MLP-Fingerprint model exhibited a higher predictive AUC value (0.94, 0.94 and 0.95) than the MLP-Descriptor model (0.94, 0.84 and 0.87) and the CNN model (0.88, 0.90 and 0.91) by external validation, respectively. The MLP-Descriptor model showed a distinct structure-taste relationship of the studied molecules, which helps to understand the key properties associated with bitterants and sweeteners. The CNN model requires only a simple 2D chemical map as input to automate feature extraction for favorable prediction. The obtained models achieved accurate predictions of bitterant/non-bitterant, sweetener/non-sweetener and bitterant and sweetener, providing vital references for the identification of bioactive molecules and toxic substances.

Caffeoyl malic acid is a potential dual inhibitor targeting TNFα/IL-4 evaluated by a combination strategy of network analysis-deep learning-molecular simulation.

Atopic dermatitis (AD) is a common inflammatory skin disease involving multiple signaling pathways. One of the effective treatment strategies of AD is to develop a new drug capable of regulating the key therapeutic targets. Here we report the combination use of network analysis, deep learning, and molecular simulation for the identification of key therapeutic targets for AD and screening of potential multi-target drugs. From the TCM@Taiwan database, we identify a small molecule, namely caffeoyl malic acid (CMA), to inhibit the key therapeutic targets (TNFα and IL-4) for AD. CMA is further identified as a TNFα inhibitor by a deep learning model based on convolutional neural network. Molecular simulations demonstrate that CMA can stably bind to TNFα and IL-4, thereby producing diverse effects on the structural fluctuation, structural flexibility, looseness, and motion strength of each protein. Furthermore, conformation alignments reveal that CMA makes the distance between chain A and C of TNFα become wider and the slit between the two α helices of IL-4 get narrow obviously. CMA leads to the change of protein conformation, which hinders the formation of the protein-receptor complex. Collectively, our findings suggest that CMA is a potential dual TNFα/IL-4 inhibitor for the treatment of AD.

Identification of the functional food ingredients with antithrombotic properties via virtual screen and experimental studies.

Thrombin is a key therapeutic target protein of thrombosis. To date, massive studies have focused on the exploration of antithrombotic compounds. Here we capitalize on molecular docking, molecular simulations and spectroscopic experiments for virtually screening natural products that can inhibit thrombin and elucidating their interaction mechanism. Six compounds are screened from a natural product database by a cross-analysis based on two semi-flexible molecular docking methods. We show that four compounds can effectively inhibit thrombin and Calceolarioside B is the most competitive one based on enzyme inhibition experiments. Moreover, the binding free energies of these compounds with thrombin exhibit a consistent rank trend with their enzyme inhibition assay results. In addition, the Van der Waals is the main force to drive the interaction between the ligands and the receptor, which can be deduced from the fluorescence spectral results. This work provides a new insight into the development of antithrombotic natural compounds.