iUmami-SCM: A Novel Sequence-Based Predictor for Prediction and Analysis of Umami Peptides Using a Scoring Card Method with Propensity Scores of Dipeptides

From prediction to design: Revealing the mechanisms of umami peptides using interpretable deep learning, quantum chemical simulations, and module substitution

This study screened and designed umami peptides using deep learning model and module substitution strategies. The predictive model, which integrates pre-training, enhanced feature, and contrastive learning module, achieved an accuracy of 0.94, outperforming other models by 2-9 %. Umami peptides were identified through virtual hydrolysis, model predictions, and sensory evaluation. Peptides EN, ETR, GK4, RK5, ER6, EF7, IL8, VR9, DL10, and PK14 demonstrated umami taste and exhibited umami-enhancing effects with MSG. Module substitution strategy, where highly contributive module from umami peptides replace corresponding module in bitter peptides, facilitates peptide design and modification. The mechanism underlying module substitution and taste presentation were elucidated via molecular docking and active site analysis, revealing that substituted peptides form more hydrogen bonds and hydrophobic interactions with T1R1/T1R3. Amino acids D, E, Q, K, and R were critical for umami taste. This study provides an efficient tool for rapid umami peptide screening and expands the repository.

Cross-modal correspondence between visual information and taste: Deciphering the relationship between color and umami using hydrolysates of salmon head as a case study

In this study, the preliminary exploration of cross-modal correspondence between visual information and umami taste was performed. To investigate the relationship between color and perception of umami, the hydrolysates of salmon head was identified as a case study. Nine novel umami peptides were identified and screened from 833 peptides by using UPLC-MS/MS combined with iUmami-SCM and UMPred-FRL protocols. The interaction between umami peptides and T1R1/T1R3 was examined using molecular docking simulation. Through systematic sensory evaluation, threshold measurement, and Pearson correlation analysis, it was demonstrated that both purple and green significantly enhanced umami perception, resulting in an increase of umami intensity by 17.2 % and 14.1 %, respectively. In contrast, dull colors such as black and brown exhibited higher thresholds compared to colorless umami peptide solution, and the dose-response effect was not found to be significant. This phenomenon may involve color stimuli that activate brain regions associated with taste processing, thus influencing the perception of umami.

Analysis of the mechanism of difference in umami peptides from oysters (Crassostrea ariakensis) prepared by trypsin hydrolysis and boiling through hydrogen bond interactions

This study compares umami peptides prepared by trypsin hydrolysis and boiling and analyzes their umami intensity and characteristics. Using a taste reconstitution model and taste evaluation analysis, the study revealed that umami peptides prepared by boiling have a higher umami contribution. Myosin and heat shock protein were identified as marker proteins for revealing differences of cleavage sites. Boiling releases a higher proportion of acidic amino acids at the protein cleavage sites p1-p1', whereas trypsin hydrolysis releases more basic amino acids. Molecular docking simulation and electrostatic potential observation showed that acidic amino acid residues have a wider binding range with the umami receptor T1R1-VFT. Acidic amino acids lower the isoelectric point (pI) of umami peptides, enhancing their negative charge at pH 7, which are more likely to bind to the positively charged regions of the umami receptor.

Virtual screening of umami peptides during sufu ripening based on machine learning and molecular docking to umami receptor T1R1/T1R3

Umami peptides might significantly contribute to the taste of sufu. However, the inefficiencies of traditional identification methods had great limitations. This study explored a new approach for umami peptides characterization in sufu. Combining peptidomics with machine learning, 637 umami peptides were identified, with their abundance gradually increased during ripening. These peptides were derived from the hydrolysis of 319 precursor proteins from soybeans at various positions, and over 30 % of them derived from 11 major precursor proteins. Thus, five novel umami peptides (DFEGDV, GRGPTVTDP, NDDRDSYNL, RVPAGTTY, and SDNFEY) in ripened sufu were selected via molecular docking. Results indicated the identified peptides could interact with key residues of the umami receptor T1R1/T1R3 through hydrogen bonding and hydrophobic interactions. Sensory evaluation confirmed their umami taste, with thresholds ranging from 0.22 to 0.38 mmol/L. These results broaden our understanding of umami peptide formation during sufu ripening and provide novel insights into their identification.

Identification of novel umami peptides from oyster hydrolysate and the mechanisms underlying their taste characteristics using machine learning

Excessive sodium consumption poses considerable health risks, prompting the exploration of umami peptides as potential alternative for reducing sodium intake. This research investigated umami peptides (PQFAPEED, EEHPVLLTEA and DQAIPNKPEE) using machine learning, determining sensory thresholds to be 0.24, 0.30 and 0.29 mg/mL. Molecular docking studies revealed hydrogen bonds and hydrophobic interactions are vital for their binding to umami receptors T1R1/T1R3, with key residues identified as Val714, Leu852, Gln853 and Glu855. Combination of DQAIPNKPEE with 3 mg/mL sodium chloride (NaCl) closely mimicked the salinity perception of 5 mg/mL NaCl. Additionally, DQAIPNKPEE and PQFAPEED were recognised as salt-enhancing peptides, with Ala283, Glu284, Glu286, Arg294, Arg330 and Arg583 identified as critical amino acid residues of human transmembrane channel-like 4 (TMC4). These peptides substitute chloride ions to activate TMC4, resulting in sensation of saltiness. This study highlights efficacy of machine learning in rapid identification of umami peptides from oysters and taste receptors interactions.

TastePeptides-Meta: A One-Stop Platform for Taste Peptides and Their Structural Derivatives, Including Taste Properties, Interactions, and Prediction Models

Taste peptides have nutritional and sensory properties, and their structural derivatives show unique taste modulation effects. The increasing number of taste peptide candidates requires a fast and accurate screening methodology using advanced detection tools. Notably, existing platforms lack integrated bioinformatics solutions to provide accurate retrieval and prediction capabilities. In response to this need, TastePeptides-Meta is proposed, comprising 2,926 peptides entries, 975 peptide structural derivatives, and 954 synergistic (enhancing) data from 282, 109, and 103 peer-reviewed studies, respectively. It was equipped with corresponding machine learning-driven prediction modules and domain-specific analytical toolkits. As an online interactive platform, TastePeptides-Meta provides multiple interfaces that allow searching, downloading and predicting taste peptides. We believe that the public availability of TastePeptides-Meta and its implementation of standardized data schemas will accelerate mechanistic investigations in the field of taste peptides and the development of data-driven, interpretable models for predicting and exploring taste mechanisms. The TastePeptides-Meta platform can be accessed online at http://www.tastepeptides-meta.com/.

Peptide classification landscape: An in-depth systematic literature review on peptide types, databases, datasets, predictors architectures and performance

Peptides are gaining significant attention in diverse fields such as the pharmaceutical market has seen a steady rise in peptide-based therapeutics over the past six decades. Peptides have been utilized in the development of distinct applications including inhibitors of SARS-COV-2 and treatments for conditions like cancer and diabetes. Distinct types of peptides possess unique characteristics, and development of peptide-specific applications require the discrimination of one peptide type from others. To the best of our knowledge, approximately 230 Artificial Intelligence (AI) driven applications have been developed for 22 distinct types of peptides, yet there remains significant room for development of new predictors. A Comprehensive review addresses the critical gap by providing a consolidated platform for the development of AI-driven peptide classification applications. This paper offers several key contributions, including presenting the biological foundations of 22 unique peptide types and categorizes them into four main classes: Regulatory, Therapeutic, Nutritional, and Delivery Peptides. It offers an in-depth overview of 47 databases that have been used to develop peptide classification benchmark datasets. It summarizes details of 288 benchmark datasets that are used in development of diverse types AI-driven peptide classification applications. It provides a detailed summary of 197 sequence representation learning methods and 94 classifiers that have been used to develop 230 distinct AI-driven peptide classification applications. Across 22 distinct types peptide classification tasks related to 288 benchmark datasets, it demonstrates performance values of 230 AI-driven peptide classification applications. It summarizes experimental settings and various evaluation measures that have been employed to assess the performance of AI-driven peptide classification applications. The primary focus of this manuscript is to consolidate scattered information into a single comprehensive platform. This resource will greatly assist researchers who are interested in developing new AI-driven peptide classification applications.

A novel directed enzymolysis strategy for the preparation of umami peptides in Stropharia rugosoannulata and its mechanism of taste perception

This study aimed to explore the effect of directed enzymolysis on the umami characteristics of S. rugosoannulata, clarify the flavour formation mechanism of umami peptides. We expressed a new aminopeptidase (DNPEP) and obtained the umami peptides of S. rugosoannulata by alkaline protease and DNPEP. The optimal enzymolysis conditions were temperature 55 °C, solid-liquid ratio 1:20 (g/mL), alkaline protease enzymolysis (60 min, 0.5 %, pH 9.0), and DNPEP enzymolysis (80 min, 0.3 %, pH 8.0). The umami peptide components were separated by ultrafiltration and gel filtration chromatography. Six umami peptides (EEAKFN, KAELDLH, LADVEEDK, LKEAHDVA, AHLDYGDGK, and LGKSEDDVSK) were identified by LC-MS/MS and virtual screening, and the umami thresholds of the peptides were 0.15-1.09 mmol/L. Molecular simulations revealed that the amino acid residues Glu301, Ser217, Asp218, and Arg277 were crucial in the binding of the umami peptide to the T1R1/T1R3. Therefore, this study provides a theoretical basis for the development of mushroom condiments.

Identification and characterization of umami-ACE inhibitory peptides from traditional fermented soybean curds

Fermented soybean curds (FSC) are popular because of its umami taste. Its bioactivities are of interest. Peptides in FSC were identified using nano-HPLC-MS/MS, and 11 candidate peptides showing potential umami and ACE inhibitory activities were screened using various databases. Pharmacophore model analysis showed their high probability of ACE inhibition with fit values >2, which showed the peptides bound to umami receptors and ACE mainly through hydrogen bond, and electrostatic and hydrophobic interactions. Additionally, their docking and interaction energy were independent of the peptide length. Three high umami-ACE inhibitory peptides (VE, FEF, and WEEF) were synthesized. Their umami thresholds were WEEF (0.32 mM) < FEF (0.55 mM) < VE (1.10 mM), while their IC50 were WEEF (85 ± 2 μM) < FEF (170 ± 10 μM) < VE (205 ± 5 μM). NO and ET-1 production were dose-dependent with WEEF showing the best ACE inhibitory activity. The results allowed identification of effective umami agents and ACE inhibitory peptides from fermented soybean products. It could also be useful method for screening potential umami-ACE inhibitory peptides.

ESMR4FBP: A pLM-based regression prediction model for specific properties of food-derived peptides optimized multiple bionic metaheuristic algorithms

Due to the growing emphasis on food safety, peptide research is increasingly focusing on food sources. Traditional methods for determining peptide properties are expensive. While artificial intelligence (AI) models can reduce cost, existing peptide models often lack accuracy. This study aimed to develop a regression model capable of predicting peptide properties. We integrated the ESM-2 model with the LSTM architecture and optimized the model structure using three metaheuristic algorithms, including WOA, SSA, and HHO. Using an antioxidant tripeptide dataset, our model achieved an R2 of 0.9458 and RMSE of 0.3135, outperforming the state-of-the-art (SOTA) model by 11.66 % and 50.00 %, respectively. The developed model was further applied to the bitter peptide dataset, resulting in R2 of 0.8385 and RMSE of 0.4414, respectively. These results suggest that our model has the potential to accurately predict the properties of various types of peptides.

Screening and identification of novel umami peptides from yeast proteins: Insights into their mechanism of action on receptors T1R1/T1R3

This study aimed to unravel the peptide profiles of six distinct yeast protein samples and identify novel umami peptides within them. Peptide characteristics analysis support the proposition that yeast protein peptide pools represent exceptional reservoirs of umami peptides. Nine potential umami peptides were screened using the iUmami_SCM, UMPred-FRL, Umami_YYDS, Umami-MRNN, Innovagen, Expasy-ProtParam, and ToxinPred tools. Peptides AGVEDVY, LFEQHPEYRK, AFDVQ, GPTVEEVD, NVVAGSDLR, ATNGSR, and VEVVALND (1 mg/mL) were confirmed to possess umami taste, and the first five peptides exhibited significant umami-enhancing effects on 0.35 % monosodium glutamate. Molecular docking indicated that peptide residues His, Arg, Tyr, Asp, Gln, Thr, Ser, and Glu primarily bound to His71, Ser107/109/148, Asp147/218, and Arg277 of T1R1 and Ser104/146, His145, Asp216, Tyr218, and Ala302 of T1R3 through hydrogen bonds. This study enriches the umami peptide repository for potential food additive use and establishes a theoretical foundation for exploring taste compounds in yeast proteins and their broader applications.

Artificial intelligence and food flavor: How AI models are shaping the future and revolutionary technologies for flavor food development

The food flavor science, traditionally reliant on experimental methods, is now entering a promising era with the help of artificial intelligence (AI). By integrating existing technologies with AI, researchers can explore and develop new flavor substances in a digital environment, saving time and resources. More and more research will use AI and big data to enhance product flavor, improve product quality, meet consumer needs, and drive the industry toward a smarter and more sustainable future. In this review, we elaborate on the mechanisms of flavor recognition and their potential impact on nutritional regulation. With the increase of data accumulation and the development of internet information technology, food flavor databases and food ingredient databases have made great progress. These databases provide detailed information on the nutritional content, flavor molecules, and chemical properties of various food compounds, providing valuable data support for the rapid evaluation of flavor components and the construction of screening technology. With the popularization of AI in various fields, the field of food flavor has also ushered in new development opportunities. This review explores the mechanisms of flavor recognition and the role of AI in enhancing food flavor analysis through high-throughput omics data and screening technologies. AI algorithms offer a pathway to scientifically improve product formulations, thereby enhancing flavor and customized meals. Furthermore, it discusses the safety challenges of integrating AI into the food flavor industry.

Pred-AHCP: Robust Feature Selection-Enabled Sequence-Specific Prediction of Anti-Hepatitis C Peptides via Machine Learning

Every year, an estimated 1.5 million people worldwide contract Hepatitis C, a significant contributor to liver problems. Although many studies have explored machine learning's potential to predict antiviral peptides, very few have addressed the problem of predicting peptides against specific viruses such as Hepatitis C. In this study, we demonstrate the application and fine-tuning of machine learning (ML) algorithms to predict peptides that are effective against Hepatitis C virus (HCV). We developed a fine-tuned and explainable ML model that harnesses the amino acid sequence of a peptide to predict its anti-hepatitis C potential. Specifically, features were computed based on sequence and physicochemical properties. The feature selection was performed using a combined strategy of mutual information and variance inflation factor. This facilitated the removal of redundant and multicollinear features, enhancing the model's generalizability in predicting anti-hepatitis C peptides (AHCPs). The model using the random forest algorithm produced the best performance with an accuracy of about 92%. The feature analysis highlights that the distributions of hydrophobicity, polarizability, coil-forming residues, frequency of glycine residues and the existence of dipeptide motifs VL, LV, and CC emerged as the key predictors for identifying AHCPs targeting different components of HCV. The developed model can be accessed through the Pred-AHCP web server, provided at http://tinyurl.com/web-Pred-AHCP. This resource facilitates the prediction and re-engineering of AHCPs for designing peptide-based therapeutics while also proposing an exploration of similar strategies for designing peptide inhibitors effective against other viruses. The developed ML model can also be used for validating peptide sequences generated using generative artificial intelligence methods for further optimization.

Investigating the effects of low-salt processing on the umami peptides of dry-cured ham using peptidomics techniques

This study investigated the effect of low-salt processing on the umami peptide profile of dry-cured hams. Peptidomics data showed 633 umami peptides in the low- and full-salt groups. Among them, 36.2% and 26.5% of shared umami peptides in the low-salt group were significantly down- and up-regulated in relative abundance. Multivariate statistical analysis showed 1011 significantly different umami peptides (SDUPs) in the low- and full-salt groups. Creatine kinase M-type (CKM) and fast skeletal muscle troponin T (TnTf) were the main precursor proteins of these SDUPs. At the end of processing, the relative expression of CKM was lower in the low-salt group than in the full-salt group (P < 0.05), but there was no significant difference in TnTf. More dipeptidyl peptidase cleavage sites were observed in CKM and TnTf proteins in the low-salt group.

Computational screening of umami tastants using deep learning

Umami, a fundamental human taste modality, refers to the savory flavors in meats and broths, often associated with monosodium glutamate and protein richness. With limited knowledge of umami molecules, the food industry seeks efficient approaches for identifying novel tastants. In this study, we have devised a virtual screening pipeline for identifying highly potent umami tastants from large molecular databases. We curated the most extensive classification dataset containing 439 umami and 428 non-umami molecules and trained a transformer-based architecture to differentiate between the two classes, achieving 93% accuracy. Additionally, we built a neural network model for predicting the potency of umami compounds, the first effort of its kind. The classification and potency prediction models were combined with similarity analysis and toxicity screening to build an end-to-end virtual framework for the rational discovery of novel tastants. We applied this framework to the FooDB database containing around 70,000 molecules as an illustrative use case for screening potent umami compounds. The screened molecules were validated using molecular docking with the umami taste receptor. This study demonstrates the potential of data-driven methods in discovering new tastants from structural and chemical features of molecules and proposes an efficient implementation for industrial applications.

LLM4THP: a computing tool to identify tumor homing peptides by molecular and sequence representation of large language model based on two-layer ensemble model strategy

Tumor homing peptides (THPs) have a distinctive capacity to specifically attach to tumor cells, providing a promising approach for targeted cancer treatment and detection. Although THPs have the potential for significant impact, their detection by conventional methods is both time-consuming and expensive. To tackle this issue, we provide LLM4THP, an innovative computational approach that utilizes large language models (LLMs) to quickly and effectively detect THPs. LLM4THP utilizes two protein LLMs, ESM2 and Prot_T5_XL_UniRef50, to encode peptide sequences. This allows for the capture of complex patterns and relationships within the peptide data. In addition, we utilize inherent sequence characteristics such as Amino Acid Composition (AAC), Pseudo Amino Acid Composition (PAAC), Amphiphilic Pseudo Amino Acid Composition (APAAC), and Composition, Transition, and Distribution (CTD) to improve the representation of peptides. The RDKitDescriptors feature representation approach transforms peptide sequences into molecular objects and computes chemical characteristics, resulting in enhanced THP identification. The LLM4THP ensemble strategy incorporates various features into a two-layer learning architecture. The first layer consists of LightGBM, XGBoost, Random Forest, and Extremely Randomized Trees, which generate a set of meta results. The second layer utilizes Logistic Regression to further refine the identification of sequences as either THP or non-THP. LLM4THP exhibits exceptional performance compared to the most advanced methods, showcasing enhancements in accuracy, Matthew's correlation coefficient, F1 score, area under the curve, and average precision. The source code and dataset can be accessed at the following URL: https://github.com/abcair/LLM4THP.

Identification and screening of umami peptides from skipjack tuna (Katsuwonus pelamis) hydrolysates using EAD/CID based micro-UPLC-QTOF-MS and the molecular interaction with T1R1/T1R3 taste receptor

In this study, the enzymatic hydrolysates of skipjack tuna, Katsuwonus pelamis, were purified by ultrafiltration and further identified through micro-ultra-performance liquid chromatography-quadrupole time-of-flight mass spectrometry (micro-UPLC-QTOF-MS). The potential umami peptides were identified using both conventional collision-induced dissociation (CID) and novel electron-activated dissociation (EAD) fragmentation techniques. Nine novel umami peptides with iUmami-SCM > 588 were screened. Sensory evaluation and electronic tongue analysis were performed to confirm the taste characteristics of the umami peptides, indicating that these umami peptides all exhibited varying degrees of umami taste. Molecular docking and molecular dynamics simulation were utilized to investigate the interaction with T1R1/T1R3 taste receptors. The docking results revealed that Asp234, Ser23, Glu231, and Ile237 appeared most frequently in all docking sites and formed stable complexes through hydrogen bonding and electrostatic interactions. Furthermore, molecular dynamics simulation allowed for a more comprehensive analysis of their interactions within a dynamic environment, providing a deeper understanding of the umami perception mechanism involving umami peptides and receptors.

Advancements in production, assessment, and food applications of salty and saltiness-enhancing peptides: A review

Salt is important for food flavor, but excessive sodium intake leads to adverse health consequences. Thus, salty and saltiness-enhancing peptides are developed for sodium-reduction products. This review elucidates saltiness perception process and analyses correlation between the peptide structure and saltiness-enhancing ability. These peptides interact with taste receptors to produce saltiness perception, including ENaC, TRPV1, and TMC4. This review also outlines preparation, isolation, purification, characterization, screening, and assessment techniques of these peptides and discusses their potential applications. These peptides are from various sources and produced through enzymatic hydrolysis, microbial fermentation, or Millard reaction and then separated, purified, identified, and screened. Sensory evaluation, electronic tongue, bioelectronic tongue, and cell and animal models are the primary saltiness assessment approaches. These peptides can be used in sodium-reduction food products to produce "clean label" items, and the peptides with biological activity can also serve as functional ingredients, making them very promising for food industry.

VmmScore: An umami peptide prediction and receptor matching program based on a deep learning approach

Peptides, with recognized physiological and medical implications, such as the ability to lower blood pressure and lipid levels, are central to our research on umami taste perception. This study introduces a computational strategy to tackle the challenge of identifying optimal umami receptors for these peptides. Our VmmScore algorithm includes two integral components: Mlp4Umami, a predictive module that evaluates the umami taste potential of peptides, and mm-Score, which enhances the receptor matching process through a machine learning-optimized molecular docking and scoring system. This system encompasses the optimization of docking structures, clustering of umami peptides, and a comparative analysis of docking energies across peptide clusters, streamlining the receptor identification process. Employing machine learning, our method offers a strategic approach to the intricate task of umami receptor determination. We undertook virtual screening of peptides derived from Lateolabrax japonicus, experimentally verifying the umami taste of three identified peptides and determining their corresponding receptors. This work not only advances our understanding of the mechanisms behind umami taste perception but also provides a rapid and cost-effective method for peptide screening. The source code is publicly accessible at https://github.com/heyigacu/mlp4umami/, encouraging further scientific exploration and collaborative efforts within the research community.

UmamiPreDL: Deep learning model for umami taste prediction of peptides using BERT and CNN

Taste is crucial in driving food choice and preference. Umami is one of the basic tastes defined by characteristic deliciousness and mouthfulness that it imparts to foods. Identification of ingredients to enhance umami taste is of significant value to food industry. Various models have been shown to predict umami taste using feature encodings derived from traditional molecular descriptors such as amphiphilic pseudo-amino acid composition, dipeptide composition, and composition-transition-distribution. Highest reported accuracy of 90.5 % was recently achieved through novel model architecture. Here, we propose use of biological sequence transformers such as ProtBert and ESM2, trained on the Uniref databases, as the feature encoders block. With combination of 2 encoders and 2 classifiers, 4 model architectures were developed. Among the 4 models, ProtBert-CNN model outperformed other models with accuracy of 95 % on 5-fold cross validation data and 94 % on independent data.

Predicting multiple taste sensations with a multiobjective machine learning method

Taste perception plays a pivotal role in guiding nutrient intake and aiding in the avoidance of potentially harmful substances through five basic tastes - sweet, bitter, umami, salty, and sour. Taste perception originates from molecular interactions in the oral cavity between taste receptors and chemical tastants. Hence, the recognition of taste receptors and the subsequent perception of taste heavily rely on the physicochemical properties of food ingredients. In recent years, several advances have been made towards the development of machine learning-based algorithms to classify chemical compounds' tastes using their molecular structures. Despite the great efforts, there remains significant room for improvement in developing multi-class models to predict the entire spectrum of basic tastes. Here, we present a multi-class predictor aimed at distinguishing bitter, sweet, and umami, from other taste sensations. The development of a multi-class taste predictor paves the way for a comprehensive understanding of the chemical attributes associated with each fundamental taste. It also opens the potential for integration into the evolving realm of multi-sensory perception, which encompasses visual, tactile, and olfactory sensations to holistically characterize flavour perception. This concept holds promise for introducing innovative methodologies in the rational design of foods, including pre-determining specific tastes and engineering complementary diets to augment traditional pharmacological treatments.

Sensoproteomic Characterization of Lactobacillus Johnsonii-Fermented Pea Protein-Based Beverage: A Promising Strategy for Enhancing Umami and Kokumi Sensations while Mitigating Bitterness

This study investigated the mechanism underlying the flavor improvement observed during fermentation of a pea protein-based beverage using Lactobacillus johnsonii NCC533. A combination of sensomics and sensoproteomics approach revealed that the fermentation process enriched or generated well-known basic taste ingredients, such as amino acids, nucleotides, organic acids, and dipeptides, besides six new taste-active peptide sequences that enhance kokumi and umami notes. The six new umami and kokumi enhancing peptides, with human recognition thresholds ranging from 0.046 to 0.555 mM, are produced through the degradation of Pisum sativum's storage protein. Our findings suggest that compounds derived from fermentation enhance umami and kokumi sensations and reduce bitterness, thus improving the overall flavor perception of pea proteins. In addition, the analysis of intraspecific variations in the proteolytic activity of L. johnsonii and the genome-peptidome correlation analysis performed in this study point at cell-wall-bound proteinases such as PrtP and PrtM as the key genes necessary to initiate the flavor improving proteolytic cascade. This study provides valuable insights into the molecular mechanisms underlying the flavor improvement of pea protein during fermentation and identifies potential future research directions. The results highlight the importance of combining fermentation and senso(proteo)mics techniques in developing tastier and more palatable plant-based protein products.

Taste properties and mechanism of umami peptides from fermented goose bones based on molecular docking and molecular dynamics simulation using umami receptor T1R1/T1R3

Umami peptides are valuable taste substances due to their exceptional taste and beneficial properties. In this study, purification of fermented goose bone broth was performed using continuous chromatography and sensory analysis, and after identification through nano-LC-MS/MS, four umami peptides were screened out by umami activity prediction and molecular docking, which are VGYDAE, GATGRDGAR, GETGEAGER, and GETGEAGERG derived from collagen. Sensory analysis indicated that they were also umami-enhancing, with thresholds ranging from 0.41 to 1.15 mmol/L, among which GER9 was the best. Combining the results of docking and molecular dynamics simulation, it was known that hydrogen bond and electrostatic interactions were vital in driving the umami formation. Moreover, Glu, Ser, and Asp of umami receptor T1R1/T1R3 were the key residues for the binding between four umami peptides and T1R1/T1R3. These findings provide novel insights into the high-value utilization of goose bones and offer profound theoretical guidance for understanding the umami mechanism.

Exploring the Relationship between Small Peptides and the T1R1/T1R3 Umami Taste Receptor for Umami Peptide Prediction: A Combined Approach

Umami peptides are known for enhancing the taste experience by binding to oral umami T1R1 and T1R3 receptors. Among them, small peptides (composed of 2-4 amino acids) constitute nearly 40% of reported umami peptides. Given the diversity in amino acids and peptide sequences, umami small peptides possess tremendous untapped potential. By investigating 168,400 small peptides, we screened candidates binding to T1R1/T1R3 through molecular docking and molecular dynamics simulations, explored bonding types, amino acid characteristics, preferred binding sites, etc. Utilizing three-dimensional molecular descriptors, bonding information, and a back-propagation neural network, we developed a predictive model with 90.3% accuracy, identifying 24,539 potential umami peptides. Clustering revealed three classes with distinct logP (-2.66 ± 1.02, -3.52 ± 0.93, -2.44 ± 1.23) and asphericity (0.28 ± 0.12, 0.26 ± 0.11, 0.25 ± 0.11), indicating significant differences in shape and hydrophobicity (P < 0.05) among potential umami peptides binding to T1R1/T1R3. Following clustering, nine representative peptides (CQ, DP, NN, CSQ, DMC, TGS, DATE, HANR, and STAN) were synthesized and confirmed to possess umami taste through sensory evaluations and electronic tongue analyses. In summary, this study provides insights into exploring small peptide interactions with umami receptors, advancing umami peptide prediction models.

CELA-MFP: a contrast-enhanced and label-adaptive framework for multi-functional therapeutic peptides prediction

Functional peptides play crucial roles in various biological processes and hold significant potential in many fields such as drug discovery and biotechnology. Accurately predicting the functions of peptides is essential for understanding their diverse effects and designing peptide-based therapeutics. Here, we propose CELA-MFP, a deep learning framework that incorporates feature Contrastive Enhancement and Label Adaptation for predicting Multi-Functional therapeutic Peptides. CELA-MFP utilizes a protein language model (pLM) to extract features from peptide sequences, which are then fed into a Transformer decoder for function prediction, effectively modeling correlations between different functions. To enhance the representation of each peptide sequence, contrastive learning is employed during training. Experimental results demonstrate that CELA-MFP outperforms state-of-the-art methods on most evaluation metrics for two widely used datasets, MFBP and MFTP. The interpretability of CELA-MFP is demonstrated by visualizing attention patterns in pLM and Transformer decoder. Finally, a user-friendly online server for predicting multi-functional peptides is established as the implementation of the proposed CELA-MFP and can be freely accessed at http://dreamai.cmii.online/CELA-MFP.

Novel Umami Peptides from Mushroom (Agaricus bisporus) and Their Umami Enhancing Effect via Virtual Screening and Molecular Simulation

This study aimed to identify novel umami peptides in Agaricus bisporus and investigate their umami enhancing effect. We virtually screened 155 potential umami peptides from the ultrasound-assisted A. bisporus hydrolysate according to Q values, iUmami-SCM, Umami_YYDS, and Tastepeptides_DM models, and molecular docking. Five peptides (AGKNTNGSQF, DEAVARGATF, REESDFQSSF, SEETTTGVHH, and WNNDAFQSSTN) were synthesized for sensory evaluation and kinetic analysis. The result showed that the umami thresholds of the five peptides were in the range of 0.21-0.40 mmol/L. Notably, REESDFQSSF, SEETTTGVHH, and WNNDAFQSSTN had low dissociation constant (KD) values and high affinity for the T1R1-VFT receptor. The enhancing effect of the three peptides with MSG or IMP was investigated by sensory evaluation, kinetic analysis, and molecular dynamics simulations. In stable complexes, ARG_277 in T1R1 played a major role in umami peptide binding to T1R1-VFT. These results provide a theoretical basis for future screening of umami peptides and improving the umami taste of food containing mushrooms.

Identification, screening and taste mechanisms analysis of two novel umami pentapeptides derived from the myosin heavy chain of Atlantic cod (Gadus morhua)

Umami peptides are new ingredients for the condiment and seasoning industries, with healthy and nutrition characteristics, some of which were identified from aquatic proteins. This study aims to further explore novel umami peptides from Atlantic cod (Gadus morhua) by combining in silico, nano-HPLC-MS/MS, sensory evaluation, and electronic tongue analysis. Two novel peptides, Leu-Val-Asp-Lys-Leu (LVDKL) and Glu-Ser-Lys-Ile-Leu (ESKIL), from the myosin heavy chain of Atlantic cod (Gadus morhua), were screened and confirmed to have strong umami tastes with the thresholds of 0.427 mM and 0.574 mM, respectively. The molecular docking was adopted to explore the interactions between the umami peptides and the umami taste receptor T1R1/T1R3, which showed that the umami peptides interacted with T1R1/T1R3 mainly by electrostatic interaction, hydrogen bond interaction, and hydrophobic interaction. Furthermore, the physicochemical properties of the peptides were investigated by in silico methods and cell viability experiments. This study will provide a better understanding of the umami taste in Atlantic cod and will promote the development of condiments and seasonings.

Bioinformatics and bioactive peptides from foods: Do they work together?

We live in the Big Data Era which affects many aspects of science, including research on bioactive peptides derived from foods, which during the last few decades have been a focus of interest for scientists. These two issues, i.e., the development of computer technologies and progress in the discovery of novel peptides with health-beneficial properties, are closely interrelated. This Chapter presents the example applications of bioinformatics for studying biopeptides, focusing on main aspects of peptide analysis as the starting point, including: (i) the role of peptide databases; (ii) aspects of bioactivity prediction; (iii) simulation of peptide release from proteins. Bioinformatics can also be used for predicting other features of peptides, including ADMET, QSAR, structure, and taste. To answer the question asked "bioinformatics and bioactive peptides from foods: do they work together?", currently it is almost impossible to find examples of peptide research with no bioinformatics involved. However, theoretical predictions are not equivalent to experimental work and always require critical scrutiny. The aspects of compatibility of in silico and in vitro results are also summarized herein.

Virtual screening and characteristics of novel umami peptides from porcine type I collagen

This study aimed to rapidly and precisely discover novel umami peptides from porcine type I collagen using virtual screening, sensory evaluation and molecular docking simulation. Porcine type I collagen was hydrolyzed in silico and six umami peptide candidates (CN, SM, CRD, GESMTDGF, MS, DGC) were shortlisted via umami taste, bioactivity, toxicity, allergenicity, solubility and stability predictions. The sensory evaluation confirmed that these peptides exhibited umami taste, with CRD, GESMTDGF and DGC displaying higher umami intensity and significant umami-enhancing effects in 0.35% sodium glutamate solution. Molecular docking predicted that Ser 276/384/385 of T1R1 and Asn68, Val277, Thr305, Ser306, Leu385 of T1R3 may also play critical roles in binding umami peptides. The umami taste of peptides may be perceived mainly through the formation of hydrogen bonds with the hydrophilic amino acids of T1R1/T1R3. This work provided a robust procedure and guidance to develop novel umami peptides from food byproducts.

Noteworthy Consensus Effects of D/E Residues in Umami Peptides Used for Designing the Novel Umami Peptides

Aspartic acid (D) and glutamic acid (E) play vital roles in the umami peptides. To understand their exact mechanism of action, umami peptides were collected and cut into 1/2/3/4 fragments. Connecting D/E to the N/C-termini of the fragments formed D/E consensus effect groups (DEEGs), and all fragments containing DEEG were summarized according to the ratio and ranking obtained in the above four situations. The interaction patterns between peptides in DEEG and T1R1/T1R3-VFD were compared by statistical analysis and molecular docking, and the most conservative contacts were found to be HdB_277_ARG and HdB_148_SER. The molecular docking score of the effector peptides significantly dropped compared to that of their original peptides (-1.076 ± 0.658 kcal/mol, p value < 0.05). Six types of consensus fingerprints were set according to the Top7 contacts. The exponential of relative umami was linearly correlated with ΔGbind (R2 = 0.961). Under the D/E consensus effect, the electrostatic effect of the umami peptide was improved, and the energy gap between the highest occupied molecular orbital-the least unoccupied molecular orbital (HOMO-LUMO) was decreased. The shortest path map showed that the peptides had similar T1R1-T1R3 recognition pathways. This study helps to reveal umami perception rules and provides support for the efficient screening of umami peptides based on the material richness in D/E sequences.

Combining molecular docking and molecular dynamics simulation to discover four novel umami peptides from tuna skeletal myosin with sensory evaluation validation

Umami peptides are an important component of food flavoring agents and have high nutritional value. This work aimed to identify umami peptides from tuna skeletal myosin using a new model method of computer simulation, explore their umami mechanism, and further validate the umami tastes with sensory evaluation. Umami peptides LADW, MEIDD, VAEQE, and EEAEGT were discovered, and all of them bound to taste type 1 receptor 1 and receptor 3 via hydrogen bonds and van der Waals forces to form stable complexes. LADW exhibited the best affinity energy and binding capability. Sensory evaluation and electronic tongue confirmed that all peptides possessed an umami taste, and LADW exhibited the strongest umami intensity. This study not only explored four novel umami peptides to improve the value of tuna skeletal myosin but also provided a new method for the rapid discovery of umami peptides.

A screening strategy for identifying umami peptides with multiple bioactivities from Stropharia rugosoannulata using in silico approaches and SPR sensing

Umami peptides from natural resources have garnered considerable attention for their potential bioactivities and flavor-enhancing characteristics. In this study, we constructed a database comprising 123 peptides from Stropharia rugosoannulata and screened for umami peptides with both angiotensin I-converting enzyme (ACE) and dipeptidyl peptidase-4 (DPP-IV) inhibitory activities using online prediction tools and molecular docking, and further confirmed by SPR sensing, intelligent sensory and activities test. Five peptides with varying chain lengths were synthesized and by evaluations analyses they exhibited strong umami, with thresholds ranging from 0.105 mmol/L to 0.547 mmol/L. According to the targeted SPR molecular interaction analysis, umami peptides and hT1R3 receptor exhibited a "fast-on/fast-off" binding mode with stronger intensity and persistence than MSG. Furthermore, in vitro experiments revealed that five peptides showed potent ACE and DPP-IV inhibitory activities. Notably, the EAF inhibitory activity was the most significant among the peptides. This comprehensive screening strategy provides a rapid approach for identifying high-sensitivity umami peptides with bioactivities.

Peptidomics Screening and Molecular Docking with Umami Receptors T1R1/T1R3 of Novel Umami Peptides from Oyster (Crassostrea gigas) Hydrolysates

In this study, novel umami peptides were prepared from oyster (Crassostrea gigas) hydrolysates, and their umami mechanisms were investigated. Umami fractions G2 and G3 were isolated by gel filtration chromatography (GFC) and sensory evaluation. The umami scores of the G2 and G3 fractions were 7.8 ± 0.12 and 7.5 ± 0.18, respectively. 36 potential umami peptides with molecular weights below 1500 Da, E and D accounting for >30% of the peptides and iUmami-SCM > 588 were screened by peptidomics. Peptide source analysis revealed that myosin, paramyosin, and sarcoplasmic were the major precursor proteins for these peptides. The electronic tongue results demonstrated that the synthetic peptides DPNDPDMKY and NARIEELEEE possessed an umami characteristic, whereas SIEDVEESRNK and ISIEDVEESRNK possessed a saltiness characteristic. Additionally, molecular docking results indicated that the umami peptide (DPNDPDMKY, NARIEELEEE, SIEDVEESRNK, and ISIEDVEESRNK) binds to H145, S276, H388, T305, Y218, D216, and Q389 residues in the T1R3 taste receptor via a conventional hydrogen bond and a carbon-hydrogen bond. This research provides a new strategy for the screening of umami peptides.

Origins, Technological Advancement, and Applications of Peptidomics

Peptidomics is the comprehensive characterization of peptides from biological sources instead of heading for a few single peptides in former peptide research. Mass spectrometry allows to detect a multitude of peptides in complex mixtures and thus enables new strategies leading to peptidomics. The term was established in the year 2001, and up to now, this new field has grown to over 3000 publications. Analytical techniques originally developed for fast and comprehensive analysis of peptides in proteomics were specifically adjusted for peptidomics. Although it is thus closely linked to proteomics, there are fundamental differences with conventional bottom-up proteomics. Fundamental technological advancements of peptidomics since have occurred in mass spectrometry and data processing, including quantification, and more slightly in separation technology. Different strategies and diverse sources of peptidomes are mentioned by numerous applications, such as discovery of neuropeptides and other bioactive peptides, including the use of biochemical assays. Furthermore, food and plant peptidomics are introduced similarly. Additionally, applications with a clinical focus are included, comprising biomarker discovery as well as immunopeptidomics. This overview extensively reviews recent methods, strategies, and applications including links to all other chapters of this book.

Excavation, identification and structure-activity relationship of heat-stable umami peptides in the processing of Wuding chicken

Umami peptides from different stages of Wuding chicken processing were discovered, isolated, and purified using ultrafiltration membrane, gel filtration chromatography, and reversed-phase high-performance liquid chromatography, and the binding mechanism was explored. Twelve umami peptides were found by nano-scale liquid chromatography-tandem mass spectrometry, three of which (HLEEEIK, LDDALR, and ELY) existed throughout the processing step. The umami score and the frequency of active fragments of umami were highest for LEEEL, followed by EEF. The main active sites between umami peptide and receptor T1R1/T1R3 were Tyr262, Glu325, and Glu292, and hydrophobic interaction and hydrogen bonding were the main forces, and bitter amino acids were also important components of umami peptides. It was found for the first time that heat-stable umami peptides exist in Wuding chickens, which provides a basis for the identification and screening of umami peptides in local chickens, and also helps to study the structure-activity relationship of umami peptides.

Identification of novel umami peptides from yeast extract and the mechanism against T1R1/T1R3

Yeast extract was separated by using ultrafiltration, gel filtration chromatography, and preparative high-performance liquid chromatography for analyzing the umami mechanism. 13 kinds of umami peptides were screened out from 73 kinds of peptides which were identified in yeast extract using nanoscale ultra-performance liquid chromatography-tandem mass spectrometry and virtual screening. The umami peptides were found to have a threshold range of 0.07-0.61 mM. DWTDDVEAR exhibited a strong umami taste with a pronounced enhancement effect for monosodium glutamate. Molecular docking studies revealed that specific amino acid residues in the T1R1 subunit, including Arg316, Ser401, and Asp315, played a critical role in the umami perception with these peptides. Overall, the study highlights the potential of natural flavor enhancers and provides insights into the mechanism of umami taste perception.

Identification, Characterization, and Receptor Binding Mechanism of New Umami Peptides from Traditional Fermented Soybean Paste (Dajiang)

Dajiang, a traditional Chinese condiment, is made from fermented soybeans. It is highly popular among consumers as a result of its delicious umami flavor, which mainly originates from umami peptides. To examine the mechanism of umami taste in Dajiang, we selected Dajiang samples with strong umami taste and subjected them to purification and identification analysis using ethanol precipitation, gel chromatography, reversed-phase high-performance liquid chromatography, and ultraperformance liquid chromatography-tandem mass spectrometry. Subsequently, on the basis of toxicity and umami prediction analysis, we screened, synthesized, and characterized three novel bean umami peptides in Dajiang: TLGGPTTL, 758.4174 Da; GALEQILQ, 870.4811 Da; and HSISDLQ, 911.4713 Da. Their sensory threshold values were 0.25, 0.40, and 0.17 mmol/L, respectively. Furthermore, molecular docking results showed that hydrogen-bonding and hydrophobic interactions are important interaction forces in the binding of umami peptide to taste receptors. Ser147 and Glu148 of the T1R3 taste receptor are important amino acid residues for binding of the three umami peptides. This study uncovers the mechanism of umami-peptide-driven flavor in fermented soybean products.

Classification of tastants: A deep learning based approach

Predicting the taste of molecules is of critical importance in the food and beverages, flavor, and pharmaceutical industries for the design and screening of new tastants. In this work, we have built deep learning models to classify sweet, bitter, and umami molecules- the three basic tastes whose sensation is mediated by G protein-coupled receptors. An extensive dataset containing 1466 bitter, 1764 sweet, and 238 umami tastants was curated from existing literature. We analyzed the chemical characteristics of the molecules, with special focus on the presence of different functional groups. A deep neural network model based on molecular descriptors and a graph neural network model were trained for taste prediction. The class imbalance due to fewer umami molecules was tackled using special sampling techniques. Both models show comparable performance during evaluation, but the graph-based model can learn task-specific representations from the molecular structure without requiring handcrafted features. We further explain the deep neural network predictions using Shapley additive explanations. Finally, we demonstrated the applicability of the models by screening bitter, sweet, and umami molecules from a large food database. This study develops an in-silico approach to classify molecules based on their taste by leveraging the recent progress in deep learning, which can serve as a powerful tool for tastant design.

Umami-BERT: An interpretable BERT-based model for umami peptides prediction

Umami peptides have received extensive attention due to their ability to enhance flavors and provide nutritional benefits. The increasing demand for novel umami peptides and the vast number of peptides present in food call for more efficient methods to screen umami peptides, and further exploration is necessary. Therefore, the purpose of this study is to develop deep learning (DL) model to realize rapid screening of umami peptides. The Umami-BERT model was devised utilizing a novel two-stage training strategy with Bidirectional Encoder Representations from Transformers (BERT) and the inception network. In the pre-training stage, attention mechanisms were implemented on a large amount of bioactive peptides sequences to acquire high-dimensional generalized features. In the re-training stage, umami peptide prediction was carried out on UMP789 dataset, which is developed through the latest research. The model achieved the performance with an accuracy (ACC) of 93.23% and MCC of 0.78 on the balanced dataset, as well as an ACC of 95.00% and MCC of 0.85 on the unbalanced dataset. The results demonstrated that Umami-BERT could predict umami peptides directly from their amino acid sequences and exceeded the performance of other models. Furthermore, Umami-BERT enabled the analysis of attention pattern learned by Umami-BERT model. The amino acids Alanine (A), Cysteine (C), Aspartate (D), and Glutamicacid (E) were found to be the most significant contributors to umami peptides. Additionally, the patterns of summarized umami peptides involving A, C, D, and E were analyzed based on the learned attention weights. Consequently, Umami-BERT exhibited great potential in the large-scale screening of candidate peptides and offers novel insight for the further exploration of umami peptides.

Classification-based machine learning approaches to predict the taste of molecules: A review

The capacity to discriminate safe from dangerous compounds has played an important role in the evolution of species, including human beings. Highly evolved senses such as taste receptors allow humans to navigate and survive in the environment through information that arrives to the brain through electrical pulses. Specifically, taste receptors provide multiple bits of information about the substances that are introduced orally. These substances could be pleasant or not according to the taste responses that they trigger. Tastes have been classified into basic (sweet, bitter, umami, sour and salty) or non-basic (astringent, chilling, cooling, heating, pungent), while some compounds are considered as multitastes, taste modifiers or tasteless. Classification-based machine learning approaches are useful tools to develop predictive mathematical relationships in such a way as to predict the taste class of new molecules based on their chemical structure. This work reviews the history of multicriteria quantitative structure-taste relationship modelling, starting from the first ligand-based (LB) classifier proposed in 1980 by Lemont B. Kier and concluding with the most recent studies published in 2022.

Identifying Umami Peptides Specific to the T1R1/T1R3 Receptor via Phage Display

Umami peptides are small molecular weight oligopeptides that play a role in umami taste attributes. However, the identification of umami peptides is easily limited by environmental conditions, and the abundant source and high chromatographic separation efficiency remain difficult. Herein, we report a robust strategy based on a phage random linear heptapeptide library that targets the T1R1-Venus flytrap domain (T1R1-VFT). Two candidate peptides (MTLERPW and MNLHLSF) were readily identified with high affinity for T1R1-VFT binding (KD of MW-7 and MF-7 were 790 and 630 nM, respectively). The two peptides exhibited umami taste and significantly enhanced the umami intensity when added to the monosodium glutamate solution. Overall, this strategy shows that umami peptides could be developed via phage display technology for the first time. The phage display platform has a promising application to discover other taste peptides with affinity for taste receptors of interest and has more room for improvement in the future.

Preparation of sunflower seed-derived umami protein hydrolysates and their synergistic effect with monosodium glutamate and disodium inosine-5'-monophosphate

Sunflower seeds are rich in protein and can be an excellent raw material for the production of umami peptides. In this study, sunflower seed meal, which was defatted at a low temperature, was taken as the raw material, and proteins were separated, followed by hydrolyzation for 4 h by flavourzyme^® to obtain hydrolysates with strong umami intensity. These hydrolysates were deamidated using glutaminase to increase the umami intensity. The highest umami value of 11.48 was recorded for hydrolysates deamidated for 6 h, and the umami intensity was determined. The umami hydrolysates mixed with 8.92 mmol IMP + 8.02 mmol MSG showed the highest umami value of 25.21. Different concentrations of ethanol were used for further separation of hydrolysates, and the highest umami value of 13.54 was observed for 20% ethanol fraction. The results of this study provide utilization method for sunflower seed meal protein and a theoretical basis for the preparation of umami peptides. PRACTICAL APPLICATION: A large number of sunflower seed meals after oil production are used as feed for livestock and poultry. Sunflower seed meal is rich in protein, and umami amino acid composition in sunflower seed meal is up to 25%-30%, which is potentially an excellent raw material for the production of umami peptides. The umami flavor and synergistic effect of obtained hydrolysates, with MSG and IMP, were analyzed in the present study. We intend to provide a novel way for utilization of protein from sunflower seed meal along with a theoretical basis for the preparation of umami peptides.

Rapid screening based on machine learning and molecular docking of umami peptides from porcine bone

BACKGROUND

The traditional screening method for umami peptide, extracted from porcine bone, was labor-intensive and time-consuming. In this study, the rapid screening method and molecular mechanism of umami peptide was investigated.

RESULTS

This article showed that a more precisely rapid screening method with composite machine learning and molecular docking was used to screen the potential umami peptide from porcine bone. As reference, 24 reported umami peptides were predicated by composite machine learning, with the accuracy of 86.7%. In this study, potential umami peptide sequences from porcine bone were screened by UMPred-FRL, Umami-MRNN Demo, and molecular docking was used to provide further screening. Finally, nine peptides were screened and verified as umami peptides by this method: LREY, HEAL, LAKVH, FQKVVA, HVKELE, AEVKKAP, EAVEKPQS, KALSEEL and KKMFETES. The hydrogen bonding was deemed to be the main interaction force with receptor T1R3, and domain binding sites were Ser146, His121 and Glu277. The result demonstrated the feasibility of machine learning assisted T1R1/T1R3 receptor for rapid screening umami peptides. The screening method would not only adapt to screen umami peptides from porcine bone but possibly applied for other sources. It also provided a reference for rapid screening of umami peptides.

CONCLUSION

The manuscript lays a rapid screening method in screening umami peptide, and nine umami peptides from porcine bone were screened and identified. © 2022 Society of Chemical Industry.

Identification of Novel Umami Peptides in Chicken Breast Soup through a Sensory-Guided Approach and Molecular Docking to the T1R1/T1R3 Taste Receptor

Ultrafiltration combined with nanoliquid chromatography quadrupole time-of-flight mass spectrometry (nano-LC-QTOF-MS) and sensory evaluation was used to separate and identify umami peptides in chicken breast soup. Fifteen peptides with umami propensity scores of >588 were identified from the fraction (molecular weight ≤1 kDa) using nano-LC-QTOF-MS, and their concentrations ranged from 0.02 ± 0.01 to 6.94 ± 0.41 μg/L in chicken breast soup. AEEHVEAVN, PKESEKPN, VGNEFVTKG, GIQKELQF, FTERVQ, and AEINKILGN were considered as umami peptides according to sensory analysis results (detection threshold: 0.18-0.91 mmol/L). The measurement of point of subjective equality showed that these six umami peptides (2.00 g/L) were equivalent to 0.53-0.66 g/L of monosodium glutamate (MSG) in terms of umami intensity. Notably, the sensory evaluation results showed that the peptide of AEEHVEAVN significantly enhanced the umami intensity of the MSG solution and chicken soup models. The molecular docking results showed that the serine residues were the most frequently observed binding sites in T1R1/T1R3. The binding site Ser276 particularly contributed to the formation of the umami peptide-T1R1 complexes. The acidic glutamate residues observed in the umami peptides were also involved in their binding to the T1R1 and T1R3 subunits.

Conserved Sites and Recognition Mechanisms of T1R1 and T2R14 Receptors Revealed by Ensemble Docking and Molecular Descriptors and Fingerprints Combined with Machine Learning

Taste peptides, as an important component of protein-rich foodstuffs, potentiate the nutrition and taste of food. Thereinto, umami- and bitter-taste peptides have been ex tensively reported, while their taste mechanisms remain unclear. Meanwhile, the identification of taste peptides is still a time-consuming and costly task. In this study, 489 peptides with umami/bitter taste from TPDB (http://tastepeptides-meta.com/) were collected and used to train the classification models based on docking analysis, molecular descriptors (MDs), and molecular fingerprints (FPs). A consensus model, taste peptide docking machine (TPDM), was generated based on five learning algorithms (linear regression, random forest, gaussian naive bayes, gradient boosting tree, and stochastic gradient descent) and four molecular representation schemes. Model interpretive analysis showed that MDs (VSA_EState, MinEstateIndex, MolLogP) and FPs (598, 322, 952) had the greatest impact on the umami/bitter prediction of peptides. Based on the consensus docking results, we obtained the key recognition modes of umami/bitter receptors (T1Rs/T2Rs): (1) residues 107S-109S, 148S-154T, 247F-249A mainly form hydrogen bonding contacts and (2) residues 153A-158L, 163L, 181Q, 218D, 247F-249A in T1R1 and 56D, 106P, 107V, 152V-156F, 173K-180F in T2R14 constituted their hydrogen bond pockets. The model is available at http://www.tastepeptides-meta.com/yyds.

A Machine Learning Method to Identify Umami Peptide Sequences by Using Multiplicative LSTM Embedded Features

Umami peptides enhance the umami taste of food and have good food processing properties, nutritional value, and numerous potential applications. Wet testing for the identification of umami peptides is a time-consuming and expensive process. Here, we report the iUmami-DRLF that uses a logistic regression (LR) method solely based on the deep learning pre-trained neural network feature extraction method, unified representation (UniRep based on multiplicative LSTM), for feature extraction from the peptide sequences. The findings demonstrate that deep learning representation learning significantly enhanced the capability of models in identifying umami peptides and predictive precision solely based on peptide sequence information. The newly validated taste sequences were also used to test the iUmami-DRLF and other predictors, and the result indicates that the iUmami-DRLF has better robustness and accuracy and remains valid at higher probability thresholds. The iUmami-DRLF method can aid further studies on enhancing the umami flavor of food for satisfying the need for an umami-flavored diet.

Empirical comparison and recent advances of computational prediction of hormone binding proteins using machine learning methods

Hormone binding proteins (HBPs) belong to the group of soluble carrier proteins. These proteins selectively and non-covalently interact with hormones and promote growth hormone signaling in human and other animals. The HBPs are useful in many medical and commercial fields. Thus, the identification of HBPs is very important because it can help to discover more details about hormone binding proteins. Meanwhile, the experimental methods are time-consuming and expensive for hormone binding proteins recognition. Computational prediction methods have played significant roles in the correct recognition of hormone binding proteins with the use of sequence information and ML algorithms. In this review, we compared and assessed the implementation of ML-based tools in recognition of HBPs in a unique way. We hope that this study will give enough awareness and knowledge for research on HBPs.

Bioactive and Sensory Di- and Tripeptides Generated during Dry-Curing of Pork Meat

Dry-cured pork products, such as dry-cured ham, undergo an extensive proteolysis during manufacturing process which determines the organoleptic properties of the final product. As a result of endogenous pork muscle endo- and exopeptidases, many medium- and short-chain peptides are released from muscle proteins. Many of them have been isolated, identified, and characterized, and some peptides have been reported to exert relevant bioactivity with potential benefit for human health. However, little attention has been given to di- and tripeptides, which are far less known, although they have received increasing attention in recent years due to their high potential relevance in terms of bioactivity and role in taste development. This review gathers the current knowledge about di- and tripeptides, regarding their bioactivity and sensory properties and focusing on their generation during long-term processing such as dry-cured pork meats.

Microbial succession and its effect on the formation of umami peptides during sufu fermentation

Sufu, a traditional Chinese fermented food, is famous for its unique flavor, especially umami. However, the formation mechanism of its umami peptides is still unclear. Here, we investigated the dynamic change of both umami peptides and microbial communities during sufu production. Based on peptidomic analysis, 9081 key differential peptides were identified, which mainly involved in amino acid transport and metabolism, peptidase activity and hydrolase activity. Twenty-six high-quality umami peptides with ascending trend were recognized by machine learning methods and Fuzzy c-means clustering. Then, through correlation analysis, five bacterial species (Enterococcus italicus, Leuconostoc citreum, L. mesenteroides, L. pseudomesenteroides, Tetragenococcus halophilus) and two fungi species (Cladosporium colombiae, Hannaella oryzae) were identified to be the core functional microorganisms for umami peptides formation. Functional annotation of five lactic acid bacteria indicated their important functions to be carbohydrate metabolism, amino acid metabolism and nucleotide metabolism, which proved their umami peptides production ability. Overall, our results enhanced the understanding of microbial communities and the formation mechanism of umami peptides in sufu, providing novel insights for quality control and flavor improvement of tofu products.