PredCoffee: A binary classification approach specifically for coffee odor.

Compared to traditional methods, using machine learning to assess or predict the odor of molecules can save costs in various aspects. Our research aims to collect molecules with coffee odor and summarize the regularity of these molecules, ultimately creating a binary classifier that can determine whether a molecule has a coffee odor. In this study, a total of 371 coffee-odor molecules and 9,700 non-coffee-odor molecules were collected. The Knowledge-guided Pre-training of Graph Transformer (KPGT), support vector machine (SVM), random forest (RF), multi-layer perceptron (MLP), and message-passing neural networks (MPNN) were used to train the data. The model with the best performance was selected as the basis of the predictor. The prediction accuracy value of the KPGT model exceeded 0.84 and the predictor has been deployed as a webserver PredCoffee.

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.

Molecular insights into chronic atrophic gastritis treatment: Coptis chinensis Franch studied via network pharmacology, molecular dynamics simulation and experimental analysis.

Chronic atrophic gastritis (CAG), characterized by inflammation and erosion of the gastric lining, is a prevalent digestive disorder and considered a precursor to gastric cancer (GC). Coptis chinensis France (CCF) is renowned for its potent heat-clearing, detoxification, and anti-inflammatory properties. Zuojin Pill (ZJP), a classic Chinese medicine primarily composed of CCF, has demonstrated effectiveness in CAG treatment. This study aims to elucidate the potential mechanism of CCF treatment for CAG through a multifaceted approach encompassing network pharmacology, molecular docking, molecular dynamics simulation and experimental verification. The study identified three major active compounds of CCF and elucidated key pathways, such as TNF signaling, PI3K-Akt signaling and p53 signaling. Molecular docking revealed interactions between these active compounds and pivotal targets like PTGS2, TNF, MTOR, and TP53. Additionally, molecular dynamics simulation validated berberine as the primary active compound of CCF, which was further confirmed through experimental verification. This study not only identified berberine as the primary active compound of CCF but also provided valuable insights into the molecular mechanisms underlying CCF's efficacy in treating CAG. Furthermore, it offers a reference for refining therapeutic strategies for CAG management.

Using Gaussian accelerated molecular dynamics combined with Markov state models to explore the mechanism of action of new oral inhibitors on Complex I.

In this study, our focus was on investigating H-1,2,3-triazole derivative HP661 as a novel and highly efficient oral OXPHOS inhibitor, with its molecular-level inhibitory mechanism not yet fully understood. We selected the ND1, NDUFS2, and NDUFS7 subunits of Mitochondrial Complex I as the receptor proteins and established three systems for comparative analysis: protein-IACS-010759, protein-lead compound 10, and protein-HP661. Through extensive analysis involving 500 ns Gaussian molecular dynamics simulations, we gained insights into these systems. Additionally, we constructed a Markov State Models to examine changes in secondary structures during the motion processes. The research findings suggest that the inhibitor HP661 enhances the extensibility and hydrophilicity of the receptor protein. Furthermore, HP661 induces the unwinding of the α-helical structure in the region of residues 726-730. Notably, key roles were identified for Met37, Phe53, and Pro212 in the binding of various inhibitors. In conclusion, we delved into the potential molecular mechanisms of triazole derivative HP661 in inhibiting Complex I. These research outcomes provide crucial information for a deeper understanding of the mechanisms underlying OXPHOS inhibition, offering valuable theoretical support for drug development and disease treatment design.

Elucidating the structural basis of vitamin B12 derivatives as novel potent inhibitors of PTP1B: Insights from inhibitory mechanisms using Gaussian accelerated molecular dynamics (GaMD) and in vitro study.

Vitamin B12 is a group of biologically active cobalamin compounds. In this study, we investigated the inhibitory effects of methylcobalamin (MeCbl) and hydroxocobalamin acetate (OHCbl Acetate) on protein tyrosine phosphatase 1B (PTP1B). MeCbl and OHCbl Acetate exhibited an IC50 of approximately 58.390 ± 2.811 µM and 8.998 ± 0.587 µM, respectively. The Ki values of MeCbl and OHCbl Acetate were 25.01 µM and 4.04 µM respectively. To elucidate the inhibition mechanism, we conducted a 500 ns Gaussian accelerated molecular dynamics (GaMD) simulation. Utilizing PCA and tICA, we constructed Markov state models (MSM) to examine secondary structure changes during motion. Our findings revealed that the α-helix at residues 37-42 remained the most stable in the PTP1B-OHCbl Acetate system. Furthermore, upon binding of OHCbl Acetate or MeCbl, the WPD loop of PTP1B moved inward to the active pocket, forming a closed conformation and potentially obstructs substrate entry. Protein-ligand interaction analysis and MM-PBSA showed that OHCbl Acetate exhibited lower binding free energy and engaged in more residue interactions with PTP1B. In summary, our study confirmed the substantial inhibitory activity of OHCbl Acetate against PTP1B, with its inhibitory potency notably surpassing that of MeCbl. We demonstrated potential molecular mechanisms of OHCbl Acetate inhibiting PTP1B.

Directed evolution of Escherichia coli surface-displayed Vitreoscilla hemoglobin as an artificial metalloenzyme for the synthesis of 5-imino-1,2,4-thiadiazoles.

Artificial metalloenzymes (ArMs) are constructed by anchoring organometallic catalysts to an evolvable protein scaffold. They present the advantages of both components and exhibit considerable potential for the in vivo catalysis of new-to-nature reactions. Herein, Escherichia coli surface-displayed Vitreoscilla hemoglobin (VHbSD-Co) that anchored the cobalt porphyrin cofactor instead of the original heme cofactor was used as an artificial thiourea oxidase (ATOase) to synthesize 5-imino-1,2,4-thiadiazoles. After two rounds of directed evolution using combinatorial active-site saturation test/iterative saturation mutagenesis (CAST/ISM) strategy, the evolved six-site mutation VHbSD-Co (6SM-VHbSD-Co) exhibited significant improvement in catalytic activity, with a broad substrate scope (31 examples) and high yields with whole cells. This study shows the potential of using VHb ArMs in new-to-nature reactions and demonstrates the applicability of E. coli surface-displayed methods to enhance catalytic properties through the substitution of porphyrin cofactors in hemoproteins in vivo.

Exploring Bitter and Sweet: The Application of Large Language Models in Molecular Taste Prediction.

The perception of bitter and sweet tastes is a crucial aspect of human sensory experience. Concerns over the long-term use of aspartame, a widely used sweetener suspected of carcinogenic risks, highlight the importance of developing new taste modifiers. This study utilizes Large Language Models (LLMs) such as GPT-3.5 and GPT-4 for predicting molecular taste characteristics, with a focus on the bitter-sweet dichotomy. Employing random and scaffold data splitting strategies, GPT-4 demonstrated superior performance, achieving an impressive 86% accuracy under scaffold partitioning. Additionally, ChatGPT was employed to extract specific molecular features associated with bitter and sweet tastes. Utilizing these insights, novel molecular compounds with distinct taste profiles were successfully generated. These compounds were validated for their bitter and sweet properties through molecular docking and molecular dynamics simulation, and their practicality was further confirmed by ADMET toxicity testing and DeepSA synthesis feasibility. This research highlights the potential of LLMs in predicting molecular properties and their implications in health and chemical science.

Integrating Computational and Experimental Methods to Identify Novel Sweet Peptides from Egg and Soy Proteins.

Sweetness in food delivers a delightful sensory experience, underscoring the crucial role of sweeteners in the food industry. However, the widespread use of sweeteners has sparked health concerns. This underscores the importance of developing and screening natural, health-conscious sweeteners. Our study represents a groundbreaking venture into the discovery of such sweeteners derived from egg and soy proteins. Employing virtual hydrolysis as a novel technique, our research entailed a comprehensive screening process that evaluated biological activity, solubility, and toxicity of the derived compounds. We harnessed cutting-edge machine learning methodologies, specifically the latest graph neural network models, for predicting the sweetness of molecules. Subsequent refinements were made through molecular docking screenings and molecular dynamics simulations. This meticulous research approach culminated in the identification of three promising sweet peptides: DCY(Asp-Cys-Tyr), GGR(Gly-Gly-Arg), and IGR(Ile-Gly-Arg). Their binding affinity with T1R2/T1R3 was lower than -15 kcal/mol. Using an electronic tongue, we verified the taste profiles of these peptides, with IGR emerging as the most favorable in terms of taste with a sweetness value of 19.29 and bitterness value of 1.71. This study not only reveals the potential of these natural peptides as healthier alternatives to traditional sweeteners in food applications but also demonstrates the successful synergy of computational predictions and experimental validations in the realm of flavor science.

Mulberry Leaf Compounds and Gut Microbiota in Alzheimer's Disease and Diabetes: A Study Using Network Pharmacology, Molecular Dynamics Simulation, and Cellular Assays.

Recently, studies have reported a correlation that individuals with diabetes show an increased risk of developing Alzheimer's disease (AD). Mulberry leaves, serving as both a traditional medicinal herb and a food source, exhibit significant hypoglycemic and antioxidative properties. The flavonoid compounds in mulberry leaf offer therapeutic effects for relieving diabetic symptoms and providing neuroprotection. However, the mechanisms of this effect have not been fully elucidated. This investigation aimed to investigate the combined effects of specific mulberry leaf flavonoids (kaempferol, quercetin, rhamnocitrin, tetramethoxyluteolin, and norartocarpetin) on both type 2 diabetes mellitus (T2DM) and AD. Additionally, the role of the gut microbiota in these two diseases' treatment was studied. Using network pharmacology, we investigated the potential mechanisms of flavonoids in mulberry leaves, combined with gut microbiota, in combating AD and T2DM. In addition, we identified protein tyrosine phosphatase 1B (PTP1B) as a key target for kaempferol in these two diseases. Molecular docking and molecular dynamics simulations showed that kaempferol has the potential to inhibit PTP1B for indirect treatment of AD, which was proven by measuring the IC50 of kaempferol (279.23 µM). The cell experiment also confirmed the dose-dependent effect of kaempferol on the phosphorylation of total cellular protein in HepG2 cells. This research supports the concept of food-medicine homology and broadens the range of medical treatments for diabetes and AD, highlighting the prospect of integrating traditional herbal remedies with modern medical research.

Synthesis of Indolyl Phenyl Diketones through Visible-Light-Promoted Ni-Catalyzed Intramolecular Cyclization/Oxidation Sequence of Ynones.

The combination of visible light catalysis and Ni catalysis has enabled the synthesis of indolyl phenyl diketones through the cyclization/oxidation process of ynones. This reaction proceeded under mild and base-free conditions and showed a broad scope and feasibility for gram-scale synthesis. Several natural products and biologically interesting molecules could be readily postfunctionalized by this method.

Prediction of bitterness based on modular designed graph neural network.

Motivation: Bitterness plays a pivotal role in our ability to identify and evade harmful substances in food. As one of the five tastes, it constitutes a critical component of our sensory experiences. However, the reliance on human tasting for discerning flavors presents cost challenges, rendering in silico prediction of bitterness a more practical alternative. Results: In this study, we introduce the use of Graph Neural Networks (GNNs) in bitterness prediction, superseding traditional machine learning techniques. We developed an advanced model, a Hybrid Graph Neural Network (HGNN), surpassing conventional GNNs according to tests on public datasets. Using HGNN and three other GNNs, we designed BitterGNNs, a bitterness predictor that achieved an AUC value of 0.87 in both external bitter/non-bitter and bitter/sweet evaluations, outperforming the acclaimed RDKFP-MLP predictor with AUC values of 0.86 and 0.85. We further created a bitterness prediction website and database, TastePD (https://www.tastepd.com/). The BitterGNNs predictor, built on GNNs, offers accurate bitterness predictions, enhancing the efficacy of bitterness prediction, aiding advanced food testing methodology development, and deepening our understanding of bitterness origins. Availability and implementation: TastePD can be available at https://www.tastepd.com, all codes are at https://github.com/heyigacu/BitterGNN.

Dual-polarization RF channelizer based on microcombs.

We report a dual-polarization radio frequency (RF) channelizer based on microcombs. Two high-Q micro-ring resonators (MRRs) with slightly different free spectral ranges (FSRs) are used: one MRR is pumped to yield soliton crystal microcombs ("active"), and the other MRR is used as a "passive" periodic optical filter supporting dual-polarization operation to slice the RF spectrum. With the tailored mismatch between the FSRs of the active and passive MRRs, wideband RF spectra can be channelized into multiple segments featuring digital-compatible bandwidths via the Vernier effect. Due to the use of dual-polarization states, the number of channelized spectral segments, and thus the RF instantaneous bandwidth (with a certain spectral resolution), can be doubled. In our experiments, we used 20 microcomb lines with ∼ 49 GHz FSR to achieve 20 channels for each polarization, with high RF spectra slicing resolutions at 144 MHz (TE) and 163 MHz (TM), respectively; achieving an instantaneous RF operation bandwidth of 3.1 GHz (TE) and 2.2 GHz (TM). Our approach paves the path towards monolithically integrated photonic RF receivers (the key components - active and passive MRRs are all fabricated on the same platform) with reduced complexity, size, and unprecedented performance, which is important for wide RF applications with digital-compatible signal detection.

Mlp4green: A Binary Classification Approach Specifically for Green Odor.

Fresh green leaves give off a smell known as "green odor." It has antibacterial qualities and can be used to attract or repel insects. However, a common method for evaluating green odor molecules has never existed. Machine learning techniques are widely used in research to forecast molecular attributes for binary classification. In this work, the green odor molecules were first trained and learned using machine learning methods, and then clustering analysis and molecular docking were performed to further explore their molecular characteristics and mechanisms of action. For comparison, four algorithmic models were employed, MLP performed the best in all metrics, including Accuracy, Precision, Average Precision, Matthews coefficient, and Area under curve. We determined by difference analysis that, in comparison to non-green odor molecules, green odor molecules have a lower molecular mass and fewer electrons. Based on the MLP algorithm, we constructed a binary classification prediction website for green odors. The first application of deep learning techniques to the study of green odor molecules can be seen as a signal of a new era in which green odor research has advanced into intelligence and standardization.

Novel design and development of Centella Asiatica extract - loaded poloxamer/ZnO nanocomposite wound closure material to improve anti-bacterial action and enhanced wound healing efficacy in diabetic foot ulcer.

Diabetic wounds can occur as a prevalent complication among people diagnosed with diabetes, frequently resulting in the necessity for amputation. The cause and effect of diabetic foot ulcer is complex, involving multiple factors. In the present study, wound healing strategies utilizing nanomaterials have proven to be effective in battling bacterial infections and improve wound regeneration. Poloxamers (PLX) exhibit extensive potential as a viable option for the development of nanomedicines owing to their inherent characteristics of self-assembly and encapsulation. This study aims to design and develop a PLX/ZnO nanocomposite incorporated with Centella Asiatica extract (CAE) for the multi-functional action in the diabetic wound healing treatment. Subsequently physico-chemical characterizations, such as XRD, FTIR, and TEM observations, demonstrated that the ZnO were evenly distributed through the PLX framework. The developed nanocomposite was biocompatible with mouse fibroblast cell line (L929), and it had multiple beneficial characteristics, such as a rapid self-healing process and effective antibacterial action against G+ and G- bacterial pathogens. After being treated with the developed formulation, skin fibroblast cell line and HUVECs demonstrated a substantial increase in their in vitro cell proliferation ability, migration, and tube-forming abilities. The utilization of a CAE@PLX/ZnO nanoformulation presents a viable strategy and a distinctive, encouraging composite for diabetic wound healing treatment.

Exploring the anti-gout potential of sunflower receptacles alkaloids: A computational and pharmacological analysis.

Gout, a painful condition marked by elevated uric acid levels often linked to the diet's high purine and alcohol content, finds a potential treatment target in xanthine oxidase (XO), a crucial enzyme for uric acid production. This study explores the therapeutic properties of alkaloids extracted from sunflower (Helianthus annuus L.) receptacles against gout. By leveraging computational chemistry and introducing a novel R-based clustering algorithm, "TriDimensional Hierarchical Fingerprint Clustering with Tanimoto Representative Selection (3DHFC-TRS)," we assessed 231 alkaloid molecules from sunflower receptacles. Our clustering analysis pinpointed six alkaloids with significant gout-targeting potential, particularly emphasizing the fifth cluster's XO inhibition capabilities. Through molecular docking and the BatchDTA prediction model, we identified three top compounds-2-naphthylalanine, medroxalol, and fenspiride-with the highest XO affinity. Further molecular dynamics simulations assessed their enzyme active site interactions and binding free energies, employing MM-PBSA calculations. This investigation not only highlights the discovery of promising compounds within sunflower receptacle alkaloids via LC-MS but also introduces medroxalol as a novel gout treatment candidate, showcasing the synergy of computational techniques and LC-MS in drug discovery.

Correlation Between Blood Cadmium Levels and Platelet Characteristics, As Well As Their Impact on Susceptibility to Coronary Heart Disease: Findings from NHANES 2005-2018 Data.

Investigating the correlation between blood cadmium levels, platelet characteristics, and susceptibility to coronary heart disease (CHD). Utilized NHANES 2005-2018 data with covariates such as age, sex, race, marital status, and socio-economic status. Blood cadmium served as the independent variable, while platelet count (PC) and mean platelet volume (MPV) were dependent variables. The average age of the participants was 68.77 ± 11.03 years, and 67.4% of them were male. The mean values for WBC, MPV, PC, and blood cadmium were 7.53 ± 3.36 × 103 cells/µL, 11.33 ± 0.27fL, 57.61 ± 5.34 × 103 cells/µL, and 2.58 ± 0.61 µg/L, respectively. Adjusting for other variables revealed increased MPV and PC with rising blood cadmium levels in cardiac patients, indicating a higher risk of CHD in those with elevated blood cadmium. The average age of the participants was 68.77 ± 11.03 years, and 67.4% of them were male. The mean values for WBC, MPV, PC, and blood cadmium were 7.53 ± 3.36 × 103 cells/µL, 11.33 ± 0.27fL, 57.61 ± 5.34 × 103 cells/µL, and 2.58 ± 0.61 µg/L, respectively. Adjusting for other variables revealed increased MPV and PC with rising blood cadmium levels in cardiac patients, indicating a higher risk of CHD in those with elevated blood cadmium. This study enhances understanding of how cadmium impacts platelet characteristics, contributing to increased CHD risk, providing insights for primary prevention strategies.

Sigmoido-rectal intussusception anastomosis in the Altemeier procedure for complete rectal prolapse: preliminary results of a new technique.

Purpose: Our research introduces an innovative surgical approach, combining the Altemeier Procedure with Sigmoido-rectal Intussusception Anastomosis, effectively reducing recurrence, minimizing complications, and improving postoperative anal function in rectal prolapse patients. Materials and methods: This retrospective study, conducted at tertiary referral hospitals including Shandong University of Traditional Chinese Medicine's Affiliated Hospital, Linyi People's Hospital, and Pingyi People's Hospital, examined data from patients undergoing conventional Altemeier surgery or Altemeier combined with Sigmoido-rectal Intussusception Anastomosis. Analyzing hospitalization and follow-up data from January 2009 to December 2022, the study focused on prolapse recurrence, complications, and anal function as primary outcome indicators across these three study centers. Results: In the study, both groups had an average follow-up of (12.5 ± 2.41) months, and only two traditional group patients experienced mortality. Recurrence rates significantly differed, with 26.47% in the traditional group and 1.54% in the modified group (P < 0.001). The modified group showed no perioperative anastomotic dehiscence, contrasting with a 13.24% occurrence in the conventional group (P = 0.003). Primary complications in the modified group included anastomotic hemorrhage, with rates of 17.65% and 6.15% in the traditional and modified groups, respectively (P = 0.077). At 12 months postoperatively, both groups improved in anal manometry parameters and the Wexner anal incontinence score. Resting pressure was significantly lower in the traditional group (32.50 ± 1.76 mmHg) than the modified group (33.24 ± 2.06 mmHg) (P = 0.027), while the extrusion pressure was higher in the modified group (64.78 ± 1.55 mmHg) than the traditional group (62.85 ± 2.30 mmHg) (P < 0.001). The Wexner anal incontinence score was significantly lower in the modified group (2.69 ± 1.65) than the traditional group (3.69 ± 1.58, P = 0.001). Conclusion: This retrospective study affirms that adding Sigmoido-rectal Intussusception Anastomosis to the Altemeier procedure reduces recurrence and complications. While both approaches enhance postoperative anal function in complete rectal prolapse patients, the combined method, particularly with Sigmoido-rectal Intussusception Anastomosis, proves more effective.

Effects of dietary supplementation of fish oil plus vitamin D3 on gut microbiota and fecal metabolites, and their correlation with nonalcoholic fatty liver disease risk factors: a randomized controlled trial.

We previously reported that fish oil plus vitamin D3 (FO + D) could ameliorate nonalcoholic fatty liver disease (NAFLD). However, it is unclear whether the beneficial effects of FO + D on NAFLD are associated with gut microbiota and fecal metabolites. In this study, we investigated the effects of dietary supplementation of FO + D on gut microbiota and fecal metabolites and their correlation with NAFLD risk factors. Methods: A total of 61 subjects were randomly divided into three groups: FO + D group (2.34 g day-1 of eicosatetraenoic acid (EPA) + docosahexaenoic acid (DHA) + 1680 IU vitamin D3), FO group (2.34 g day-1 of EPA + DHA), and corn oil (CO) group (1.70 g d-1 linoleic acid). Blood and fecal samples were collected at the baseline and day 90. Gut microbiota were analyzed through 16S rRNA PCR analysis, and fecal co-metabolites were determined via untargeted ultraperformance liquid chromatography-quadrupole time-of-flight mass spectrometry (UPLC-Q-TOF-MS). Results: The relative abundance of Eubacterium (p = 0.03) and Lactobacillus (p = 0.05) increased, whereas that of Streptococcus (p = 0.02) and Dialister (p = 0.04) decreased in the FO + D group compared with the CO group. Besides, changes in tetracosahexaenoic acid (THA, C24:6 n-3) (p = 0.03) levels were significantly enhanced, whereas 8,9-DiHETrE levels (p < 0.05) were reduced in the FO + D group compared with the CO group. The changes in 1,25-dihydroxyvitamin D3 levels in the fecal samples were inversely associated with insulin resistance, which was determined using the homeostatic model assessment model (HOMA-IR, r = -0.29, p = 0.02), and changes in 8,9-DiHETrE levels were positively associated with adiponectin levels (r = -0.43, p < 0.05). Conclusion: The present results indicate that the beneficial effects of FO + D on NAFLD may be partially attributed to the impact on gut microbiota and fecal metabolites.

Building a Kokumi Database and Machine Learning-Based Prediction: A Systematic Computational Study on Kokumi Analysis.

Kokumi is a subtle sensation characterized by a sense of fullness, continuity, and thickness. Traditional methods of taste discovery and analysis, including those of kokumi, have been labor-intensive and costly, thus necessitating the emergence of computational methods as critical strategies in molecular taste analysis and prediction. In this study, we undertook a comprehensive analysis, prediction, and screening of the kokumi compounds. We categorized 285 kokumi compounds from a previously unreleased kokumi database into five groups based on their molecular characteristics. Moreover, we predicted kokumi/non-kokumi and multi-flavor compositions using six structure-taste relationship models: MLP-E3FP, MLP-PLIF, MLP-RDKFP, SVM-RDKFP, RF-RDKFP, and WeaveGNN feature of Atoms and Bonds. These six predictors exhibited diverse performance levels across two different models. For kokumi/non-kokumi prediction, the WeaveGNN model showed an exceptional predictive AUC value (0.94), outperforming the other models (0.87, 0.90, 0.89, 0.92, and 0.78). For multi-flavor prediction, the MLP-E3FP model demonstrated a higher predictive AUC and MCC value (0.94 and 0.74) than the others (0.73 and 0.33; 0.92 and 0.70; 0.95 and 0.73; 0.94 and 0.64; and 0.88 and 0.69). This data highlights the model's proficiency in accurately predicting kokumi molecules. As a result, we sourced kokumi active compounds through a high-throughput screening of over 100 million molecules, further refined by toxicity and similarity screening. Lastly, we launched a web platform, KokumiPD (https://www.kokumipd.com/), offering a comprehensive kokumi database and online prediction services for users.

Using deep learning and molecular dynamics simulations to unravel the regulation mechanism of peptides as noncompetitive inhibitor of xanthine oxidase.

Xanthine oxidase (XO) is a crucial enzyme in the development of hyperuricemia and gout. This study focuses on LWM and ALPM, two food-derived inhibitors of XO. We used molecular docking to obtain three systems and then conducted 200 ns molecular dynamics simulations for the Apo, LWM, and ALPM systems. The results reveal a stronger binding affinity of the LWM peptide to XO, potentially due to increased hydrogen bond formation. Notable changes were observed in the XO tunnel upon inhibitor binding, particularly with LWM, which showed a thinner, longer, and more twisted configuration compared to ALPM. The study highlights the importance of residue F914 in the allosteric pathway. Methodologically, we utilized the perturbed response scan (PRS) based on Python, enhancing tools for MD analysis. These findings deepen our understanding of food-derived anti-XO inhibitors and could inform the development of food-based therapeutics for reducing uric acid levels with minimal side effects.