Prediction of flavor and retention index for compounds in beer depending on molecular structure using a machine learning method

Inhibition of the Janus kinase protein (JAK1) by the A. Pyrethrum Root Extract for the treatment of Vitiligo pathology. Design, Molecular Docking, ADME-Tox, MD Simulation, and in-silico investigation

This study delves into the therapeutic efficacy of A. pyrethrum in addressing vitiligo, a chronic inflammatory disorder known for inducing psychological distress and elevating susceptibility to autoimmune diseases. Notably, JAK inhibitors have emerged as promising candidates for treating immune dermatoses, including vitiligo. Our investigation primarily focuses on the anti-vitiligo potential of A. pyrethrum root extract, specifically targeting N-alkyl-amides, utilizing computational methodologies. Density Functional Theory (DFT) is deployed to meticulously scrutinize molecular properties, while comprehensive evaluations of ADME-Tox properties for each molecule contribute to a nuanced understanding of their therapeutic viability, showcasing remarkable drug-like characteristics. Molecular docking analysis probes ligand interactions with pivotal site JAK1, with all compounds demonstrating significant interactions; notably, molecule 6 exhibits the most interactions with crucial inhibition residues. Molecular dynamics simulations over 500ns further validate the importance and sustainability of these interactions observed in molecular docking, favoring energetically both molecules 6 and 1; however, in terms of stability, the complex with molecule 6 outperforms others. DFT analyses elucidate the distribution of electron-rich oxygen atoms and electron-poor regions within heteroatoms-linked hydrogens. Remarkably, N-alkyl-amides extracted from A. pyrethrum roots exhibit similar compositions, yielding comparable DFT and Electrostatic Potential (ESP) results with subtle distinctions. These findings underscore the considerable potential of A. pyrethrum root extracts as a natural remedy for vitiligo.

Accurate prediction of isothermal gas chromatographic Kováts retention indices

We describe a freely available web server called Retention Index Predictor (RIpred) (https://ripred.ca) that rapidly and accurately predicts Gas Chromatographic Kováts Retention Indices (RI) using SMILES strings as chemical structure input. RIpred performs RI prediction for three different stationary phases (semi-standard non-polar (SSNP), standard non-polar (SNP), and standard polar (SP)) for both derivatized (trimethylsilyl (TMS) and tert‑butyldimethylsilyl (TBDMS) derivatized) and underivatized (base compound) forms of GC-amenable structures. RIpred was developed to address the need for freely available, fast, highly accurate RI predictions for a wide range of derivatized and underivatized chemicals for all common GC stationary phases. RIpred was trained using a Graph Neural Network (GNN) that used compound structures, their extracted features (mostly atom-level features) and the GC-RI data from the National Institute of Standards and Technology databases (NIST 17 and NIST 20). We curated this NIST 17 and NIST 20 GC-RI data, which is available for all three stationary phases, to create appropriate inputs (molecular graphs in this case) needed to enhance our model performance. The performance of different RIpred predictive models was evaluated using 10-fold cross validation (CV). The best performing RIpred models were identified and when tested on hold-out test sets from all stationary phases, achieved a Mean Absolute Error (MAE) of <73 RI units (SSNP: 16.5-29.5, SNP: 38.5-45.9, SP: 46.52-72.53). The Mean Absolute Percentage Error (MAPE) of these models were typically within 3% (SSNP: 0.78-1.62%, SNP: 1.87-2.88%, SP: 2.34-4.05%). When compared to the best performing model by Qu et al., 2021, RIpred performed similarly (MAE of 16.57 RI units [RIpred] vs. 16.84 RI units [Qu et al., 2021 predictor] for derivatized compounds). RIpred also includes ∼5 million predicted RI values for all GC-amenable compounds (∼57,000) in the Human Metabolome Database HMDB 5.0 (Wishart et al., 2022).

A machine learning method for juice human sensory hedonic prediction using electronic sensory features

This study proposed a method that combines fused electronic sensory analysis technology with artificial neural network to predict the human sensory hedonic of fruit juice. Quantitative descriptive analysis (QDA) and the scoring test method were utilized for human sensory evaluation. The first step involved modeling the fused e-sensory features with human sensory attributes, followed by establishing a fitting model of human sensory attributes and acceptance. The R2 and RMSE values obtained were 0.77 and 0.42 (QDA method), and 0.63 and 0.63 (scoring test method). Finally, the relationship between the fusion e-sensory features and the human sensory hedonic was established. Model-1 achieved an R2 of 0.95 and an RMSE of 0.04, while model-2 achieved an R2 value of 0.88 and an RMSE value of 0.21. This study demonstrates the potential of fusing e-sensory technologies to replace human senses, which may lead to the development of devices with simultaneous multiple senses.

Compare the performance of multiple binary classification models in microbial high-throughput sequencing datasets

The development of machine learning and deep learning provided solutions for predicting microbiota response on environmental change based on microbial high-throughput sequencing. However, there were few studies specifically clarifying the performance and practical of two types of binary classification models to find a better algorithm for the microbiota data analysis. Here, for the first time, we evaluated the performance, accuracy and running time of the binary classification models built by three machine learning methods - random forest (RF), support vector machine (SVM), logistic regression (LR), and one deep learning method - back propagation neural network (BPNN). The built models were based on the microbiota datasets that removed low-quality variables and solved the class imbalance problem. Additionally, we optimized the models by tuning. Our study demonstrated that dataset pre-processing was a necessary process for model construction. Among these 4 binary classification models, BPNN and RF were the most suitable methods for constructing microbiota binary classification models. Using these 4 models to predict multiple microbial datasets, BPNN showed the highest accuracy and the most robust performance, while the RF method was ranked second. We also constructed the optimal models by adjusting the epochs of BPNN and the n_estimators of RF for six times. The evaluation related to performances of models provided a road map for the application of artificial intelligence to assess microbial ecology.