Prediction of Chromatography Conditions for Purification in Organic Synthesis Using Deep Learning

In this research, a process for developing normal-phase liquid chromatography solvent systems has been proposed. In contrast to the development of conditions via thin-layer chromatography (TLC), this process is based on the architecture of two hierarchically connected neural network-based components. Using a large database of reaction procedures allows those two components to perform an essential role in the machine-learning-based prediction of chromatographic purification conditions, i.e., solvents and the ratio between solvents. In our paper, we build two datasets and test various molecular vectorization approaches, such as extended-connectivity fingerprints, learned embedding, and auto-encoders along with different types of deep neural networks to demonstrate a novel method for modeling chromatographic solvent systems employing two neural networks in sequence. Afterward, we present our findings and provide insights on the most effective methods for solving prediction tasks. Our approach results in a system of two neural networks with long short-term memory (LSTM)-based auto-encoders, where the first predicts solvent labels (by reaching the classification accuracy of 0.950 ± 0.001) and in the case of two solvents, the second one predicts the ratio between two solvents (R² metric equal to 0.982 ± 0.001). Our approach can be used as a guidance instrument in laboratories to accelerate scouting for suitable chromatography conditions.     

基于深度学习构建探究实验设计思路*——以“探秘铜(II)离子配合物”为例

新课程背景下,依托教育部化学学科深度学习项目组提出的深度学习教学设计“四要素”,以配合物为例,开展深度学习,深入挖掘核心知识的素养功能和教育价值,促进学习方式转变,发展化学学科核心素养。     

A Method for Clustering and Screening of Long-dimensional Chemical Data Based on Fingerprints and Similarity Measurements

A method for the treatment of long-dimensional chemical data arrays is presented in this work with the aim of maximising classification models. The method is based on the construction of fingerprints and the subsequent generation of a similarity matrix. The similarity calculation has been modified through a scaling process to take into account different significance shown by the variables. The method was applied to spectral measurements of wines and several aspects were studied, namely: threshold considered in the construction of fingerprints and patterns, weighting factor used for scaling, normalisation method, etc. The application of both Principal Components Analysis and Soft-Independent Modelling of Class Analogies to the similarity matrices gave better classifications of the information than those obtained using original data.     

Deep Learning and Structure-Based Virtual Screening for Drug Discovery against NEK7: A Novel Target for the Treatment of Cancer

NIMA-related kinase7 (NEK7) plays a multifunctional role in cell division and NLRP3 inflammasone activation. A typical expression or any mutation in the genetic makeup of NEK7 leads to the development of cancer malignancies and fatal inflammatory disease, i.e., breast cancer, non-small cell lung cancer, gout, rheumatoid arthritis, and liver cirrhosis. Therefore, NEK7 is a promising target for drug development against various cancer malignancies. The combination of drug repurposing and structure-based virtual screening of large libraries of compounds has dramatically improved the development of anticancer drugs. The current study focused on the virtual screening of 1200 benzene sulphonamide derivatives retrieved from the PubChem database by selecting and docking validation of the crystal structure of NEK7 protein (PDB ID: 2WQN). The compounds library was subjected to virtual screening using Auto Dock Vina. The binding energies of screened compounds were compared to standard Dabrafenib. In particular, compound 762 exhibited excellent binding energy of −42.67 kJ/mol, better than Dabrafenib (−33.89 kJ/mol). Selected drug candidates showed a reactive profile that was comparable to standard Dabrafenib. To characterize the stability of protein–ligand complexes, molecular dynamic simulations were performed, providing insight into the molecular interactions. The NEK7–Dabrafenib complex showed stability throughout the simulated trajectory. In addition, binding affinities, pIC50, and ADMET profiles of drug candidates were predicted using deep learning models. Deep learning models predicted the binding affinity of compound 762 best among all derivatives, which supports the findings of virtual screening. These findings suggest that top hits can serve as potential inhibitors of NEK7. Moreover, it is recommended to explore the inhibitory potential of identified hits compounds through in-vitro and in-vivo approaches.     

Predictive Model for Drug-Induced Liver Injury Using Deep Neural Networks Based on Substructure Space

Drug-induced liver injury (DILI) is a major concern for drug developers, regulators, and clinicians. However, there is no adequate model system to assess drug-associated DILI risk in humans. In the big data era, computational models are expected to play a revolutionary role in this field. This study aimed to develop a deep neural network (DNN)-based model using extended connectivity fingerprints of diameter 4 (ECFP4) to predict DILI risk. Each data set for the predictive model was retrieved and curated from DILIrank, LiverTox, and other literature. The best model was constructed through ten iterations of stratified 10-fold cross-validation, and the applicability domain was defined based on integer ECFP4 bits of the training set which represented substructures. For the robustness test, we employed the concept of the endurance level. The best model showed an accuracy of 0.731, a sensitivity of 0.714, and a specificity of 0.750 on the validation data set in the complete applicability domain. The model was further evaluated with four external data sets and attained an accuracy of 0.867 on 15 drugs with DILI cases reported since 2019. Overall, the results suggested that the ECFP4-based DNN model represents a new tool to identify DILI risk for the evaluation of drug safety.     

Non-Targeted Screening Approaches for Profiling of Volatile Organic Compounds Based on Gas Chromatography-Ion Mobility Spectroscopy (GC-IMS) and Machine Learning

Due to its high sensitivity and resolving power, gas chromatography-ion mobility spectrometry (GC-IMS) is a powerful technique for the separation and sensitive detection of volatile organic compounds. It is a robust and easy-to-handle technique, which has recently gained attention for non-targeted screening (NTS) approaches. In this article, the general working principles of GC-IMS are presented. Next, the workflow for NTS using GC-IMS is described, including data acquisition, data processing and model building, model interpretation and complementary data analysis. A detailed overview of recent studies for NTS using GC-IMS is included, including several examples which have demonstrated GC-IMS to be an effective technique for various classification and quantification tasks. Lastly, a comparison of targeted and non-targeted strategies using GC-IMS are provided, highlighting the potential of GC-IMS in combination with NTS.     

基于“虚拟化学实验室”的在线课堂深度学习*—以“价层电子对互斥模型(VSEPR)”在线教学设计为例

在线课堂作为一种远程教育方式,往往会导致学生缺乏学习社区感。面对抽象的理论性知识,学生易陷入一种“离身”的困境。基于此,借助虚拟化学实验室,设计一堂“身临其境”“做中学”的价层电子对互斥模型课,实现“抽象内容具身认知化”“在线学习互动现实化”的在线课堂深度学习。     

Sensitive and Green Method for Determination of Chemical Oxygen Demand Using a Nano‐copper Based Electrochemical Sensor

Copper nanoparticles (nano‐Cu) were electrodeposited on the surface of glassy carbon electrode (GCE) potentiostatically at −0.6 V vs. Ag/AgCl for 60 s. The developed nano‐copper modified glassy carbon electrode (nano‐Cu/GCE) was optimized and utilized for electrochemical assay of chemical oxygen demand (COD) using glycine as a standard. The surface morphology and chemical composition of nano‐Cu/GCE were investigated using scanning electron microscope (SEM) and energy dispersive X‐ray spectrometer (EDX), respectively. The electrochemical behavior was investigated using linear sweep voltammetry (LSV) which is characterized by a remarkable anodic peak at ∼0.6 V, compared to bare GCE. This indicates that nano‐Cu enhances significantly the electrochemical oxidation of glycine. The effect of different deposition parameters, such as Cu²⁺ concentration, deposition potential, deposition time, pH, and scan rate on the response of the developed sensor were investigated. The optimized nano‐Cu/GCE based COD sensor exhibited a linear range of 15 to 629.3 ppm, and a lower limit of detection (LOD) of 1.7 ppm (S/N=3). This developed method exhibited high tolerance level to chloride ion (0.35 M chloride ion has minimal influence). The analytical utility of the prepared COD sensor was demonstrated by investigating the COD recovery (99.8±4.3) and the assay of COD in different water samples. The results obtained were verified using the standard dichromate method.     

Investigating the Role of Obesity in Prostate Cancer and Identifying Biomarkers for Drug Discovery: Systems Biology and Deep Learning Approaches

Prostate cancer (PCa) is the second most frequently diagnosed cancer for men and is viewed as the fifth leading cause of death worldwide. The body mass index (BMI) is taken as a vital criterion to elucidate the association between obesity and PCa. In this study, systematic methods are employed to investigate how obesity influences the noncutaneous malignancies of PCa. By comparing the core signaling pathways of lean and obese patients with PCa, we are able to investigate the relationships between obesity and pathogenic mechanisms and identify significant biomarkers as drug targets for drug discovery. Regarding drug design specifications, we take drug–target interaction, drug regulation ability, and drug toxicity into account. One deep neural network (DNN)-based drug–target interaction (DTI) model is trained in advance for predicting drug candidates based on the identified biomarkers. In terms of the application of the DNN-based DTI model and the consideration of drug design specifications, we suggest two potential multiple-molecule drugs to prevent PCa (covering lean and obese PCa) and obesity-specific PCa, respectively. The proposed multiple-molecule drugs (apigenin, digoxin, and orlistat) not only help to prevent PCa, suppressing malignant metastasis, but also result in lower production of fatty acids and cholesterol, especially for obesity-specific PCa.     

Genetic Algorithm Based Potential Selection in Simultaneous Voltammetric Determination of Isoniazid and Hydrazine by Using Partial Least Squares (PLS) and Artificial Neural Networks (ANNs)

The voltammetric behavior of isoniazid and hydrazine at an overoxidized polypyrrole modified glassy carbon electrode has been investigated. The obtained cyclic voltammograms showed that their oxidation peaks were overlapped and it is difficult to determine them individually from a mixture without separation. To overcome this limitation, a procedure was proposed for resolution of overlapped voltammetric signals from mixtures of isoniazid and hydrazine. In this procedure, genetic algorithm was used for the selection of potentials for partial least squares. A feed forward artificial neural network with back propagation error algorithm was used to process the nonlinear relationship between currents and concentrations of hydrazine and isoniazid. The proposed method was suitable for determination of isoniazid in pharmaceutical tablets and detection of hydrazine impurities in the same samples.