Structural features of toxic chemicals for specific toxicity

We have studied the structural features of toxic chemicals from the RTECS database associated with specific toxicity. The frameworks, functional groups, and structure patterns of molecules are taken into account. Potential active frameworks, groups, and structure patterns for specific toxicity are gained by computational chemistry approaches. These structural features of toxic chemicals will be helpful in understanding activities of toxic chemicals and useful in predicting the toxicity of chemicals, especially in the early stage of drug design.     

Giving molecules an identity. On the interplay between QSARs and partial order ranking

The interplay between 'noise-deficient' QSAR and Partial Order Ranking, including analysis of average linear ranks, constitutes an effective tool in giving substances which have not been investigated experimentally an identity by comparison with experimentally well-characterized, structurally similar compounds. It is disclosed that experimentally well-characterized compounds may serve as substitutes for highly toxic compounds in experimental studies without exhibiting the same extreme toxicity, while from an overall viewpoint they exhibit analogous environmental characteristics.     

Modeling Structure–Activity Relationship of AMPK Activation

The adenosine monophosphate activated protein kinase (AMPK) is critical in the regulation of important cellular functions such as lipid, glucose, and protein metabolism; mitochondrial biogenesis and autophagy; and cellular growth. In many diseases—such as metabolic syndrome, obesity, diabetes, and also cancer—activation of AMPK is beneficial. Therefore, there is growing interest in AMPK activators that act either by direct action on the enzyme itself or by indirect activation of upstream regulators. Many natural compounds have been described that activate AMPK indirectly. These compounds are usually contained in mixtures with a variety of structurally different other compounds, which in turn can also alter the activity of AMPK via one or more pathways. For these compounds, experiments are complicated, since the required pure substances are often not yet isolated and/or therefore not sufficiently available. Therefore, our goal was to develop a screening tool that could handle the profound heterogeneity in activation pathways of the AMPK. Since machine learning algorithms can model complex (unknown) relationships and patterns, some of these methods (random forest, support vector machines, stochastic gradient boosting, logistic regression, and deep neural network) were applied and validated using a database, comprising of 904 activating and 799 neutral or inhibiting compounds identified by extensive PubMed literature search and PubChem Bioassay database. All models showed unexpectedly high classification accuracy in training, but more importantly in predicting the unseen test data. These models are therefore suitable tools for rapid in silico screening of established substances or multicomponent mixtures and can be used to identify compounds of interest for further testing.     

In Silico Identification of Anti-SARS-CoV-2 Medicinal Plants Using Cheminformatics and Machine Learning

Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), the causative pathogen of COVID-19, is spreading rapidly and has caused hundreds of millions of infections and millions of deaths worldwide. Due to the lack of specific vaccines and effective treatments for COVID-19, there is an urgent need to identify effective drugs. Traditional Chinese medicine (TCM) is a valuable resource for identifying novel anti-SARS-CoV-2 drugs based on the important contribution of TCM and its potential benefits in COVID-19 treatment. Herein, we aimed to discover novel anti-SARS-CoV-2 compounds and medicinal plants from TCM by establishing a prediction method of anti-SARS-CoV-2 activity using machine learning methods. We first constructed a benchmark dataset from anti-SARS-CoV-2 bioactivity data collected from the ChEMBL database. Then, we established random forest (RF) and support vector machine (SVM) models that both achieved satisfactory predictive performance with AUC values of 0.90. By using this method, a total of 1011 active anti-SARS-CoV-2 compounds were predicted from the TCMSP database. Among these compounds, six compounds with highly potent activity were confirmed in the anti-SARS-CoV-2 experiments. The molecular fingerprint similarity analysis revealed that only 24 of the 1011 compounds have high similarity to the FDA-approved antiviral drugs, indicating that most of the compounds were structurally novel. Based on the predicted anti-SARS-CoV-2 compounds, we identified 74 anti-SARS-CoV-2 medicinal plants through enrichment analysis. The 74 plants are widely distributed in 68 genera and 43 families, 14 of which belong to antipyretic detoxicate plants. In summary, this study provided several medicinal plants with potential anti-SARS-CoV-2 activity, which offer an attractive starting point and a broader scope to mine for potentially novel anti-SARS-CoV-2 drugs.     

Data mining the NCI60 to predict generalized cytotoxicity

Elimination of cytotoxic compounds in the early and later stages of drug discovery can help reduce the costs of research and development. Through the application of principal components analysis (PCA), we were able to data mine and prove that approximately 89% of the total log GI 50 variance is due to the nonspecific cytotoxic nature of substances. Furthermore, PCA led to the identification of groups of structurally unrelated substances showing very specific toxicity profiles, such as a set of 45 substances toxic only to the Leukemia_SR cancer cell line. In an effort to predict nonspecific cytotoxicity on the basis of the mean log GI 50, we created a decision tree using MACCS keys that can correctly classify over 83% of the substances as cytotoxic/noncytotoxic in silico, on the basis of the cutoff of mean log GI 50 = -5.0. Finally, we have established a linear model using least-squares in which nine of the 59 available NCI60 cancer cell lines can be used to predict the mean log GI 50. The model has R (2) = 0.99 and a root-mean-square deviation between the observed and calculated mean log GI 50 (RMSE) = 0.09. Our predictive models can be applied to flag generally cytotoxic molecules in virtual and real chemical libraries, thus saving time and effort.     

Design,synthesis and experimental validation of novel potential chemopreventive agents using random forest and support vector machine binary classifiers

Compared to the current knowledge on cancer chemotherapeutic agents, only limited information is available on the ability of organic compounds, such as drugs and/or natural products, to prevent or delay the onset of cancer. In order to evaluate chemical chemopreventive potentials and design novel chemopreventive agents with low to no toxicity, we developed predictive computational models for chemopreventive agents in this study. First, we curated a database containing over 400 organic compounds with known chemoprevention activities. Based on this database, various random forest and support vector machine binary classifiers were developed. All of the resulting models were validated by cross validation procedures. Then, the validated models were applied to virtually screen a chemical library containing around 23,000 natural products and derivatives. We selected a list of 148 novel chemopreventive compounds based on the consensus prediction of all validated models. We further analyzed the predicted active compounds by their ease of organic synthesis. Finally, 18 compounds were synthesized and experimentally validated for their chemopreventive activity. The experimental validation results paralleled the cross validation results, demonstrating the utility of the developed models. The predictive models developed in this study can be applied to virtually screen other chemical libraries to identify novel lead compounds for the chemoprevention of cancers.     

基于QSAR模型的有机磷化合物毒性预测

随着有机磷化合物(OPs)的广泛应用,其在越来越多的环境介质中被检测出来。大多数OPs具有毒性,但人们缺乏快速且有效的预测手段来对毒性进行评估。本文将结合E-Dragon软件计算的分子描述符,采用不同的QSAR模型对36个OPs的毒性进行预测。文中采用后退法作为描述符筛选方法,以均方根误差(RMSE)作为评价标准,共找到14个对线性核函数支持向量机(SVM)模型贡献较大的描述符;在最终得到的SVM模型交叉验证结果中,计算值与实际值的相关系数为0. 913,均方根误差为0. 388;外部测试验证结果中,平均相对误差为9. 10%。此外,采用多元线性回归(MLR)、人工神经网络(ANN)以及偏最小二乘回归(PLS)模型对OPs的毒性进行预测,交叉验证结果显示,三个模型的计算值与实际值的相关系数分别为0. 878、0. 686与0. 620,没有SVM模型的预测能力好。因此采用线性核函数的SVM模型对OPs进行毒性预测是一个行之有效的方法。     

Challenges for the Periodic Systems of Elements: Chemical,Historical and Mathematical Perspectives

We celebrate 150 years of periodic systems that reached their maturity in the 1860s. They began as pedagogical efforts to project corpuses of substances on the similarity and order relationships of the chemical elements. However, these elements are not the canned substances wrongly displayed in many periodic tables, but rather the abstract preserved entities in compound transformations. We celebrate the systems, rather than their tables or ultimate table. The periodic law, we argue, is not an all-encompassing achievement, as it does not apply to every property of all elements and compounds. Periodic systems have been generalised as ordered hypergraphs, which solves the long-lasting question on the mathematical structure of the systems. In this essay, it is shown that these hypergraphs may solve current issues such as order reversals in super-heavy elements and lack of system predictive power. We discuss research in extending the limits of the systems in the super-heavy-atom region and draw attention to other limits: the antimatter region and the limit arising from compounds under extreme conditions. As systems depend on the known chemical substances (chemical space) and such a space grows exponentially, we wonder whether systems still aim at projecting knowledge of compounds on the relationships among the elements. We claim that systems are not based on compounds anymore, rather on 20th century projections of the 1860s systems of elements on systems of atoms. These projections bring about oversimplifications based on entities far from being related to compounds. A linked oversimplification is the myth of vertical group similarity, which raises questions on the approaches to locate new elements in the system. Finally, we propose bringing back chemistry to the systems by exploring similarity and order relationships of elements using the current information of the chemical space. We ponder whether 19th century periodic systems are still there or whether they have faded away, leaving us with an empty 150^th celebration.     

Lead hopping using SVM and 3D pharmacophore fingerprints

The combination of 3D pharmacophore fingerprints and the support vector machine classification algorithm has been used to generate robust models that are able to classify compounds as active or inactive in a number of G-protein-coupled receptor assays. The models have been tested against progressively more challenging validation sets where steps are taken to ensure that compounds in the validation set are chemically and structurally distinct from the training set. In the most challenging example, we simulate a lead-hopping experiment by excluding an entire class of compounds (defined by a core substructure) from the training set. The left-out active compounds comprised approximately 40% of the actives. The model trained on the remaining compounds is able to recall 75% of the actives from the "new" lead series while correctly classifying >99% of the 5000 inactives included in the validation set.     

Predictive models for cytochrome p450 isozymes based on quantitative high throughput screening data

The human cytochrome P450 (CYP450) isozymes are the most important enzymes in the body to metabolize many endogenous and exogenous substances including environmental toxins and therapeutic drugs. Any unnecessary interactions between a small molecule and CYP450 isozymes may raise a potential to disarm the integrity of the protection. Accurately predicting the potential interactions between a small molecule and CYP450 isozymes is highly desirable for assessing the metabolic stability and toxicity of the molecule. The National Institutes of Health Chemical Genomics Center (NCGC) has screened a collection of over 17,000 compounds against the five major isozymes of CYP450 (1A2, 2C9, 2C19, 2D6, and 3A4) in a quantitative high throughput screening (qHTS) format. In this study, we developed support vector classification (SVC) models for these five isozymes using a set of customized generic atom types. The CYP450 data sets were randomly split into equal-sized training and test sets. The optimized SVC models exhibited high predictive power against the test sets for all five CYP450 isozymes with accuracies of 0.93, 0.89, 0.89, 0.85, and 0.87 for 1A2, 2C9, 2C19, 2D6, and 3A4, respectively, as measured by the area under the receiver operating characteristic (ROC) curves. The important atom types and features extracted from the five models are consistent with the structural preferences for different CYP450 substrates reported in the literature. We also identified novel features with significant discerning power to separate CYP450 actives from inactives. These models can be useful in prioritizing compounds in a drug discovery pipeline or recognizing the toxic potential of environmental chemicals.     

基于分子描述符和机器学习方法预测和虚拟筛选乳腺癌靶向蛋白HEC1抑制剂

HEC1(癌症高表达蛋白)是纺锤体检查点控制、着丝粒功能、细胞存活的关键的有丝分裂调节器,与原发性乳腺癌的不良预后有关.筛选具有高亲和力的HEC1新型抑制剂对探索乳腺癌的靶向治疗具有重要意义.本文从结构多样性的化合物库中筛选HEC1抑制剂.通过对分子描述符的特征筛选,采用支持向量机(SVM)和随机森林(RF)方法分别对HEC1抑制剂和非抑制剂建立了分类模型.经对比, RF模型显示了更好的预测精度.我们采用RF模型对HEC1抑制剂进行了虚拟筛选,从“in-house”实体库筛选得到2个潜在的HEC1抑制剂分子.随后对筛出的化合物进行了体外活性实验,发现对乳腺癌细胞株MDA-MB-468和MDA-MB-231均有一定程度的抗肿瘤活性.研究结果表明,机器学习方法对于设计和虚拟筛选HEC1抑制剂有良好的效果.     

Electrochemical oxidation of p-hydroxybenzoic and protocathecuic acids at a dimensional stable anode (DSA) in the presence of NaCl

This work is part of a wider research programme on innovative technologies for industrial wastewater treatment. Results from electrolyses at DSA commercial anodes of synthetic solutions with composition analogous to that of agro-industrial wastes are presented. The results obtained indicate that the rate of degradation of phenolic compounds is high, provided that chloride ions are present in solution. Oxidation of phenolic compounds is faster than that of biodegradable substances, such as sugars or amminoacids. Moreover, investigation on the trend of toxicity during the treatment, seems to exclude that toxic intermediates persist in solution when phenolic compounds are removed. Experiments on olive oil mill wastewater (OMW) samples show that the results obtained from synthetic solutions are extensible to real wastewater. When phenolic compounds are completely removed, the toxicity of the solution is very low; the initial dark colour of the solution, due to the brown pigment which characterises OMW, is nearly completely disappeared.     

Combinatorial Synthesis of Small Organic Molecules

Combinatorial synthesis has developed within a few years from a laboratory curiosity to a method that is taken seriously in drug research. Rapid progress in molecular biology and the resulting ability to determine the activity of new substances extremely efficiently have led to a change in paradigm for the synthesis of test compounds: in addition to the conventional procedure of synthesizing one substance after another, new methods allowing simultaneous creation of many structurally defined substances are becoming increasingly important. A characteristic of combinatorial synthesis is that a reaction is performed with many synthetic building blocks at once—in parallel or in a mixture— rather than with just one building block. All possible combinations are formed in each step, so that a large number of products, a so-called library, is obtained from only a few reactants. Several methods have been developed for combinatorial synthesis of small organic molecules, based on research into peptide library synthesis: single substances are produced by highly automated parallel syntheses, and special techniques enable targeted synthesis of mixtures with defined components. Many structures can be obtained by combinatorial synthesis, and the size of the libraries created ranges from a few individual compounds to many thousand substances in mixtures. This article gives an overview of the combinatorial syntheses of small organic molecules reported to date, performed both in solution and on a solid support. In addition, different techniques for identification of active compounds in mixtures are presented, together with ways to automate syntheses and process the large amounts of data produced. An overview of pionering companies active in this area is also given. The final outlook attempts to predict the future development of this exponentially growing area and the influence of this new thinking in other areas of chemistry.     

Classification of highly unbalanced CYP450 data of drugs using cost sensitive machine learning techniques

In this paper, we study the classifications of unbalanced data sets of drugs. As an example we chose a data set of 2D6 inhibitors of cytochrome P450. The human cytochrome P450 2D6 isoform plays a key role in the metabolism of many drugs in the preclinical drug discovery process. We have collected a data set from annotated public data and calculated physicochemical properties with chemoinformatics methods. On top of this data, we have built classifiers based on machine learning methods. Data sets with different class distributions lead to the effect that conventional machine learning methods are biased toward the larger class. To overcome this problem and to obtain sensitive but also accurate classifiers we combine machine learning and feature selection methods with techniques addressing the problem of unbalanced classification, such as oversampling and threshold moving. We have used our own implementation of a support vector machine algorithm as well as the maximum entropy method. Our feature selection is based on the unsupervised McCabe method. The classification results from our test set are compared structurally with compounds from the training set. We show that the applied algorithms enable the effective high throughput in silico classification of potential drug candidates.     

Toxication of Foreign Substances by Conjugation Reactions

Elucidation of the metabolic pathways of foreign compounds in mammalian organisms contributes substantially to the understanding of toxic effects and is therefore a basic component of every risk analysis. The abundance of chemical reactions which take part in metabolic transformations allows one to speculate that we, with our present state of knowledge, are just at the beginning of a development which will help explain the interplay between chemical structure, biochemical transformation and toxic effects. This applies in particular to the conjugation of foreign compounds with structures and molecules endogenous to the body. Until recently it was thought that these conjugation reactions lead to chemically and biologically inert products, which could be easily eliminated by the organism. Using new biological testing procedures and sensitive methods of analysis, this assumption has been refuted. The fact is, that highly toxic, mutagenic and carcinogenic products can result from the chemical interactions of foreign substances with endogenous substrates.