Structure-based chemical ontology improves chemometric prediction of antibacterial essential oils.

Plants are valuable resources for drug discovery as they produce diverse bioactive compounds. However, the chemical diversity makes it difficult to predict the biological activity of plant extracts via conventional chemometric methods. In this research, we propose a new computational model that integrates chemical composition data with structure-based chemical ontology. For a model validation, two training datasets were prepared from literature on antibacterial essential oils to classify active/inactive oils. Random forest classifiers constructed from the data showed improved prediction performance in both test datasets. Prior feature selection using hierarchical information criterion further improved the performance. Furthermore, an antibacterial assay using a standard strain of Staphylococcus aureus revealed that the classifier correctly predicted the activity of commercially available oils with an accuracy of 83% (= 10/12). The results of this study indicate that machine learning of chemical composition data integrated with chemical ontology can be a highly efficient approach for exploring bioactive plant extracts.

Metabology: Analysis of metabolomics data using community ecology tools.

Several areas such as microbiology, botany, and medicine use genetic information and computational tools to organize, classify and analyze data. However, only recently has it been possible to obtain the chemical ontology of metabolites computationally. The systematic classification of metabolites into classes opens the way for adapting methods that previously used genetic taxonomy to now accept chemical ontology. Community ecology tools are ideal for this adaptation as they have mature methods and enable exploratory data analysis with established statistical tools. This study introduces the Metabology approach, which transforms metabolites into an ecosystem where the metabolites (species) are related by chemical ontology. In the present work, we demonstrate the applicability of this new approach using publicly available data from a metabolomics study of human plasma that searched for prognostic markers of COVID-19, and in an untargeted metabolomics study carried out by our laboratory using Lasiodiplodia theobromae fungal pathogen supernatants.

Learning chemistry: exploring the suitability of machine learning for the task of structure-based chemical ontology classification.

Chemical data is increasingly openly available in databases such as PubChem, which contains approximately 110 million compound entries as of February 2021. With the availability of data at such scale, the burden has shifted to organisation, analysis and interpretation. Chemical ontologies provide structured classifications of chemical entities that can be used for navigation and filtering of the large chemical space. ChEBI is a prominent example of a chemical ontology, widely used in life science contexts. However, ChEBI is manually maintained and as such cannot easily scale to the full scope of public chemical data. There is a need for tools that are able to automatically classify chemical data into chemical ontologies, which can be framed as a hierarchical multi-class classification problem. In this paper we evaluate machine learning approaches for this task, comparing different learning frameworks including logistic regression, decision trees and long short-term memory artificial neural networks, and different encoding approaches for the chemical structures, including cheminformatics fingerprints and character-based encoding from chemical line notation representations. We find that classical learning approaches such as logistic regression perform well with sets of relatively specific, disjoint chemical classes, while the neural network is able to handle larger sets of overlapping classes but needs more examples per class to learn from, and is not able to make a class prediction for every molecule. Future work will explore hybrid and ensemble approaches, as well as alternative network architectures including neuro-symbolic approaches.

STS-NLSP: A Network-Based Label Space Partition Method for Predicting the Specificity of Membrane Transporter Substrates Using a Hybrid Feature of Structural and Semantic Similarity.

Membrane transport proteins play crucial roles in the pharmacokinetics of substrate drugs, the drug resistance in cancer and are vital to the process of drug discovery, development and anti-cancer therapeutics. However, experimental methods to profile a substrate drug against a panel of transporters to determine its specificity are labor intensive and time consuming. In this article, we aim to develop an in silico multi-label classification approach to predict whether a substrate can specifically recognize one of the 13 categories of drug transporters ranging from ATP-binding cassette to solute carrier families using both structural fingerprints and chemical ontologies information of substrates. The data-driven network-based label space partition (NLSP) method was utilized to construct the model based on a hybrid of similarity-based feature by the integration of 2D fingerprint and semantic similarity. This method builds predictors for each label cluster (possibly intersecting) detected by community detection algorithms and takes union of label sets for a compound as final prediction. NLSP lies into the ensembles of multi-label classifier category in multi-label learning field. We utilized Cramér's V statistics to quantify the label correlations and depicted them via a heatmap. The jackknife tests and iterative stratification based cross-validation method were adopted on a benchmark dataset to evaluate the prediction performance of the proposed models both in multi-label and label-wise manner. Compared with other powerful multi-label methods, ML-kNN, MTSVM, and RAkELd, our multi-label classification model of NLPS-RF (random forest-based NLSP) has proven to be a feasible and effective model, and performed satisfactorily in the predictive task of transporter-substrate specificity. The idea behind NLSP method is intriguing and the power of NLSP remains to be explored for the multi-label learning problems in bioinformatics. The benchmark dataset, intermediate results and python code which can fully reproduce our experiments and results are available at https://github.com/dqwei-lab/STS.

Encoding of Fundamental Chemical Entities of Organic Reactivity Interest using chemical ontology and XML.

Fundamental chemical entities are identified in the context of organic reactivity and classified as appropriate concept classes namely ElectronEntity, AtomEntity, AtomGroupEntity, FunctionalGroupEntity and MolecularEntity. The entity classes and their subclasses are organized into a chemical ontology named "ChemEnt" for the purpose of assertion, restriction and modification of properties through entity relations. Individual instances of entity classes are defined and encoded as a library of chemical entities in XML. The instances of entity classes are distinguished with a unique notation and identification values in order to map them with the ontology definitions. A model GUI named Entity Table is created to view graphical representations of all the entity instances. The detection of chemical entities in chemical structures is achieved through suitable algorithms. The possibility of asserting properties to the entities at different levels and the mechanism of property flow within the hierarchical entity levels is outlined.