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.

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 more than 110 million compound entries as of October 2020. 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 articial neural networks, and different encoding approaches for the chemical structures, including cheminformatics fingerprints and character-based encoding from chemical line notation representations. We nd 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.

The Transporter Classification Database (TCDB): 2021 update

The Transporter Classification Database (TCDB; tcdb.org) is a freely accessible reference resource, which provides functional, structural, mechanistic, medical and biotechnological information about transporters from organisms of all types. TCDB is the only transport protein classification database adopted by the International Union of Biochemistry and Molecular Biology (IUBMB) and now (October 1, 2020) consists of 20 653 proteins classified in 15 528 non-redundant transport systems with 1567 tabulated 3D structures, 18 336 reference citations describing 1536 transporter families, of which 26% are members of 82 recognized superfamilies. Overall, this is an increase of over 50% since the last published update of the database in 2016. This comprehensive update of the database contents and features include (i) adoption of a chemical ontology for substrates of transporters, (ii) inclusion of new superfamilies, (iii) a domain-based characterization of transporter families for the identification of new members as well as functional and evolutionary relationships between families, (iv) development of novel software to facilitate curation and use of the database, (v) addition of new subclasses of transport systems including 11 novel types of channels and 3 types of group translocators and (vi) the inclusion of many man-made (artificial) transmembrane pores/channels and carriers.

The Chemical Philosophy of Robert Boyle

This book examines the way in which Robert Boyle seeks to accommodate his complex chemical philosophy within the framework of a mechanistic theory of matter. More specifically, the book proposes that Boyle regards chemical qualities as properties that emerge from the mechanistic structure of chymical atoms. Within Boyle’s chemical ontology, chymical atoms are structured concretions of particles that Boyle regards as chemically elementary entities, that is, as chemical wholes that resist experimental analysis. Although this interpretation of Boyle’s chemical philosophy has already been suggested by other Boyle scholars, the present book provides a sustained philosophical argument to demonstrate that, for Boyle, chemical properties are dispositional, relational, emergent, and supervenient properties. This argument is strengthened by a detailed mereological analysis of Boylean chymical atoms that establishes the kind of theory of wholes and parts that is most consistent with his emergentist conception of chemical properties. The emergentist position that is being attributed to Boyle supports his view that chemical reactions resist direct explanation in terms of the mechanistic properties of fundamental particles, as well as his position regarding the scientific autonomy of chemistry from mechanics and physics.

Boyle’s View of Chemical Properties as Dispositional, Relational, and Emergent Properties

This chapter presents original arguments for the view that Boyle regarded chemical properties as being dispositional, relational, and emergent properties. The chapter begins by discussing the hierarchy of properties in Boyle’s chemical ontology and Boyle’s notion of sensible properties as being dispositional and relational. Both of these sections are informed by Peter Anstey’s discussion of these topics. The chapter then moves beyond Anstey’s discussion by arguing for the view that Boyle regarded chemical properties as dispositional, relational, emergent, and supervenient properties. The chapter cites many examples from Boyle’s writings to demonstrate that he considered chemical properties to display the various features that are required for emergence, that is, supervenience, non-summative difference, and underdetermination. After this extensive discussion, the chapter concludes by establishing that Boyle also considered cosmical qualities as dispositional and relational, thus demonstrating the considerable philosophical sophistication of Boyle’s natural philosophy and of his entire experimental programme.

iATC-FRAKEL: a simple multi-label web server for recognizing anatomical therapeutic chemical classes of drugs with their fingerprints only

Motivation Anatomical therapeutic chemical (ATC) classification system is very important for drug utilization and studies. Correct prediction of the 14 classes in the first level for given drugs is an essential problem for the study on such system. Several multi-label classifiers have been proposed in this regard. However, only two of them provided the web servers and their performance was not very high. On the other hand, although some rest classifiers can provide better performance, they were built based on some prior knowledge on drugs, such as information of chemical–chemical interaction and chemical ontology, leading to limited applications. Furthermore, provided codes of these classifiers are almost inaccessible for pharmacologists. Results In this study, we built a simple web server, namely iATC-FRAKEL. This web server only required the SMILES format of drugs as input and extracted their fingerprints for making prediction. The performance of the iATC-FRAKEL was much higher than all existing web servers and was comparable to the best multi-label classifier but had much wider applications. Such web server can be visited at http://cie.shmtu.edu.cn/iatc/index. Availability and implementation The web server is available at http://cie.shmtu.edu.cn/iatc/index. Contact [email protected] Supplementary information Supplementary data are available at Bioinformatics online.