Extraction of Data on Parent Compounds and Their Metabolites from Texts of Scientific Abstracts

Abstract

The growing amount of experimental data on chemical objects includes properties of small molecules, results of studies of their interaction with human and animal proteins, and methods of synthesis of organic compounds (OCs). The data obtained can be used to identify the names of OCs automatically, including all possible synonyms and relevant data on the molecular properties and biological activity. Utilization of different synonymic names of chemical compounds allows researchers to increase the completeness of data on their properties available from publications. Enrichment of the data on the names of chemical compounds by information about their possible metabolites can help estimate the biological effects of parent compounds and their metabolites more thoroughly. Therefore, an attempt at automated extraction of the names of parent compounds and their metabolites from the texts is a rather important task. In our study, we aimed at developing a method that provides the extraction of the named entities (NEs) of parent compounds and their metabolites from abstracts of scientific publications. Based on the application of the conditional random fields' algorithm, we extracted the NEs of chemical compounds. We developed a set of rules allowing identification of parent compound NEs and their metabolites in the texts. We evaluated the possibility of extracting the names of potential metabolites based on cosine similarity between strings representing names of parent compounds and all other chemical NEs found in the text. Additionally, we used conditional random fields to fetch the names of parent compounds and their metabolites from the texts based on the corpus of texts labeled manually. Our computational experiments showed that usage of rules in combination with cosine similarity could increase the accuracy of recognition of the names of metabolites compared to the rulebased algorithm and application of a machine-learning algorithm (conditional random fields).

Chemical named entity recognition in the texts of scientific publications using the naïve Bayes classifier approach

“…It was shown that the half-maximal inhibitory concentration of SARS-CoV-2 Mpro by dihydromyricetin reached 1.76 µM. Additionally, the authors [ 42 ] confirmed the activity of dihydromyricetin on the proteins included in the TGF-β 1/Smad pathway, which are responsible for the development of pulmonary fibrosis.…”

“…Many various artificial intelligence (AI) approaches aimed at chemical and biological named entity recognition have been developed [ 15 , 18 , 21 ]. Most approaches that have been under recent development for several years are based on the usage of neural networks with different variants of long-short term memory (LSTM) architecture or conditional random fields (CRF) [ 16 , 42 ].…”

“…As an input, CRF based models require a set of parameters for sequences of tokens. Our previously developed approach for CNER based on CRF allows extraction of chemical named entities with precision 0,91 and recall 0,87 [16,42]. Tang and colleagues [44] performed a comparison of CRF-based and structured support vector machines (SSVM)-based CNER model performance.…”

Identification of Molecular Mechanisms Involved in Viral Infection Progression Based on Text Mining: Case Study for HIV Infection

“…Using the set of pattern phrases [ 19 ], we obtained a set of interaction maps between human and viral genes and (or) proteins. An example of such an interaction map is provided in Figure 1 for the set of human proteins that can bind or modulate HIV proteins and which most commonly appear in scientific publications.…”

“…To identify interactions between pairs of proteins, genes, and protein–gene interactions, we used the rule-based approach described in the study by O. Tarasova et al [ 19 ]. Initially, a set of pattern phrases that indicate association (e.g., “is up-regulated by”) were identified by manual analysis of the text.…”