Neural machine translation of chemical nomenclature between English and Chinese.
Ontology highlight
ABSTRACT:
SUBMITTER: Xu T
PROVIDER: S-EPMC7460765 | biostudies-literature | 2020 Aug
REPOSITORIES: biostudies-literature
Publications
Neural machine translation of chemical nomenclature between English and Chinese.
Xu Tingjun T Chen Weiming W Zhou Junhong J Dai Jingfang J Li Yingyong Y Zhao Yingli Y
Journal of cheminformatics 20200831 1
Machine translation of chemical nomenclature has considerable application prospect in chemical text data processing between languages. However, rule based machine translation tools have to face significant complication in rule sets building, especially in translation of chemical names between English and Chinese, which are the two most used languages of chemical nomenclature in the world. We applied two types of neural networks in the task of chemical nomenclature translation between English and ...[more]
Similar Datasets
Project description:Chemical compound names remain the primary method for conveying molecular structures between chemists and researchers. In research articles, patents, chemical catalogues, government legislation, and textbooks, the use of IUPAC and traditional compound names is universal, despite efforts to introduce more machine-friendly representations such as identifiers and line notations. Fortunately, advances in computing power now allow chemical names to be parsed and generated (read and written) with almost the same ease as conventional connection tables. A significant complication, however, is that although the vast majority of chemistry uses English nomenclature, a significant fraction is in other languages. This complicates the task of filing and analyzing chemical patents, purchasing from compound vendors, and text mining research articles or Web pages. We describe some issues with manipulating chemical names in various languages, including British, American, German, Japanese, Chinese, Spanish, Swedish, Polish, and Hungarian, and describe the current state-of-the-art in software tools to simplify the process.
| S-EPMC2659868 | biostudies-other
Project description:We present Chinese translation norms for 1,429 English words. Chinese-English bilinguals (N = 28) were asked to provide the first Chinese translation that came to mind for 1,429 English words. The results revealed that 71 % of the English words received more than one correct translation indicating the large amount of translation ambiguity when translating from English to Chinese. The relationship between translation ambiguity and word frequency, concreteness and language proficiency was investigated. Although the significant correlations were not strong, results revealed that English word frequency was positively correlated with the number of alternative translations, whereas English word concreteness was negatively correlated with the number of translations. Importantly, regression analyses showed that the number of Chinese translations was predicted by word frequency and concreteness. Furthermore, an interaction between these predictors revealed that the number of translations was more affected by word frequency for more concrete words than for less concrete words. In addition, mixed-effects modelling showed that word frequency, concreteness and English language proficiency were all significant predictors of whether or not a dominant translation was provided. Finally, correlations between the word frequencies of English words and their Chinese dominant translations were higher for translation-unambiguous pairs than for translation-ambiguous pairs. The translation norms are made available in a database together with lexical information about the words, which will be a useful resource for researchers investigating Chinese-English bilingual language processing.
| S-EPMC5429370 | biostudies-literature
Project description:ObjectiveTo analyze techniques for machine translation of electronic health records (EHRs) between long distance languages, using Basque and Spanish as a reference. We studied distinct configurations of neural machine translation systems and used different methods to overcome the lack of a bilingual corpus of clinical texts or health records in Basque and Spanish.Materials and methodsWe trained recurrent neural networks on an out-of-domain corpus with different hyperparameter values. Subsequently, we used the optimal configuration to evaluate machine translation of EHR templates between Basque and Spanish, using manual translations of the Basque templates into Spanish as a standard. We successively added to the training corpus clinical resources, including a Spanish-Basque dictionary derived from resources built for the machine translation of the Spanish edition of SNOMED CT into Basque, artificial sentences in Spanish and Basque derived from frequently occurring relationships in SNOMED CT, and Spanish monolingual EHRs. Apart from calculating bilingual evaluation understudy (BLEU) values, we tested the performance in the clinical domain by human evaluation.ResultsWe achieved slight improvements from our reference system by tuning some hyperparameters using an out-of-domain bilingual corpus, obtaining 10.67 BLEU points for Basque-to-Spanish clinical domain translation. The inclusion of clinical terminology in Spanish and Basque and the application of the back-translation technique on monolingual EHRs significantly improved the performance, obtaining 21.59 BLEU points. This was confirmed by the human evaluation performed by 2 clinicians, ranking our machine translations close to the human translations.DiscussionWe showed that, even after optimizing the hyperparameters out-of-domain, the inclusion of available resources from the clinical domain and applied methods were beneficial for the described objective, managing to obtain adequate translations of EHR templates.ConclusionWe have developed a system which is able to properly translate health record templates from Basque to Spanish without making use of any bilingual corpus of clinical texts or health records.
| S-EPMC7647170 | biostudies-literature
Project description:We present a sequence-to-sequence machine learning model for predicting the IUPAC name of a chemical from its standard International Chemical Identifier (InChI). The model uses two stacks of transformers in an encoder-decoder architecture, a setup similar to the neural networks used in state-of-the-art machine translation. Unlike neural machine translation, which usually tokenizes input and output into words or sub-words, our model processes the InChI and predicts the IUPAC name character by character. The model was trained on a dataset of 10 million InChI/IUPAC name pairs freely downloaded from the National Library of Medicine's online PubChem service. Training took seven days on a Tesla K80 GPU, and the model achieved a test set accuracy of 91%. The model performed particularly well on organics, with the exception of macrocycles, and was comparable to commercial IUPAC name generation software. The predictions were less accurate for inorganic and organometallic compounds. This can be explained by inherent limitations of standard InChI for representing inorganics, as well as low coverage in the training data.
| S-EPMC8496104 | biostudies-literature
Project description:With the rapid improvement of machine translation approaches, neural machine translation has started to play an important role in retrosynthesis planning, which finds reasonable synthetic pathways for a target molecule. Previous studies showed that utilizing the sequence-to-sequence frameworks of neural machine translation is a promising approach to tackle the retrosynthetic planning problem. In this work, we recast the retrosynthetic planning problem as a language translation problem using a template-free sequence-to-sequence model. The model is trained in an end-to-end and a fully data-driven fashion. Unlike previous models translating the SMILES strings of reactants and products, we introduced a new way of representing a chemical reaction based on molecular fragments. It is demonstrated that the new approach yields better prediction results than current state-of-the-art computational methods. The new approach resolves the major drawbacks of existing retrosynthetic methods such as generating invalid SMILES strings. Specifically, our approach predicts highly similar reactant molecules with an accuracy of 57.7%. In addition, our method yields more robust predictions than existing methods.
| S-EPMC7802345 | biostudies-literature
Project description:Metabolic processes in the human body can alter the structure of a drug affecting its efficacy and safety. As a result, the investigation of the metabolic fate of a candidate drug is an essential part of drug design studies. Computational approaches have been developed for the prediction of possible drug metabolites in an effort to assist the traditional and resource-demanding experimental route. Current methodologies are based upon metabolic transformation rules, which are tied to specific enzyme families and therefore lack generalization, and additionally may involve manual work from experts limiting scalability. We present a rule-free, end-to-end learning-based method for predicting possible human metabolites of small molecules including drugs. The metabolite prediction task is approached as a sequence translation problem with chemical compounds represented using the SMILES notation. We perform transfer learning on a deep learning transformer model for sequence translation, originally trained on chemical reaction data, to predict the outcome of human metabolic reactions. We further build an ensemble model to account for multiple and diverse metabolites. Extensive evaluation reveals that the proposed method generalizes well to different enzyme families, as it can correctly predict metabolites through phase I and phase II drug metabolism as well as other enzymes. Compared to existing rule-based approaches, our method has equivalent performance on the major enzyme families while it additionally finds metabolites through less common enzymes. Our results indicate that the proposed approach can provide a comprehensive study of drug metabolism that does not restrict to the major enzyme families and does not require the extraction of transformation rules.
| S-EPMC8162519 | biostudies-literature
Project description:With the development of next generation sequencing techniques, it is fast and cheap to determine protein sequences but relatively slow and expensive to extract useful information from protein sequences because of limitations of traditional biological experimental techniques. Protein function prediction has been a long standing challenge to fill the gap between the huge amount of protein sequences and the known function. In this paper, we propose a novel method to convert the protein function problem into a language translation problem by the new proposed protein sequence language "ProLan" to the protein function language "GOLan", and build a neural machine translation model based on recurrent neural networks to translate "ProLan" language to "GOLan" language. We blindly tested our method by attending the latest third Critical Assessment of Function Annotation (CAFA 3) in 2016, and also evaluate the performance of our methods on selected proteins whose function was released after CAFA competition. The good performance on the training and testing datasets demonstrates that our new proposed method is a promising direction for protein function prediction. In summary, we first time propose a method which converts the protein function prediction problem to a language translation problem and applies a neural machine translation model for protein function prediction.
| S-EPMC6151571 | biostudies-literature
Project description:With the rapid development of big data and deep learning, breakthroughs have been made in phonetic and textual research, the two fundamental attributes of language. Language is an essential medium of information exchange in teaching activity. The aim is to promote the transformation of the training mode and content of translation major and the application of the translation service industry in various fields. Based on previous research, the SCN-LSTM (Skip Convolutional Network and Long Short Term Memory) translation model of deep learning neural network is constructed by learning and training the real dataset and the public PTB (Penn Treebank Dataset). The feasibility of the model's performance, translation quality, and adaptability in practical teaching is analyzed to provide a theoretical basis for the research and application of the SCN-LSTM translation model in English teaching. The results show that the capability of the neural network for translation teaching is nearly one times higher than that of the traditional N-tuple translation model, and the fusion model performs much better than the single model, translation quality, and teaching effect. To be specific, the accuracy of the SCN-LSTM translation model based on deep learning neural network is 95.21%, the degree of translation confusion is reduced by 39.21% compared with that of the LSTM (Long Short Term Memory) model, and the adaptability is 0.4 times that of the N-tuple model. With the highest level of satisfaction in practical teaching evaluation, the SCN-LSTM translation model has achieved a favorable effect on the translation teaching of the English major. In summary, the performance and quality of the translation model are improved significantly by learning the language characteristics in translations by teachers and students, providing ideas for applying machine translation in professional translation teaching.
| S-EPMC7676682 | biostudies-literature
Project description:Background: As an emerging infectious disease, COVID-19 has garnered great research interest. We aimed to explore the differences between English language and Chinese language Medical/Scientific journals publications, particularly aiming to explore the efficacy/contents of the literature published in English and Chinese in relation to the outcomes of management and characterization of COVID-19 during the early stage of COVID-19 pandemic. Methods: Publications on COVID-19 research were retrieved from both English and Chinese databases. Bibliometric analyses were performed using VOSviewer 1.6.14, and CiteSpace V software. Network maps were generated to evaluate the collaborations between different authors, countries/provinces, and institutions. Results: A total of 143 English and 721 Chinese original research articles and reviews on COVID-19 were included in our study. Most of the authors and institutions of the papers were from China before March 1st, 2020, however, the distribution of authors and institutions were mainly in developed countries or more wealthy areas of China. The range of the keywords in English publications was more extensive than those in Chinese. Traditional Chinese Medicine was seen more frequently in Chinese papers than in English. Of the 143 articles published in English, 54 articles were published by Chinese authors only and 21 articles were published jointly by Chinese and other overseas authors. Conclusions: The publications in English have enabled medical practitioners and scientists to share/exchange information, while on the other hand, the publications in the Chinese language have provided complementary educational approaches for the local medical practitioners to understand the essential and key information to manage COVID-19 in the relatively remote regions of China, for the general population with a general level of education.
| S-EPMC7456831 | biostudies-literature
Project description:Drug discovery for a protein target is a very laborious, long and costly process. Machine learning approaches and, in particular, deep generative networks can substantially reduce development time and costs. However, the majority of methods imply prior knowledge of protein binders, their physicochemical characteristics or the three-dimensional structure of the protein. The method proposed in this work generates novel molecules with predicted ability to bind a target protein by relying on its amino acid sequence only. We consider target-specific de novo drug design as a translational problem between the amino acid "language" and simplified molecular input line entry system representation of the molecule. To tackle this problem, we apply Transformer neural network architecture, a state-of-the-art approach in sequence transduction tasks. Transformer is based on a self-attention technique, which allows the capture of long-range dependencies between items in sequence. The model generates realistic diverse compounds with structural novelty. The computed physicochemical properties and common metrics used in drug discovery fall within the plausible drug-like range of values.
| S-EPMC7801439 | biostudies-literature