{"title":"基于机器学习的药物蛋白识别方法的实证比较和分析。","authors":"Watshara Shoombuatong, Nalini Schaduangrat, Jaru Nikom","doi":"10.17179/excli2023-6410","DOIUrl":null,"url":null,"abstract":"<p><p>Efficiently and precisely identifying drug targets is crucial for developing and discovering potential medications. While conventional experimental approaches can accurately pinpoint these targets, they suffer from time constraints and are not easily adaptable to high-throughput processes. On the other hand, computational approaches, particularly those utilizing machine learning (ML), offer an efficient means to accelerate the prediction of druggable proteins based solely on their primary sequences. Recently, several state-of-the-art computational methods have been developed for predicting and analyzing druggable proteins. These computational methods showed high diversity in terms of benchmark datasets, feature extraction schemes, ML algorithms, evaluation strategies and webserver/software usability. Thus, our objective is to reexamine these computational approaches and conduct a comprehensive assessment of their strengths and weaknesses across multiple aspects. In this study, we deliver the first comprehensive survey regarding the state-of-the-art computational approaches for <i>in silico</i> prediction of druggable proteins. First, we provided information regarding the existing benchmark datasets and the types of ML methods employed. Second, we investigated the effectiveness of these computational methods in druggable protein identification for each benchmark dataset. Third, we summarized the important features used in this field and the existing webserver/software. Finally, we addressed the present constraints of the existing methods and offer valuable guidance to the scientific community in designing and developing novel prediction models. We anticipate that this comprehensive review will provide crucial information for the development of more accurate and efficient druggable protein predictors.</p>","PeriodicalId":12247,"journal":{"name":"EXCLI Journal","volume":null,"pages":null},"PeriodicalIF":3.8000,"publicationDate":"2023-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10539545/pdf/","citationCount":"0","resultStr":"{\"title\":\"Empirical comparison and analysis of machine learning-based approaches for druggable protein identification.\",\"authors\":\"Watshara Shoombuatong, Nalini Schaduangrat, Jaru Nikom\",\"doi\":\"10.17179/excli2023-6410\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><p>Efficiently and precisely identifying drug targets is crucial for developing and discovering potential medications. While conventional experimental approaches can accurately pinpoint these targets, they suffer from time constraints and are not easily adaptable to high-throughput processes. On the other hand, computational approaches, particularly those utilizing machine learning (ML), offer an efficient means to accelerate the prediction of druggable proteins based solely on their primary sequences. Recently, several state-of-the-art computational methods have been developed for predicting and analyzing druggable proteins. These computational methods showed high diversity in terms of benchmark datasets, feature extraction schemes, ML algorithms, evaluation strategies and webserver/software usability. Thus, our objective is to reexamine these computational approaches and conduct a comprehensive assessment of their strengths and weaknesses across multiple aspects. In this study, we deliver the first comprehensive survey regarding the state-of-the-art computational approaches for <i>in silico</i> prediction of druggable proteins. First, we provided information regarding the existing benchmark datasets and the types of ML methods employed. Second, we investigated the effectiveness of these computational methods in druggable protein identification for each benchmark dataset. Third, we summarized the important features used in this field and the existing webserver/software. Finally, we addressed the present constraints of the existing methods and offer valuable guidance to the scientific community in designing and developing novel prediction models. We anticipate that this comprehensive review will provide crucial information for the development of more accurate and efficient druggable protein predictors.</p>\",\"PeriodicalId\":12247,\"journal\":{\"name\":\"EXCLI Journal\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":3.8000,\"publicationDate\":\"2023-08-29\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10539545/pdf/\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"EXCLI Journal\",\"FirstCategoryId\":\"99\",\"ListUrlMain\":\"https://doi.org/10.17179/excli2023-6410\",\"RegionNum\":3,\"RegionCategory\":\"生物学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"2023/1/1 0:00:00\",\"PubModel\":\"eCollection\",\"JCR\":\"Q1\",\"JCRName\":\"BIOLOGY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"EXCLI Journal","FirstCategoryId":"99","ListUrlMain":"https://doi.org/10.17179/excli2023-6410","RegionNum":3,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2023/1/1 0:00:00","PubModel":"eCollection","JCR":"Q1","JCRName":"BIOLOGY","Score":null,"Total":0}
Empirical comparison and analysis of machine learning-based approaches for druggable protein identification.
Efficiently and precisely identifying drug targets is crucial for developing and discovering potential medications. While conventional experimental approaches can accurately pinpoint these targets, they suffer from time constraints and are not easily adaptable to high-throughput processes. On the other hand, computational approaches, particularly those utilizing machine learning (ML), offer an efficient means to accelerate the prediction of druggable proteins based solely on their primary sequences. Recently, several state-of-the-art computational methods have been developed for predicting and analyzing druggable proteins. These computational methods showed high diversity in terms of benchmark datasets, feature extraction schemes, ML algorithms, evaluation strategies and webserver/software usability. Thus, our objective is to reexamine these computational approaches and conduct a comprehensive assessment of their strengths and weaknesses across multiple aspects. In this study, we deliver the first comprehensive survey regarding the state-of-the-art computational approaches for in silico prediction of druggable proteins. First, we provided information regarding the existing benchmark datasets and the types of ML methods employed. Second, we investigated the effectiveness of these computational methods in druggable protein identification for each benchmark dataset. Third, we summarized the important features used in this field and the existing webserver/software. Finally, we addressed the present constraints of the existing methods and offer valuable guidance to the scientific community in designing and developing novel prediction models. We anticipate that this comprehensive review will provide crucial information for the development of more accurate and efficient druggable protein predictors.
期刊介绍:
EXCLI Journal publishes original research reports, authoritative reviews and case reports of experimental and clinical sciences.
The journal is particularly keen to keep a broad view of science and technology, and therefore welcomes papers which bridge disciplines and may not suit the narrow specialism of other journals. Although the general emphasis is on biological sciences, studies from the following fields are explicitly encouraged (alphabetical order):
aging research, behavioral sciences, biochemistry, cell biology, chemistry including analytical chemistry, clinical and preclinical studies, drug development, environmental health, ergonomics, forensic medicine, genetics, hepatology and gastroenterology, immunology, neurosciences, occupational medicine, oncology and cancer research, pharmacology, proteomics, psychiatric research, psychology, systems biology, toxicology