Antibiotic Resistance Determination Utilizing Machine Learning

利用机器学习确定抗生素耐药性

• 批准号: 10663905
• 负责人: David Elihu Greenberg
• 金额: $ 47.87万
• 依托单位: UT SOUTHWESTERN MEDICAL CENTER
• 依托单位国家: 美国
• 财政年份: 2022
• 资助国家: 美国
• 起止时间: 2022-07-12 至 2025-04-30
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10663905
• 关键词: Algorithms; Antibiotic Resistance; Antibiotic susceptibility; Antibiotics; Antimicrobial susceptibility; Artificial Intelligence; Bacteria; Bacterial Antibiotic Resistance; Bacterial Drug Resistance; Bacterial Genome; Bacterial Infections; Biological Assay; Clinical; Collection; Combined Antibiotics; Communicable Diseases; Communities; Culture Techniques; Custom; Cystic Fibrosis; Data; Data Collection; Data Science; Development; Diagnosis; Diagnostic; Electronic Health Record; Ensure; Epidemiology; Face; Feedback; Foundations; Generations; Goals; Individual; Infrastructure; Laboratories; Machine Learning; Mass Spectrum Analysis; Methodology; Methods; Modeling; Molecular; Online Systems; Organism; Output; Patient Care; Patients; Pattern; Performance; Pharmaceutical Preparations; Phenotype; Physicians; Procedures; Process; Proteins; Public Health; Pulmonary Cystic Fibrosis; Reproducibility; Research; Research Personnel; Resistance; Resistance development; Resources; Sampling; Solid; Specimen; Speed; Techniques; Technology; Test Result; Testing; Time; Validation; Variant; Visualization software; Work; algorithm development; antimicrobial; chronic infection; cloud based; cohort; community engagement; computerized tools; cost; deep learning; deep learning model; design; effective therapy; emerging pathogen; empowerment; falls; genome sequencing; genomic data; in silico; infectious disease treatment; informatics tool; innovation; interest; large datasets; machine learning algorithm; machine learning model; machine learning prediction; microbial; novel; online resource; open source; pathogen; pathogenic bacteria; phenotypic data; prediction algorithm; predictive modeling; programs; prospective; resistance mechanism; tool; tool development; transfer learning; usability; user-friendly; web site; whole genome

Summary Our long-term objective is to tackle antibiotic resistance by developing accurate and interpretable prediction machine learning models that could be used clinically to speed up the care of patients with bacterial infections. Current approaches to diagnosing bacterial infections rely on first culturing a pathogen from a collected specimen followed by a variety of phenotypic tests to determine what antibiotic a particular bacterial isolate would be sensitive or resistant to. This process can, in many cases, take days to finish. Developing an accurate way to predict antibiotic resistance utilizing whole-genome sequencing data without the need for phenotypic testing is the overall goal of this project. Our team applies the latest advances in deep learning and cloud computation. We will pursue the following Specific Aims: 1) Curate a large dataset and develop a deep-learning prediction model with state-of-the-art accuracies for a wide range of bacterial species and antibiotic combinations; 2) Develop personalized machine learning models for chronic infections; 3) create open-sourced scalable user- friendly resources for the broad research community. The successful completion of this work will provide a paradigm shift in the way we diagnose bacterial infections and speed up the time to providing the correct antibiotic for a specific pathogen.

总结 我们的长期目标是通过开发准确和可解释的预测来解决抗生素耐药性问题 这些机器学习模型可用于临床，以加快对细菌感染患者的护理。 目前诊断细菌感染的方法依赖于首先从收集的标本中培养病原体 随后进行各种表型测试，以确定特定细菌分离物是什么抗生素 对……敏感或者抵抗。在许多情况下，这个过程可能需要几天才能完成。开发一种准确的方法， 利用全基因组测序数据预测抗生素耐药性，而不需要进行表型测试， 这个项目的总体目标。我们的团队应用了深度学习和云计算的最新进展。 我们将追求以下具体目标：1）管理大型数据集并开发深度学习预测 模型具有最先进的精度，适用于各种细菌物种和抗生素组合; 2） 开发针对慢性感染的个性化机器学习模型; 3）创建开源的可扩展用户- 为广大研究界提供友好的资源。这项工作的顺利完成将提供一个 我们诊断细菌感染的方式发生范式转变，并加快提供正确治疗的时间 针对特定病原体的抗生素。