Machine-Learning Approach to Label-free Detection of new Bacterial Pathogens

无标记检测新细菌病原体的机器学习方法

• 批准号: 8070004
• 负责人: Murat Dundar
• 金额: $ 14.79万
• 依托单位: INDIANA UNIV-PURDUE UNIV AT INDIANAPOLIS
• 依托单位国家: 美国
• 财政年份: 2010
• 资助国家: 美国
• 起止时间: 2010-05-15 至 2013-04-30
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/8070004
• 关键词: Academia; Accounting; Address; Algorithms; American; Applications Grants; Bacteria; Benchmarking; Biochemical Process; Centers for Disease Control and Prevention (U.S.); Characteristics; Classification; Collaborations; Complex; Computer Vision Systems; Critiques; Data Set; Detection; Disease; Disease Outbreaks; Escherichia coli; Food; Food Supply; Frequencies; Future; Genus staphylococcus; Goals; Grant; Head; Health; Industry; Infection; International; Knowledge Discovery; Label; Lasers; Learning; Libraries; Listeria; Machine Learning; Manuscripts; Medical; Methods; Modeling; Mutate; Mutation; Nature; Optics; Paper; Pathogenicity; Pattern; Pattern Recognition; Peer Review; Phenotype; Process; Productivity; Public Health; Published Comment; Qualifying; Reagent; Recording of previous events; Reporting; Research; Research Methodology; Safety; Salmonella; Sampling; Screening procedure; Secure; Serotyping; Solutions; Suggestion; System; Techniques; Technology; Test Result; Testing; Textbooks; Time; Training; Update; Validation; Vibrio; Work; base; cost; data mining; disorder prevention; falls; foodborne; foodborne pathogen; image processing; improved; interest; light scattering; new technology; novel strategies; optical sensor; pathogen; pathogenic bacteria; rapid detection; sensor; simulation; symposium; text searching; tool

DESCRIPTION (provided by applicant): We appreciate the time and effort spent by all the reviewers, and we are grateful for the useful comments and provided suggestions. We have carefully reviewed the critiques and we are happy to see that the panel was receptive to our proposal. The reviewers expressed three major concerns in the summary statement: (1) although the investigating team is well qualified our history of collaboration is short; (2) details regarding the practical constraints of the BARDOT system are lacking; (3) the machine learning techniques employed in the project are considered fairly standard. Below we briefly discuss the reviewers comments and indicate how we have changed our revised application to address the critique. (1) Dr. Dundar moved from industry to academia in the fall of 2008, at which point Dr. Rajwa (one of the original inventors of BARDOT) and Dr. Dundar began their collaboration on new approaches to the problem of non-exhaustively defined classes in phenotypic screening. This scientific partnership immediately produced interesting results, and at the time of submission of the original application, Dr. Dundar and Dr. Rajwa had their first manuscript under review. The approach presented in the original proposal was tested and the results were submitted to the ACM 15th Annual SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD'09), which is the largest and one of the most respected conferences in this field. The manuscript was accepted after a full peer review as one of the 50 regular papers selected from 551 submissions [20]. Following the proposal submission, research efforts continued and produced yet another approach to the problem described in this grant application. The preliminary findings are reported in a new manuscript which is currently under review [4]. (2) We rewrote the background and research methods sections of our proposal to include information re- quested by the reviewers regarding practical aspects of the BARDOT system, such as accuracy issues (Section D.3.2), frequency of encountering new, unknown classes (Section B.3.1), and validation (Section D.3.1). (3) The problem of phenotypic screening and classification of bacteria can be defined within exhaustive (stan- dard) or non-exhaustive learning frameworks. Although we agree that the implementation of an exhaustive clas- sification approach for BARDOT does require only fairly standard tools, the problem of the non-exhaustive nature of training libraries cannot be addressed by straightforward use of any textbook-level technique. In fact, the presence of non-exhaustively defined set of classes violates basic assumptions for most supervised learning systems. The issue of non-exhaustively defined classes is the major obstacle for application of machine learning in phenotypic analysis since the number of possible phenotypes may be infinite. In our original proposal we argued that learning with a non-exhaustively defined set of classes remains a very challenging problem, and presented evidence demonstrating that simple extensions of standard techniques cannot provide an acceptable solution. Subsequently, we proposed a new approach based on Bayesian simulation of classes and showed that preliminary results outperformed benchmark techniques [4]. Although these initial results looked promising, we did not consider the described preliminary algorithms final and definitive, and we do not believe that at this point we are able to provide an exact algorithmic solution to this complex problem. If we were able to do that, it would mean that we had already accomplished all the grant goals. The very essence of the proposed research is finding the answer to the defined problem, and the answer will remain unknown until after the work has been done. However, positive reviews and an acceptance of our work by KDD'09 conference judges, tell us that we are heading in the right direction. In the amended version of this application we propose a modified Bayesian approach based on Wishart priors (Section D.2.3). The algorithm creates new classes on the fly and evaluates maximum likelihood with the updated set of classes, gradually improving detection accuracy for future samples. We believe that this offers a substantial improvement over the previous method. Consequently, the preliminary results in Section C are updated to reflect our progress. Since the modified technique allows for classification with non-exhaustive and exhaustive sets using the same algorithm, we consolidated the previous specific aims 3 and 5 into one in the revised application.

描述（由申请人提供）：我们感谢所有审稿人所花费的时间和精力，并且感谢您提供的有用的意见和建议。我们仔细审查了这些批评，我们很高兴看到专家组接受了我们的建议。审稿人在总结陈述中表达了三个主要担忧：（1）尽管调查团队资质良好，但我们的合作历史较短； (2) 缺乏有关 BARDOT 系统实际限制的详细信息； (3)项目中采用的机器学习技术被认为是相当标准的。 下面我们简要讨论审稿人的意见，并指出我们如何更改修改后的申请以解决批评。 (1) Dundar 博士于 2008 年秋季从工业界转向学术界，此时 Rajwa 博士（BARDOT 的原始发明人之一）和 Dundar 博士开始合作开发新方法，以解决表型筛选中非详尽定义类别的问题。这种科学合作伙伴关系立即产生了有趣的结果，在提交原始申请时，Dundar 博士和 Rajwa 博士的第一份手稿正在接受审查。对原始提案中提出的方法进行了测试，并将结果提交给 ACM 第 15 届年度 SIGKDD 知识发现和数据挖掘国际会议 (KDD'09)，这是该领域规模最大、最受尊敬的会议之一。该手稿经过全面的同行评审后被接受，作为从 551 篇投稿中选出的 50 篇常规论文之一 [20]。提交提案后，研究工作继续进行，并针对本拨款申请中描述的问题提出了另一种方法。初步调查结果报告在一份新手稿中，目前正在审查中 [4]。 （2）我们重写了提案的背景和研究方法部分，以包括评审者要求的有关 BARDOT 系统实际方面的信息，例如准确性问题（第 D.3.2 节）、遇到新的未知类别的频率（第 B.3.1 节）和验证（第 D.3.1 节）。 （3）细菌的表型筛选和分类问题可以在详尽（标准）​​或非详尽的学习框架内定义。尽管我们同意 BARDOT 的详尽分类方法的实施确实只需要相当标准的工具，但训练库的非详尽性问题不能通过直接使用任何教科书级别的技术来解决。事实上，非详尽定义的类集的存在违反了大多数监督学习系统的基本假设。由于可能的表型数量可能是无限的，非详尽定义的类别问题是机器学习在表型分析中应用的主要障碍。在我们最初的提案中，我们认为使用非详尽定义的类集进行学习仍然是一个非常具有挑战性的问题，并提供了证据表明标准技术的简单扩展无法提供可接受的解决方案。随后，我们提出了一种基于贝叶斯类模拟的新方法，并表明初步结果优于基准技术 [4]。 尽管这些初步结果看起来很有希望，但我们并不认为所描述的初步算法是最终的和确定的，并且我们不相信目前我们能够为这个复杂问题提供精确的算法解决方案。如果我们能够做到这一点，那就意味着我们已经完成了所有的资助目标。拟议研究的本质是找到已定义问题的答案，而在工作完成之前答案将仍然未知。然而，KDD'09 会议评委对我们工作的积极评价和接受告诉我们，我们正在朝着正确的方向前进。 在本申请的修改版本中，我们提出了一种基于 Wishart 先验的修改贝叶斯方法（第 D.2.3 节）。该算法动态创建新类别，并使用更新的类别集评估最大似然性，逐渐提高未来样本的检测准确性。我们相信这比以前的方法有了实质性的改进。因此，C 节中的初步结果已更新，以反映我们的进展。由于修改后的技术允许使用相同的算法对非穷举和穷举集进行分类，因此我们在修订后的应用程序中将先前的具体目标 3 和 5 合并为一个。

项目成果

Laser optical sensor, a label-free on-plate Salmonella enterica colony detection tool.

• DOI: 10.1128/mbio.01019-13
• 发表时间: 2014-02-04
• 期刊: mBio
• 影响因子: 6.4
• 作者: Singh AK;Bettasso AM;Bae E;Rajwa B;Dundar MM;Forster MD;Liu L;Barrett B;Lovchik J;Robinson JP;Hirleman ED;Bhunia AK
• 通讯作者: Bhunia AK

A Machine-Learning Approach to Detecting Unknown Bacterial Serovars.

• DOI: 10.1002/sam.10085
• 发表时间: 2010-10
• 期刊: STATISTICAL ANALYSIS AND DATA MINING
• 影响因子: 1.3
• 作者: Akova, Ferit;Dundar, Murat;Davisson, V Jo;Hirleman, E Daniel;Bhunia, Arun K;Robinson, J Paul;Rajwa, Bartek
• 通讯作者: Rajwa, Bartek