Real-time prediction of cellular states in 3D lattice light sheet microscopy

项目概述：这个由MRC资助的博士培训伙伴关系（DTP）将尖端的分子和分析科学与数据分析中的创新计算方法结合在一起，使学生能够解决以假设为主导的生物医学研究问题。这是一个为期4年的计划，其第一年涉及一系列教学模块和两个基于实验室的研究项目，导致跨学科生物医学研究硕士学位。前两个学期包括一系列教学模块，让学生在多学科科学中获得坚实的基础。学生还参加了一系列由学术和行业专家领导的大师班，这些专家在分子，细胞和组织动力学，微生物学和感染，应用生物医学技术以及人工智能和数据科学领域。在第三和夏季学期，学生在他们选择的实验室进行两个为期11周的研究项目。 项目概述：点阵光片显微镜（LLSM）是一种新技术，可以在1秒的时间尺度上以3D方式可视化快速细胞过程。然而，LLSM的吞吐量非常低，限制了其用于研究罕见事件，如细胞分裂。通过与工业合作伙伴Intelligent Imaging Innovations Ltd.（3 i）（LLSM供应商）的密切合作，我们将开发一个集成的成像管道，使用最先进的机器学习对细胞周期中有生理意义的事件进行分类和预测。其主要目标是：1）实现图像采集的自动化控制并提高其吞吐量; 2）能够从早期阶段分析统计学上显著数量的明确定义的细胞事件及其进展，即使是最专业的人类实验者也经常忽略这些事件。对3D成像数据进行详细的时空分析将有助于更好地了解细胞分裂不同阶段的时间和控制，并识别细胞分裂中更微妙的缺陷，这些缺陷可能影响发育或疾病，如癌症，其中分裂不受控制。这是一个跨学科的项目，在细胞生物学，计算机科学和工程的接口，使基础科学，以改善人类健康，通过世界一流的生物医学研究。健康重点是使生物学研究能够深入遗传风险和疾病机制，旨在制定早期诊断和治疗的新战略。学生将接受的具体培训是面向定量和跨学科的技能和整个生物体生理学的理解，除了在主要项目的单细胞。先进的机器学习和计算培训解决了对团队科学家和技术专家的需求，并将有助于建立未来可供生物医学界使用的新软件技术和成像仪器。

Programme overview:This MRC-funded doctoral training partnership (DTP) brings together cutting-edge molecular and analytical sciences with innovative computational approaches in data analysis to enable students to address hypothesis-led biomedical research questions. This is a 4-year programme whose first year involves a series of taught modules and two laboratory-based research projects that lead to an MSc in Interdisciplinary Biomedical Research. The first two terms consist of a selection of taught modules that allow students to gain a solid grounding in multidisciplinary science. Students also attend a series of masterclasses led by academic and industry experts in areas of molecular, cellular and tissue dynamics, microbiology and infection, applied biomedical technologies and artificial intelligence and data science. During the third and summer terms students conduct two eleven-week research projects in labs of their choice. Project overview: Lattice light sheet microscopy (LLSM) is a new technology to visualise fast cellular processes at the time scale of 1 second, in 3D. LLSM is very low through-put however, limiting its use for studying rare events, such as cell divisions. In close collaboration with industrial partner Intelligent Imaging Innovations Ltd. (3i), suppliers of LLSM, we will develop an integrated imaging pipeline to classify and anticipate physiologically meaningful events during the cell cycle using state of the art machine learning. The main goal is to 1) enable automated control of the image acquisition and increase its throughput, and 2) make it possible to analyse statistically significant numbers of well-defined cellular events and their progression from an early stage, which often go unnoticed by even the most expert human experimenter. Enabling detailed spatio-temporal analysis of the 3D imaging data will help to better understand the timing and control of different stages of cell division and recognise more subtle defects in cell division which can affect development or diseases such as cancer where divisions occur uncontrolled. This is an interdisciplinary project at the interface of cell biology, computer science and engineering, enabling fundamental science to improve human health through world-class biomedical research. Health focus is enabling biological research into genetic risk and disease mechanisms, aiming at new strategies for early diagnosis and treatment. The specific training the student will receive is geared towards quantitative and interdisciplinary skills and understanding of whole organism physiology in addition to that of single cells in the main project. The training in advanced machine learning and computing addresses the demand for team scientists and technology specialists and will help to build new software technologies and imaging instruments that will become available to the biomedical community in the future.