CAREER: Intelligent Systems and Advanced Computation in Molecular Biology

该项目的目的是将先进计算和人工智能的研究和教育结合起来，应用于分子生物学问题。潜在的研究主题是复杂系统中结构与功能的关系。具体应用重点是增强蛋白质结构预测能力及其与功能的后续关系。结构模型和经验目标函数是从现有的科学数据库中提取出来的，从而利用了几十年来积累的巨大科学投资。对新的蛋白质序列进行结构预测，将序列与模型对齐，从而优化目标函数。一种新颖的分支定界算法允许找到真正的全局最优对齐，即使潜在的搜索问题是np困难的。教育计划创造了一个协作的环境，其中计算机科学家和生物学家都可以在跨学科的研究计划中进行互动。这两个学科的学生都可以通过对现实和重要问题的研究获得实践经验。这项研究将提高我们从序列中预测蛋白质结构和功能的能力，这是设计新型药物化合物的关键一步，实现人类基因组计划的全部潜力，并了解基本的生命过程。

The aim of this project is to integrate research and education in advanced computation and artificial intelligence as applied to problems in molecular biology. The underlying research theme is the relation of structure to function in complex systems. The specific application focus is on enhanced protein structure prediction capability and its subsequent relation to function. Structural models and empirical objective functions are extracted from the existing scientific databases, thereby capitalizing on an enormous scientific investment compiled over decades. Structural predictions for novel protein sequences are made by aligning the sequence to the models so as to optimize the objective function. A novel branch and bound algorithm permits the true global optimum alignment to be found even though the underlying search problem is NP-hard. The education program creates a collaborative setting wherein computer scientists and biologists both can interact within an interdisciplinary research program. Students from both disciplines can get hands-on experience ``learning by doing'' research on real and important problems. The research will lead to improvements in our ability to predict protein structure and function from sequence, a crucial step toward design of novel pharmaceutical compounds, realizing the full potential of the human genome project, and understanding fundamental life processes.