人工智能助力当代化学研究

以机器学习为代表的人工智能在当代的科学研究中正在发挥越来越重要的作用.不同于传统的计算机程序,机器学习人工智能可以通过对大量数据的反复分析和自身模型的优化,即“学习”过程,从而在大量的数据中寻找客观事物的相互联系,形成具有更好预测和决策能力的新模型,做出合理的判断.化学研究的特点恰恰是机器学习人工智能的强项.化学研究经常要面对十分复杂的物质体系和实验过程,从而很难通过化学物理原理进行精准的分析和判断.人工智能可以挖掘化学实验中产生的海量实验数据的相关性,帮助化学家做出合理分析预测,大大加速化学研发过程.本文介绍了当代人工智能方法及用其解决化学问题基本原理,并通过具体案例展示了人工智能辅助解决不同化学研发问题的方法以及对应的机器学习算法.将人工智能运用在化学科学的尝试正处于蓬勃上升期,人工智能已经初步展示出对化学研究的强大助力,希望本文能帮助更多的国内的化学工作者了解和运用这一有力的工具.     

人工智能在锂离子电池研发中的应用

锂离子电池已成为解决现代社会储能问题的最佳解决方案之一。然而,电池材料和器件开发都是复杂的多变量问题,传统的依赖研究人员进行实验的试错法在电池性能提升方面遇到了瓶颈。人工智能（AI）具有强大的高速、海量数据处理能力,是上述突破研究瓶颈的最具潜力的技术。其中,机器学习 (ML) 算法在评估多维数据变量和集合之间的组合关联方面的独特优势有望帮助研究人员发现不同因素之间的相互作用规律并阐明材料合成和设备制造的机制。本综述总结了锂离子电池传统研究方法遇到的各种挑战,并详细介绍了人工智能在电池材料研究、电池器件设计与制造、材料与器件表征、电池循环寿命与安全性评估等方面的应用。最重要的是,我们介绍了AI和ML在电池研究中面临的挑战,并讨论了它们应用的缺点和前景。我们相信,未来实验科学家、数学建模专家和AI专家之间更紧密的合作将极大地促进AI和ML方法用以解决传统方法难以克服的电池和材料问题。     

分析化学计量学的若干新进展

对分析化学计量学的若干新进展进行了讨论, 侧重从作者实验室所进行的研究工作的视角论述了高维数据的分辨、用于化学信号处理的形态学理论和方法、解决复杂化学问题的多元校正和化学模式识别以及联用色谱仪二维数据的分辨新方法的发展.     

化学科普专刊序言

正化学是一门与我们人类社会发展和日常生活密切相关,充分满足社会需求的中心学科,为人类的生存和发展做出了巨大贡献。目前,以数字化、网络化、人工智能化为代表的科学技术已经深刻改变了当今世界,也在改变着人类的生产生活和思维方式。这些改变同时也在深刻影响着知识传播的方式。由于云计算、大数据、互联网和人工智能等现代信息技术的应用,科普的传播方式正在发生重大的变化,化学知识的传播以及化学对社会的影响力不能只在课堂上、考卷上,更不能只体现在我们的科     

初中生化学问题解决中元认知能力的现状分析

初中生化学问题解决中的元认知能力是构成学生化学问题解决能力的重要成分,对学生化学问题解决起着关键作用。本研究采用访谈和调查的方法对上述问题做了初步探讨。研究结果表明：（1）初中生化学问题解决中元认知能力总体水平不高,其中监测性、调控性和评价性总体偏低。（2）学优生、中等生和学困生在化学问题解决中的元认知能力差异非常显著。（3）化学问题解决中元认知能力的高低是影响初中生化学学习成绩的因素之一。     

化学计量学方法在生物组学中的应用研究

近年来,组学研究十分活跃,基因组学、蛋白组学、代谢组学等极大推动了生物学的进展,提高了人们对生命现象的认识,增强了人们与疾病斗争的能力.这些研究产生了海量的数据,促进了生物信息学的蓬勃发展,也提出了许多难点问题,化学计量学者十分关注这个领域,并积极参与研究和创新.这一方面是由于生物信息学中大多数方法与化学计量学相同,另一方面由于生物多样性及复杂性,需要不同的理论和方法,展示了巨大的空间,深深吸引我们进入生物组学研究.本文简单介绍我们研究小组近期做的工作.     

人工智能发现活性分子背景下天然药物化学教学的转型与发展*

人工智能(AI)在活性分子发现及药物筛选方面的应用日趋深入,革新了传统发现天然药物的方式,重构了药物发现及设计的格局。这就要求天然药物化学人才熟练掌握天然药物化学基础知识、具备多学科交叉分析问题能力以及培养和树立与时俱进的逻辑思维。为顺应人工智能时代发展要求,天然药物化学教学需要构建AI参与天然药物发现教学体系、提供AI参与天然药物发现的直观教学、筛选优秀网络教学资源引导学生自主学习,同时培养学生在AI参与天然药物发现中的思考能力。     

前言:化学热力学专刊

<正>化学热力学是物理化学和热力学的一个重要分支学科,其利用热力学原理研究物质体系中的化学现象和规律,根据物质体系的宏观可测性质和热力学函数关系判断体系的稳定性、变化方向和变化的程度.学科交叉发展对化学热力学不断提出新的、更高的要求,化学热力学研究目前已涵盖溶液化学热力学、热化学、相平衡、热分析、统计热力学与分子模拟、生物化学热力学、材料化学热力学、绿色化学热力学、胶体界面化学热力学、能源化学热力学等方向.发展化学热力学理论、方法和手段,解决多年来一直没有解决的重要化学热力学难题,     

高中生化学问题解决中元认知能力的实验研究

本研究以53名不同化学基础的高二学生为研究对象,采用口语报告法对高二学生化学问题解决中元认知能力做了初步探讨。结果表明:高中生化学问题解决中自我监控和自我调节能力相对偏低;学优生、中等生和学困生在化学问题解决中的元认知能力差异非常显著。     

能源材料的第一性原理模拟

能源问题是目前我国面临重要问题之一,这一问题的解决是我国实现可持续发展战略的重要环节.能源化学的发展对于能源问题的解决具有重要意义.理论计算与实验观测的结合可以促进能源化学更快更好地发展.目前,理论计算已经广泛应用于能源化学中的各个领域,包括碳基能源化学、电能转化与存储以及太阳能能源化学等.本文综述了理论计算在能源化学这些重要领域应用的研究现状及发展趋势,并提出了在进一步发展和应用中所面临的关键科学与技术问题.最后,文章对理论计算在能源化学中应用的未来发展方向进行了展望,建议了几个可能的重点基础研究方向,以期达到理论计算应用于在能源化学这一领域的终极目标——理论设计高效廉价的新型能源材料.     

Artificial intelligence in chemistry

The techniques and tools of artificial intelligence are reviewed. Chemical problems can serve as test domains for the development of new artificial intelligence methods. Artificial intelligence techniques can also be applied to the solution of practical problems in chemistry. Applications in chemistry include problems where it is necessary to encode chemical expertise, and where chemistry is merely an additional domain to which standard artificial intelligence techniques can be applied. Programs exploiting encoded chemical expertise can assist in solving problems of structure elucidation, synthesis planning, and experiment design. Robotics methods based on artifical intelligence and expert systems can enhance the performance of chemical instrumentation. Systems understanding natural language could improve the handling of chemical information, and artificial intelligence techniques may extend the capabilities of computer-assisted instruction.     

A data-oriented approach to making new molecules as a student experiment: artificial intelligence-enabling FAIR publication of NMR data for organic esters

The lack of machine-readable data is a major obstacle in the application of nuclear magnetic resonance (NMR) in artificial intelligence (AI). As a way to overcome this, a procedure for capturing primary NMR spectroscopic instrumental data annotated with rich metadata and publication in a Findable, Accessible, Interoperable and Reusable (FAIR) data repository is described as part of an undergraduate student laboratory experiment in a chemistry department. This couples the techniques of chemical synthesis of a never before made organic ester with illustration of modern data management practices and serves to raise student awareness of how FAIR data might improve research quality and replicability. Searches of the registered metadata are shown, which enable actionable finding and accessing of such data. The potential for re-use of the data in AI applications is discussed.     

Artificial Neural Networks for Pyrolysis,Thermal Analysis,and Thermokinetic Studies: The Status Quo

Artificial neural networks (ANNs) are a method of machine learning (ML) that is now widely used in physics, chemistry, and material science. ANN can learn from data to identify nonlinear trends and give accurate predictions. ML methods, and ANNs in particular, have already demonstrated their worth in solving various chemical engineering problems, but applications in pyrolysis, thermal analysis, and, especially, thermokinetic studies are still in an initiatory stage. The present article gives a critical overview and summary of the available literature on applying ANNs in the field of pyrolysis, thermal analysis, and thermokinetic studies. More than 100 papers from these research areas are surveyed. Some approaches from the broad field of chemical engineering are discussed as the venues for possible transfer to the field of pyrolysis and thermal analysis studies in general. It is stressed that the current thermokinetic applications of ANNs are yet to evolve significantly to reach the capabilities of the existing isoconversional and model-fitting methods.     

Artificial Intelligence for Autonomous Molecular Design: A Perspective

Domain-aware artificial intelligence has been increasingly adopted in recent years to expedite molecular design in various applications, including drug design and discovery. Recent advances in areas such as physics-informed machine learning and reasoning, software engineering, high-end hardware development, and computing infrastructures are providing opportunities to build scalable and explainable AI molecular discovery systems. This could improve a design hypothesis through feedback analysis, data integration that can provide a basis for the introduction of end-to-end automation for compound discovery and optimization, and enable more intelligent searches of chemical space. Several state-of-the-art ML architectures are predominantly and independently used for predicting the properties of small molecules, their high throughput synthesis, and screening, iteratively identifying and optimizing lead therapeutic candidates. However, such deep learning and ML approaches also raise considerable conceptual, technical, scalability, and end-to-end error quantification challenges, as well as skepticism about the current AI hype to build automated tools. To this end, synergistically and intelligently using these individual components along with robust quantum physics-based molecular representation and data generation tools in a closed-loop holds enormous promise for accelerated therapeutic design to critically analyze the opportunities and challenges for their more widespread application. This article aims to identify the most recent technology and breakthrough achieved by each of the components and discusses how such autonomous AI and ML workflows can be integrated to radically accelerate the protein target or disease model-based probe design that can be iteratively validated experimentally. Taken together, this could significantly reduce the timeline for end-to-end therapeutic discovery and optimization upon the arrival of any novel zoonotic transmission event. Our article serves as a guide for medicinal, computational chemistry and biology, analytical chemistry, and the ML community to practice autonomous molecular design in precision medicine and drug discovery.     

Quantitative Impact of a Cognitive Modeling Intelligent Tutoring System on Student Performance in Balancing Chemical Equations

The need for improved interactive tutoring capabilities in educational software for chemistry problem solving is an important one clearly articulated by teachers and students. To deliver the next generation of individualized interactive capabilities users demand, it is necessary to go beyond the conventional computer-assisted instruction methodology. The focus of this paper is the assessment with first-semester general chemistry students of a recently developed artificial intelligence (AI) tutor for balancing chemical equations. This is the first such assessment of an AI-based learning tool in chemistry. Students in CHEM 121 in the Fall 2001 semester at Duquesne University (N = 273) participated in the study. Students were divided into a test group that used the AI tutor as part of their study activities and a control group that did not use the tutor. It was found that the tutor improved the performance of the test group students to a statistically significant degree, helping the weakest students the most. This study establishes the feasibility of an AI-based approach to creating advanced new tutoring software for chemistry problem solving. Access to a Web-based demonstration of the equation-balancing tutor may be obtained by emailing the corresponding author.     

Designing AI-Aided Analysis and Prediction Models for Nonprecious Metal Electrocatalyst-Based Proton-Exchange Membrane Fuel Cells

Traditionally, a larger number of experiments are needed to optimize the performance of the membrane electrode assembly (MEA) in proton-exchange membrane fuel cells (PEMFCs) since it involves complex electrochemical, thermodynamic, and hydrodynamic processes. Herein, we introduce artificial intelligence (AI)-aided models for the first time to determine key parameters for nonprecious metal electrocatalyst-based PEMFCs, thus avoiding unnecessary experiments during MEA development. Among 16 competing algorithms widely applied in the AI field, decision tree and XGBoost showed good accuracy (86.7 % and 91.4 %) in determining key factors for high-performance MEA. Artificial neural network (ANN) shows the best accuracy (R2=0.9621) in terms of predictions of the maximum power density and a decent reproducibility (R2>0.99) on uncharted I–V polarization curves with 26 input features. Hence, machine learning is shown to be an excellent method for improving the efficiency of MEA design and experiments.     

Br?nsted酸性离子液体催化合成乙酸丁酯的化学动力学研究——一个物理化学综合实验

综合了物理化学和有机化学等实验的原理和基本操作,以Br?nsted酸性离子液体作催化剂制备乙酸丁酯,探讨了实验的化学动力学原理、动力学方程式及有关计算。结果显示,假设的动力学方程与实验结果相符。     

在垃圾分类中寻找化学元素*——基于生活情境的探究性学习

介绍一个结合4种教学策略(情境教学、探究性学习、合作学习、混合式教学)面向非化学专业类大一学生开展元素化学教学的案例。以垃圾分类为主题,学生分组协作完成探究性学习任务,调查不同种类垃圾中存在的化学元素及其用途,通过线下课堂展示、线上成果共享以及校外推广等3项活动传播探究结论。对比活动前后收集的数据,活动前有75%的学生只认识原子序数前20的化学元素,活动后学生认识的元素数量明显增多,平均值是原来的1.7倍。元素中文名称与元素符号记忆混乱的情况得到改善。最后问卷调查表明活动提高了学生上课的积极性并且对了解生活中的化学元素有帮助。     

绿色化学关键技术在精细化工中的应用

绿色化学理念及技术的创新发展,能够更好与精细化工的各环节结合,提升效率、降低消耗、节约成本、增强竞争力,符合我国低碳发展方向,满足行业的可持续发展需求。本文主要介绍近年来绿色化学技术在精细化工领域的发展现状和应用前景,探讨了生物催化/发酵技术、非贵金属或无金属催化技术、微通道反应技术、新能源驱动的化学反应技术、新型高效分离技术、生产过程的人工智能和自动化等绿色化学关键技术在精细化工研制中的应用实例,为推动绿色化学技术的综合利用和可持续发展提供参考和借鉴。