High-throughput discovery of chemical structure-polarity relationships combining automation and machine learning techniques

英文原文与中文译文逐段对照 · English original with Chinese translation

Article

文章

High-throughput discovery of chemical structure-polarity relationships combining automation and machine-learning techniques

结合自动化和机器学习技术的化学结构 - 极性关系的高通量发现

We invented a robotic experimentation platform and supporting software for standardized TLC data collection. An effective prediction model is constructed to predict ${R}_{f}$ curves, discover chemical structure-polarity relationships, and facilitate chromatographic separation. The effective prediction model, based on automated data collection, confirms that combining machine-learning methods with automation is a promising way to improve data fidelity and enhance laboratory efficiency.

我们发明了一个用于标准化TLC数据收集的机器人实验平台和支持软件。构建了一个有效的预测模型来预测${R}_{f}$曲线，发现化学结构 - 极性关系，并促进色谱分离。基于自动数据收集的有效预测模型证实，将机器学习方法与自动化相结合是提高数据保真度和提高实验室效率的一种有前途的方法。

Hao Xu, Jinglong Lin, Qianyi Liu, …, Yan Xu, Dongxiao Zhang, Fanyang Mo

徐浩，林京龙，刘谦益，…，许言，张东晓，莫凡洋

(D.Z.)

(F.M.)

Highlights

亮点

An automated platform is invented to conduct high-throughput TLC analysis

发明了一个自动化平台来进行高通量薄层色谱分析

4,944 standardized ${R}_{f}$ values from 387 compounds under 17 solvent conditions

在17种溶剂条件下，从387种化合物中获得4944个标准化的${R}_{f}$值

A machine-learning model facilitates ${R}_{f}$ prediction and chromatographic separation

一个机器学习模型有助于${R}_{f}$预测和色谱分离

Higher topological polar surface area (TPSA) contributes to smaller ${R}_{f}$ values

更高的拓扑极性表面积(TPSA)导致更小的${R}_{f}$值

Xu et al., Chem 8, 3202-3214

Xu等人，《化学》8，3202 - 3214

https://doi.org/10.1016/j.chempr.2022.08.008

Article

文章

High-throughput discovery of chemical structure-polarity relationships combining automation and machine-learning techniques

结合自动化和机器学习技术的化学结构 - 极性关系的高通量发现

Hao Xu, ${}^{1,2,9}$ Jinglong Lin, ${}^{1,9}$ Qianyi Liu, ${}^{1}$ Yuntian Chen, ${}^{3}$ Jianning Zhang, ${}^{1}$ Yang Yang, ${}^{4}$ Michael C. Young, ${}^{5}$ Yan Xu, ${}^{6}$ Dongxiao Zhang, ${}^{7,8, \star }$ and Fanyang Mo ${}^{1,{10}, \star }$

徐浩，${}^{1,2,9}$ 林敬龙，${}^{1,9}$ 刘千艺，${}^{1}$ 陈云天，${}^{3}$ 张建宁，${}^{1}$ 杨阳，${}^{4}$ 迈克尔·C·杨，${}^{5}$ 徐岩，${}^{6}$ 张东晓，${}^{7,8, \star }$ 以及莫帆洋 ${}^{1,{10}, \star }$

SUMMARY

总结

As an essential attribute of organic compounds, polarity has a profound influence on many molecular properties. Thin-layer chromatography (TLC) represents a commonly used technique for empirical polarity estimations. Current TLC techniques need repetitive attempts to obtain suitable development conditions and have low reproducibility due to a low degree of standardization. Herein, we describe an automated system to conduct TLC analysis automatically, facilitating high-throughput collection of a large quantity of experimental data under standardized conditions. Using this dataset, machine-learning (ML) methods are employed to construct surrogate models correlating organic compound structures and their polarity reflected by retardation factor $\left( {R}_{f}\right)$ . The trained ML models are able to predict the ${R}_{f}$ value curve of organic compounds in different solvent combinations with high accuracy, thus providing general guidelines for the selection of purification conditions and expediting the generation and analysis of quality TLC data.

作为有机化合物的一个基本属性，极性对许多分子性质有着深远影响。薄层色谱法(TLC)是一种常用的经验性极性评估技术。当前的TLC技术需要反复尝试以获得合适的展开条件，并且由于标准化程度低而具有低重现性。在此，我们描述了一种自动进行TLC分析的系统，便于在标准化条件下高通量收集大量实验数据。使用该数据集，采用机器学习(ML)方法构建替代模型，将有机化合物结构与其由阻滞因子$\left( {R}_{f}\right)$反映的极性相关联。经过训练的ML模型能够高精度预测有机化合物在不同溶剂组合中的${R}_{f}$值曲线，从而为纯化条件的选择提供通用指导，并加快高质量TLC数据的生成和分析。

INTRODUCTION

引言

Thin-layer chromatography (TLC) is a commonly used technique in modern chemistry and biology laboratories. As a key chromatography technique, the employment of a solid stationary phase and a liquid mobile phase allows for the separation of individual components of a complex mixture on the basis of their relative affinities for the two phases (Figure 1A). ${}^{1}$ TLC analysis is currently used routinely for reaction monitoring, product identification, and determination of chromatography conditions for subsequent purification. Even though highly experienced synthetic practitioners are able to use this tool, TLC techniques often present a hurdle for scientists in synthesis-adjacent fields. Furthermore, the identification of TLC conditions for new compound classes requires the judicious selection of several variables, most notably the mobile phases and their ratios, to achieve optimal separation. Traditionally, such goals are accomplished through trial-and-error in a time-consuming and labor-intensive manner.

薄层色谱法(TLC)是现代化学和生物学实验室中常用的技术。作为一种关键的色谱技术，使用固体固定相和液体流动相能够基于复杂混合物中各个组分对两相的相对亲和力来分离它们(图1A)。${}^{1}$ TLC分析目前常用于反应监测、产物鉴定以及确定后续纯化的色谱条件。尽管经验丰富的合成从业者能够使用这个工具，但TLC技术对于合成相关领域的科学家来说常常是一个障碍。此外，确定新化合物类别的TLC条件需要明智地选择几个变量，最显著的是流动相及其比例，以实现最佳分离。传统上，这些目标是通过耗时且费力的反复试验来实现的。

In recent years, cutting-edge techniques in artificial intelligence (AI) have revolutionized the extrapolation of structure-property relationships in chemical sciences. ${}^{2}$ In particular, machine-learning (ML) algorithms are able to solve complex chemical problems with respect to prediction, surrogate model construction, and constitutive relationship discovery. ${}^{3 - 6}$ Although the chemical structure-retardation factor relationship in TLC has been studied using linear or random forest (RF) ML models, ${}^{7,8}$ the manually acquired TLC data are scant in both quantity and standardization, resulting in limited application and low accuracy $\left( {{R}^{2} < {0.7}}\right)$ . We envision that the development and implementation of an automated platform will significantly speed up data acquisition and generate sufficiently standardized data for further ML research.

近年来，人工智能(AI)的前沿技术彻底改变了化学科学中结构-性质关系的推断。${}^{2}$ 特别是，机器学习(ML)算法能够在预测、替代模型构建和本构关系发现方面解决复杂的化学问题。${}^{3 - 6}$ 尽管已经使用线性或随机森林(RF)ML模型研究了TLC中的化学结构-阻滞因子关系，${}^{7,8}$ 但手动获取的TLC数据在数量和标准化方面都很匮乏，导致应用有限且准确性低。$\left( {{R}^{2} < {0.7}}\right)$ 我们设想，一个自动化平台的开发和实施将显著加快数据采集，并生成足够标准化的数据用于进一步的ML研究。

THE BIGGER PICTURE

全局视角

Optimizing chemical experiments is labor intensive, time consuming, and frequently influenced by many factors that make it difficult to collect sufficiently standardized experimental data for machine-learning models. Focusing on the essential technique of thin-layer chromatography (TLC) analysis, we present a successful combination of machine-learning (ML) methods and automation to enhance laboratory efficiency. The effective prediction model aids chromatographic separation by providing optimal elution conditions and, at the same time, deepens our understanding of the underlying chemical structure-polarity relationships. We anticipate that this work will bring forth the broader implementation of automated platforms for repetitive chemical experiments, enabling researchers to focus on thinking and innovating, which will accelerate scientific discovery and further the development of industry and technology.

优化化学实验是一项劳动密集型、耗时的工作，并且经常受到许多因素的影响，这使得难以收集足够标准化的实验数据用于机器学习模型。我们聚焦于薄层色谱(TLC)分析的关键技术，成功地将机器学习(ML)方法与自动化相结合，以提高实验室效率。有效的预测模型通过提供最佳洗脱条件辅助色谱分离，同时加深我们对潜在化学结构-极性关系的理解。我们预计这项工作将推动重复性化学实验自动化平台的更广泛应用，使研究人员能够专注于思考和创新，这将加速科学发现并进一步推动工业和技术的发展。

Figure 1. Context of the work

图1. 工作背景

(A) Thin-layer chromatography (TLC) is a chromatography technique used to separate non-volatile mixtures. Synthetic laboratories heavily use TLC techniques to monitor reactions and identify compounds daily. Choosing suitable TLC conditions is usually time-consuming for novices or for new compounds. The retardation factor $\left( {R}_{f}\right)$ is the fraction of an analyte in the mobile phase of a chromatographic system. It is defined as the ratio of the distance traveled by the center of a spot to the distance traveled by the solvent front.

(A) 薄层色谱法(TLC)是一种用于分离非挥发性混合物的色谱技术。合成实验室每天大量使用TLC技术来监测反应和鉴定化合物。对于新手或新化合物而言，选择合适的TLC条件通常很耗时。阻滞因子$\left( {R}_{f}\right)$是分析物在色谱系统流动相中的比例。它被定义为斑点中心移动的距离与溶剂前沿移动的距离之比。

(B) A sigmoid function is a mathematical function having a characteristic “S”-shaped curve, and it has domain of all real numbers with a return value in the range 0-1 . Considering that the ${R}_{f}$ value also has the same value range, we deliberately associate it with the sigmoid function.

(B) Sigmoid函数是一种具有特征“S”形曲线的数学函数，其定义域为所有实数，返回值范围在0 - 1之间。考虑到${R}_{f}$值也具有相同的值域，我们特意将其与Sigmoid函数联系起来。

(C) The subjective and objective factors of compound ${R}_{f}$ value measurement. The subjective factors include the compound’s structure and other physical properties, as well as elution solvents. The information can be mapped to a vector space via feature engineering and then can be fed to ML algorithms. Other factors like chamber size, humidity, etc., can also affect the measurement. The inuence of these objective factors should be eliminated as much as possible to avoid their impact on model training.

(C) 化合物${R}_{f}$值测量的主观和客观因素。主观因素包括化合物的结构和其他物理性质，以及洗脱溶剂。这些信息可以通过特征工程映射到向量空间，然后输入到机器学习算法中。其他因素如腔室大小、湿度等也会影响测量。应尽可能消除这些客观因素的影响，以避免它们对模型训练的影响。

Essentially, the task of prediction is to establish a certain mathematical model that maps between input and output. We noted that the sigmoid function, a common activation function in neural network algorithms, is tightly bound to the pair of horizontal asymptotes and highly useful in compressing or squashing outputs within a 0-1 range. The output of TLC, ${R}_{f}$ , is also a value between 0 and 1 . Thus, we

本质上，预测任务是建立一个在输入和输出之间进行映射的数学模型。我们注意到，Sigmoid函数是神经网络算法中常用的激活函数，它与一对水平渐近线紧密相关，并且在将输出压缩或挤压到0 - 1范围内非常有用。TLC的输出${R}_{f}$也是一个介于0和1之间的值。因此，我们

${}^{1}$ School of Materials Science and Engineering, Peking University, Beijing 100871, China

${}^{1}$ 中国北京大学材料科学与工程学院，北京100871

${}^{2}$ BIC-ESAT, ERE, and SKLTCS, College of Engineering, Peking University, Beijing 100871, China

${}^{2}$ 中国北京大学工程学院BIC - ESAT、ERE和SKLTCS，北京100871

${}^{3}$ Eastern Institute for Advanced Study, Yongriver Institute of Technology, Ningbo 315200, China

${}^{3}$ 中国宁波永河理工学院先进研究东部学院，宁波315200

${}^{4}$ Department of Chemistry and Biochemistry, University of California, Santa Barbara, Santa Barbara, CA 93106, USA

${}^{4}$ 美国加利福尼亚大学圣巴巴拉分校化学与生物化学系，圣巴巴拉，CA 93106

${}^{5}$ Department of Chemistry & Biochemistry, School of Green Chemistry & Engineering, The University of Toledo, 2801 W. Bancroft St., Toledo, OH 43606, USA

${}^{5}$ 美国托莱多大学绿色化学与工程学院化学与生物化学系，西 Bancroft 街2801号，托莱多，OH 43606

6Chemistry Service Unit, WuXi AppTec Co., Ltd., Shanghai 200131, China

6 药明康德股份有限公司化学服务部，中国上海200131

${}^{7}$ Department of Mathematics and Theories, Peng Cheng Laboratory, Shenzhen 518000, China

${}^{7}$ 中国深圳鹏城实验室数学与理论部，深圳518000

${}^{8}$ National Center for Applied Mathematics Shenzhen (NCAMS), Southern University of Science and Technology, Shenzhen 518000, China

${}^{8}$ 中国深圳南方科技大学国家应用数学中心(NCAMS)，深圳518000

9These authors contributed equally

9 这些作者贡献相同

10Lead contact

10 通讯联系人

*Correspondence: (D.Z.), (F.M.)

*通讯作者: (D.Z.)， (F.M.)

https://doi.org/10.1016/j.chempr.2022.08.008 envisioned that the ${R}_{f}$ values could be reasonably fitted using a sigmoid function (Figure 1B). In this case, all the factors that have an influence on the ${R}_{f}$ value will be selected, and subject to a matrix operation through certain input forms to determine an $x$ , and the output, the ${R}_{f}$ value, will be the sigmoid function value of the $x$ . Additionally, in a reverse perspective, through such a transformative operation, the original range of 0-1 is extended to the entire real number domain. In other words, we can predict the ${R}_{f}$ value by regression in a larger range to improve the accuracy of the model (vide infra). Meanwhile, we also put forward a mathematical model of adsorption equilibria on the surface of silica gel and prove that the ${R}_{f}$ value is a sigmoid function of the change in Gibbs free energy for the competitive adsorption reaction, which provides a physical explanation for the utilization of sigmoid function. The detailed derivation process is provided in the supplemental information.

https://doi.org/10.1016/j.chempr.2022.08.008设想可以使用S形函数(图1B)合理拟合${R}_{f}$值。在这种情况下，所有影响${R}_{f}$值的因素都将被选择，并通过特定的输入形式进行矩阵运算以确定一个$x$，而输出的${R}_{f}$值将是$x$的S形函数值。此外，从相反的角度来看，通过这样的变换操作，原来的0到1的范围被扩展到整个实数域。换句话说，我们可以在更大的范围内通过回归来预测${R}_{f}$值，以提高模型的准确性(见下文)。同时，我们还提出了硅胶表面吸附平衡的数学模型，并证明${R}_{f}$值是竞争吸附反应吉布斯自由能变化的S形函数，这为S形函数的应用提供了物理解释。详细的推导过程见补充信息。

ML methods capture underlying patterns from a large amount of training data to make predictions. The availability of large, high-quality datasets is a prerequisite for ML methods. As illustrated in Figure 1C, the accuracy and reproducibility of the TLC analysis can be affected by many factors, including the chamber size, operation time, temperature, and the TLC plates used in the experiment, which often lead to inconsistent data and impede the development of predictive ML models. Generating a sufficient amount of highly standardized data through conventional means is tedious and time-consuming. To address this challenge, we sought to exploit automated instrumentation to accelerate and standardize the measurement of the ${R}_{f}$ values of organic compounds in TLC analysis. Furthermore, we use these data for ML model training to correlate compound structures and their ${R}_{f}$ values (Figure 1C).

机器学习方法从大量训练数据中捕捉潜在模式以进行预测。大量高质量数据集的可用性是机器学习方法的前提条件。如图1C所示，薄层色谱分析的准确性和可重复性可能受到许多因素的影响，包括腔室大小、操作时间、温度以及实验中使用的薄层色谱板，这些因素常常导致数据不一致，并阻碍预测性机器学习模型的开发。通过传统方法生成足够数量的高度标准化数据既繁琐又耗时。为了应对这一挑战，我们试图利用自动化仪器来加速和标准化薄层色谱分析中有机化合物${R}_{f}$值的测量。此外，我们使用这些数据进行机器学习模型训练，以关联化合物结构及其${R}_{f}$值(图1C)。

RESULTS

结果

Data acquisition

数据采集

The automation of chemical experimentation has been an expanding field in the last decade. ${}^{9 - {11}}$ These automated platforms enable standardization and enhance reproducibility while reducing experimental costs. Most importantly, automation allows for the generation of large, high-quality datasets for further statistical analysis. ${}^{12}$ The research paradigm combining automation and ML techniques has already been successfully applied to chemical sciences in various scenarios ranging from reaction condition optimization to mechanism interpretation. ${}^{{13} - {18}}$

在过去十年中，化学实验自动化一直是一个不断发展的领域。${}^{9 - {11}}$ 这些自动化平台能够实现标准化，提高可重复性，同时降低实验成本。最重要的是，自动化有助于生成大量高质量数据集，用于进一步的统计分析。${}^{12}$ 将自动化与机器学习技术相结合的研究范式已经在从反应条件优化到机理解释等各种场景中成功应用于化学科学领域。${}^{{13} - {18}}$

We realized that the most effective strategy would be to develop an automated robotic platform to collect the necessary TLC data. However, TLC analysis requires several experimental steps, including dissolving the analyte, spotting the analyte, developing the TLC plate, and ultimately measuring and calculating the ${R}_{f}$ value for each analyte, thus demanding sophisticated automation.

我们意识到最有效的策略是开发一个自动化机器人平台来收集必要的薄层色谱(TLC)数据。然而，TLC分析需要几个实验步骤，包括溶解分析物、点样分析物、展开TLC板，以及最终测量和计算每个分析物的${R}_{f}$值，因此需要复杂的自动化技术。

To address the challenges mentioned above, we built a custom desktop robot system for high-throughput collection of TLC data. Our robotic platform is shown in Figure 2. Two collaborative robots are the core of this system, which are able to accomplish complex actions like human arms with high precision and safety. The system also comprises two cameras, two lights, a router, and a laptop (Figures 2A and S2-S4). The smaller robot, DOBOT MG400, is responsible for drawing TLC samples on the sample tray (Figure 2B) and then spotting samples onto the TLC plates (Figure 2C). Subsequently, the bigger robot, AUBO i5, is responsible for gripping the TLC plate and then putting it into the chamber for development (Figures 2D and

为应对上述挑战，我们构建了一个定制的桌面机器人系统，用于高通量收集TLC数据。我们的机器人平台如图2所示。两个协作机器人是该系统的核心，它们能够像人类手臂一样高精度、安全地完成复杂动作。该系统还包括两个摄像头、两盏灯、一个路由器和一台笔记本电脑(图2A和S2 - S4)。较小的机器人DOBOT MG400负责在样品盘上绘制TLC样品(图2B)，然后将样品点到TLC板上(图2C)。随后，较大的机器人AUBO i5负责抓取TLC板，然后将其放入展开室(图2D和

Figure 2. Automated thin-layer chromatography robots and experimental station

图2. 自动化薄层色谱机器人与实验站

(A) Schematic of the automated robotic platform for TLC data collection.

(A) TLC数据收集自动化机器人平台示意图。

(B) The DOBOT MG400 robot equipped with a capillary is drawing TLC samples on the sample tray.

(B) 配备毛细管的DOBOT MG400机器人在样品盘上绘制TLC样品。

(D) The AUBO i5 robot is gripping a TLC plate prior to moving.

(D) AUBO i5机器人在移动前抓取TLC板。

(E) The AUBO i5 robot is putting a TLC plate into TLC chamber (or retrieving a plate from the chamber).

(E) AUBO i5机器人将TLC板放入TLC展开室(或从室中取出板)。

(F) After developing, the AUBO i5 robot is taking the TLC plate to a UV light box to visualize and photograph.

(F) 展开后，AUBO i5机器人将TLC板拿到紫外灯箱进行可视化和拍照。

(G) The AUBO i5 robot is retrieving a plate from storage.

(G) AUBO i5机器人从储存处取出板。

(H) The AUBO i5 robot is placing a pristine TLC plate onto the stand.

(H) AUBO i5机器人将一块全新的TLC板放在支架上。

2E). Upon completion, the TLC plate is transferred to a box for visualizing and photographing under UV light (Figure 2F). Finally, the AUBO i5 will retrieve a pristine plate from storage and place it onto the stand for regenerating the system for the next usage (Figures 2G and 2H). In order to increase throughput and efficiency, six chambers are placed on the platform with different elution solvents in each. A Python program is built to control the robots, cameras, and lights, thus managing the whole workflow. Through this robotic TLC experiment platform, high-throughput standardized measurements of the ${R}_{f}$ values are achieved.

2E)。完成后，TLC板被转移到一个盒子里，以便在紫外光下进行可视化和拍照(图2F)。最后，AUBO i5将从储存处取出一块全新的板并将其放在支架上，为系统的下一次使用进行重置(图2G和2H)。为了提高通量和效率，平台上放置了六个展开室，每个室装有不同的洗脱溶剂。构建了一个Python程序来控制机器人、摄像头和灯光，从而管理整个工作流程。通过这个机器人TLC实验平台，实现了${R}_{f}$值的高通量标准化测量.

After the data collection is completed by the automated TLC system, the ${R}_{f}$ values can be automatically calculated by an image analysis computer program, leading to highly standardized TLC runs. For UV-inactive compounds, other visualization methods can be adopted, which is detailed in the supplemental information. In a typical task, the ${R}_{f}$ values of each compound under different elution solvent ratios are plotted, which helps chemists find outliers based on intuition and experience. Through this method, a high-quality dataset of compound ${R}_{f}$ values is established, containing 4,944 standardized measurements of the ${R}_{f}$ values from 387 organic compounds (Figure 3A) under three mobile phase systems, including hexane/ethyl acetate, dichloromethane/methanol, and hexane/diethyl ether, with a total of 17 different solvent compositions. The distribution of ${R}_{f}$ values for each mobile phase combination is displayed in Figure 3B. All of these experiments were conducted once to construct the dataset. These commonly encountered compounds are collected based on their chemical class to achieve better representation. This standard dataset of ${R}_{f}$ values, generated for the first time, is very valuable since the ${R}_{f}$ values are usually sensitive to external factors in the experiments, which means that statistically meaningful data can only be obtained through automated high-throughput standardized experiments.

自动TLC系统完成数据收集后，${R}_{f}$值可通过图像分析计算机程序自动计算，从而实现高度标准化的TLC运行。对于无紫外活性的化合物，可以采用其他可视化方法，补充信息中有详细说明。在一个典型任务中，绘制每种化合物在不同洗脱溶剂比例下的${R}_{f}$值，这有助于化学家根据直觉和经验找出异常值。通过这种方法，建立了一个高质量的化合物${R}_{f}$值数据集，包含在三种流动相系统(己烷/乙酸乙酯、二氯甲烷/甲醇和己烷/乙醚)下387种有机化合物的4944个标准化${R}_{f}$值测量结果(图3A)，共有17种不同的溶剂组成。图3B显示了每种流动相组合的${R}_{f}$值分布。所有这些实验都只进行了一次以构建数据集。这些常见化合物是根据其化学类别收集的，以实现更好的代表性。这个首次生成的${R}_{f}$值标准数据集非常有价值，因为${R}_{f}$值通常在实验中对外部因素敏感，这意味着只有通过自动化高通量标准化实验才能获得具有统计意义的数据。

Machine-learning model for ${R}_{f}$ value prediction

用于${R}_{f}$值预测的机器学习模型

Before constructing the ML model, we first turn to selecting suitable molecular descriptors to represent the compounds in the dataset. In terms of mechanism, the ${R}_{f}$ value reflects molecular polarity, which is a reflection of a compound’s polar bonds and their spatial distribution, and is therefore essentially a reflection of a compound’s structure. In addition, TLC is based on the principle of separation through adsorption type. For this reason, the ${R}_{f}$ value is correlated with the properties that affect the molecular adsorption between stationary phase and mobile phase, for example, hydrogen bonding and topological polar surface area (TPSA), etc. Although many molecular fingerprints have been developed, we pay more attention to the ones that relate to structure. Molecular access system (MACCS) keys are of the most commonly used structural keys employed to represent molecular structure, fragments, and substructural information. ${}^{19}$ Each compound can be converted into MACCS keys with 167 dimensions. Meanwhile, molecular properties such as molecular weight (MW), TPSA, and many others can also be conveniently extracted by using RDKit software. ${}^{20}$ Moreover, another possible factor, dipole moment (DM), is calculated using Mopac2016 (PM6-D3). ${}^{21}$ In order to express the mobile phase information, a weighted vectorization technique based on the molecular descriptors for solvents is employed. A six-dimensional vector of descriptors is utilized to represent each solvent, and the representation of the mobile phase is obtained by the weighted average of vectors of different solvents according to the proportion of each solvent. To avoid prohibitively time-consuming analysis and logging of computational data, we developed software to automate feature generation. The program requires only the input of simplified molecular input line entry system (SMILES) strings ${}^{22}$ of compounds in a Python script. The program then generates the data table that can be used for modeling. In total, 180-dimensional input metrics are extracted by the software to characterize each TLC’s set of conditions (Figures 3C-3E). One of the advantages of ML modeling is that one can define feature engineering relatively freely without recourse to a specific hypothesis. This, to a certain extent, allows the machine to discover the connection, or even knowledge hidden in data, without relying on human experience. With these data in hand, we evaluated the predictive accuracies of a series of ML methods, including

在构建机器学习模型之前，我们首先转向选择合适的分子描述符来表示数据集中的化合物。从机理上讲，${R}_{f}$值反映分子极性，这是化合物极性键及其空间分布的反映，因此本质上是化合物结构的反映。此外，薄层色谱基于吸附类型的分离原理。因此，${R}_{f}$值与影响固定相和流动相之间分子吸附的性质相关，例如氢键和拓扑极性表面积(TPSA)等。尽管已经开发了许多分子指纹，但我们更关注与结构相关的指纹。分子访问系统(MACCS)键是最常用的用于表示分子结构、片段和子结构信息的结构键。${}^{19}$ 每个化合物都可以转换为167维的MACCS键。同时，使用RDKit软件也可以方便地提取分子量(MW)、TPSA等分子性质。${}^{20}$ 此外，另一个可能的因素，偶极矩(DM)，使用Mopac2016(PM6-D3)进行计算。${}^{21}$ 为了表达流动相信息，采用基于溶剂分子描述符的加权矢量化技术。利用一个六维描述符向量来表示每种溶剂，流动相的表示通过不同溶剂向量根据每种溶剂的比例进行加权平均得到。为了避免极其耗时的计算数据分析和记录，我们开发了软件来自动生成特征。该程序只需要在Python脚本中输入化合物的简化分子输入线性输入系统(SMILES)字符串${}^{22}$。然后程序生成可用于建模的数据表。该软件总共提取180维输入指标来表征每个薄层色谱的条件集(图3C - 3E)。机器学习建模的优点之一是可以相对自由地定义特征工程，而无需依赖特定假设。这在一定程度上允许机器发现数据中隐藏的联系甚至知识，而不依赖人类经验。有了这些数据，我们评估了一系列机器学习方法的预测准确性，包括

Figure 3. Description of the obtained ${R}_{f}$ value dataset and data processing

图3. 所获得的${R}_{f}$值数据集及数据处理说明

(A) The top 10 classes of the compounds in the dataset.

(A) 数据集中前10类化合物。

(B) The distribution of ${R}_{f}$ values for each mobile phase system.

(B) 每个流动相系统的${R}_{f}$值分布。

(C) The input matrix includes molecular fingerprints, several molecular descriptors, and solvent information. The label is the ${R}_{f}$ value. DM, dipole moment; MW, molecular weight; TPSA, topological polar surface area; NROTBs, number of rotatable bonds; HBA, hydrogen bond acceptor; HBD, hydrogen bond donor; LogP, lipid-water partition coefficient.

(D) The molecular access system (MACCS) keys are one of the most commonly used structural keys. In these structural keys, the structure of a molecule is encoded into a binary bit string (a sequence of 0’s and 1’s), each bit of which corresponds to a “pre-defined” structural feature. This binary bit string makes up the fingerprint vector.

(D) 分子访问系统(MACCS)键是最常用的结构键之一。在这些结构键中，分子结构被编码为一个二进制位串(0和1的序列)，其中每一位对应一个“预定义”的结构特征。这个二进制位串构成指纹向量。

(E) An example for the weighted vectorization technique of the mobile phase system.

(E) 流动相系统加权矢量化技术的一个示例。

Figure 4. Prediction for ${R}_{f}$ values with machine-learning techniques and the analysis of the descriptors

图4. 用机器学习技术预测${R}_{f}$值及描述符分析

(A) Observed versus predicted ${R}_{f}$ values for different ML algorithms. For all the models, an 80/10/10 random split of training, validation, and test data by TLC data is performed to measure the

(A) 不同机器学习算法的${R}_{f}$值观测值与预测值对比。对于所有模型，通过薄层色谱数据对训练、验证和测试数据进行80/10/10随机划分以测量

Figure 4. Continued

图4. 续

prediction ability of each model. Only test set data are shown in plots. The dashed line is the $y = x$ line.

每个模型的预测能力。图中仅显示测试集数据。虚线为$y = x$线。

(B) Observed versus predicted ${R}_{f}$ values for the proposed ensemble method to predict out-of-

(B) 针对所提出的集成方法预测${R}_{f}$值时的观测值与预测值，该方法用于预测外部的

sample compounds. The dataset is randomly split into ${80}/{10}/{10}$ by compounds, and only test set data are shown in plots. The dashed line is the $y = x$ line.

样品化合物。数据集按化合物随机分为${80}/{10}/{10}$，图中仅显示测试集数据。虚线为$y = x$线。

(C) Test set performance of the ensemble prediction model with sparse data. The smaller training sets are selected randomly from the total compounds, and the test data are kept the same. A gradual decline in predictive accuracy occurred, from 70% of the total compounds down to 2.5%.

(D) The relative importance of the molecular descriptors utilized in this work.

(D) 本研究中使用的分子描述符的相对重要性。

(E) The heatmap of correlation coefficients between molecular descriptors.

(E) 分子描述符之间的相关系数热图。

(F) The scatterplot of ${R}_{f}$ values on TPSAs of all compounds when hexane/EA = 5/1.

(F) 当正己烷/乙酸乙酯 = 5/1 时，所有化合物的 ${R}_{f}$ 值与拓扑极性表面积(TPSA)的散点图。

(G) The boxplot of ${R}_{f}$ values of the compounds with different HBDs when hexane/EA $= 5/1$ .

(G) 当正己烷/乙酸乙酯$= 5/1$时，具有不同氢键供体数的化合物的${R}_{f}$值的箱线图。

Bayesian regression, RF, LightGBM (LGB), XGBoost (XGB), and artificial neural network (ANN). Here, the dataset is randomly divided into training, validation, and test sets according to the ratio of ${80}\% ,{10}\%$ , and ${10}\%$ by TLC data. Considering the physical constraint that the range of ${R}_{f}$ values is between 0 and 1, in the training process of the above-mentioned ML algorithms, the output will be mapped from the entire real number domain to $\left\lbrack {0,1}\right\rbrack$ through the sigmoid function. It is discovered that a deep learning-based algorithm like ANN and decision tree-based algorithms like RF, LGB, and XGB all show a satisfactory prediction ability with ${R}^{2}$ over 0.92 (Figure 4A). To avoid randomness, 10 independent experiments with different random seeds are conducted of which the results are shown in Figure S10. On the basis of these techniques, an ensemble method is proposed to form a better model and further improve the accuracy. We are delighted to find that a predictive model with the highest accuracy $\left( {{R}^{2} = {0.951}}\right)$ can be obtained by a simple weighted average of these methods. This improvement may be attributed to the ability of the ensemble algorithm to avoid overfitting and decrease the risk of obtaining a local minimum. ${}^{23}$ These satisfactory results also reflect the precision and consistency of the dataset obtained by the automatic platform since ML techniques have a stringent requirement for accurate, independent, and identically distributed data.

贝叶斯回归、随机森林(RF)、轻量级梯度提升机(LightGBM，LGB)、极端梯度提升(XGBoost，XGB)和人工神经网络(ANN)。在此，数据集根据${80}\% ,{10}\%$和${10}\%$的比例通过薄层色谱数据随机分为训练集、验证集和测试集。考虑到${R}_{f}$值的范围在0到1之间这一物理限制，在上述机器学习算法的训练过程中，输出将通过sigmoid函数从整个实数域映射到$\left\lbrack {0,1}\right\rbrack$。研究发现，像ANN这样基于深度学习的算法以及像RF、LGB和XGB这样基于决策树的算法在${R}^{2}$超过0.92时都表现出令人满意的预测能力(图4A)。为避免随机性，进行了10次具有不同随机种子的独立实验，其结果如图S10所示。在这些技术的基础上，提出了一种集成方法以形成更好的模型并进一步提高准确性。我们很高兴地发现，通过对这些方法进行简单加权平均可以获得具有最高准确性$\left( {{R}^{2} = {0.951}}\right)$的预测模型。这种改进可能归因于集成算法避免过拟合和降低获得局部最小值风险的能力。${}^{23}$这些令人满意的结果也反映了自动平台获得的数据集的精确性和一致性，因为机器学习技术对准确、独立且同分布的数据有严格要求。

Next, a more difficult and practical problem is considered, which is that of predicting the ${R}_{f}$ values of out-of-sample compounds under different solvent compositions. In this task, the dataset is randomly split into a training dataset with 3,922 ${R}_{f}$ values from 308 compounds (80% of total compounds), a validation dataset with ${484}{R}_{f}$ values from 38 compounds (10% of total compounds), and an out-of-sample test dataset with 473 ${R}_{f}$ values from 38 compounds (10% of total compounds). The proposed ensemble model is trained, and the prediction performance on the test set is examined. On average, the root-mean-square error (RMSE) of the predicted ${R}_{f}$ values of the out-of-sample 38 compounds is 0.100, with an ${R}^{2}$ value of 0.898 (Figure 4B). The effective out-of-sample prediction of the proposed model suggests that the constitutive relationship between the input information and output ${R}_{f}$ value measurements is well captured by the prediction model, which means that it may be possible to predict the ${R}_{f}$ values of compounds under specified elution solvents.

接下来，考虑一个更具挑战性且实际的问题，即预测不同溶剂组成下样本外化合物的${R}_{f}$值。在这项任务中，数据集被随机划分为一个训练数据集，包含来自308种化合物的3922个${R}_{f}$值(占化合物总数的80%)、一个验证数据集，包含来自38种化合物的${484}{R}_{f}$值(占化合物总数的10%)以及一个样本外测试数据集，包含来自38种化合物的473个${R}_{f}$值(占化合物总数的10%)。对所提出的集成模型进行训练，并检验其在测试集上的预测性能。平均而言，样本外38种化合物预测${R}_{f}$值的均方根误差(RMSE)为0.100，${R}^{2}$值为0.898(图4B)。所提出模型有效的样本外预测表明，预测模型很好地捕捉了输入信息与输出${R}_{f}$值测量之间的本构关系，这意味着有可能预测指定洗脱溶剂下化合物的${R}_{f}$值。

In order to explore the relationship between the predictive power of the model and input data more deeply, different numbers of compounds are utilized to train the model, whereas the test set is fixed. It is surprising to discover that the prediction model is able to maintain satisfactory predictive power with a markedly smaller training dataset, since the ${R}^{2}$ of the model trained from the ${R}_{f}$ values of 116 compounds (30% of total compounds) achieves 0.878 , which is only a decrease of 0.012 when compared with the model trained from 70% of the total compounds (Figure 4C). This indicates that there is a tight physical relationship between the structure and properties of the compound and the ${R}_{f}$ value that could be learned by the proposed ensemble model through only 116 compounds, so as to predict the ${R}_{f}$ values with a certain degree of accuracy, which provides an example of “small data, big task. 24”

为了更深入地探索模型预测能力与输入数据之间的关系，使用了不同数量的化合物来训练模型，而测试集是固定的。令人惊讶的是，发现预测模型能够在明显更小的训练数据集上保持令人满意的预测能力，因为从116种化合物(占总化合物的30%)的${R}_{f}$值训练的模型的${R}^{2}$达到0.878，与从70%的总化合物训练的模型相比，仅下降了0.012(图4C)。这表明化合物的结构和性质与${R}_{f}$值之间存在紧密的物理关系，所提出的集成模型仅通过116种化合物就可以学习到这种关系，从而以一定的准确度预测${R}_{f}$值，这提供了一个“小数据，大任务。24”的例子。

Statistical analysis for descriptors

描述符的统计分析

After having obtained a satisfactory predictive model, we seek to explore the physical and chemical knowledge underlying the trained model. The molecular descriptors that characterize molecular properties are contained in the input information. As a consequence, the relative importance of the utilized molecular descriptors is evaluated by the percent increase in the predictive model’s mean absolute error (MAE) when values of certain descriptors in the test set are randomly reassigned according to data distribution. It is found that, among these descriptors, the TPSA shows significant importance over all others (Figure 4D). The correlation coefficients between molecular descriptors are also explored (Figure 4E). It is found that the TPSA and hydrogen bond acceptor (HBA) have a very strong positive correlation. The TPSA of a molecule is defined as the surface sum over all polar atoms, primarily oxygen and nitrogen, which is often used to evaluate the transport properties of drugs in cells, and it is proven to have an inseparable relationship with the ${R}_{f}$ values in this work. We rationalize that a larger TPSA leads to a stronger interaction between the adsorbate and the adsorbent (e.g., silica gel), leading to smaller ${R}_{f}$ values. This is proved in Figure 4F where the Spearman coefficient is -0.654 , which indicates a strong negative correlation. As for the hydrogen bond donor (HBD) and HBA, they indicate the number of hydrogen bond donors and acceptors, respectively. Our results show that the HBD is more relevant to the ${R}_{f}$ value than the HBA, and the ${R}_{f}$ values present a clear downward trend as HBDs increase, which are illustrated in Figure 4G. The explanation is that the solid phase used in this study is silica gel, which contains many bridging oxygens and hydroxyl groups on the surface acting as HBAs. Therefore, the analyte will have more binding interactions with silica gel when it contains HBDs rather than HBAs. The relationship between the ${R}_{f}$ values and descriptors was indistinct before and is revealed statistically in this work for the first time.

在获得令人满意的预测模型后，我们试图探索训练模型背后的物理和化学知识。表征分子性质的分子描述符包含在输入信息中。因此，当根据数据分布随机重新分配测试集中某些描述符的值时，通过预测模型的平均绝对误差(MAE)的百分比增加来评估所使用的分子描述符的相对重要性。结果发现，在这些描述符中，TPSA比所有其他描述符都具有显著的重要性(图4D)。还探索了分子描述符之间的相关系数(图4E)。结果发现，TPSA与氢键受体(HBA)具有非常强的正相关。分子的TPSA定义为所有极性原子(主要是氧和氮)的表面总和，它通常用于评估药物在细胞中的转运性质，并且在这项工作中被证明与${R}_{f}$值有不可分割的关系。我们推断，较大的TPSA会导致吸附质与吸附剂(例如硅胶)之间的相互作用更强，从而导致${R}_{f}$值更小。这在图4F中得到了证明，其中斯皮尔曼系数为-0.654，表明存在很强的负相关。至于氢键供体(HBD)和HBA，它们分别表示氢键供体和受体的数量。我们的结果表明，HBD比HBA与${R}_{f}$值更相关，并且随着HBD的增加，${R}_{f}$值呈现出明显的下降趋势，如图4G所示。解释是本研究中使用的固相是硅胶，其表面含有许多桥连氧和羟基作为HBA。因此，当分析物含有HBD而不是HBA时，它与硅胶将有更多的结合相互作用。${R}_{f}$值与描述符之间的关系以前不明确，并且在这项工作中首次通过统计揭示。

Application and extendibility

应用与可扩展性

The predictive model has a wide range of applications that facilitates the acquisition of ${R}_{f}$ values and deepens understanding. Its primary utilization is to predict the ${R}_{f}$ curve of a given compound. Three out-of-sample compounds where the ${R}_{f}$ curves present different patterns are examined. The predicted and experimental ${R}_{f}$ curves under different mobile phase systems are illustrated in Figure 5. It is discovered that the predicted curves have achieved satisfactory accuracy for compounds of different classes in all systems, although the patterns of curves are different. On this basis, the predictive model is able to provide prior information of the ${R}_{f}$ values in different mobile phase systems before chemical experiments, which averts repeated trials for selecting an appropriate system in common practice. Furthermore, the predictive model is able to facilitate the chromatographic separation of known compounds by giving an appropriate initial solvent system from the predicted ${R}_{f}$ curves. Meanwhile, the ability of the predictive model to facilitate chromatographic separation is also examined by a large number of hypothetical experiments, and an 80.8% accuracy is obtained (Table S3).

该预测模型具有广泛的应用，有助于获取${R}_{f}$值并加深理解。其主要用途是预测给定化合物的${R}_{f}$曲线。研究了三种${R}_{f}$曲线呈现不同模式的样本外化合物。图5展示了不同流动相系统下预测的和实验的${R}_{f}$曲线。结果发现，尽管曲线模式不同，但预测曲线在所有系统中对不同类别的化合物都达到了令人满意的准确度。在此基础上，预测模型能够在化学实验之前提供不同流动相系统中${R}_{f}$值的先验信息，这避免了在常规操作中为选择合适系统而进行的重复试验。此外，预测模型能够通过从预测的${R}_{f}$曲线给出合适的初始溶剂系统来促进已知化合物的色谱分离。同时，还通过大量假设实验检验了预测模型促进色谱分离的能力，获得了80.8%的准确度(表S3)。

Considering the wide variety of organic compounds, it is difficult to complete a sweep of all classes of compounds; therefore, we selected some representative classes such as ketone, aldehyde, phenol, and others to form the dataset of ${R}_{f}$ values. Although the predicted model has been proven to possess a satisfactory accuracy when predicting the ${R}_{f}$ curves of the classes involved in the dataset, its extendibility to other classes that have never appeared in the dataset is also a challenge. As a consequence, the predictive model is employed to predict the ${R}_{f}$ values of saccha-rides of which the results are displayed in Figure S11. Saccharides are polyhydroxy aldehydes and ketones, and their derivatives are not included in our dataset. It is shown that the predictive model has the ability, to a certain degree, to predict compounds of new classes with the accuracy of the prediction slightly affected. This result implies that the ML model actually discovers a strong relationship between compound structures and ${R}_{f}$ values, and it can predict the properties of compounds from new classes to a certain degree.

考虑到有机化合物种类繁多，很难对所有类别的化合物进行全面研究；因此，我们选择了一些具有代表性的类别，如酮、醛、酚等，来形成${R}_{f}$值数据集。尽管预测模型在预测数据集中所涉及类别的${R}_{f}$曲线时已被证明具有令人满意的准确度，但其对数据集中从未出现过的其他类别的可扩展性也是一个挑战。因此，使用预测模型来预测糖类的${R}_{f}$值，结果如图S11所示。糖类是多羟基醛和酮，其衍生物不包括在我们的数据集中。结果表明，预测模型在一定程度上有能力预测新类别的化合物，只是预测准确度略有影响。这一结果意味着机器学习模型实际上发现了化合物结构与${R}_{f}$值之间的强关系，并且它可以在一定程度上预测新类别化合物的性质。

Figure 5. Predicted ${R}_{f}$ curves

图5. 预测的${R}_{f}$曲线

(A and B) Predicted ${R}_{f}$ curves and experimental ${R}_{f}$ curves for two out-of-sample compounds under three mobile phase systems, including hexane/ethyl acetate (left), dichloromethane/methanol (middle), and hexane/diethyl ether (right).

(A和B) 三种流动相系统下两种样本外化合物的预测${R}_{f}$曲线和实验${R}_{f}$曲线，包括己烷/乙酸乙酯(左)、二氯甲烷/甲醇(中)和己烷/乙醚(右)。

(C) Predicted ${R}_{f}$ curves and experimental ${R}_{f}$ curves for three compounds of different classes under a certain mobile phase system. The log ratio is calculated as $\log \left( {r + 1}\right)$ , where $r$ is the ratio of eluent.

DISCUSSION

讨论

TLC experiments are performed extensively every day in synthetic laboratories around the world. Determination of suitable TLC conditions usually requires chemists with ample experience, and a large number of attempts would be inevitable. Here, we have built a robotic experimentation platform and its software for TLC data collection, which generates a large amount of standardized compound’s structure-polarity data represented by SMILES and ${R}_{f}$ values automatically. Using the dataset, we further developed ML models that can predict the compound’s ${R}_{f}$ values, and the experiments performed have proved that the proposed predictive model shows satisfactory accuracy in our dataset and a certain degree of expansibility, which has a hopeful prospect for facilitating the acquirement and application of ${R}_{f}$ values. This TLC prediction approach confirms that combining ML methods and automation is a promising way to facilitate laboratory efficiency, and we believe it will prove to be useful to the synthetic community.

薄层色谱(TLC)实验每天都在世界各地的合成实验室中广泛进行。确定合适的TLC条件通常需要经验丰富的化学家，并且不可避免地需要进行大量尝试。在这里，我们构建了一个用于TLC数据收集的机器人实验平台及其软件，该平台可自动生成大量由SMILES和${R}_{f}$值表示的标准化化合物结构 - 极性数据。利用该数据集，我们进一步开发了可以预测化合物${R}_{f}$值的机器学习(ML)模型，并且所进行的实验证明，所提出的预测模型在我们的数据集中显示出令人满意的准确性和一定程度的可扩展性，这对于促进${R}_{f}$值的获取和应用具有充满希望的前景。这种TLC预测方法证实，将ML方法与自动化相结合是提高实验室效率的一种有前途的方法，并且我们相信它将被证明对合成化学界是有用的。

There also remain some limitations in this work. Considering that TLC analysis is affected by many factors (Figure 1C), high-throughput techniques based on collaborative robots are employed in our work to obtain standardized ${R}_{f}$ value data for ML, thereby constructing a high-precision predictive model. However, the direct use of this model in other laboratories may not work in the way of predicting a precise ${R}_{f}$ value of a given compound due to different experimental conditions, e.g., the size of the chamber, TLC plates, and so on. Nevertheless, the model can compute a series of ${R}_{f}$ values under various combinations of eluents in seconds, which could be used as an initial trial point. As for separation tasks, the model can predict the probability of separation of two (or more) compounds as reflected by the predicted difference in the ${R}_{f}$ values.

这项工作也仍然存在一些局限性。考虑到TLC分析受许多因素影响(图1C)，我们的工作中采用了基于协作机器人的高通量技术来获取用于ML的标准化${R}_{f}$值数据，从而构建高精度预测模型。然而，由于不同的实验条件，例如展开缸的尺寸、TLC板等，在其他实验室直接使用该模型可能无法以预测给定化合物精确${R}_{f}$值的方式起作用。尽管如此，该模型可以在几秒钟内计算出各种洗脱剂组合下的一系列${R}_{f}$值，这些值可以用作初始试验点。至于分离任务，该模型可以通过预测的${R}_{f}$值差异来预测两种(或更多种)化合物分离的概率。

EXPERIMENTAL PROCEDURES

实验步骤

Resource availability

资源可用性

Lead contact

主要联系人

Further information and requests for resources should be directed to and will be fulfilled by the lead contact, Fanyang Mo ().

有关资源的更多信息和请求应直接联系主要联系人Fanyang Mo ()，并将由其处理。

Materials availability

材料可用性

This study did not generate new unique reagents.

本研究未产生新的独特试剂。

Data and code availability

数据和代码可用性

The TLC dataset have been deposited at the website https://github.com/ woshixuhao/ML-Prediction-for-Rf-values and are publicly available as of the date of publication.

TLC数据集已存放在网站https://github.com/ woshixuhao/ML-Prediction-for-Rf-values上，自发布之日起可公开获取。

All original code has been deposited at the website https://github.com/ woshixuhao/ML-Prediction-for-Rf-values and is publicly available as of the date of publication.

所有原始代码已存放在网站https://github.com/ woshixuhao/ML-Prediction-for-Rf-values上，自发布之日起可公开获取。

A video associated with this project can be found via the following links:

可以通过以下链接找到与该项目相关的视频:

English version: https://www.bilibili.com/video/BV1am4y1o7yE/

英文版:https://www.bilibili.com/video/BV1am4y1o7yE/

Chinese version: https://www.bilibili.com/video/BV17R4y1j7jz/

中文版:https://www.bilibili.com/video/BV17R4y1j7jz/

SUPPLEMENTAL INFORMATION

补充信息

Supplemental information can be found online at https://doi.org/10.1016/j.chempr.2022.08.008.

补充信息可在网上获取:https://doi.org/10.1016/j.chempr.2022.08.008。

ACKNOWLEDGMENTS

致谢

We thank Prof. Suwei Dong at Peking University Health Science Center, Prof. Shu-feng Chen at Inner Mongolia University, and Prof. Qing Xiao at Third Military Medical University for generously providing some organic compounds. This work is supported by the National Natural Science Foundation of China (grant nos. 22071004, 21933001, and 22150013).

我们感谢北京大学医学部的董苏伟教授、内蒙古大学的陈淑凤教授和第三军医大学的肖青教授慷慨提供了一些有机化合物。本研究得到了中国国家自然科学基金(项目编号:22071004、21933001和22150013)的资助。

AUTHOR CONTRIBUTIONS

作者贡献

H.X. and F.M. built the robotics platform for high-throughput experimentation. J.L. performed TLC experiments. H.X. performed chemoinformatic and ML studies. Q.L. derived the theoretical formula for TLC mechanisms. J.Z. and Q.L. performed DFT calculation. All authors analyzed the data. H.X. and F.M. wrote the manuscript. F.M. conceived the idea and designed the overall research. F.M. and D.Z. supervised the whole project.

H.X.和F.M.搭建了用于高通量实验的机器人平台。J.L.进行了薄层层析(TLC)实验。H.X.进行了化学信息学和机器学习研究。Q.L.推导了TLC机制的理论公式。J.Z.和Q.L.进行了密度泛函理论(DFT)计算。所有作者都分析了数据。H.X.和F.M.撰写了手稿。F.M.提出了想法并设计了整体研究。F.M.和D.Z.监督了整个项目。

DECLARATION OF INTERESTS

利益声明

F.M., H.X., and D.Z. are inventors on two patent applications (CN 202111638511.2 and 202122346010.9) submitted by Peking University that cover an organic chemistry laboratory automation system and a ML method for TLC conditions prediction, respectively.

F.M.、H.X. 和 D.Z. 是北京大学提交的两项专利申请(CN 202111638511.2 和 202122346010.9)的发明人，这两项专利申请分别涵盖了一个有机化学实验室自动化系统和一种用于TLC条件预测的机器学习方法。

Received: May 19, 2022

收到日期:2022年5月19日

Revised: July 20, 2022

修订日期:2022年7月20日

Accepted: August 12, 2022

接受日期:2022年8月12日

Published: September 7, 2022

发布日期:2022年9月7日

REFERENCES

参考文献

Sherma, J., and Fried, B. (2003). Handbook of Thin-Layer Chromatography (CRC Press).
Muratov, E.N., Bajorath, J., Sheridan, R.P., Tetko, I.V., Filimonov, D., Poroikov, V., Oprea, T.I., Baskin, I.I., Varnek, A., Roitberg, A., et al. (2020). QSAR without borders. Chem. Soc. Rev. 49, 3525-3564. https://doi.org/10.1039/ d0cs00098a.
Yang, Q., Li, Y., Yang, J.D., Liu, Y., Zhang, L., Luo, S., and Cheng, J.P. (2020). Holistic prediction of the pKa in diverse solvents based on a machine-learning approach. Angew. Chem. Int. Ed. Engl. 59, 19282-19291. https:// doi.org/10.1002/anie.202008528.
Howarth, A., Ermanis, K., and Goodman, J.M. (2020). DP4-AI automated NMR data analysis: straight from spectrometer to structure. Chem. Sci. 11, 4351-4359. https://doi.org/10.1039/ dOsc00442a.
Reid, J.P., and Sigman, M.S. (2019). Holistic prediction of enantioselectivity in asymmetric catalysis. Nature 571, 343-348. https://doi.org/ 10.1038/s41586-019-1384-z.
Kirkpatrick, J., McMorrow, B., Turban, D.H.P., Gaunt, A.L., Spencer, J.S., Matthews, A.G.D.G., Obika, A., Thiry, L., Fortunato, M., Pfau, D., et al. (2021). Pushing the frontiers of density functionals by solving the fractional electron problem. Science 374, 1385-1389. https://doi.org/10.1126/science.abj6511.
Kursa, M.B., Komsta, Ł., and Rudnicki, W.R. (2011). The robust models of retention for thin layer chromatography. Soft Comput. 103, 169-176. https://doi.org/10.1007/978-3-642- 23169-8_19.
Komsta, Ł. (2008). A functional-based approach to the retention in thin layer chromatographic screening systems. Anal. Chim. Acta 629, 66-72. https://doi.org/10.1016/j.aca.2008.09.036.
Ley, S.V., Fitzpatrick, D.E., Ingham, R.J., and Myers, R.M. (2015). Organic synthesis: march of the machines. Angew. Chem. Int. Ed. Engl. 54, 3449-3464. https://doi.org/10.1002/anie.201410744.
Häse, F., Roch, L.M., and Aspuru-Guzik, A. (2019). Next-generation experimentation with self-driving laboratories. J. Trends Chem. 1, 282-291. https://doi.org/10.1016/j.trechm.2019.02.007.
Wilbraham, L., Mehr, S.H.M., and Cronin, L. (2021). Digitizing chemistry using the chemical processing unit: From synthesis to discovery. Acc. Chem. Res. 54, 253-262. https://doi.org/ 10.1021/acs.accounts.0c00674.
Mahjour, B., Shen, Y., and Cernak, T. (2021). Ultrahigh-throughput experimentation for Information-rich chemical synthesis. Acc. Chem. Res. 54, 2337-2346. https://doi.org/10.1021/acs.accounts.1c00119.
Ahneman, D.T., Estrada, J.G., Lin, S., Dreher, S.D., and Doyle, A.G. (2018). Predicting reaction performance in C-N cross-coupling using machine learning. Science 360, 186-190. https://doi.org/10.1126/science.aar5169.
Granda, J.M., Donina, L., Dragone, V., Long, D.L., and Cronin, L. (2018). Controlling an organic synthesis robot with machine learning to search for new reactivity. Nature 559, 377-381. https://doi.org/10.1038/s41586-018- 0307-8.
Steiner, S., Wolf, J., Glatzel, S., Andreou, A., Granda, J.M., Keenan, G., Hinkley, T., Aragon-Camarasa, G., Kitson, P.J., Angelone, D., et al. (2019). Organic synthesis in a modular robotic system driven by a chemical programming language. Science 363. https://doi.org/10.1126/science.aav2211.
Burger, B., Maffettone, P.M., Gusev, V.V., Aitchison, C.M., Bai, Y., Wang, X., Li, X., Alston, B.M., Li, B., Clowes, R., et al. (2020). A mobile robotic chemist. Nature 583, 237-241. https:// doi.org/10.1038/s41586-020-2442-2.
Newman-Stonebraker, S.H., Smith, S.R., Borowski, J.E., Peters, E., Gensch, T., Johnson, H.C., Sigman, M.S., and Doyle, A.G. (2021). Univariate classification of phosphine ligation state and reactivity in cross-coupling catalysis. Science 374, 301-308. https://doi.org/10.1126/ science.abj4213.
Shields, B.J., Stevens, J., Li, J., Parasram, M., Damani, F., Alvarado, J.I.M., Janey, J.M., Adams, R.P., and Doyle, A.G. (2021). Bayesian reaction optimization as a tool for chemical synthesis. Nature 590, 89-96. https://doi.org/ 10.1038/s41586-021-03213-y.
Durant, J.L., Leland, B.A., Henry, D.R., and Nourse, J.G. (2002). Reoptimization of MDL keys for use in drug discovery. J. Chem. Inf. Comput. Sci. 42, 1273-1280. https://doi.org/ 10.1021/ci010132r.
Landrum, G. (2017). Getting started with the RDKit in Python. http://www.rdkit.org/docs/ GettingStartedInPython.html.
Stewart, J.J.P. (2016). Stewart Computational Chemistry. http://openmopac.net/.
Weininger, D. (1988). SMILES, a chemical language and information system: 1: Introduction to methodology and encoding rules. J. Chem. Inf. Model. 28, 31-36. https:// doi.org/10.1021/ci00057a005.
Sagi, O., and Rokach, L. (2018). Ensemble learning: A survey. WIREs Data Mining Knowl. Discov. 8. https://doi.org/10.1002/widm.1249.
Qi, G.J., and Luo, J. (2022). Small data challenges in big data era: A survey of recent progress on unsupervised and semi-supervised methods. IEEE Trans. Pattern Anal. Mach. Intell. 44, 2168-2187. https://doi.org/10.1109/ TPAMI.2020.3031898.