Machine learning-based solubility prediction and methodology evaluation of active pharmaceutical ingredients in industrial crystallization

Ma, Yiming; Gao, Zhenguo; Shi, Peng; Chen, Mingyang; Wu, Songgu; Yang, Chao; Wang, Jingkang; Cheng, Jie; Gong, Junbo

doi:10.1007/s11705-021-2083-5

Cited by 14 publications

(21 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…RFs is an ensemble learning method. RFs has higher accuracy in feature importance evaluation due to its strong robustness . In the industrial production process, the characteristic of high dimension of industrial data often affects the complexity and prediction performance of the model.…”

Section: Proposed Methodologymentioning

confidence: 99%

“…RFs has higher accuracy in feature importance evaluation due to its strong robustness. 21 In the industrial production process, the characteristic of high dimension of industrial data often affects the complexity and prediction performance of the model. A forest-based variable selection algorithm can analyze the distribution of variables to measure the importance of each variable, and it has been proved in several cases that the algorithm can identify important information in different applications.…”

Section: Proposed Methodologymentioning

confidence: 99%

See 1 more Smart Citation

Yield and Properties Prediction Based on the Multicondition LSTM Model for the Solvent Deasphalting Process

et al. 2023

View full text Add to dashboard Cite

Solvent deasphalting (SDA) is a complex multiscale continuous process. The operation mode of the SDA process is not considered in the related data-driven model. Therefore, this paper proposes a time lag process prediction model with multiple operation modes to solve the above problem. First, based on random forests, the relative importance of initial input variables in the SDA process on DAO yield and Conradson carbon residual are studied and features are selected according to the results. Then, the stack denoising autoencoder (SDAE) is used to reconstruct the data and obtain the nonlinear mapping information of hidden layers of SDAE and achieve feature dimension reduction. SDAE can improve clustering accuracy of fuzzy c-means, and the operation mode of SDA process is accurately divided. Long short-term memory (LSTM) is used to establish a multicondition LSTM model. Compared with the traditional LSTM model, the multicondition LSTM model has a higher prediction accuracy with R 2 > 0.95. The sensitivity analyses of the properties of feed and operating conditions on DAO yield are consistent with the principle of two-phase countercurrent extraction in the SDA process. In addition, the benchmark test of the Tennessee Eastman process shows that the proposed method is also effective in the fault detection of other processes. Because the multicondition LSTM can predict the future process measurement data according to operating mode, it can better avoid the false alarm problem and predict the fault earlier.

show abstract

Section: Proposed Methodologymentioning

confidence: 99%

Section: Proposed Methodologymentioning

confidence: 99%

Yield and Properties Prediction Based on the Multicondition LSTM Model for the Solvent Deasphalting Process

et al. 2023

View full text Add to dashboard Cite

show abstract

“…Large solubility collections of the same solute−solvent system must be carefully curated to avoid inconsistencies, such as data collected from different methods (e.g., isothermal and polythermal), equipment, and protocols, and to understand variability and the associated source. Similarly, the development and performance of ML algorithms often depend on hyperparameters such as maximum number of features, number of components, nodes, layers, 194 and activation functions, which are seldom evaluated explicitly in the publications and are impossible to analyze/optimize exhaustively. Hence, claims on the limitations of both descriptors and algorithms are valid.…”

Section: Solubilitymentioning

confidence: 99%

Applications of Artificial Intelligence and Machine Learning Algorithms to Crystallization

et al. 2022

View full text Add to dashboard Cite

Artificial intelligence and specifically machine learning applications are nowadays used in a variety of scientific applications and cutting-edge technologies, where they have a transformative impact. Such an assembly of statistical and linear algebra methods making use of large data sets is becoming more and more integrated into chemistry and crystallization research workflows. This review aims to present, for the first time, a holistic overview of machine learning and cheminformatics applications as a novel, powerful means to accelerate the discovery of new crystal structures, predict key properties of organic crystalline materials, simulate, understand, and control the dynamics of complex crystallization process systems, as well as contribute to high throughput automation of chemical process development involving crystalline materials. We critically review the advances in these new, rapidly emerging research areas, raising awareness in issues such as the bridging of machine learning models with first-principles mechanistic models, data set size, structure, and quality, as well as the selection of appropriate descriptors. At the same time, we propose future research at the interface of applied mathematics, chemistry, and crystallography. Overall, this review aims to increase the adoption of such methods and tools by chemists and scientists across industry and academia.

show abstract

“…The last few years have seen a rapidly growing interest in the application of machine learning (ML) techniques to understand, predict and determine the functional properties of a diverse array of molecules and materials. [1][2][3][4][5][6] Properties ranging from the thermal conductivity of alloys [7][8][9][10][11] to the solubility of pharmaceutical drugs [12][13][14][15][16][17][18] have all been predicted with various levels of success using modern ML techniques. A large contributing factor to the meteoric rise of ML in the last two decades is the large amount of data that is becoming more easily accessible.…”

Section: Introductionmentioning

confidence: 99%

Leveraging genetic algorithms to maximise the predictive capabilities of the SOAP descriptor

Barnard

Tseng

Darby

et al. 2023

Mol. Syst. Des. Eng.

View full text Add to dashboard Cite

show abstract

Machine learning-based solubility prediction and methodology evaluation of active pharmaceutical ingredients in industrial crystallization

Cited by 14 publications

References 44 publications

Yield and Properties Prediction Based on the Multicondition LSTM Model for the Solvent Deasphalting Process

Yield and Properties Prediction Based on the Multicondition LSTM Model for the Solvent Deasphalting Process

Applications of Artificial Intelligence and Machine Learning Algorithms to Crystallization

Leveraging genetic algorithms to maximise the predictive capabilities of the SOAP descriptor

Contact Info

Product

Resources

About