Intelligent Recommendation Systems Powered by Consensus Neural Networks: The Ultimate Solution for Finding Suitable Chiral Chromatographic Systems?

• Published in: Analytical chemistry (Washington) Vol. 96; no. 29; pp. 12205 - 12212
• Main Authors: Sagrado, Salvador, Pardo-Cortina, Carlos, Escuder-Gilabert, Laura, Medina-Hernández, María José, Martín-Biosca, Yolanda
• Format: Journal Article
• Language: English
• Published: United States American Chemical Society 23-07-2024
• Subjects: Acetonitrile; Algorithms; Amylose; Artificial neural networks; Cellulose; Chromatography; Complexity; Machine learning; Molecular structure; Neural networks; Recommender systems
• ISSN: 0003-2700; 1520-6882; 1520-6882
• DOI: 10.1021/acs.analchem.4c02656

The selection of suitable combinations of chiral stationary phases (CSPs) and mobile phases (MPs) for the enantioresolution of chiral compounds is a complex issue that often requires considerable experimental effort and can lead to significant waste. Linking the structure of a chiral compound to a CSP/MP system suitable for its enantioseparation can be an effective solution to this problem. In this study, we evaluate algorithmic tools for this purpose. Our proposed consensus model, which uses multiple optimized artificial neural networks (ANNs), shows potential as an intelligent recommendation system (IRS) for ranking chromatographic systems suitable for the enantioresolution of chiral compounds with different molecular structures. To evaluate the IRS potential in a proof-of-concept stage, 56 structural descriptors for 56 structurally unrelated chiral compounds across 14 different families are considered. Chromatographic systems under study comprise 7 cellulose and amylose derivative CSPs and acetonitrile or methanol aqueous MPs (14 chromatographic systems in all). The ANNs are optimized using a fit-for-purpose version of the chaotic neural network algorithm with competitive learning (CCLNNA), a novel approach not previously applied in the chemical domain. CCLNNA is adapted to define the inner ANN complexity and perform feature selection of the structural descriptors. A customized target function evaluates the correctness of recommending the appropriate CSP/MP system. The ANN-consensus model exhibits no advisory failures and requires only an experimental attempt to verify the IRS recommendation for complete enantioresolution. This outstanding performance highlights its potential to effectively resolve this problem.