Biodegradability Prediction of Fragrant Molecules by Molecular Topology

Blay, Vincent; Gullón-Soleto, Jesús; Gálvez-Llompart, María; Gálvez, Jorge; García-Domènech, Ramón

doi:10.1021/acssuschemeng.6b00717

Cited by 18 publications

(12 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Given the large numbers of conventional molecular descriptors that are typically computed (hundreds to thousands), a variable selection step was conducted to select a small subset of informative descriptors with which to build a model. The selection was carried out using a heuristic forward stepwise selection algorithm, which is commonly applied to conventional molecular descriptors [35][36][37][38] . This algorithm tends to give good results, although it can be timeconsuming, as it requires to train and evaluate 𝑁 × 𝐷 × 𝐹 models, where 𝑁 is the number of variables considered for the selection (several hundred in this case), 𝐷 is the number of desired descriptors being eventually selected (15 in this case), and 𝐹 is the number of cross-validation folds used to evaluate each model (5 in this case).…”

Section: Datasets Biofuel Propertiesmentioning

confidence: 99%

MACAW: an accessible tool for molecular embedding and inverse molecular design

Blay

Radivojević

Allen

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

The growing capabilities of synthetic biology and organic chemistry demand tools to guide syntheses towards useful molecules. Here, we present MACAW (Molecular AutoenCoding Auto-Workaround), a tool that uses a novel approach to generate molecules predicted to meet a desired property specification (e.g. a binding affinity of 50 nM or an octane number of 90). MACAW describes molecules by embedding them into a smooth multidimensional numerical space, avoiding uninformative dimensions that previous methods often introduce. The coordinates in this embedding provide a natural choice of features for accurately predicting molecular properties, which we demonstrate with examples for cetane and octane numbers, flash points, and histamine H1 receptor binding affinity. The approach is computationally efficient and well-suited to the small- and medium-size datasets commonly used in the biosciences. We showcase the utility of MACAW for virtual screening by identifying molecules with high predicted binding affinity to the histamine H1 receptor and limited affinity to the muscarinic M2 receptor, which are targets of medicinal relevance. Combining these predictive capabilities with a novel generative algorithm for molecules allows us to recommend molecules with a desired property value (i.e. inverse molecular design). We demonstrate this capability by recommending molecules with predicted octane numbers of 40, 80, and 120, which is an important characteristic for biofuels. Thus, MACAW augments classical retrosynthesis tools by providing recommendations for molecules on specification.

show abstract

Section: Datasets Biofuel Propertiesmentioning

confidence: 99%

MACAW: an accessible tool for molecular embedding and inverse molecular design

Blay

Radivojević

Allen

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Their numerical format notably simplifies the automatic search of other molecules with similar structural properties, hence they are strong candidates to share the physicochemical and biological properties sought . 49 Each compound was characterized by a set of 436 topological indices. All indices were calculated with Dragon software.…”

Section: Molecular Descriptorsmentioning

confidence: 99%

Identification of New Templates for the Synthesis of BEA, BEC, and ISV Zeolites Using Molecular Topology and Monte Carlo Techniques

Gálvez-Llompart

Gálvez

Rey

et al. 2020

J. Chem. Inf. Model.

Self Cite

View full text Add to dashboard Cite

The presence of organic structure directing agents (templates) in the synthesis of zeolites allows the synthesis to be directed, in many cases, towards structures in which there is a large stabilisation between the template and the zeolite micropore due to dispersion interactions.Although other factors are also important (temperature, pH, Si/Al ratio, etc), systems with strong zeolite-template interactions are good candidates for an application of new computational algorithms, for instance those based in molecular topology (MT), that can be used in combination with large databases of organic molecules. Computational design of new templates allows the synthesis of existing and new zeolites to be expanded and refined. Three zeolites with similar 3-D large pore system, BEA, BEC and ISV were selected with the aim of finding new templates for their selective synthesis. Using a training set of active and inactive templates (obtained from literature) for the synthesis of target zeolites it was possible to select chemical descriptors related to activity, meaning a good candidate template. With a discriminant function defined upon MT, the screening through a database of organic molecules led to a small subset (preselection) of candidate templates for the synthesis of BEA, BEC and ISV. As far as we know, this is the first time that topological/topochemical descriptors, which do not consider 3-D information of the molecules, have been used to predict the activity of zeolite structure directing agents (SDA).Following the prediction of SDAs using MT, an automated approach of sequential template filling of micropores based on a combination of Monte Carlo and lattice energy minimization was applied for all the candidate templates in the three zeolites. Two results can be obtained from this: an evaluation of the quality of the molecular topology QSAR models leading to the preselection of templates, and, a final selection of candidate templates for the selective synthesis of BEA, BEC and ISV. Regarding the latter, a good template will be that which maximizes the zeolite-template dispersion interactions with one, and only one, of the three zeolites. The presented methodology can be used to find alternative (maybe cheaper or perhaps more selective) templates than those already known.

show abstract

“…One of the furthermost usually applied methods to replace the experimental techniques is the use of computer-assisted quantitative structure–property relation (QSPR) models . A QSPR model is a mathematical model that relates the component’s molecular-level structure to its macroscopic-level physicochemical properties. , This modeling approach showed its reliability in predicting the physical, chemical, and biological properties of numerous solvents. − In an attempt to develop a QSPR model, the following should be obtained: (1) an extensive data set which covers different chemicals for sufficient statistical analysis, (2) selection of molecular descriptors, (3) calculation and generating the molecular descriptors of these compounds, (4) selecting a proper algorithm to relate the molecular descriptors with the dependent variable, and (5) performing a statistical analysis to ensure the robustness and the applicability of the predictive model. The application of QSPR models in predicting the physicochemical properties of ionic liquids has been reported extensively in the literature.…”

Section: Introductionmentioning

confidence: 99%

Molecular-Based Guide to Predict the pH of Eutectic Solvents: Promoting an Efficient Design Approach for New Green Solvents

Lemaoui

Hatab

Darwish

et al. 2021

ACS Sustainable Chem. Eng.

View full text Add to dashboard Cite

The case of sustainable solvents is of great interest both academically and industrially. With research communities becoming more aware of the negative impacts of conventional organic solvents, a range of greener and more sustainable solvents have been developed to counter the harmful drawbacks associated with conventional solvents. Among these, eutectic solvents (ESs) attracted considerable attention for their "green" properties and have proven their usefulness as environmentally benign alternatives to classical solvents. Among the various desirable characteristics of ESs, pH is a key property with significant implications for the design and control of industrial-scale applications. However, selecting an ES with the required pH for a particular application is a challenging task, especially with extensive experimentally determined data being time consuming and expensive. Therefore, in this work, the pH of various ESs have been predicted via novel quantitative structure−property relationships (QSPR) models using two machine learning algorithms, a multiple linear regression (MLR) and an artificial neural network (ANN), with a set of molecular descriptors generated by COSMO-RS. A total of 648 experimental points for 41 chemically unique ESs prepared from 9 HBAs and 21 HBDs at different temperatures were utilized for sufficient data set representation. On the basis of the statistical analysis of the models, it can be concluded that both approaches can be utilized as powerful predictive tools in estimating the pH of new ESs with the ANN model having better predictive capabilities and the MLR model being more interpretable. These models inspire and stimulate the development of robust models to predict the properties of designer solvents from the drawn molecular structures, which will save time and resources.

show abstract

Biodegradability Prediction of Fragrant Molecules by Molecular Topology

Cited by 18 publications

References 24 publications

MACAW: an accessible tool for molecular embedding and inverse molecular design

MACAW: an accessible tool for molecular embedding and inverse molecular design

Identification of New Templates for the Synthesis of BEA, BEC, and ISV Zeolites Using Molecular Topology and Monte Carlo Techniques

Molecular-Based Guide to Predict the pH of Eutectic Solvents: Promoting an Efficient Design Approach for New Green Solvents

Contact Info

Product

Resources

About