Simplified Molecular Input Line Entry System Research Articles

Traditional Machine and Deep Learning for Predicting Toxicity Endpoints.

Molecular structure property modeling is an increasingly important tool for predicting compounds with desired properties due to the expensive and resource-intensive nature and the problem of toxicity-related attrition in late phases during drug discovery and development. Lately, the interest for applying deep learning techniques has increased considerably. This investigation compares the traditional physico-chemical descriptor and machine learning-based approaches through autoencoder generated descriptors to two different descriptor-free, Simplified Molecular Input Line Entry System (SMILES) based, deep learning architectures of Bidirectional Encoder Representations from Transformers (BERT) type using the Mondrian aggregated conformal prediction method as overarching framework. The results show for the binary CATMoS non-toxic and very-toxic datasets that for the former, almost equally balanced, dataset all methods perform equally well while for the latter dataset, with an 11-fold difference between the two classes, the MolBERT model based on a large pre-trained network performs somewhat better compared to the rest with high efficiency for both classes (0.93-0.94) as well as high values for sensitivity, specificity and balanced accuracy (0.86-0.87). The descriptor-free, SMILES-based, deep learning BERT architectures seem capable of producing well-balanced predictive models with defined applicability domains. This work also demonstrates that the class imbalance problem is gracefully handled through the use of Mondrian conformal prediction without the use of over- and/or under-sampling, weighting of classes or cost-sensitive methods.

Development of a CSRML version of the Analog identification Methodology (AIM) fragments and their evaluation within the Generalised Read-Across (GenRA) approach

The Analog Identification Methodology (AIM) was developed over 20 years ago to identify analogues to support read-across at the US Environmental Protection Agency. However, the current public version of the standalone tool, released in 2012, is no longer usable on Windows operating systems supported by Microsoft. Additionally, the structural logic for analogue selection is based on older, customised Simplified molecular-input-line-entry system (SMILES)-type features that are incompatible with modern cheminformatics tools. Given these limitations, a case study was undertaken to explore a more transparent, extensible method of implementing the AIM fragments using Chemical Subgraphs and Reactions Mark-up Language (CSRML). A CSRML file was developed to codify the original AIM fragments, and the extent to which AIM fragments were faithfully replicated was assessed using the AIM Database. The overall mean performance of the CSRML-AIM across all fragments in terms of sensitivity, specificity, and Jaccard similarity was 89.5%, 99.9%, and 82.2%, respectively. Comparing the AIM fragments with public ToxPrints using a large set of ∼25,000 substances of regulatory interest to EPA found them to be dissimilar, with an average maximum Jaccard score of 0.24 for AIM and 0.29 for ToxPrint fingerprints. Both fragment sets were then used as inputs in the automated read-across approach, Generalised Read-Across (GenRA), to evaluate the quality of fit in predicting rat acute oral toxicity LD50 values with the coefficient of determination (R2) and root mean squared error (RMSE). The performance of AIM fragments was R2=0.434 and RMSE=0.663 whereas that of ToxPrints was R2=0.477 and RMSE=0.638. A bootstrap resampling using 100 iterations found the mean and the 95th confidence interval of R2 to be 0.349 [0.319, 0.379] for AIM fragments and 0.377 [0.338, 0.412] for ToxPrints. Although AIM and ToxPrints performed similarly in predicting LD50, they differed in their performance at a local level, revealing that their features can offer complementary insights.

Exploration of Chemical Space Guided by PixelCNN for Fragment-Based De Novo Drug Discovery.

We report a novel framework for achieving fragment-based molecular design using pixel convolutional neural network (PixelCNN) combined with the simplified molecular input line entry system (SMILES) as molecular representation. While a widely used recurrent neural network (RNN) assumes monotonically decaying correlations in strings, PixelCNN captures a periodicity among characters of SMILES. Thus, PixelCNN provides us with a novel solution for the analysis of chemical space by extracting the periodicity of molecular structures that will be buried in SMILES. Moreover, this characteristic enables us to generate molecules by combining several simple building blocks, such as a benzene ring and side-chain structures, which contributes to the effective exploration of chemical space by step-by-step searching for molecules from a target fragment. In conclusion, PixelCNN could be a powerful approach focusing on the periodicity of molecules to explore chemical space for the fragment-based molecular design.

Universal machine-learning algorithm for predicting adsorption performance of organic molecules based on limited data set: Importance of feature description

Adsorption of organic molecules from aqueous solution offers a simple and effective method for their removal. Recently, there have been several attempts to apply machine learning (ML) for this problem. To this end, polyparameter linear free energy relationships (pp-LFERs) were employed, and poor prediction results were observed outside model applicability domain of pp-LFERs. In this study, we improved the applicability of ML methods by adopting a chemical-structure (CS) based approach. We used the prediction of adsorption of organic molecules on carbon-based adsorbents as an example. Our results show that this approach can fully differentiate the structural differences between any organic molecules, while providing significant information that is relevant to their interaction with the adsorbents. We compared two CS feature descriptors: 3D-coordination and simplified molecular-input line-entry system (SMILES). We then built CS-ML models based on neural networks (NN) and extreme gradient boosting (XGB). They all outperformed pp-LFERs based models and are capable to accurately predict adsorption isotherm of isomers with similar physiochemical properties such as chiral molecules, even though they are trained with achiral molecules and racemates. We found for predicting adsorption isotherm, XGB shows better performance than NN, and 3D-coordinations allow effective differentiation between organic molecules.

Quasi-SMILES: Self-consistent models for toxicity of organic chemicals to tadpoles

Simplified molecular input-line entry systems (SMILES) are the representation of the molecular structure that can be used to establish quantitative structure-property/activity relationships (QSPRs/QSARs) for various endpoints expressed as mathematical functions of the molecular architecture. Quasi-SMILES is extending the traditional SMILES by means of additional symbols that reflect experimental conditions. Using the quasi-SMILES models of toxicity to tadpoles gives the possibility to build up models by taking into account the time of exposure. Toxic effects of experimental situations expressed via 188 quasi-SMILES (the negative logarithm of molar concentrations which lead to lethal 50% tadpoles effected during 12 h, 24 h, 48 h, 72 h, and 96 h) were modelled with good results (the average determination coefficient for the validation sets is about 0.97). In this way, we developed new models for this amphibian endpoint, which is poorly studied.

Cocrystal virtual screening based on the XGBoost machine learning model

Co-crystal formation can improve the physicochemical properties of a compound, thus enhancing its druggability. Therefore, artificial intelligence-based co-crystal virtual screening in the early stage of drug development has attracted extensive attention from researchers. However, the complexity of developing and applying algorithms hinders it wide application. This study presents a data-driven co-crystal prediction method based on the XGBoost machine learning model of the scikit-learn package. The simplified molecular input line entry specification (SMILES) information of two compounds is simply inputted to determine whether a co-crystal can be formed. The data set includs the co-crystal records presented in the Cambridge Structural Database (CSD) and the records of no co-crystal formation from extant literature and experiments. RDKit molecular descriptors are adopted as the features of a compound in the data set. The developed model shows excellent performance in the proposed co-crystal training and validation sets with high accuracy, sensitivity, and F1 score. The prediction success rate of the model exceeds 90%. The model therefore provides a simple and feasible scheme for designing and screening co-crystal drugs efficiently and accurately.

Novel bacterial taxa in a minimal lignocellulolytic consortium and their potential for lignin and plastics transformation.

The understanding and manipulation of microbial communities toward the conversion of lignocellulose and plastics are topics of interest in microbial ecology and biotechnology. In this study, the polymer-degrading capability of a minimal lignocellulolytic microbial consortium (MELMC) was explored by genome-resolved metagenomics. The MELMC was mostly composed (>90%) of three bacterial members (Pseudomonas protegens; Pristimantibacillus lignocellulolyticus gen. nov., sp. nov; and Ochrobactrum gambitense sp. nov) recognized by their high-quality metagenome-assembled genomes (MAGs). Functional annotation of these MAGs revealed that Pr. lignocellulolyticus could be involved in cellulose and xylan deconstruction, whereas Ps. protegens could catabolize lignin-derived chemical compounds. The capacity of the MELMC to transform synthetic plastics was assessed by two strategies: (i) annotation of MAGs against databases containing plastic-transforming enzymes; and (ii) predicting enzymatic activity based on chemical structural similarities between lignin- and plastics-derived chemical compounds, using Simplified Molecular-Input Line-Entry System and Tanimoto coefficients. Enzymes involved in the depolymerization of polyurethane and polybutylene adipate terephthalate were found to be encoded by Ps. protegens, which could catabolize phthalates and terephthalic acid. The axenic culture of Ps. protegens grew on polyhydroxyalkanoate (PHA) nanoparticles and might be a suitable species for the industrial production of PHAs in the context of lignin and plastic upcycling.

CNN-based two-branch multi-scale feature extraction network for retrosynthesis prediction

BackgroundRetrosynthesis prediction is the task of deducing reactants from reaction products, which is of great importance for designing the synthesis routes of the target products. The product molecules are generally represented with some descriptors such as simplified molecular input line entry specification (SMILES) or molecular fingerprints in order to build the prediction models. However, most of the existing models utilize only one molecular descriptor and simply consider the molecular descriptors in a whole rather than further mining multi-scale features, which cannot fully and finely utilizes molecules and molecular descriptors features.ResultsWe propose a novel model to address the above concerns. Firstly, we build a new convolutional neural network (CNN) based feature extraction network to extract multi-scale features from the molecular descriptors by utilizing several filters with different sizes. Then, we utilize a two-branch feature extraction layer to fusion the multi-scale features of several molecular descriptors to perform the retrosynthesis prediction without expert knowledge. The comparing result with other models on the benchmark USPTO-50k chemical dataset shows that our model surpasses the state-of-the-art model by 7.4%, 10.8%, 11.7% and 12.2% in terms of the top-1, top-3, top-5 and top-10 accuracies. Since there is no related work in the field of bioretrosynthesis prediction due to the fact that compounds in metabolic reactions are much more difficult to be featured than those in chemical reactions, we further test the feasibility of our model in task of bioretrosynthesis prediction by using the well-known MetaNetX metabolic dataset, and achieve top-1, top-3, top-5 and top-10 accuracies of 45.2%, 67.0%, 73.6% and 82.2%, respectively.ConclusionThe comparison result on USPTO-50k indicates that our proposed model surpasses the existing state-of-the-art model. The evaluation result on MetaNetX dataset indicates that the models used for retrosynthesis prediction can also be used for bioretrosynthesis prediction.

Use of quasi-SMILES to build models based on quantitative results from experiments with nanomaterials.

Quasi-SMILES deviate from traditional SMILES (simplified molecular input-line entry system) by the extension of additional symbols that encode for conditions of an experiment. Descriptors calculated with SMILES are useful for the development of quantitative structure-property/activity relationships (QSPRs/QSARs), while descriptors calculated with quasi-SMILES can be useful for the development of quantitative models of experimental results obtained under different conditions. Here, this approach has been applied for the development of generalized models using aquatic nanotoxicity data (i.e., related to fish and daphnia). The statistical quality of the above models (pLC50) is quite good with a determination coefficient for the external validation set ranging from 0.62 to 0.71 and RMSE ranging from 0.58 to 0.60. The principle of the approach includes splitting the experimental data into three random distributions defining training, calibration, and validation sets.

SMICLR: Contrastive Learning on Multiple Molecular Representations for Semisupervised and Unsupervised Representation Learning.

Machine learning as a tool for chemical space exploration broadens horizons to work with known and unknown molecules. At its core lies molecular representation, an essential key to improve learning about structure-property relationships. Recently, contrastive frameworks have been showing impressive results for representation learning in diverse domains. Therefore, this paper proposes a contrastive framework that embraces multimodal molecular data. Specifically, our approach jointly trains a graph encoder and an encoder for the simplified molecular-input line-entry system (SMILES) string to perform the contrastive learning objective. Since SMILES is the basis of our method, i.e., we built the molecular graph from the SMILES, we call our framework as SMILES Contrastive Learning (SMICLR). When stacking a nonlinear regressor on the SMICLR's pretrained encoder and fine-tuning the entire model, we reduced the prediction error by, on average, 44% and 25% for the energetic and electronic properties of the QM9 data set, respectively, over the supervised baseline. We further improved our framework's performance when applying data augmentations in each molecular-input representation. Moreover, SMICLR demonstrated competitive representation learning results in an unsupervised setting.

A merged molecular representation deep learning method for blood–brain barrier permeability prediction

The ability of a compound to permeate across the blood-brain barrier (BBB) is a significant factor for central nervous system drug development. Thus, for speeding up the drug discovery process, it is crucial to perform high-throughput screenings to predict the BBB permeability of the candidate compounds. Although experimental methods are capable of determining BBB permeability, they are still cost-ineffective and time-consuming. To complement the shortcomings of existing methods, we present a deep learning-based multi-model framework model, called Deep-B3, to predict the BBB permeability of candidate compounds. In Deep-B3, the samples are encoded in three kinds of features, namely molecular descriptors and fingerprints, molecular graph and simplified molecular input line entry system (SMILES) text notation. The pre-trained models were built to extract latent features from the molecular graph and SMILES. These features depicted the compounds in terms of tabular data, image and text, respectively. The validation results yielded from the independent dataset demonstrated that the performance of Deep-B3 is superior to that of the state-of-the-art models. Hence, Deep-B3 holds the potential to become a useful tool for drug development. A freely available online web-server for Deep-B3 was established at http://cbcb.cdutcm.edu.cn/deepb3/, and the source code and dataset of Deep-B3 are available at https://github.com/GreatChenLab/Deep-B3.

Convolutional neural network prediction of molecular properties for aerosol chemistry and health effects

AbstractQuinones are chemical compounds commonly found in air particulate matter (PM). Their redox activity can generate reactive oxygen species (ROS) and contribute to the oxidative potential (OP) of PM leading to adverse health effects of aerosols. The quinones' OP and ability to form ROS are linked to their reduction potential (RP, measured in volts), a metric for the tendency to lose electrons in redox reactions. Here, we use convolutional neural networks (CNN) as quantitative structure‐activity relationship (QSAR) models to relate the one‐electron RP of quinones to their molecular structure. For CNN training and testing, a data set of more than 100,000 quinones with associated RP values derived from density functional theory calculations was encoded in simplified molecular input line entry system (SMILES). The best performing CNN model achieved a root mean square error (RMSE) of 0.115 V for an independent test data set and outperformed linear regression models fitted on common molecular descriptors (≥ 0.140 V RMSE). Augmentation methods were newly adapted or applied to support CNN training with smaller data sets, improving RMSE by up to approximately 37% for a data set of 321 molecules. Adjusted for solvent effects, the CNN‐derived RP predictions showed good agreement with experimental data. Using the newly developed method, we identified a subset of atmospherically relevant quinones that are likely to have a high OP and play a role in aerosol health effects, which remains to be further elucidated by experimental studies. We suggest to use the presented machine learning approach in further investigations of atmospheric aerosol chemistry and health effects as well as other studies that require a target‐oriented screening of the properties and effects of large classes of substances.Key Points Convolutional neural networks can be used to estimate unknown physical and chemical properties of chemical substances and outperform additive group contribution methods. Augmentation methods aid in the prevalent problem of data availability. Quinone species detected in the environment are screened for potential relevance in atmospheric chemistry and public health and presented in this study.

Fine-tuning of BERT Model to Accurately Predict Drug–Target Interactions

The identification of optimal drug candidates is very important in drug discovery. Researchers in biology and computational sciences have sought to use machine learning (ML) to efficiently predict drug–target interactions (DTIs). In recent years, according to the emerging usefulness of pretrained models in natural language process (NLPs), pretrained models are being developed for chemical compounds and target proteins. This study sought to improve DTI predictive models using a Bidirectional Encoder Representations from the Transformers (BERT)-pretrained model, ChemBERTa, for chemical compounds. Pretraining features the use of a simplified molecular-input line-entry system (SMILES). We also employ the pretrained ProBERT for target proteins (pretraining employed the amino acid sequences). The BIOSNAP, DAVIS, and BindingDB databases (DBs) were used (alone or together) for learning. The final model, taught by both ChemBERTa and ProtBert and the integrated DBs, afforded the best DTI predictive performance to date based on the receiver operating characteristic area under the curve (AUC) and precision-recall-AUC values compared with previous models. The performance of the final model was verified using a specific case study on 13 pairs of subtrates and the metabolic enzyme cytochrome P450 (CYP). The final model afforded excellent DTI prediction. As the real-world interactions between drugs and target proteins are expected to exhibit specific patterns, pretraining with ChemBERTa and ProtBert could teach such patterns. Learning the patterns of such interactions would enhance DTI accuracy if learning employs large, well-balanced datasets that cover all relationships between drugs and target proteins.

Multi-library synchronization for suspect screening using LC-HRMS: The importance of InChIkeys

To generate two major LC-HRMS semi-targeted screening libraries in addition to the in-house targeted library: (1) an extended general toxicology library by synchronizing an in-house targeted library with compounds found in Baselt's 12th Edition of Disposition of Toxic Drugs and Chemicals in Man, and (2) the extended general toxicology library synchronized with HighResNPS, a comprehensive database of NPS. Firstly, InChiKeys for the compounds ( n = 1765) in the Waters Forensic Toxicology Screening Library (i.e. the targeted Library) were extracted in addition to the observed retention times and product ions. Secondly, compounds listed in Baselt ( n = 2057) were extracted from the contents and then converted to simplified molecular-input line-entry system (SMILES) strings and InChIKeys using Python's cheminformatics package, rdkit. Compounds which were not suited for LC-ESI-MS analysis, such as volatiles and elements, and compounds with masses either less than 50 Da or greater than 1,000 Da were removed. The precursor ion masses of the remaining compounds were calculated from the SMILES string. Lastly, the January 2022 library was downloaded from HighResNPS ( n = 2166), which contained InChIKeys and, both observed ( n = 351) and predicted ( n = 1815) retention times. Using the connectivity layer of the InChIKey, i.e. the first 14 characters, the target library and the Baselt library were combined so that only the unique compounds from each library were included to create the Baselt semi-target library. Similarly, the Baselt semi-target library was then combined with the HighResNPS library to create the HighResNPS semi-target library. These libraries were then converted to a Waters Corporation UNIFI library format (.ulc) and applied to special cases submitted in 2021–2022. The Baselt semi-target library consisted of 2690 compounds of which 925 were unique to the Baselt library while the HighResNPS semi-targeted library consisted of 4242 compounds of which, 1552 were unique to the HighResNPS library. The application of the Baselt semi-target library to selected special cases resulted in the detection of compounds like vortioxetine, darunavir, abacavir, zonisamide, drotaverine and brexpiprazole were detected in blood. Similarly, 3-Me-PCPy and 5F-3,5-AB-PFUPPYCA were detected in seized material using the HighResNPS semi-target library. The use of only the in-house targeted libraries would have missed these relevant compounds in both forensic toxicology and forensic chemistry contexts. The use of InChIKeys rather than compound names or other standard identifiers made it easy to identify the unique compounds in each of the selected libraries with little effort and thus increased the scope by 52% and 140% relative to the target library. Inclusion of InChIKeys in target libraries offers the possibility for laboratories to synchronize their libraries with libraries from other laboratories to broaden their screening capacity.

Identification of anti-schistosomal, anthelmintic and anti-parasitic compounds curated and text-mined from the scientific literature.

More than a billion people are infected with parasitic worms, including nematodes, such as hookworms, and flatworms, such as blood flukes. Few drugs are available to treat worm infections, but high-throughput screening approaches hold promise to identify novel drug candidates. One problem for researchers who find an interesting 'hit' from a high-throughput screen is to identify whether that compound, or a similar compound has previously been published as having anthelmintic or anti-parasitic activity. Here, we present (i) data sets of 2,828 anthelmintic compounds, and 1,269 specific anti-schistosomal compounds, manually curated from scientific papers and books, and (ii) a data set of 24,335 potential anthelmintic and anti-parasitic compounds identified by text-mining PubMed abstracts. We provide their structures in simplified molecular-input line-entry system (SMILES) format so that researchers can easily compare 'hits' from their screens to these anthelmintic compounds and anti-parasitic compounds and find previous literature on them to support/halt their progression in drug discovery pipelines.

Quasi-SMILES as a basis to build up models of endpoints for nanomaterials

ABSTRACT Simplified molecular input-line entry system (SMILES) is a format for representing of the molecular structure. Quasi-SMILES is an extended format for representing molecular structure data and some eclectic data, which in principle could be applied to improve a model's predictive potential. Nano-quantitative structure–property relationships (nano-QSPRs) for energy gap (Eg , eV) of the metals oxide nanoparticles based on the quasi-SMILES give a predictive model for Eg , characterized by the following statistical quality for external validation set n = 22, R2 = 0.83, RMSE = 0.267.

FGDB: a comprehensive graph database of ligand fragments from the Protein Data Bank.

This work presents Fragment Graph DataBase (FGDB), a graph database of ligand fragments extracted and generated from the protein entries available in the Protein Data Bank (PDB). FGDB is meant to support and elicit campaigns of fragment-based drug design, by enabling users to query it in order to construct ad hoc, target-specific libraries. In this regard, the database features more than 17 000 fragments, typically small, highly soluble and chemically stable molecules expressed via their canonical Simplified Molecular Input Line Entry System (SMILES) representation. For these fragments, the database provides information related to their contact frequencies with the amino acids, the ligands they are contained in and the proteins the latter bind to. The graph database can be queried via standard web forms and textual searches by a number of identifiers (SMILES, ligand and protein PDB ids) as well as via graphical queries that can be performed against the graph itself, providing users with an intuitive and effective view upon the underlying biological entities. Further search mechanisms via advanced conjunctive/disjunctive/negated textual queries are also possible, in order to allow scientists to look for specific relationships and export their results for further studies. This work also presents two sample use cases where maternal embryonic leucine zipper kinase and mesotrypsin are used as a target, being proteins of high biomedical relevance for the development of cancer therapies. Database URL: http://biochimica3.bio.uniroma3.it/fragments-web/

Application of Machine Learning in Developing Quantitative Structure-Property Relationship for Electronic Properties of Polyaromatic Compounds.

The degree of π orbital overlap (DPO) model has been demonstrated to be an excellent quantitative structure–property relationship (QSPR) that can map two-dimensional structural information of polycyclic aromatic hydrocarbons (PAHs) and thienoacenes to their electronic properties, namely, band gaps, electron affinities, and ionization potentials. However, the model suffers from significant limitations that narrow its applications due to inefficient manual procedures in parameter optimization and descriptor formulation. In this work, we developed a machine learning (ML)-based method for efficiently optimizing DPO parameters and proposed a truncated DPO descriptor, which is simple enough that can be automatically extracted from simplified molecular-input line-entry system strings of PAHs and thienoacenes. Compared with the result from our previous studies, the ML-based methodology can optimize DPO parameters with four times fewer data, while it can achieve the same level of accuracy in predictions of the mentioned electronic properties to within 0.1 eV. The truncated DPO model also has similar accuracy to the full DPO model. Consequently, the ML-based DPO approach coupled with the truncated DPO model enables new possibilities for developing automatic pipelines for high-throughput screening and investigating new QSPR for new chemical classes.

Polygrammar: Grammar for Digital Polymer Representation and Generation.

Polymers are widely studied materials with diverse properties and applications determined by molecular structures. It is essential to represent these structures clearly and explore the full space of achievable chemical designs. However, existing approaches cannot offer comprehensive design models for polymers because of their inherent scale and structural complexity. Here, a parametric, context‐sensitive grammar designed specifically for polymers (PolyGrammar) is proposed. Using the symbolic hypergraph representation and 14 simple production rules, PolyGrammar can represent and generate all valid polyurethane structures. An algorithm is presented to translate any polyurethane structure from the popular Simplified Molecular‐Input Line‐entry System (SMILES) string format into the PolyGrammar representation. The representative power of PolyGrammar is tested by translating a dataset of over 600 polyurethane samples collected from the literature. Furthermore, it is shown that PolyGrammar can be easily extended to other copolymers and homopolymers. By offering a complete, explicit representation scheme and an explainable generative model with validity guarantees, PolyGrammar takes an essential step toward a more comprehensive and practical system for polymer discovery and exploration. As the first bridge between formal languages and chemistry, PolyGrammar also serves as a critical blueprint to inform the design of similar grammars for other chemistries, including organic and inorganic molecules.

CORAL: Quantitative Structure Retention Relationship (QSRR) of flavors and fragrances compounds studied on the stationary phase methyl silicone OV-101 column in gas chromatography using correlation intensity index and consensus modelling

The quantitative structure-retention relationship (QSRR) is a significant approach in chromatography and is used to predict the retention time of unknown compounds. In the present research article, the QSRR approach is employed to develop robust models of 1176 flavor and fragrance compounds on the OV-101 glass capillary gas chromatography column using a statistical parameter “correlation intensity index (CII)”. This CII parameter is featured in the most recent release of the CORAL programme (www.insilico.eu/coral). The optimal descriptor i.e. descriptor of correlation weight (DCW) computed by simplified molecular input-line entry system (SMILES) notation is employed to build QSRR models. Two target functions, TF1 (WCII=0) and TF2 (WCII=0.3) are applied to design 12 QSRR models from six splits using the balance of correlation strategy. The models created using CII are better in terms of statistical results. The numerical value of Rvalidation2=0.9561 of TF2Split1 is found to be considerably greater than that of the Rvalidation2 of the other splits of both target functions, hence, it is acknowledged as a leading model. The lists of structural attributes responsible for the changes in the retention index (RI) of flavors and fragrances compounds are also retrieved and discussed. Finally, a consensus model is built utilising the allocation structure of split 1 and the modified consensus (CM1) i.e. an average of predictions from all 'qualified' Individual models is found best model based on MAE (95%; test). The numerical value of the determination coefficient (R2) of the test set for the modified consensus (CM1) model is found 0.9772 which is higher than the leading Model.