Simplified Molecular Input Line Entry System Research Articles

Machine Learning-Based Prediction of Drug-Drug Interactions for Histamine Antagonist Using Hybrid Chemical Features.

The requesting of detailed information on new drugs including drug-drug interactions or targets is often unavailable and resource-intensive in assessing adverse drug events. To shorten the common evaluation process of drug-drug interactions, we present a machine learning framework-HAINI to predict DDI types for histamine antagonist drugs using simplified molecular-input line-entry systems (SMILES) combined with interaction features based on CYP450 group as inputs. The data used in our research consisted of approved drugs of histamine antagonists that are connected to 26,344 DDI pairs from the DrugBank database. Various classification algorithms such as Naive Bayes, Decision Tree, Random Forest, Logistic Regression, and XGBoost were used with 5-fold cross-validation to approach a large-scale DDIs prediction among histamine antagonist drugs. The prediction performance shows that our model outperformed previously published works on DDI prediction with the best precision of 0.788, a recall of 0.921, and an F1-score of 0.838 among 19 given DDIs types. An important finding of the study is that our prediction is based solely on the SMILES and CYP450 and thus can be applied at the early stage of drug development.

CBDPS 1.0: A Python GUI Application for Machine Learning Models to Predict Bitter-Tasting Children’s Oral Medicines

Bitter tastes are innately aversive and are thought to help protect animals from consuming poisons. Children are extremely sensitive to drug tastes, and their compliance is especially poor with bitter medicine. Therefore, judging whether a drug is bitter and adopting flavor correction and taste-masking strategies are key to solving the problem of drug compliance in children. Although various machine learning models for bitterness and sweetness prediction have been reported in the literature, no learning model or bitterness database for children's medication has yet been reported. In this study, we trained four different machine learning models to predict bitterness. The goal of this study was to develop and validate a machine learning model called the "Children's Bitter Drug Prediction System" (CBDPS) based on Tkinter, which predicts the bitterness of a medicine based on its chemical structure. Users can enter the Simplified Molecular-Input Line-Entry System (SMILES) formula for a single compound or multiple compounds, and CBDPS will predict the bitterness of children's medicines made from those XGBoost-Molecular ACCess System (XgBoost-MACCS) model yielded an accuracy of 88% under cross-validation.

Prediction of power conversion efficiency of phenothiazine-based dye-sensitized solar cells using Monte Carlo method with index of ideality of correlation

ABSTRACT Simplified molecular-input line-entry system (SMILES) notation and inbuilt Monte Carlo algorithm of CORAL software were employed to construct generative and prediction QSPR models for the analysis of the power conversion efficiency (PCE) of 215 phenothiazine derivatives. The dataset was divided into four splits and each split was further divided into four sets. A hybrid descriptor, a combination of SMILES and hydrogen suppressed graph (HSG), was employed to build reliable and robust QSPR models. The role of the index of ideality of correlation (IIC) was also studied in depth. We performed a comparative study to predict PCE using two target functions (TF1 without IIC and TF2 with IIC). Eight QSPR models were developed and the models developed with TF2 was shown robust and reliable. The QSPR model generated from split 4 was considered a leading model. The different statistical benchmarks were computed for the lead model and these were ; ; ; ; ; ; ; ; IICtraining set = 0.8590; IICinvisible training set = 0.8297; IICcalibration set = 0.8796; IICvalidation set = 0.8293, etc. The promoters of increase and decrease of endpoint PCE were also extracted.

Application of quasi-SMILES to the model of gold-nanoparticles uptake in A549cells.

Cell death is critical to human health and is associated with a variety of medical conditions. Therefore, new controllers of cell death are needed for the treatment of diverse diseases. In particular, nanoparticles (NP) are now regularly used in various applications, including a variety of products and medicines. Gold nanoparticles (GNPs) are widely used in the medical field against A549 lung carcinoma cells. The present study is devoted to developing computational models of the cellular uptake potentials by A549cells of gold nanoparticles (GNPs) under various conditions. Simplified molecular input-line entry system (SMILES) is an efficient tool to represent the molecular structure by a sequence of symbols. Quasi-SMILES represents an extended version of SMILES where symbols to denote physicochemical and/or biochemical conditions are added. In other words, the quasi-SMILES represents a biochemical (medical) phenomenon related to the whole matter (not only molecular structure). We developed models for the cellular utpake potential of gold nanoparticles (GNPs) in A549 [10-11g Au/Cell] under various conditions based on quasi-SMILES using the Monte Carlo method. The statistical quality of these models is quite good.

Predicting the melting point of imidazole-based ionic liquids using QSPR model based on SMILES optimal descriptors

Recently, ionic liquids (ILs) are known as potential green materials with unique properties such as low vapor pressure, high thermal stability, and excellent solution ability of organic or inorganic materials. In this paper, the quantitative structure property relationship (QSPR) models of 111 common imidazole-based ionic liquids were established by using CORrelation and Logic (CORAL) software to predict the melting point of imidazole-based ionic liquids. The molecular structure of imidazole-based ionic liquids is represented by simplified molecular input line entry system (SMILES). The balance of correlations and the classic scheme were compared by building the models of QSPR based on the Mont Carlo method. SMILES descriptors were randomly divided into three data sets, and the results showed that the model of classic scheme was more reliable. The best correlation coefficient (R2) values for the validation sets of two models were 0.9512 and 0.9219, respectively. Their best internal validated correlation coefficient (Q2) values were 0.9414 and 0.8961, respectively.

Learning to SMILES: BAN-based strategies to improve latent representation learning from molecules.

Computational methods have become indispensable tools to accelerate the drug discovery process and alleviate the excessive dependence on time-consuming and labor-intensive experiments. Traditional feature-engineering approaches heavily rely on expert knowledge to devise useful features, which could be costly and sometimes biased. The emerging deep learning (DL) methods deliver a data-driven method to automatically learn expressive representations from complex raw data. Inspired by this, researchers have attempted to apply various deep neural network models to simplified molecular input line entry specification (SMILES) strings, which contain all the composition and structure information of molecules. However, current models usually suffer from the scarcity of labeled data. This results in a low generalization ability of SMILES-based DL models, which prevents them from competing with the state-of-the-art computational methods. In this study, we utilized the BiLSTM (bidirectional long short term merory) attention network (BAN) in which we employed a novel multi-step attention mechanism to facilitate the extracting of key features from the SMILES strings. Meanwhile, SMILES enumeration was utilized as a data augmentation method in the training phase to substantially increase the number of labeled data and enlarge the probability of mining more patterns from complex SMILES. We again took advantage of SMILES enumeration in the prediction phase to rectify model prediction bias and provide a more accurate prediction. Combined with the BAN model, our strategies can greatly improve the performance of latent features learned from SMILES strings. In 11 canonical absorption, distribution, metabolism, excretion and toxicity-related tasks, our method outperformed the state-of-the-art approaches.

AI-Based Drug Discovery of TKIs Targeting L858R/T790M/C797S-Mutant EGFR in Non-small Cell Lung Cancer.

Lung cancer has a high mortality rate, and non-small cell lung cancer (NSCLC) is the most common type of lung cancer. Patients have been observed to acquire resistance against various anticancer agents used for NSCLC due to L858R (or Exon del19)/T790M/C797S-EGFR mutations. Therefore, next-generation drugs are being developed to overcome this problem of acquired resistance. The goal of this study was to use artificial intelligence (AI) to discover drug candidates that can overcome acquired resistance and reduce the limitations of the current drug discovery process, such as high costs and long durations of drug design and production. To generate ligands using AI, we collected data related to tyrosine kinase inhibitors (TKIs) from accessible libraries and used LSTM (Long short term memory) based transfer learning (TL) model. Through the simplified molecular-input line-entry system (SMILES) datasets of the generated ligands, we obtained drug-like ligands via parameter-filtering, cyclic skeleton (CSK) analysis, and virtual screening utilizing deep-learning method. Based on the results of this study, we are developing prospective EGFR TKIs for NSCLC that have overcome the limitations of existing third-generation drugs.

Generative Adversarial Networks for De Novo Molecular Design

In the chemical industry, the generation of novel molecular structures with beneficial pharmacological and physicochemical properties in de novo molecular design is a critical problem. The advent of deep learning and neural generative models has recently enabled significant achievements in constructing molecular design models in de novo design. Consequently, studies on new generative models continue to generate molecules that exhibit more useful chemical properties. In this study, we propose a method for de novo design that utilizes generative adversarial networks based on reinforcement learning for realistic molecule generation. This method learns to reproduce the training data distribution of simplified molecular-input line-entry system strings. The proposed method is demonstrated to effectively generate novel molecular structures from five benchmark results using a real-world public dataset, ChEMBL. The code is available at https://github.com/dudwojae/SMILES-MaskGAN.

Molecular graph enhanced transformer for retrosynthesis prediction

With massive possible synthetic routes in chemistry, retrosynthesis prediction is still a challenge for researchers. Recently, retrosynthesis prediction is formulated as a Machine Translation (MT) task. Namely, since each molecule can be represented as a Simplified Molecular-Input Line-Entry System (SMILES) string, the process of retrosynthesis is analogized to a process of language translation from the product to reactants. However, the MT models that applied on SMILES data usually ignore the information of natural atomic connections and the topology of molecules. To make more chemically plausible constrains on the atom representation learning for better performance, in this paper, we propose a Graph Enhanced Transformer (GET) framework, which adopts both the sequential and graphical information of molecules. Four different GET designs are proposed, which fuse the SMILES representations with atom embeddings learned from our improved Graph Neural Network (GNN). Empirical results show that our model significantly outperforms the vanilla Transformer model in test accuracy.

Convolutional neural networks (CNNs): concepts and applications in pharmacogenomics

Convolutional neural networks (CNNs) have been used to extract information from various datasets of different dimensions. This approach has led to accurate interpretations in several subfields of biological research, like pharmacogenomics, addressing issues previously faced by other computational methods. With the rising attention for personalized and precision medicine, scientists and clinicians have now turned to artificial intelligence systems to provide them with solutions for therapeutics development. CNNs have already provided valuable insights into biological data transformation. Due to the rise of interest in precision and personalized medicine, in this review, we have provided a brief overview of the possibilities of implementing CNNs as an effective tool for analyzing one-dimensional biological data, such as nucleotide and protein sequences, as well as small molecular data, e.g., simplified molecular-input line-entry specification, InChI, binary fingerprints, etc., to categorize the models based on their objective and also highlight various challenges. The review is organized into specific research domains that participate in pharmacogenomics for a more comprehensive understanding. Furthermore, the future intentions of deep learning are outlined.

Enhancing the Discovery of Chemistry Theses by Registering Substances and Depositing in PubChem

Chemical substances from theses are not widely accessible as searchable machine-readable formats. In this article, we describe our workflow for extracting, registering, and sharing chemical substances from the University of Alabama theses to enhance discovery. In total, 73 theses were selected for the project, resulting in about 3,000 substances registered using the IUPAC International Chemical Identifier and deposited in PubChem as either structure-data files or Simplified Molecular-Input Line-Entry System notations. In addition to substances being deposited in PubChem, an archive copy was also deposited in the University of Alabama Institutional Repository. The PubChem records for the substance depositions include the full bibliographic reference and link to the thesis full text or thesis metadata when the full text is not yet available. Excluding mixtures, we found that 40% of the shared substances were new to PubChem at the time of deposition. We conclude this article with a detailed discussion about our experiences, challenges, and recommendations for librarians and curators engaged in sharing chemical substance data from theses and similar documents.

The Monte Carlo method to build up models of the hydrolysis half-lives of organic compounds

ABSTRACT The hydrolysis of organic chemicals such as pesticides, pollutants, or drugs can affect the fate and behaviour of environmental contaminants, so it is of interest to evaluate the stability of substances in water for various purposes. For the registration of organic compounds in Europe, information on hydrolysis must be presented. However, the experimental measurements of all chemicals would require enormous resources, and computational models may become attractive. Applying the CORAL software (http://www.insilico.eu/coral) quantitative structure-property relationships (QSPRs) were built up to model hydrolysis. The 2D-optimal descriptor is calculated with so-called correlation weights for attributes of simplified molecular input-line entry systems (SMILES). The correlation weights are obtained as results of the special Monte Carlo optimization. The nature of (five- and six-member) rings is an important component of this approach. Another important component is the atom pair proportions for nitrogen, oxygen, and sulphur. The statistical quality of the best model is: n = 44, r 2 = 0.74 (training set); n = 14, r 2 = 0.75 (calibration set); and n = 12, r 2 = 0.80 (validation set).

Deep Learning Model for Identifying Critical Structural Motifs in Potential Endocrine Disruptors.

This paper aims to identify structural motifs within a molecule that contribute the most toward a chemical being an endocrine disruptor. We have developed a deep neural network-based toolkit toward this aim. The trained model can virtually assess a synthetic chemical's potential to be an endocrine disruptor using machine-readable molecular representation, simplified molecular input line entry system (SMILES). Our proposed toolkit is a multilabel or multioutput classification model that combines both convolution and long short-term memory (LSTM) architectures. The toolkit leverages the advantages of an active learning-based framework that combines multiple sources of data. Class activation maps (CAMs) generated from the feature-extraction layers can identify the structural alerts and the chemical environment that determines the specificity of the structural alerts.

Can the Monte Carlo method predict the toxicity of binary mixtures?

Risk assessment of toxicants mainly is a result of experiments with single substances. However, toxicity in natural ecosystems typically does not result from single toxicant exposure but is rather a result of exposure to mixtures of toxicants. It is not surprising a mixture of toxicity is a subject of eco-toxicological interest for several decades. A quantitative structure-activity relationships (QSAR)-based approach is an attractive approach to assessing the joint effects in the binary mixtures. The validity of the proposed approach was demonstrated by comparing the predicted values against the experimentally determined values. Simplified molecular input-line entry system (SMILES) is used for the representation of the molecular structures of components of two-component mixtures to build up QSAR. The SMILES-based models are improving if the Monte Carlo optimization aimed to define 2D-optimal descriptors apply the so-called index of ideality of correlation (IIC), which is a mathematical function of both the correlation coefficient and mean absolute error calculated for the positive and negative difference between observed and calculated values of toxicity. The average statistical quality of these models (for the validation set) is n=25, R2=0.95, and RMSE=0.375.

SMILES Pair Encoding: A Data-Driven Substructure Tokenization Algorithm for Deep Learning.

Simplified molecular input line entry system (SMILES)-based deep learning models are slowly emerging as an important research topic in cheminformatics. In this study, we introduce SMILES pair encoding (SPE), a data-driven tokenization algorithm. SPE first learns a vocabulary of high-frequency SMILES substrings from a large chemical dataset (e.g., ChEMBL) and then tokenizes SMILES based on the learned vocabulary for the actual training of deep learning models. SPE augments the widely used atom-level tokenization by adding human-readable and chemically explainable SMILES substrings as tokens. Case studies show that SPE can achieve superior performances on both molecular generation and quantitative structure-activity relationship (QSAR) prediction tasks. In particular, the SPE-based generative models outperformed the atom-level tokenization model in the aspects of novelty, diversity, and ability to resemble the training set distribution. The performance of SPE-based QSAR prediction models were evaluated using 24 benchmark datasets where SPE consistently either did match or outperform atom-level and k-mer tokenization. Therefore, SPE could be a promising tokenization method for SMILES-based deep learning models. An open-source Python package SmilesPE was developed to implement this algorithm and is now freely available at https://github.com/XinhaoLi74/SmilesPE.

A machine learning approach for estimating surface tension based on pendant drop images

An image-based machine learning (ML) method is introduced to predict the surface tension of an ethanol-water pendant drop made of unknown ethanol-water composition. In contrast to previous neural-network based surface tension predictors that rely on using either the simplified molecular-input line-entry system or experimentally measured surface tension values, the present image-based deep neural network model directly predicts surface tensions based on arbitrary pendant drop shapes at any stage before breakup. Using convolutional neural networks (CNNs), surface tension values are accurately obtained independent of the drop size and liquid properties. Two CNN architectures are presented that accurately predict the surface tension of a pendant drop for three different ML models. To improve the generality of the ML models, image data augmentation technique is used to generate more representatives from available data. Approximating the surface tension for unknown pendant drops outside the range of the given classes has also been demonstrated. The trained machine learning models have an overall accuracy of about 98% in predicting the surface tension of a pendant drop containing an unknown ethanol-water composition. Additionally, the ML models are tested on unknown methanol-water mixtures to demonstrate the generality and the results show good predicting accuracy. Besides the accuracy of CNN models, performance measures including Precision, Recall and F1-score are reported for each surface tension value in the dataset. Compared with the physics-based axisymmetric drop shape analysis techniques, the present method is not limited to equilibrium pendant drop images and is much faster and more versatile. This image-based ML method shows great promise in directly predicting the surface tension values based on vastly available pendant drop images.

Cocrystal Prediction Using Machine Learning Models and Descriptors

Cocrystals are of much interest in industrial application as well as academic research, and screening of suitable coformers for active pharmaceutical ingredients is the most crucial and challenging step in cocrystal development. Recently, machine learning techniques are attracting researchers in many fields including pharmaceutical research such as quantitative structure-activity/property relationship. In this paper, we develop machine learning models to predict cocrystal formation. We extract descriptor values from simplified molecular-input line-entry system (SMILES) of compounds and compare the machine learning models by experiments with our collected data of 1476 instances. As a result, we found that artificial neural network shows great potential as it has the best accuracy, sensitivity, and F1 score. We also found that the model achieved comparable performance with about half of the descriptors chosen by feature selection algorithms. We believe that this will contribute to faster and more accurate cocrystal development.

A deep learning approach to evaluate the feasibility of enzymatic reactions generated by retrobiosynthesis.

Retrobiosynthesis allows the designing of novel biosynthetic pathways for the production of chemicals and materials through metabolic engineering, but generates a large number of reactions beyond the experimental feasibility. Thus, an effective method that can reduce a large number of the initially predicted enzymatic reactions has been needed. Here, we present Deep learning-based Reaction Feasibility Checker (DeepRFC) to classify the feasibility of a given enzymatic reaction with high performance and speed. DeepRFC is designed to receive Simplified Molecular-Input Line-Entry System (SMILES) strings of a reactant pair, which is defined as a substrate and a product of a reaction, as an input, and evaluates whether the input reaction is feasible. A deep neural network is selected for DeepRFC as it leads to better classification performance than five other representative machine learning methods examined. For validation, the performance of DeepRFC is compared with another in-house reaction feasibility checker that uses the concept of reaction similarity. Finally, the use of DeepRFC is demonstrated for the retrobiosynthesis-based design of novel one-carbon assimilation pathways. DeepRFC will allow retrobiosynthesis to be more practical for metabolic engineering applications by efficiently screening a large number of retrobiosynthesis-derived enzymatic reactions. DeepRFC is freely available at https://bitbucket.org/kaistsystemsbiology/deeprfc.

Machine-OlF-Action: a unified framework for developing and interpreting machine-learning models for chemosensory research.

Machine Learning-based techniques are emerging as state-of-the-art methods in chemoinformatics to selectively, effectively and speedily identify biologically relevant molecules from large databases. So far, a multitude of such techniques have been proposed, but unfortunately due to their sparse availability, and the dependency on high-end computational literacy, their wider adaptation faces challenges, at least in the context of G-Protein Coupled Receptors (GPCRs)-associated chemosensory research. Here, we report Machine-OlF-Action (MOA), a user-friendly, open-source computational framework, that utilizes user-supplied SMILES (simplified molecular input line entry system) of the chemicals, along with their activation status, to synthesize classification models. MOA integrates a number of popular chemical databases collectively harboring approximately 103 million chemical moieties. MOA also facilitates customized screening of user-supplied chemical datasets. A key feature of MOA is its ability to embed molecules based on the similarity of their local neighborhood, by utilizing a state-of-the-art model interpretability framework LIME. We demonstrate the utility of MOA in identifying previously unreported agonists for human and mouse olfactory receptors OR1A1 and MOR174-9 by leveraging the chemical features of their known agonists and non-agonists. In summary, here we develop an ML-powered software playground for performing supervisory learning tasks involving chemical compounds. MOA is available for Windows, Mac and Linux operating systems. It's accessible at (https://ahuja-lab.in/). Source code, user manual, step-by-step guide and support is available at GitHub (https://github.com/the-ahuja-lab/Machine-Olf-Action). For results, reproducibility and hyperparameters, refer to Supplementary Notes. Supplementary data are available at Bioinformatics online.

Transfer Learned Designer Polymers For Organic Solar Cells.

Organic photovoltaic (OPV) materials have been examined extensively over the past two decades for solar cell applications because of the potential for device flexibility, low-temperature solution processability, and negligible environmental impact. However, discovery of new candidate OPV materials, especially polymer-based electron donors, that demonstrate notable power conversion efficiencies (PCEs), is nontrivial and time-intensive exercise given the extensive set of possible chemistries. Recent progress in machine learning accelerated materials discovery has facilitated to address this challenge, with molecular line representations, such as Simplified Molecular-Input Line-Entry Systems (SMILES), gaining popularity as molecular fingerprints describing the donor chemical structures. Here, we employ a transfer learning based recurrent neural (LSTM) model, which harnesses the SMILES molecular fingerprints as an input to generate novel designer chemistries for OPV devices. The generative model, perfected on a small focused OPV data set, predicts new polymer repeat units with potentially high PCE. Calculations of the similarity coefficient between the known and the generated polymers corroborate the accuracy of the model predictability as a function of the underlying chemical specificity. The data-enabled framework is sufficiently generic for use in accelerated machine learned materials discovery for various chemistries and applications, mining the hitherto available experimental and computational data.