Search

This perspective discusses the current progress of a chemoinformatics group in a major university in Latin America. Three major aspects are discussed in a critical manner: research, education, and collaboration with industry and other public research networks. It is also presented an overview of the progress in applied research and development of research concepts. Efforts to teach chemoinformatics at the undergraduate and graduate levels are discussed. It is addressed how the partnership with industry and other not-for-profit research institutions not only brings additional sources of funding but, more importantly, increases the impact of the multidisciplinary work and offers the students to be exposed to other research environments. We also discuss the main perspectives and challenges that remain to be addressed in these settings.

In QSAR/QSPR modeling, the indispensable way to validate the predictability of a model is to perform its statistical external validation. It is common that a division algorithm should be used to select training sets from chemical compound libraries or collections prior to external validations. In this study, a division method based on the posterior variance of leave-one-out cross-validation (PV LOO ) of the Gaussian process (GP) has been developed with the goal of producing more predictive models. Four structurally diverse data sets of good quality are collected from the literature and then redeveloped and validated on the basis of training set selection methods, namely, four kinds of PV LOO -based training set selection methods with three types of covariance functions (squared exponential, rational quadratic, and neural network covariance functions), the Kennard-Stone algorithm, and random division. The root mean squared error (RMSE) of external validation reported for each model serves as a basis for the final comparison. The results of this study indicate that the training sets with higher values of PV LOO have statistically better external predictability than the training sets generated from other division methods discussed here. These findings could be explained by proposing that the PV LOO value of GP could indicate the mechanism diversity of a specific compound in QSAR/QSPR data sets.

n/a., Competing Interests: The authors declare no conflict of interest.

The field of chemoinformatics has developed from different roots, starting in the 1960s. These branches have now merged into a scientific discipline of its own, exchanging ideas and methods across different areas of chemistry. In the last 40 years chemoinformatics has achieved a lot. Without access to the databases in chemistry developed with chemoinformatics methods, modern chemical research would not be able to work at its present high level of competence. However, there are quite a few challenges, such as drug design and understanding the effect of chemicals on human health and on the environment, as well as furthering our knowledge of chemistry and of biological systems, that can benefit from a more intensive use of chemoinformatics methods. Approaches to meet these challenges will be briefly outlined. All this emphasizes that chemoinformatics has matured into a scientific discipline of its own that reaches out to many other chemical fields and will increase in attractiveness to students and researchers.

Quantitative structure-activity relationship (QSAR) models are being used increasingly in skin permeation studies. The main idea of QSAR modelling is to quantify the relationship between biological activities and chemical properties, and thus to predict the activity of chemical solutes. As a key step, the selection of a representative and structurally diverse training set is critical to the prediction power of a QSAR model. Early QSAR models selected training sets in a subjective way and solutes in the training set were relatively homogenous. More recently, statistical methods such as D-optimal design or space-filling design have been applied but such methods are not always ideal. This paper describes a comprehensive procedure to select training sets from a large candidate set of 4534 solutes. A newly proposed 'Baynes' rule', which is a modification of Lipinski's 'rule of five', was used to screen out solutes that were not qualified for the study. U-optimality was used as the selection criterion. A principal component analysis showed that the selected training set was representative of the chemical space. Gas chromatograph amenability was verified. A model built using the training set was shown to have greater predictive power than a model built using a previous dataset [1].

The Hammett σ constant has for a long time been known to be one of most important linear free-energy related parameters that correlate with biological activity. It is a conventionally used electronic parameter in studies of enzymatic quantitative structure-activity relationships (QSAR). However, it is not necessarily obvious why σ represents variations in the free-energy change associated with the complex formation between a congeneric series of ligands with their target protein. So far, several powerful molecular calculations, such as the ab initio fragment molecular orbital (FMO) one, that are directly applicable to ligand-protein complexes have emerged. In this study, we comprehensively reevaluate experimentally derived parameter σ confirming it represents intermolecular interaction energy terms, by applying molecular orbital (MO) calculations to a simple ligand-protein complex model. The current results provide a rational and quantitative basis for bridging the gap between the traditional QSAR approach and 'the modern QSAR one', which involves the molecular calculations to evaluate the overall free-energy change for complex formation., (Copyright © 2011 Elsevier Ltd. All rights reserved.)

This introductory chapter gives a brief overview of the history of cheminformatics, and then summarizes some recent trends in computing, cultures, open systems, chemical structure representation, docking, de novo design, fragment-based drug design, molecular similarity, quantitative structure-activity relationships (QSAR), metabolite prediction, the use of phamacophores in drug discovery, data reduction and visualization, and text mining. The aim is to set the scene for the more detailed exposition of these topics in the later chapters.

This work presents a new approach to predict thermal stability of nitroaromatic compounds based on quantum chemical calculations and on quantitative structure-property relationship (QSPR) methods. The data set consists of 22 nitroaromatic compounds of known decomposition enthalpy (taken as a macroscopic property related to explosibility) obtained from differential scanning calorimetry. Geometric, electronic and energetic descriptors have been selected and computed using density functional theory (DFT) calculation to describe the 22 molecules. First approach consisted in looking at their linear correlations with the experimental decomposition enthalpy. Molecular weight, electrophilicity index, electron affinity and oxygen balance appeared as the most correlated descriptors (respectively R(2)=0.76, 0.75, 0.71 and 0.64). Then multilinear regression was computed with these descriptors. The obtained model is a six-parameter equation containing descriptors all issued from quantum chemical calculations. The prediction is satisfactory with a correlation coefficient R(2) of 0.91 and a predictivity coefficient R(cv)(2) of 0.84 using a cross validation method.

This review summarizes the use of partial order ranking (POR) techniques for the assessment of chemicals. Simple partial order ranking may advantageously be applied to give the single chemicals investigated an identity in relation to other substances. Thus, it constitutes an effective tool for the prioritization of chemicals, e.g., based on their PBT (Persistence, Bioaccumulating, Toxicity) characteristics. In more elaborate cases where a larger number of descriptors are taken into account, e.g., comprising physico-chemical characteristics, atmospheric parameters, geospecific factors, and possibly socio-economic factors, hierarchical partial order ranking (HPOR) may be applied. Thus, in a first ordering step, a series of meta-descriptors are generated that later subsequently may be used as descriptors in subsequent ordering. HPOR allows a sensible ranking model even if a relatively high number of descriptors are included. Finally, accumulation partial order ranking (APOR) is illustrated. Accumulating partial APOR is a technique where data from a series of individual tests of various characteristics are aggregated while maintaining the basics of the partial order ranking methodology. APOR offers prioritization based on mutual probabilities derived from the aggregated data. Alternatively, prioritization may be achieved based on averaged ranks derived from the APOR. The application APOR is demonstrated by an assessment of a series of potential PBT substances. In all cases, an absolute ranking can be achieved based on the average ranks of the single substances. Alternatively, ranking probabilities can be derived.

Once regarded as an eccentric and unpromising algorithm for the analysis of scientific data, the neural network has been developed in the last decade into a powerful computational tool. Its use now spans all areas of science, from the physical sciences and engineering to the life sciences and allied subjects. Applications range from the assessment of epidemiological data or the deconvolution of spectra to highly practical applications, such as the electronic nose. This introductory chapter considers briefly the growth in the use of neural networks and provides some general background in preparation for the more detailed chapters that follow.

A concept termed Emerging Chemical Patterns (ECPs) is introduced as a novel approach to molecular classification. The methodology makes it possible to extract key molecular features from very few known active compounds and classify molecules according to different potency levels. The approach was developed in light of the situation often faced during the early stages of lead optimization efforts: too few active reference molecules are available to build computational models for the prediction of potent compounds. The ECP method generates high-resolution signatures of active compounds. Predictive ECP models can be built based on the information provided by sets of only three molecules with potency in the nanomolar and micromolar range. In addition to individual compound predictions, an iterative ECP scheme has been designed. When applied to different sets of active molecules, iterative ECP classification produced compound selection sets with increases in average potency of up to 3 orders of magnitude.

Quantitative Structure Activity Relationship (QSAR) is a term describing a variety of approaches that are of substantial interest for chemistry. This method can be defined as indirect molecular design by the iterative sampling of the chemical compounds space to optimize a certain property and thus indirectly design the molecular structure having this property. However, modeling the interactions of chemical molecules in biological systems provides highly noisy data, which make predictions a roulette risk. In this paper we briefly review the origins for this noise, particularly in multidimensional QSAR. This was classified as the data, superimposition, molecular similarity, conformational, and molecular recognition noise. We also indicated possible robust answers that can improve modeling and predictive ability of QSAR, especially the self-organizing mapping of molecular objects, in particular, the molecular surfaces, a method that was brought into chemistry by Gasteiger and Zupan.

Chemical-biological interactions in human are currently attracting our attention particularly in the area of QSAR (quantitative structure-activity relationships). In the present review, an attempt has been made to collect the data for the effect of chemicals in human and discussed by the formulation of a total number of 37 QSAR.

Zagreb indices were reformulated in terms of the edge-degrees instead of the vertex-degrees as the original Zagreb indices. Three types of Zagreb indices were considered: original, modified and variable Zagreb indices. It is found that the optimum exponent of the variable reformulated Zagreb M2 index (v = -1/2) is identical with the exponent of the vertex-connectivity index, which is the most used topological index in QSPR and QSAR. The close relationship between the graph and its line graph is used to relate the original and reformulated indices.

Abstract De novo molecular design is the process of searching chemical space for drug-like molecules with desired properties, and deep learning has been recognized as a promising solution. In this study, I developed an effective computational method called Scoring-Assisted Generative Exploration (SAGE) to enhance chemical diversity and property optimization through virtual synthesis simulation, the generation of bridged bicyclic rings, and multiple scoring models for drug-likeness. In six protein targets, SAGE generated molecules with high scores within reasonable numbers of steps by optimizing target specificity without a constraint and even with multiple constraints such as synthetic accessibility, solubility, and metabolic stability. Furthermore, I suggested a top-ranked molecule with SAGE as dual inhibitors of acetylcholinesterase and monoamine oxidase B through multiple desired property optimization. Therefore, SAGE can generate molecules with desired properties by optimizing multiple properties simultaneously, indicating the importance of de novo design strategies in the future of drug discovery and development. Scientific contribution The scientific contribution of this study lies in the development of the Scoring-Assisted Generative Exploration (SAGE) method, a novel computational approach that significantly enhances de novo molecular design. SAGE uniquely integrates virtual synthesis simulation, the generation of complex bridged bicyclic rings, and multiple scoring models to optimize drug-like properties comprehensively. By efficiently generating molecules that meet a broad spectrum of pharmacological criteria—including target specificity, synthetic accessibility, solubility, and metabolic stability—within a reasonable number of steps, SAGE represents a substantial advancement over traditional methods. Additionally, the application of SAGE to discover dual inhibitors for acetylcholinesterase and monoamine oxidase B not only demonstrates its potential to streamline and enhance the drug development process but also highlights its capacity to create more effective and precisely targeted therapies. This study emphasizes the critical and evolving role of de novo design strategies in reshaping the future of drug discovery and development, providing promising avenues for innovative therapeutic discoveries.

In the field of the cosmetic industry, significant efforts are made to develop methods that are not only cost effective and time effective but are also environmentally friendly and cruelty free. Cosmetic tests using in vivo animal models are currently banned in the European Union. To fulfil regulatory requirements, new approach methodologies (NAMs) are implemented, and thereupon, in silico techniques have constantly acquired significance. This review aimed to show the general picture of the available computational methods and approaches, give some examples of their applications, present capabilities and limitations, and propose the way forward. The general information about in silico modelling and examples of its usage in the context of cosmetics and its legal regulation are presented. The review is divided with a focus on three endpoints of interest: (1) safety assessment, (2) exposure assessment, and (3) formulation characterization. With this comprehensive analysis, we try to answer the question as to whether we are using the opportunity.

The accurate modeling and prediction of small molecule properties and bioactivities depend on the critical choice of molecular representation. Decades of informatics-driven research have relied on expert-designed molecular descriptors to establish quantitative structure-activity and structure-property relationships for drug discovery. Now, advances in deep learning make it possible to efficiently and compactly learn molecular representations directly from data. In this review, we discuss how active research in molecular deep learning can address limitations of current descriptors and fingerprints while creating new opportunities in cheminformatics and virtual screening. We provide a concise overview of the role of representations in cheminformatics, key concepts in deep learning, and argue that learning representations provides a way forward to improve the predictive modeling of small molecule bioactivities and properties.

The Ames/quantitative structure–activity relationship (QSAR) International Challenge Projects, held during 2014–2017 and 2020–2022, evaluated the performance of various predictive models. Despite the significant insights gained, the rules allowing participants to select prediction targets introduced ambiguity in model performance evaluation. This reanalysis identified the highest-performing prediction model, assuming a 100% coverage rate (COV) for all prediction target compounds and an estimated performance variation due to changes in COV. All models from both projects were evaluated using balance accuracy (BA), the Matthews correlation coefficient (MCC), the F1 score (F1), and the first principal component (PC1). After normalizing the COV, a correlation analysis with these indicators was conducted, and the evaluation index for all prediction models in terms of the COV was estimated. In total, using 109 models, the model with the highest estimated BA (76.9) at 100% COV was MMI-VOTE1, as reported by Meiji Pharmaceutical University (MPU). The best models for MCC, F1, and PC1 were all MMI-STK1, also reported by MPU. All the models reported by MPU ranked in the top four. MMI-STK1 was estimated to have F1 scores of 59.2, 61.5, and 63.1 at COV levels of 90%, 60%, and 30%, respectively. These findings highlight the current state and potential of the Ames prediction technology.

Abstract Reliable uncertainty quantification for statistical models is crucial in various downstream applications, especially for drug design and discovery where mistakes may incur a large amount of cost. This topic has therefore absorbed much attention and a plethora of methods have been proposed over the past years. The approaches that have been reported so far can be mainly categorized into two classes: distance-based approaches and Bayesian approaches. Although these methods have been widely used in many scenarios and shown promising performance with their distinct superiorities, being overconfident on out-of-distribution examples still poses challenges for the deployment of these techniques in real-world applications. In this study we investigated a number of consensus strategies in order to combine both distance-based and Bayesian approaches together with post-hoc calibration for improved uncertainty quantification in QSAR (Quantitative Structure–Activity Relationship) regression modeling. We employed a set of criteria to quantitatively assess the ranking and calibration ability of these models. Experiments based on 24 bioactivity datasets were designed to make critical comparison between the model we proposed and other well-studied baseline models. Our findings indicate that the hybrid framework proposed by us can robustly enhance the model ability of ranking absolute errors. Together with post-hoc calibration on the validation set, we show that well-calibrated uncertainty quantification results can be obtained in domain shift settings. The complementarity between different methods is also conceptually analyzed.

Cyclooxygenase-2 (COX-2) overexpression in many humans plays a key role in carcinogenic and inflammation-associated diseases. Several therapeutic and pharmaceutic drugs have been developed but some of them either lack the potency to control the COX-2 related diseases or promote unwanted side effects. The prospect and possibility for the development of drugs with novel therapeutic and pharmacological properties using the quantitative structure–activity relationship (QSAR) model were investigated. The model involves the application of chemical descriptors and supervised machine learning to predict the bioactivity classes of molecules for COX-2 inhibition using real multidimensional COX-2 inhibitors obtained from a curated database. The PubChem Fingerprints is the class of descriptor used in developing the model. A model performance check is carried out on 22 SciKit-Learn models and a comparative analysis of their predictive performance in classifying bioactivity of compounds is given in terms of validation accuracy. Unsupervised learning using principal component analysis (PCA) and t-distributed stochastic neighbor embedding (t-SNE) algorithms are applied as techniques to explore the effect of dimensionality in the training data. The PCA algorithm is a tool used to reduce the number of variables contained in the dataset, though preserving as much information as possible. The t-SNE algorithm is mainly used for data exploration and visualization of the multi-dimensional data set. Despite their high predictive performances, the eXtreme Gradient Boosting Classifier (XGB Classifier) algorithm is the ultimate performer. More so, hyperparameter tuning, and regularization account for excellent model statistics with higher predictive power at 10-fold cross-validation. Model metrics including log-loss probability (0.1208), accuracy score (0.9484), Matthew’s correlation coefficient (0.8741), among others proved adequately significant. Furthermore, the developed model is validated using recommended OECD metrics, such as Precision, Recall, and Balanced Accuracy for classification. The results in this study offer important pharmacological insight, and this insight can lead to designing novel bioactive drugs with undesired side effects. The proposed QSAR approach in this study achieves a futuristic performance when applied in drug development schemes different from conventional methods.

Quinones and quinone-containing organics have potential of activating persulfate to produce sulfate radical. In this work, the optimal condition for quinone activation of persulfate was investigated. It was found representative monoaromatics were degraded fastest in alkaline environment (pH 10.0), but excessive alkalinity restrained the reaction instead. The mechanisms to explain this phenomenon were speculated. The effect of initial quinone concentration on persulfate oxidation was also investigated at pH 10.0. In addition, a quantitative structure-activity relationship model was established with 15 kinds of monoaromatics, which revealed the most negative atomic net charges on carbon atom played an important role on degradation rates. Chemicals with a smaller qC- were easier oxidized in quinone-activate system. This finding helps further exploration of effective activator in alkaline environment.

Quantitative structure–activity relationship (QSAR) and quantitative structure–property relationship (QSPR) are established techniques to relate endpoints to molecular features. We present the Alvascience software suite that takes care of the whole QSAR/QSPR workflow necessary to use models to predict endpoints for untested molecules. The first step, data curation, is covered by alvaMolecule. Features such as molecular descriptors and fingerprints are generated by using alvaDesc. Models are built and validated with alvaModel. The models can then be deployed and used on new molecules by using alvaRunner. We use these software tools on a real case scenario to predict the blood–brain barrier (BBB) permeability. The resulting predictive models have accuracy equal or greater than 0.8. The models are bundled in an alvaRunner project available on the Alvascience website.

Polo-like kinase 1 (PLK1) plays an important role in cell cycle progression and proliferation in cancer cells. PLK1 also contributes to anticancer drug resistance and is a valuable target in anticancer therapeutics. To identify additional effective PLK1 inhibitors, we performed QSAR studies of two series of known PLK1 inhibitors and proposed a new structure based on a hybridized 3D-QSAR model. Given the hybridized 3D-QSAR models, we designed and synthesized 4-benzyloxy-1-(2-arylaminopyridin-4-yl)-1H-pyrazole-3-carboxamides, and we inspected its inhibitory activities to identify novel PLK1 inhibitors with decent potency and selectivity.

The quinazolinone compounds (1 and 2) in this work were examined for their in vitro antibacterial activities against gram-positive (Staphylococcus aureus) and gram-negative bacteria (Klebsiella pneumonia, Proteus bacilli and Shigella flexneri). Compared to the reference antibiotic chloramphenicol, these compounds showed high antibacterial activities against studied strains with inhibition zones observation. The ground state geometries have been optimized by using density functional theory (DFT) at B3LYP/6-31G* level of theory. The absorption spectra have been calculated by using time dependent density functional theory (TDDFT) with and without solvent. The effect of different functionals (B3LYP, MPW1PW91, and PBE1PBE) on the absorption wavelengths has been studied. The ionization potential (IP), electron affinity (EA), energy gap (Egap), electronegativity (χ), hardness (η), electrophilicity (ω), softness (S) and electrophilicity index (ωi) were computed and discussed. The nonlinear optical (NLO) properties vary by changing the theory (DFT to HF) or functional (B3LYP to CAM-B3LYP). The physicochemical parameters have been studied by quantitative structure–activity relationship (QSAR). The computed properties of investigated compounds have been compared with the Chloramphenicol as well as available experimental data.

Monoclonal antibodies (mAbs) constitute a rapidly growing biopharmaceutical sector. However, their growth is impeded by high failure rates originating from failed clinical trials and developability issues in process development. There is, therefore, a growing need for better in silico tools to aid in risk assessment of mAb candidates to promote early-stage screening of potentially problematic mAb candidates. In this study, a quantitative structure–activity relationship (QSAR) modelling workflow was designed for the prediction of hydrophobic interaction chromatography (HIC) retention times of mAbs. Three novel descriptor sets derived from primary sequence, homology modelling, and atomistic molecular dynamics (MD) simulations were developed and assessed to determine the necessary level of structural resolution needed to accurately capture the relationship between mAb structures and HIC retention times. The results showed that descriptors derived from 3D structures obtained after MD simulations were the most suitable for HIC retention time prediction with a R2 = 0.63 in an external test set. It was found that when using homology modelling, the resulting 3D structures became biased towards the used structural template. Performing an MD simulation therefore proved to be a necessary post-processing step for the mAb structures in order to relax the structures and allow them to attain a more natural conformation. Based on the results, the proposed workflow in this paper could therefore potentially contribute to aid in risk assessment of mAb candidates in early development.

The vast majority of marketed drugs are orally administrated. As such, drug absorption is one of the important drug metabolism and pharmacokinetics parameters that should be assessed in the process of drug discovery and development. A nonlinear quantitative structure–activity relationship (QSAR) model was constructed in this investigation using the novel machine learning-based hierarchical support vector regression (HSVR) scheme to render the extremely complicated relationships between descriptors and intestinal permeability that can take place through various passive diffusion and carrier-mediated active transport routes. The predictions by HSVR were found to be in good agreement with the observed values for the molecules in the training set (n = 53, r2 = 0.93, q CV 2 = 0.84, RMSE = 0.17, s = 0.08), test set (n = 13, q2 = 0.75–0.89, RMSE = 0.26, s = 0.14), and even outlier set (n = 8, q2 = 0.78–0.92, RMSE = 0.19, s = 0.09). The built HSVR model consistently met the most stringent criteria when subjected to various statistical assessments. A mock test also assured the predictivity of HSVR. Consequently, this HSVR model can be adopted to facilitate drug discovery and development.