PTML Combinatorial Model of ChEMBL Compounds Assays for Multiple Types of Cancer

Modeling and Interpretability Study of the Structure-Activity Relationship for Multigeneration EGFR Inhibitors

The fourth-generation EGFR inhibitors targeting L858R/T790M/C797S mutations are in clinical trials mostly, and it is necessary to develop new inhibitors. In this study, an internal data set containing 2302 multitarget EGFR inhibitors targeting the wild type (83%) and the L858R (92%), L858R/T790M (96%), and L858R/T790M/C797S (60%) mutations was collected. We established a structure-activity relationship model for predicting the bioactivities of multigeneration EGFR inhibitors by a multitask deep neural network (MT-DNN). We also constructed four single-task models on 1384 L858R/T790M/C797S (60%) mutation inhibitors by support vector machine (SVM), random forest (RF), XGBoost (XGB), and single-target neural network (ST-DNN), respectively. The MT-DNN model significantly outperformed single-task models on the external data set of 304 fourth-generation EGFR inhibitors. Furthermore, the combined application of MT-DNN and SHAP/delta-SHAP value interpretability analysis offers rigorous structural information from a global perspective. With SHAP/delta-SHAP methods, the MT-DNN model can mine the core scaffold and important fragments of multigeneration EGFR inhibitors and provide valuable information from a structure-activity relationship perspective to address the resistant mutation problem.

In Silico Approach for Antibacterial Discovery: PTML Modeling of Virtual Multi-Strain Inhibitors Against Staphylococcus aureus

Background/Objectives: Infectious diseases caused by Staphylococcus aureus (S. aureus) have become alarming health issues worldwide due to the ever-increasing emergence of multidrug resistance. In silico approaches can accelerate the identification and/or design of versatile antibacterial chemicals with the ability to target multiple S. aureus strains with varying degrees of drug resistance. Here, we develop a perturbation theory machine learning model based on a multilayer perceptron neural network (PTML-MLP) for the prediction and design of versatile virtual inhibitors against S. aureus strains. Methods: To develop the PTML-MLP model, chemical and biological data associated with antibacterial activity against S. aureus strains were retrieved from the ChEMBL database. We applied the Box-Jenkins approach to convert the topological indices into multi-label graph-theoretical indices; the latter were used as inputs for the creation of the PTML-MLP model. Results: The PTML-MLP model exhibited accuracy higher than 80% in both training and test sets. The physicochemical and structural interpretation of the PTML-MLP model was performed through the fragment-based topological design (FBTD) approach. Such interpretations permitted the analysis of different molecular fragments with favorable contributions to the multi-strain antibacterial activity and the design of four new drug-like molecules using different fragments as building blocks. The designed molecules were predicted/confirmed by our PTML model as multi-strain inhibitors of diverse S. aureus strains, thus representing promising chemotypes to be considered for future synthesis and biological testing of versatile anti-S. aureus agents. Conclusions: This work envisages promising applications of PTML modeling for early antibacterial drug discovery and related antimicrobial research areas.

Perturbation-theory machine learning for mood disorders: virtual design of dual inhibitors of NET and SERT proteins

Mood disorders affect the daily lives of millions of people worldwide. The search for more efficient therapies for mood disorders remains an active field of research. In silico approaches can accelerate the search for inhibitors against protein targets related to mood disorders. Here, we developed the first model perturbation-theory machine learning model based on a multiplayer perceptron network (PTML-MLP) for the simultaneous prediction and design of virtual dual-target inhibitors against two proteins associated with mood disorders, namely norepinephrine and serotonin transporters (NET and SERT, respectively). The PTML-MLP model had an accuracy of around 80%. From a chemical point of view, the PTML-MLP model could accurately identify both single- and dual-target inhibitors present in the dataset used to build it. Through the application of the fragment-based topological design (FBTD) approach, the molecular descriptors (multi-label graph-based indices) present in the PTML-MLP model were physicochemically and structurally interpreted. Such interpretations enabled (a) the extraction of different molecular fragments with a positive influence on the enhancement of the dual-target activity and (b) the design of four new drug-like molecules by assembling (fusing and/or connecting) several suitable molecular fragments. The designed molecules were predicted by the PTML-MLP model to exhibit dual-target activity against the NET and SERT proteins. These predictions, together with the estimated druglikeness suggest that the designed molecules could be new promising chemotypes to be considered for future synthesis and biological experimentation in the context of treatments for mood disorders.

Perturbation Theory Machine Learning Model for Phenotypic Early Antineoplastic Drug Discovery: Design of Virtual Anti-Lung-Cancer Agents

Lung cancer is the most diagnosed malignant neoplasm worldwide and it is associated with great mortality. Currently, developing antineoplastic agents is a challenging, time-consuming, and costly process. Computational methods can speed up the early discovery of anti-lung-cancer chemicals. Here, we report a perturbation theory machine learning model based on a multilayer perceptron (PTML-MLP) model for phenotypic early antineoplastic drug discovery, enabling the rational design and prediction of new molecules as virtual versatile inhibitors of multiple lung cancer cell lines. The PTML-MLP model achieved an accuracy above 80%. We applied the fragment-based topological design (FBTD) approach to physicochemically and structurally interpret the PTML-MLP model. This enabled the extraction of suitable fragments with a positive influence on anti-lung-cancer activity against the different lung cancer cell lines. By following the aforementioned interpretations, we could assemble several suitable fragments to design four novel molecules, which were predicted by the PTML-MLP model as versatile anti-lung-cancer agents. Such predictions of potent multi-cellular anticancer activity against diverse lung cancer cell lines were rigorously confirmed by a well-established virtual screening tool reported in the literature. The present work envisages new opportunities for the application of PTML models to accelerate early antineoplastic discovery from phenotypic assays.

Identification of Riluzole derivatives as novel calmodulin inhibitors with neuroprotective activity by a joint synthesis, biosensor, and computational guided strategy

The development of new molecules for the treatment of calmodulin related cardiovascular or neurodegenerative diseases is an interesting goal. In this work, we introduce a novel strategy with four main steps: (1) chemical synthesis of target molecules, (2) Förster Resonance Energy Transfer (FRET) biosensor development and in vitro biological assay of new derivatives, (3) Cheminformatics models development and in vivo activity prediction, and (4) Docking studies. This strategy is illustrated with a case study. Firstly, a series of 4-substituted Riluzole derivatives 1-3 were synthetized through a strategy that involves the construction of the 4-bromoriluzole framework and its further functionalization via palladium catalysis or organolithium chemistry. Next, a FRET biosensor for monitoring Ca2+-dependent CaM-ligands interactions has been developed and used for the in vitro assay of Riluzole derivatives. In particular, the best inhibition (80%) was observed for 4-methoxyphenylriluzole 2b. Besides, we trained and validated a new Networks Invariant, Information Fusion, Perturbation Theory, and Machine Learning (NIFPTML) model for predicting probability profiles of in vivo biological activity parameters in different regions of the brain. Next, we used this model to predict the in vivo activity of the compounds experimentally studied in vitro. Last, docking study conducted on Riluzole and its derivatives has provided valuable insights into their binding conformations with the target protein, involving calmodulin and the SK4 channel. This new combined strategy may be useful to reduce assay costs (animals, materials, time, and human resources) in the drug discovery process of calmodulin inhibitors.

Support Vector Machine-Based Prediction Models for Drug Repurposing and Designing Novel Drugs for Colorectal Cancer

Colorectal cancer (CRC) has witnessed a concerning increase in incidence and poses a significant therapeutic challenge due to its poor prognosis. There is a pressing demand to identify novel drug therapies to combat CRC. In this study, we addressed this need by utilizing the pharmacological profiles of anticancer drugs from the Genomics of Drug Sensitivity in Cancer (GDSC) database and developed QSAR models using the Support Vector Machine (SVM) algorithm for prediction of alternative and promiscuous anticancer compounds for CRC treatment. Our QSAR models demonstrated their robustness by achieving a high correlation of determination (R2) after 10-fold cross-validation. For 12 CRC cell lines, R2 ranged from 0.609 to 0.827. The highest performance was achieved for SW1417 and GP5d cell lines with R2 values of 0.827 and 0.786, respectively. Further, we listed the most common chemical descriptors in the drug profiles of the CRC cell lines and we also further reported the correlation of these descriptors with drug activity. The KRFP314 fingerprint was the predominantly occurring descriptor, with the KRFPC314 fingerprint following closely in prevalence within the drug profiles of the CRC cell lines. Beyond predictive modeling, we also confirmed the applicability of our developed QSAR models via in silico methods by conducting descriptor-drug analyses and recapitulating drug-to-oncogene relationships. We also identified two potential anti-CRC FDA-approved drugs, viomycin and diamorphine, using QSAR models. To ensure the easy accessibility and utility of our research findings, we have incorporated these models into a user-friendly prediction Web server named "ColoRecPred", available at https://project.iith.ac.in/cgntlab/colorecpred. We anticipate that this Web server can be used for screening of chemical libraries to identify potential anti-CRC drugs.

Implementation of IFPTML Computational Models in Drug Discovery Against Flaviviridae Family

The Flaviviridae family consists of single-stranded positive-sense RNA viruses, which contains the genera Flavivirus, Hepacivirus, Pegivirus, and Pestivirus. Currently, there is an outbreak of viral diseases caused by this family affecting millions of people worldwide, leading to significant morbidity and mortality rates. Advances in computational chemistry have greatly facilitated the discovery of novel drugs and treatments for diseases associated with this family. Chemoinformatic techniques, such as the perturbation theory machine learning method, have played a crucial role in developing new approaches based on ML models that can effectively aid drug discovery. The IFPTML models have shown its capability to handle, classify, and process large data sets with high specificity. The results obtained from different models indicates that this methodology is proficient in processing the data, resulting in a reduction of the false positive rate by 4.25%, along with an accuracy of 83% and reliability of 92%. These values suggest that the model can serve as a computational tool in assisting drug discovery efforts and the development of new treatments against Flaviviridae family diseases.

COIMMR: a computational framework to reveal the contribution of herbal ingredients against human cancer via immune microenvironment and metabolic reprogramming

Immune evasion and metabolism reprogramming have been regarded as two vital hallmarks of the mechanism of carcinogenesis. Thus, targeting the immune microenvironment and the reprogrammed metabolic processes will aid in developing novel anti-cancer drugs. In recent decades, herbal medicine has been widely utilized to treat cancer through the modulation of the immune microenvironment and reprogrammed metabolic processes. However, labor-based herbal ingredient screening is time consuming, laborious and costly. Luckily, some computational approaches have been proposed to screen candidates for drug discovery rapidly. Yet, it has been challenging to develop methods to screen drug candidates exclusively targeting specific pathways, especially for herbal ingredients which exert anti-cancer effects by multiple targets, multiple pathways and synergistic ways. Meanwhile, currently employed approaches cannot quantify the contribution of the specific pathway to the overall curative effect of herbal ingredients. Hence, to address this problem, this study proposes a new computational framework to infer the contribution of the immune microenvironment and metabolic reprogramming (COIMMR) in herbal ingredients against human cancer and specifically screen herbal ingredients targeting the immune microenvironment and metabolic reprogramming. Finally, COIMMR was applied to identify isoliquiritigenin that specifically regulates the T cells in stomach adenocarcinoma and cephaelin hydrochloride that specifically targets metabolic reprogramming in low-grade glioma. The in silico results were further verified using in vitro experiments. Taken together, our approach opens new possibilities for repositioning drugs targeting immune and metabolic dysfunction in human cancer and provides new insights for drug development in other diseases. COIMMR is available at https://github.com/LYN2323/COIMMR.

Optimizing drug discovery using multitasking models for quantitative structure-biological effect relationships: an update of the literature

INTRODUCTION

Drug discovery has provided modern societies with the means to fight against many diseases. In this sense, computational methods have been at the forefront, playing an important role in rationalizing the search for novel drugs. Yet, tackling phenomena such as the multi-genic nature of diseases and drug resistance are limitations of the current computational methods. Multi-tasking models for quantitative structure-biological effect relationships (mtk-QSBER) have emerged to overcome such limitations.

AREAS COVERED

The present review describes an update on the fundamentals and applications of the mtk-QSBER models as tools to accelerate multiple stages/substages of the drug discovery process.

EXPERT OPINION

Computational approaches are extremely important for the rationalization of the search for novel and efficacious therapeutic agents. However, they need to focus more on the multi-target drug discovery paradigm. In this sense, mtk-QSBER models are particularly suited for multi-target drug discovery, offering encouraging opportunities across multiple therapeutic areas and scientific disciplines associated with drug discovery.

Machine Learning Study of Metabolic Networks vs ChEMBL Data of Antibacterial Compounds

Antibacterial drugs (AD) change the metabolic status of bacteria, contributing to bacterial death. However, antibiotic resistance and the emergence of multidrug-resistant bacteria increase interest in understanding metabolic network (MN) mutations and the interaction of AD vs MN. In this study, we employed the IFPTML = Information Fusion (IF) + Perturbation Theory (PT) + Machine Learning (ML) algorithm on a huge dataset from the ChEMBL database, which contains >155,000 AD assays vs >40 MNs of multiple bacteria species. We built a linear discriminant analysis (LDA) and 17 ML models centered on the linear index and based on atoms to predict antibacterial compounds. The IFPTML-LDA model presented the following results for the training subset: specificity (Sp) = 76% out of 70,000 cases, sensitivity (Sn) = 70%, and Accuracy (Acc) = 73%. The same model also presented the following results for the validation subsets: Sp = 76%, Sn = 70%, and Acc = 73.1%. Among the IFPTML nonlinear models, the k nearest neighbors (KNN) showed the best results with Sn = 99.2%, Sp = 95.5%, Acc = 97.4%, and Area Under Receiver Operating Characteristic (AUROC) = 0.998 in training sets. In the validation series, the Random Forest had the best results: Sn = 93.96% and Sp = 87.02% (AUROC = 0.945). The IFPTML linear and nonlinear models regarding the ADs vs MNs have good statistical parameters, and they could contribute toward finding new metabolic mutations in antibiotic resistance and reducing time/costs in antibacterial drug research.

PTML Modeling for Pancreatic Cancer Research: In Silico Design of Simultaneous Multi-Protein and Multi-Cell Inhibitors

Pancreatic cancer (PANC) is a dangerous type of cancer that is a major cause of mortality worldwide and exhibits a remarkably poor prognosis. To date, discovering anti-PANC agents remains a very complex and expensive process. Computational approaches can accelerate the search for anti-PANC agents. We report for the first time two models that combined perturbation theory with machine learning via a multilayer perceptron network (PTML-MLP) to perform the virtual design and prediction of molecules that can simultaneously inhibit multiple PANC cell lines and PANC-related proteins, such as caspase-1, tumor necrosis factor-alpha (TNF-alpha), and the insulin-like growth factor 1 receptor (IGF1R). Both PTML-MLP models exhibited accuracies higher than 78%. Using the interpretation from one of the PTML-MLP models as a guideline, we extracted different molecular fragments desirable for the inhibition of the PANC cell lines and the aforementioned PANC-related proteins and then assembled some of those fragments to form three new molecules. The two PTML-MLP models predicted the designed molecules as potentially versatile anti-PANC agents through inhibition of the three PANC-related proteins and multiple PANC cell lines. Conclusions: This work opens new horizons for the application of the PTML modeling methodology to anticancer research.

In Silico Drug Repurposing for Anti-Inflammatory Therapy: Virtual Search for Dual Inhibitors of Caspase-1 and TNF-Alpha

Inflammation involves a complex biological response of the body tissues to damaging stimuli. When dysregulated, inflammation led by biomolecular mediators such as caspase-1 and tumor necrosis factor-alpha (TNF-alpha) can play a detrimental role in the progression of different medical conditions such as cancer, neurological disorders, autoimmune diseases, and cytokine storms caused by viral infections such as COVID-19. Computational approaches can accelerate the search for dual-target drugs able to simultaneously inhibit the aforementioned proteins, enabling the discovery of wide-spectrum anti-inflammatory agents. This work reports the first multicondition model based on quantitative structure–activity relationships and a multilayer perceptron neural network (mtc-QSAR-MLP) for the virtual screening of agency-regulated chemicals as versatile anti-inflammatory therapeutics. The mtc-QSAR-MLP model displayed accuracy higher than 88%, and was interpreted from a physicochemical and structural point of view. When using the mtc-QSAR-MLP model as a virtual screening tool, we could identify several agency-regulated chemicals as dual inhibitors of caspase-1 and TNF-alpha, and the experimental information later retrieved from the scientific literature converged with our computational results. This study supports the capabilities of our mtc-QSAR-MLP model in anti-inflammatory therapy with direct applications to current health issues such as the COVID-19 pandemic.

Indirect-Acting Pan-Antivirals vs. Respiratory Viruses: A Fresh Perspective on Computational Multi-Target Drug Discovery

Respiratory viruses continue to afflict mankind. Among them, pathogens such as coronaviruses [including the current pandemic agent known as severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2)] and the one causing influenza A (IAV) are highly contagious and deadly. These can evade the immune system defenses while causing a hyperinflammatory response that can damage different tissues/organs. Simultaneously targeting immunomodulatory proteins is a plausible antiviral strategy since it could lead to the discovery of indirect-acting pan-antiviral (IAPA) agents for the treatment of diseases caused by respiratory viruses. In this context, computational approaches, which are an essential part of the modern drug discovery campaigns, could accelerate the identification of multi-target immunomodulators. This perspective discusses the usefulness of computational multi-target drug discovery for the virtual screening (drug repurposing) of IAPA agents capable of boosting the immune system through the activation of the toll-like receptor 7 (TLR7) and/or the stimulator of interferon genes (STING) while inhibiting key pro-inflammatory proteins, such as caspase-1 and tumor necrosis factor-alpha (TNF-α).

Computational Drug Repurposing for Antituberculosis Therapy: Discovery of Multi-Strain Inhibitors

Tuberculosis remains the most afflicting infectious disease known by humankind, with one quarter of the population estimated to have it in the latent state. Discovering antituberculosis drugs is a challenging, complex, expensive, and time-consuming task. To overcome the substantial costs and accelerate drug discovery and development, drug repurposing has emerged as an attractive alternative to find new applications for “old” drugs and where computational approaches play an essential role by filtering the chemical space. This work reports the first multi-condition model based on quantitative structure–activity relationships and an ensemble of neural networks (mtc-QSAR-EL) for the virtual screening of potential antituberculosis agents able to act as multi-strain inhibitors. The mtc-QSAR-EL model exhibited an accuracy higher than 85%. A physicochemical and fragment-based structural interpretation of this model was provided, and a large dataset of agency-regulated chemicals was virtually screened, with the mtc-QSAR-EL model identifying already proven antituberculosis drugs while proposing chemicals with great potential to be experimentally repurposed as antituberculosis (multi-strain inhibitors) agents. Some of the most promising molecules identified by the mtc-QSAR-EL model as antituberculosis agents were also confirmed by another computational approach, supporting the capabilities of the mtc-QSAR-EL model as an efficient tool for computational drug repurposing.

The QSAR Paradigm in Fragment-Based Drug Discovery: From the Virtual Generation of Target Inhibitors to Multi-Scale Modeling

Fragment-Based Drug Design (FBDD) has established itself as a promising approach in modern drug discovery, accelerating and improving lead optimization, while playing a crucial role in diminishing the high attrition rates at all stages in the drug development process. On the other hand, FBDD has benefited from the application of computational methodologies, where the models derived from the Quantitative Structure-Activity Relationships (QSAR) have become consolidated tools. This mini-review focuses on the evolution and main applications of the QSAR paradigm in the context of FBDD in the last five years. This report places particular emphasis on the QSAR models derived from fragment-based topological approaches to extract physicochemical and/or structural information, allowing to design potentially novel mono- or multi-target inhibitors from relatively large and heterogeneous databases. Here, we also discuss the need to apply multi-scale modeling, to exemplify how different datasets based on target inhibition can be simultaneously integrated and predicted together with other relevant endpoints such as the biological activity against non-biomolecular targets, as well as in vitro and in vivo toxicity and pharmacokinetic properties. In this context, seminal papers are briefly analyzed. As huge amounts of data continue to accumulate in the domains of the chemical, biological and biomedical sciences, it has become clear that drug discovery must be viewed as a multi-scale optimization process. An ideal multi-scale approach should integrate diverse chemical and biological data and also serve as a knowledge generator, enabling the design of potentially optimal chemicals that may become therapeutic agents.

Predicting Metabolic Reaction Networks with Perturbation-Theory Machine Learning (PTML) Models

BACKGROUND

Checking the connectivity (structure) of complex Metabolic Reaction Networks (MRNs) models proposed for new microorganisms with promising properties is an important goal for chemical biology.

OBJECTIVE

In principle, we can perform a hand-on checking (Manual Curation). However, this is a challenging task due to the high number of combinations of pairs of nodes (possible metabolic reactions).

RESULTS

The CPTML linear model obtained using the LDA algorithm is able to discriminate nodes (metabolites) with the correct assignation of reactions from incorrect nodes with values of accuracy, specificity, and sensitivity in the range of 85-100% in both training and external validation data series.

METHODS

In this work, we used Combinatorial Perturbation Theory and Machine Learning techniques to seek a CPTML model for MRNs >40 organisms compiled by Barabasis' group. First, we quantified the local structure of a very large set of nodes in each MRN using a new class of node index called Markov linear indices fk. Next, we calculated CPT operators for 150000 combinations of query and reference nodes of MRNs. Last, we used these CPT operators as inputs of different ML algorithms.

CONCLUSION

Meanwhile, PTML models based on Bayesian network, J48-Decision Tree and Random Forest algorithms were identified as the three best non-linear models with accuracy greater than 97.5%. The present work opens the door to the study of MRNs of multiple organisms using PTML models.

Bioactivity Comparison across Multiple Machine Learning Algorithms Using over 5000 Datasets for Drug Discovery

Machine learning methods are attracting considerable attention from the pharmaceutical industry for use in drug discovery and applications beyond. In recent studies, we and others have applied multiple machine learning algorithms and modeling metrics and, in some cases, compared molecular descriptors to build models for individual targets or properties on a relatively small scale. Several research groups have used large numbers of datasets from public databases such as ChEMBL in order to evaluate machine learning methods of interest to them. The largest of these types of studies used on the order of 1400 datasets. We have now extracted well over 5000 datasets from CHEMBL for use with the ECFP6 fingerprint and in comparison of our proprietary software Assay Central with random forest, k-nearest neighbors, support vector classification, naïve Bayesian, AdaBoosted decision trees, and deep neural networks (three layers). Model performance was assessed using an array of fivefold cross-validation metrics including area-under-the-curve, F1 score, Cohen's kappa, and Matthews correlation coefficient. Based on ranked normalized scores for the metrics or datasets, all methods appeared comparable, while the distance from the top indicated that Assay Central and support vector classification were comparable. Unlike prior studies which have placed considerable emphasis on deep neural networks (deep learning), no advantage was seen in this case. If anything, Assay Central may have been at a slight advantage as the activity cutoff for each of the over 5000 datasets representing over 570,000 unique compounds was based on Assay Central performance, although support vector classification seems to be a strong competitor. We also applied Assay Central to perform prospective predictions for the toxicity targets PXR and hERG to further validate these models. This work appears to be the largest scale comparison of these machine learning algorithms to date. Future studies will likely evaluate additional databases, descriptors, and machine learning algorithms and further refine the methods for evaluating and comparing such models.

Activity Prediction of Small Molecule Inhibitors for Antirheumatoid Arthritis Targets Based on Artificial Intelligence

Rheumatoid arthritis (RA) is a chronic autoimmune disease, which is compared to "immortal cancer" in industry. Currently, SYK, BTK, and JAK are the three major targets of protein tyrosine kinase for this disease. According to existing research, marketed and research drugs for RA are mostly based on single target, which limits their efficacy. Therefore, designing multitarget or dual-target inhibitors provide new insights for the treatment of RA regarding of the specific association between SYK, BTK, and JAK from two signal transduction pathways. In this study, machine learning (XGBoost, SVM) and deep learning (DNN) models were combined for the first time to build a powerful integrated model for SYK, BTK, and JAK. The predictive power of the integrated model was proved to be superior to that of a single classifier. In order to accurately assess the generalization ability of the integrated model, comprehensive similarity analysis was performed on the training and the test set, and the prediction accuracy of the integrated model was specifically analyzed under different similarity thresholds. External validation was conducted using single-target and dual-target inhibitors, respectively. Results showed that our model not only obtained a high recall rate (97%) in single-target prediction, but also achieved a favorable yield (54.4%) in dual-target prediction. Furthermore, by clustering dual-target inhibitors, the prediction performance of model in various classes were proved, evaluating the applicability domain of the model in the dual-target drug screening. In summary, the integrated model proposed is promising to screen dual-target inhibitors of SYK/JAK or BTK/JAK as RA drugs, which is beneficial for the clinical treatment of rheumatoid arthritis.

A Multi-Objective Approach for Anti-Osteosarcoma Cancer Agents Discovery through Drug Repurposing

Osteosarcoma is the most common type of primary malignant bone tumor. Although nowadays 5-year survival rates can reach up to 60–70%, acute complications and late effects of osteosarcoma therapy are two of the limiting factors in treatments. We developed a multi-objective algorithm for the repurposing of new anti-osteosarcoma drugs, based on the modeling of molecules with described activity for HOS, MG63, SAOS2, and U2OS cell lines in the ChEMBL database. Several predictive models were obtained for each cell line and those with accuracy greater than 0.8 were integrated into a desirability function for the final multi-objective model. An exhaustive exploration of model combinations was carried out to obtain the best multi-objective model in virtual screening. For the top 1% of the screened list, the final model showed a BEDROC = 0.562, EF = 27.6, and AUC = 0.653. The repositioning was performed on 2218 molecules described in DrugBank. Within the top-ranked drugs, we found: temsirolimus, paclitaxel, sirolimus, everolimus, and cabazitaxel, which are antineoplastic drugs described in clinical trials for cancer in general. Interestingly, we found several broad-spectrum antibiotics and antiretroviral agents. This powerful model predicts several drugs that should be studied in depth to find new chemotherapy regimens and to propose new strategies for osteosarcoma treatment.

Cell-based multi-target QSAR model for design of virtual versatile inhibitors of liver cancer cell lines

Liver cancers are one of the leading fatal diseases among malignant neoplasms. Current chemotherapeutic treatments used to fight these illnesses have become less efficient in terms of both efficacy and safety. Therefore, there is a great need of search for new anti-liver cancer agents and this can be accelerated by using computer-aided drug discovery approaches. In this work, we report the development of the first cell-based multi-target model based on quantitative structure-activity relationships (CBMT-QSAR) for the design and prediction of chemicals as anticancer agents against 17 liver cancer cell lines. While having a good quality and predictive power (accuracy higher than 80%) in the training and test sets, respectively, the CBMT-QSAR model was employed as a tool to directly extract suitable fragments from the physicochemical and structural interpretations of the molecular descriptors. Some of these desirable fragments were assembled, leading to the virtual design of eight molecules with drug-like properties, with six of them being predicted as versatile anticancer agents against the 17 liver cancer cell lines reported here.

Perturbation-Theory Machine Learning (PTML) Multilabel Model of the ChEMBL Dataset of Preclinical Assays for Antisarcoma Compounds

Sarcomas are a group of malignant neoplasms of connective tissue with a different etiology than carcinomas. The efforts to discover new drugs with antisarcoma activity have generated large datasets of multiple preclinical assays with different experimental conditions. For instance, the ChEMBL database contains outcomes of 37,919 different antisarcoma assays with 34,955 different chemical compounds. Furthermore, the experimental conditions reported in this dataset include 157 types of biological activity parameters, 36 drug targets, 43 cell lines, and 17 assay organisms. Considering this information, we propose combining perturbation theory (PT) principles with machine learning (ML) to develop a PTML model to predict antisarcoma compounds. PTML models use one function of reference that measures the probability of a drug being active under certain conditions (protein, cell line, organism, etc.). In this paper, we used a linear discriminant analysis and neural network to train and compare PT and non-PT models. All the explored models have an accuracy of 89.19-95.25% for training and 89.22-95.46% in validation sets. PTML-based strategies have similar accuracy but generate simplest models. Therefore, they may become a versatile tool for predicting antisarcoma compounds.

PTML Modeling for Alzheimer’s Disease: Design and Prediction of Virtual Multi-Target Inhibitors of GSK3B, HDAC1, and HDAC6

Background:

Alzheimer’s disease is characterized by a progressive pattern of cognitive and functional impairment, which ultimately leads to death. Computational approaches have played an important role in the context of drug discovery for anti-Alzheimer's therapies. However, most of the computational models reported to date have been focused on only one protein associated with Alzheimer's, while relying on small datasets of structurally related molecules.

Objective:

We introduce the first model combining perturbation theory and machine learning based on artificial neural networks (PTML-ANN) for simultaneous prediction and design of inhibitors of three Alzheimer’s disease-related proteins, namely glycogen synthase kinase 3 beta (GSK3B), histone deacetylase 1 (HDAC1), and histone deacetylase 6 (HDAC6).

Methods:

The PTML-ANN model was obtained from a dataset retrieved from ChEMBL, and it relied on a classification approach to predict chemicals as active or inactive.

Results:

The PTML-ANN model displayed sensitivity and specificity higher than 85% in both training and test sets. The physicochemical and structural interpretation of the molecular descriptors in the model permitted the direct extraction of fragments suggested to favorably contribute to enhancing the multitarget inhibitory activity. Based on this information, we assembled ten molecules from several fragments with positive contributions. Seven of these molecules were predicted as triple target inhibitors while the remaining three were predicted as dual-target inhibitors. The estimated physicochemical properties of the designed molecules complied with Lipinski’s rule of five and its variants.

Conclusion:

This work opens new horizons toward the design of multi-target inhibitors for anti- Alzheimer's therapies.

PTML Model for Selection of Nanoparticles, Anticancer Drugs, and Vitamins in the Design of Drug-Vitamin Nanoparticle Release Systems for Cancer Cotherapy

Nanosystems are gaining momentum in pharmaceutical sciences because of the wide variety of possibilities for designing these systems to have specific functions. Specifically, studies of new cancer cotherapy drug-vitamin release nanosystems (DVRNs) including anticancer compounds and vitamins or vitamin derivatives have revealed encouraging results. However, the number of possible combinations of design and synthesis conditions is remarkably high. In addition, a large number of anticancer and vitamin derivatives have been already assayed, but a notably less number of cases of DVRNs were assayed as a whole (with the anticancer compound and the vitamin linked to them). Our approach combines with the perturbation theory and machine learning (PTML) model to predict the probability of obtaining an interesting DVRN by changing the anticancer compound and/or the vitamin present in a DVRN that is already tested for other anticancer compounds or vitamins that have not been tested yet as part of a DVRN. In a previous work, we built a linear PTML model useful for the design of these nanosystems. In doing so, we used information fusion (IF) techniques to carry out data enrichment of DVRN data compiled from the literature with the data for preclinical assays of vitamins from the ChEMBL database. The design features of DVRNs and the assay conditions of nanoparticles (NPs) and vitamins were included as multiplicative PT operators (PTOs) to the system, which indicates the importance of these variables. However, the previous work omitted experiments with nonlinear ML techniques and different types of PTOs such as metric-based PTOs. More importantly, the previous work does not consider the structure of the anticancer drug to be included in the new DVRNs. In this work, we are going to accomplish three main objectives (tasks). In the first task, we found a new model, alternative to the one published before, for the rational design of DVRNs using metric-based PTOs. The most accurate PTML model was the artificial neural network model, which showed values of specificity, sensitivity, and accuracy in the range of 90-95% in training and external validation series for more than 130,000 cases (DVRNs vs ChEMBL assays). Furthermore, in the second task, we used IF techniques to carry out data enrichment of our previous data set. In doing so, we constructed a new working data set of >970,000 cases with the data of preclinical assays of DVRNs, vitamins, and anticancer compounds from the ChEMBL database. All these assays have multiple continuous variables or descriptors d_k and categorical variables c_j (conditions of the assays) for drugs (d_ack, c_acj), vitamins (d_vk, c_vj), and NPs (d_nk, c_nj). These data include >20,000 potential anticancer compounds with >270 protein targets (c_ac1), >580 assay cell organisms (c_ac2), and so forth. Furthermore, we include >36,000 assay vitamin derivatives in >6200 types of cells (c_2vit), >120 assay organisms (c_3vit), >60 assay strains (c_4vit), and so forth. The enriched data set also contains >20 types of DVRNs (c_5n) with 9 NP core materials (c_4n), 8 synthesis methods (c_7n), and so forth. We expressed all this information with PTOs and developed a qualitatively new PTML model that incorporates information of the anticancer drugs. This new model presents 96-97% of accuracy for training and external validation subsets. In the last task, we carried out a comparative study of ML and/or PTML models published and described how the models we are presenting cover the gap of knowledge in terms of drug delivery. In conclusion, we present here for the first time a multipurpose PTML model that is able to select NPs, anticancer compounds, and vitamins and their conditions of assay for DVRN design.

Predicting coated-nanoparticle drug release systems with perturbation-theory machine learning (PTML) models

Nanoparticles (NPs) decorated with coating agents (polymers, gels, proteins, etc.) form Nanoparticle Drug Delivery Systems (DDNS), which are of high interest in nanotechnology and biomaterials science. There have been increasing reports of experimental data sets of biological activity, toxicity, and delivery properties of DDNS. However, these data sets are still dispersed and not as large as the datasets of DDNS components (NP and drugs). This has prompted researchers to train Machine Learning (ML) algorithms that are able to design new DDNS based on the properties of their components. However, most ML models reported up to date predictions of the specific activities of NP or drugs over a determined target or cell line. In this paper, we combine Perturbation Theory and Machine Learning (PTML algorithm) to train a model that is able to predict the best components (NP, coating agent, and drug) for DDNS design. In so doing, we downloaded a dataset of >30 000 preclinical assays of drugs from ChEMBL. We also downloaded an NP data set formed by preclinical assays of coated Metal Oxide Nanoparticles (MONPs) from public sources. Both the drugs and NP datasets of preclinical assays cover multiple conditions of assays that can be listed as two arrays, namely, cjdrug and cjNP. The cjdrug array includes >504 biological activity parameters (c0drug), >340 target proteins (c1drug), >650 types of cells (c2drug), >120 assay organisms (c3drug), and >60 assay strains (c4drug). On the other hand, the cjNP array includes 3 biological activity parameters (c0NP), 40 types of proteins (c1NP), 10 shapes of nanoparticles (c2NP), 6 assay media (c3NP), and 12 coating agents (c4NP). After downloading, we pre-processed both the data sets by separate calculation PT operators that are able to account for changes (perturbations) in the drug, coating agents, and NP chemical structure and/or physicochemical properties as well as for the assay conditions. Next, we carry out an information fusion process to form a final dataset of above 500 000 DDNS (drug + MONP pairs). We also trained other linear and non-linear PTML models using R studio scripts for comparative purposes. To the best of our knowledge, this is the first multi-label PTML model that is useful for the selection of drugs, coating agents, and metal or metal-oxide nanoparticles to be assembled in order to design new DDNS with optimal activity/toxicity profiles.

Synthesis, pharmacological profile and 2D-QSAR studies of curcumin-amino acid conjugates as potential drug candidates

A series of curcumin bis-conjugates 3a-q, 5a-k and 6a-k were synthesized in good yields utilizing an optimized reaction condition. We explored the effect of different amino acids and protecting groups on biological activities of curcumin. The conjugates were screened for anti-inflammatory, analgesic and antimicrobial properties. Some of the conjugates showed promising biological observations with a potency comparable with the standard references. The variations in biological properties concerning different amino acids and protecting groups are interesting observations. Effects of the synthesized conjugates on splenocytes and the production of nitric oxide by lipopolysaccharide-stimulated peritoneal macrophages are correlated with the observed anti-inflammatory properties. We have also established the safety profile of the most active conjugates. Robust 2D-QSAR studies supported and validated biological data.

A Review on Applications of Computational Methods in Drug Screening and Design

Drug development is one of the most significant processes in the pharmaceutical industry. Various computational methods have dramatically reduced the time and cost of drug discovery. In this review, we firstly discussed roles of multiscale biomolecular simulations in identifying drug binding sites on the target macromolecule and elucidating drug action mechanisms. Then, virtual screening methods (e.g., molecular docking, pharmacophore modeling, and QSAR) as well as structure- and ligand-based classical/de novo drug design were introduced and discussed. Last, we explored the development of machine learning methods and their applications in aforementioned computational methods to speed up the drug discovery process. Also, several application examples of combining various methods was discussed. A combination of different methods to jointly solve the tough problem at different scales and dimensions will be an inevitable trend in drug screening and design.

PTML Model of ChEMBL Compounds Assays for Vitamin Derivatives

Determining the biological activity of vitamin derivatives is needed given that organic synthesis of analogs of vitamins is an active field of interest for medicinal chemistry, pharmaceuticals, and food additives. Accordingly, scientists from different disciplines perform preclinical assays (n_ij) with a considerable combination of assay conditions (c_j). Indeed, the ChEMBL platform contains a database that includes results from 36 220 different biological activity bioassays of 21 240 different vitamins and vitamin derivatives. These assays present are heterogeneous in terms of assay combinations of c_j. They are focused on >500 different biological activity parameters (c₀), >340 different targets (c₁), >6200 types of cell (c₂), >120 organisms of assay (c₃), and >60 assay strains (c₄). It includes a total of >1850 niacin assays, >1580 tretinoin assays, >1580 retinol assays, 857 ascorbic acid assays, etc. Given the complexity of this combinatorial data in terms of being assimilated by researchers, we propose to build a model by combining perturbation theory (PT) and machine learning (ML). Through this study, we propose a PTML (PT + ML) combinatorial model for ChEMBL results on biological activity of vitamins and vitamins derivatives. The linear discriminant analysis (LDA) model presented the following results for training subset a: specificity (%) = 90.38, sensitivity (%) = 87.51, and accuracy (%) = 89.89. The model showed the following results for the external validation subset: specificity (%) = 90.58, sensitivity (%) = 87.72, and accuracy (%) = 90.09. Different types of linear and nonlinear PTML models, such as logistic regression (LR), classification tree (CT), näive Bayes (NB), and random Forest (RF), were applied to contrast the capacity of prediction. The PTML-LDA model predicts with more accuracy by applying combinatorial descriptors. In addition, a PCA experiment with chemical structure descriptors allowed us to characterize the high structural diversity of the chemical space studied. In any case, PTML models using chemical structure descriptors do not improve the performance of the PTML-LDA model based on ALOGP and PSA. We can conclude that the three variable PTML-LDA model is a simplified and adaptable tool for the prediction, for different experiment combinations, the biological activity of derivative vitamins.

Pollutants in Organic Chemistry and Medicinal Chemistry Education Laboratory. Experimental and Machine Learning Studies

AIMS

Computational modelling may help us to detect the more important factors governing this process in order to optimize it.

BACKGROUND

The generation of hazardous organic waste in teaching and research laboratories poses a big problem that universities have to manage.

METHODS

In this work, we report on the experimental measurement of waste generation on the chemical education laboratories within our department. We measured the waste generated in the teaching laboratories of the Organic Chemistry Department II (UPV/EHU), in the second semester of the 2017/2018 academic year. Likewise, to know the anthropogenic and social factors related to the generation of waste, a questionnaire has been utilized. We focused on all students of Experimentation in Organic Chemistry (EOC) and Organic Chemistry II (OC2) subjects. It helped us to know their prior knowledge about waste, awareness of the problem of separate organic waste and the correct use of the containers. These results, together with the volumetric data, have been analyzed with statistical analysis software. We obtained two Perturbation-Theory Machine Learning (PTML) models including chemical, operational, and academic factors. The dataset analyzed included 6050 cases of laboratory practices vs. practices of reference.

RESULTS

These models predict the values of acetone waste with R2 = 0.88 and non-halogenated waste with R2 = 0.91.

CONCLUSION

This work opens a new gate to the implementation of more sustainable techniques and a circular economy with the aim of improving the quality of university education processes.

Big Data Challenges Targeting Proteins in GPCR Signaling Pathways; Combining PTML-ChEMBL Models and [35S]GTPγS Binding Assays

G-protein-coupled receptors (GPCRs), also known as 7-transmembrane receptors, are the single largest class of drug targets. Consequently, a large amount of preclinical assays having GPCRs as molecular targets has been released to public sources like the Chemical European Molecular Biology Laboratory (ChEMBL) database. These data are also very complex covering changes in drug chemical structure and assay conditions like c₀ = activity parameter (K_i, IC₅₀, etc.), c₁ = target protein, c₂ = cell line, c₃ = assay organism, etc., making difficult the analysis of these databases that are placed in the borders of a Big Data challenge. One of the aims of this work is to develop a computational model able to predict new GPCRs targeting drugs taking into consideration multiple conditions of assay. Another objective is to perform new predictive and experimental studies of selective 5-HTA2 receptor agonist, antagonist, or inverse agonist in human comparing the results with those from the literature. In this work, we combined Perturbation Theory (PT) and Machine Learning (ML) to seek a general PTML model for this data set. We analyzed 343 738 unique compounds with 812 072 end points (assay outcomes), with 185 different experimental parameters, 592 protein targets, 51 cell lines, and/or 55 organisms (species). The best PTML linear model found has three input variables only and predicted 56 202/58 653 positive outcomes (sensitivity = 95.8%) and 470 230/550 401 control cases (specificity = 85.4%) in training series. The model also predicted correctly 18 732/19 549 (95.8%) of positive outcomes and 156 739/183 469 (85.4%) of cases in external validation series. To illustrate its practical use, we used the model to predict the outcomes of six different 5-HT2A receptor drugs, namely, TCB-2, DOI, DOB, altanserin, pimavanserin, and nelotanserin, in a very large number of different pharmacological assays. 5-HT2A receptors are altered in schizophrenia and represent drug target for antipsychotic therapeutic activity. The model correctly predicted 93.83% (76 of 86) experimental results for these compounds reported in ChEMBL. Moreover, [³⁵S]GTPγS binding assays were performed experimentally with the same six drugs with the aim of determining their potency and efficacy in the modulation of G-proteins in human brain tissue. The antagonist ketanserin was included as inactive drug with demonstrated affinity for 5-HT2A/C receptors. Our results demonstrate that some of these drugs, previously described as serotonin 5-HT2A receptor agonists, antagonists, or inverse agonists, are not so specific and show different intrinsic activity to that previously reported. Overall, this work opens a new gate for the prediction of GPCRs targeting compounds.

Multioutput Perturbation-Theory Machine Learning (PTML) Model of ChEMBL Data for Antiretroviral Compounds

Retroviral infections, such as HIV, are, until now, diseases with no cure. Medicine and pharmaceutical chemistry need and consider it a huge goal to define target proteins of new antiretroviral compounds. ChEMBL manages Big Data features with a complex data set, which is hard to organize. This makes information difficult to analyze due to a big number of characteristics described in order to predict new drug candidates for retroviral infections. For this reason, we propose to develop a new predictive model combining perturbation theory (PT) bases and machine learning (ML) modeling to create a new tool that can take advantage of all the available information. The PTML model proposed in this work for the ChEMBL data set preclinical experimental assays for antiretroviral compounds consists of a linear equation with four variables. The PT operators used are founded on multicondition moving averages, combining different features and simplifying the difficulty to manage all data. More than 140 000 preclinical assays for 56 105 compounds with different characteristics or experimental conditions have been carried out and can be found in ChEMBL database, covering combinations with 359 biological activity parameters (c₀), 55 protein accessions (c₁), 83 cell lines (c₂), 64 organisms of assay (c₃), and 773 subtypes or strains. We have included 150 148 preclinical experimental assays for HIV virus, 1188 for HTLV virus, 84 for simian immunodeficiency virus, 370 for murine leukemia virus, 119 for Rous sarcoma virus, 1581 for MMTV, etc. We also included 5277 assays for hepatitis B virus. The developed PTML model reached considerable values in sensibility (73.05% for training and 73.10% for validation), specificity (86.61% for training and 87.17% for validation), and accuracy (75.84% for training and 75.98% for validation). We also compared alternative PTML models with different PT operators such as covariance, moments, and exponential terms. Finally, we made a comparison between literature ML models with our PTML model and also artificial neural network (ANN) nonlinear models. We conclude that this PTML model is the first one to consider multiple characteristics of preclinical experimental antiretroviral assays combined, generating a simple, useful, and adaptable instrument, which could reduce time and costs in antiretroviral drugs research.

Modeling Antibacterial Activity with Machine Learning and Fusion of Chemical Structure Information with Microorganism Metabolic Networks

Predicting the activity of new chemical compounds over pathogenic microorganisms with different metabolic reaction networks (MRN _s) is an important goal due to the different susceptibility to antibiotics. The ChEMBL database contains >160 000 outcomes of preclinical assays of antimicrobial activity for 55 931 compounds with >365 parameters of activity (MIC, IC₅₀, etc.) and >90 bacteria strains of >25 bacterial species. In addition, the Leong and Barabàsi data set includes >40 MRNs of microorganisms. However, there are no models able to predict antibacterial activity for multiple assays considering both drug and MRN structures at the same time. In this work, we combined perturbation theory, machine learning, and information fusion techniques to develop the first PTMLIF model. The best linear model found presented values of specificity = 90.31/90.40 and sensitivity = 88.14/88.07 in training/validation series. We carried out a comparison to nonlinear artificial neural network (ANN) techniques and previous models from the literature. Next, we illustrated the practical use of the model with an experimental case of study. We reported for the first time the isolation and characterization of terpenes from the plant Cissus incisa. The antibacterial activity of the terpenes was experimentally determined. The more active compounds were phytol and α-amyrin, with MIC = 100 μg/mL for Vancomycin-resistant Enterococcus faecium and Acinetobacter baumannii resistant to carbapenems. These compounds are already known from other sources. However, they have been isolated and evaluated for the first time here against several strains of multidrug-resistant bacteria including World Health Organization (WHO) priority pathogens. Last, we used the model to predict the activity of these compounds versus other microorganisms with different MRNs in order to find other potential targets.

Combining Ensemble Learning with a Fragment-Based Topological Approach To Generate New Molecular Diversity in Drug Discovery: In Silico Design of Hsp90 Inhibitors

Machine learning methods have revolutionized modern science, providing fast and accurate solutions to multiple problems. However, they are commonly treated as "black boxes". Therefore, in important scientific fields such as medicinal chemistry and drug discovery, machine learning methods are restricted almost exclusively to the task of performing predictions of large and heterogeneous data sets of chemicals. The lack of interpretability prevents the full exploitation of the machine learning models as generators of new chemical knowledge. This work focuses on the development of an ensemble learning model for the prediction and design of potent dual heat shock protein 90 (Hsp90) inhibitors. The model displays accuracy higher than 80% in both training and test sets. To use the ensemble model as a generator of new chemical knowledge, three steps were followed. First, a physicochemical and/or structural interpretation was provided for each molecular descriptor present in the ensemble learning model. Second, the term "pseudolinear equation" was introduced within the context of machine learning to calculate the relative quantitative contributions of different molecular fragments to the inhibitory activity against the two Hsp90 isoforms studied here. Finally, by assembling the fragments with positive contributions, new molecules were designed, being predicted as potent Hsp90 inhibitors. According to Lipinski's rule of five, the designed molecules were found to exhibit potentially good oral bioavailability, a primordial property that chemicals must have to pass early stages in drug discovery. The present approach based on the combination of ensemble learning and fragment-based topological design holds great promise in drug discovery, and it can be adapted and applied to many different scientific disciplines.

BET bromodomain inhibitors: fragment-based in silico design using multi-target QSAR models

Epigenetics has become a focus of interest in drug discovery. In this sense, bromodomain-containing proteins have emerged as potential epigenetic targets in cancer research and other therapeutic areas. Several computational approaches have been applied to the prediction of bromodomain inhibitors. Nevertheless, such approaches have several drawbacks such as the fact that they predict activity against only one bromodomain-containing protein, using structurally related compounds. Also, there are no reports focused on meaningfully analyzing the physicochemical/structural features that are necessary for the design of a bromodomain inhibitor. This work describes the development of two different multi-target models based on quantitative structure-activity relationships (mt-QSAR) for the prediction and in silico design of multi-target bromodomain inhibitors against the proteins BRD2, BRD3, and BRD4. The first model relied on linear discriminant analysis (LDA) while the second focused on artificial neural networks. Both models exhibited accuracies higher than 85% in the dataset. Several molecular fragments were extracted, and their contributions to the inhibitory activity against the three BET proteins were calculated by the LDA model. Six molecules were designed by assembling the fragments with positive contributions, and they were predicted as multi-target BET bromodomain inhibitors by the two mt-QSAR models. Molecular docking calculations converged with the predictions performed by the mt-QSAR models, suggesting that the designed molecules can exhibit potent activity against the three BET proteins. These molecules complied with the Lipinski's rule of five.