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.

Multi-Endpoint Acute Toxicity Assessment of Organic Compounds Using Large-Scale Machine Learning Modeling.

In recent years, alternative animal testing methods such as computational and machine learning approaches have become increasingly crucial for toxicity testing. However, the complexity and scarcity of available biomedical data challenge the development of predictive models. Combining nonlinear machine learning together with multicondition descriptors offers a solution for using data from various assays to create a robust model. This work applies multicondition descriptors (MCDs) to develop a QSTR (Quantitative Structure-Toxicity Relationship) model based on a large toxicity data set comprising more than 80,000 compounds and 59 different end points (122,572 data points). The prediction capabilities of developed single-task multi-end point machine learning models as well as a novel data analysis approach with the use of Convolutional Neural Networks (CNN) are discussed. The results show that using MCDs significantly improves the model and using them with CNN-1D yields the best result (R2train = 0.93, R2ext = 0.70). Several structural features showed a high level of contribution to the toxicity, including van der Waals surface area (VSA), number of nitrogen-containing fragments (nN+), presence of S-P fragments, ionization potential, and presence of C-N fragments. The developed models can be very useful tools to predict the toxicity of various compounds under different conditions, enabling quick toxicity assessment of new compounds.

NANO.PTML model for read-across prediction of nanosystems in neurosciences. computational model and experimental case of study.

Neurodegenerative diseases involve progressive neuronal death. Traditional treatments often struggle due to solubility, bioavailability, and crossing the Blood-Brain Barrier (BBB). Nanoparticles (NPs) in biomedical field are garnering growing attention as neurodegenerative disease drugs (NDDs) carrier to the central nervous system. Here, we introduced computational and experimental analysis. In the computational study, a specific IFPTML technique was used, which combined Information Fusion (IF) + Perturbation Theory (PT) + Machine Learning (ML) to select the most promising Nanoparticle Neuronal Disease Drug Delivery (N2D3) systems. For the application of IFPTML model in the nanoscience, NANO.PTML is used. IF-process was carried out between 4403 NDDs assays and 260 cytotoxicity NP assays conducting a dataset of 500,000 cases. The optimal IFPTML was the Decision Tree (DT) algorithm which shown satisfactory performance with specificity values of 96.4% and 96.2%, and sensitivity values of 79.3% and 75.7% in the training (375k/75%) and validation (125k/25%) set. Moreover, the DT model obtained Area Under Receiver Operating Characteristic (AUROC) scores of 0.97 and 0.96 in the training and validation series, highlighting its effectiveness in classification tasks. In the experimental part, two samples of NPs (Fe3O4_A and Fe3O4_B) were synthesized by thermal decomposition of an iron(III) oleate (FeOl) precursor and structurally characterized by different methods. Additionally, in order to make the as-synthesized hydrophobic NPs (Fe3O4_A and Fe3O4_B) soluble in water the amphiphilic CTAB (Cetyl Trimethyl Ammonium Bromide) molecule was employed. Therefore, to conduct a study with a wider range of NP system variants, an experimental illustrative simulation experiment was performed using the IFPTML-DT model. For this, a set of 500,000 prediction dataset was created. The outcome of this experiment highlighted certain NANO.PTML systems as promising candidates for further investigation. The NANO.PTML approach holds potential to accelerate experimental investigations and offer initial insights into various NP and NDDs compounds, serving as an efficient alternative to time-consuming trial-and-error procedures.

Prediction of Antileishmanial Compounds: General Model, Preparation, and Evaluation of 2-Acylpyrrole Derivatives.

In this work, the SOFT.PTML tool has been used to pre-process a ChEMBL dataset of pre-clinical assays of antileishmanial compound candidates. A comparative study of different ML algorithms, such as logistic regression (LOGR), support vector machine (SVM), and random forests (RF), has shown that the IFPTML-LOGR model presents excellent values of specificity and sensitivity (81-98%) in training and validation series. The use of this software has been illustrated with a practical case study focused on a series of 28 derivatives of 2-acylpyrroles 5a,b, obtained through a Pd(II)-catalyzed C-H radical acylation of pyrroles. Their in vitro leishmanicidal activity against visceral (L. donovani) and cutaneous (L. amazonensis) leishmaniasis was evaluated finding that compounds 5bc (IC50 = 30.87 µM, SI > 10.17) and 5bd (IC50 = 16.87 µM, SI > 10.67) were approximately 6-fold more selective than the drug of reference (miltefosine) in in vitro assays against L. amazonensis promastigotes. In addition, most of the compounds showed low cytotoxicity, CC50 > 100 µg/mL in J774 cells. Interestingly, the IFPMTL-LOGR model predicts correctly the relative biological activity of these series of acylpyrroles. A computational high-throughput screening (cHTS) study of 2-acylpyrroles 5a,b has been performed calculating >20,700 activity scores vs a large space of 647 assays involving multiple Leishmania species, cell lines, and potential target proteins. Overall, the study demonstrates that the SOFT.PTML all-in-one strategy is useful to obtain IFPTML models in a friendly interface making the work easier and faster than before. The present work also points to 2-acylpyrroles as new lead compounds worthy of further optimization as antileishmanial hits.

Prediction of acute toxicity of pesticides for Americamysis bahia using linear and nonlinear QSTR modelling approaches.

Globally, pesticides are toxic substances with wide applications. However, the widespread use of pesticides has received increasing attention from regulatory agencies due to their various acute and chronic effects on multiple organisms. In this study, Quantitative Structure-Toxicity Relationship (QSTR) models were established using Multiple Linear Regression (MLR) and five Machine Learning (ML) algorithms to predict pesticide toxicity in Americamysis bahia. The most influential descriptors included in the MLR model are RBF, JGI2, nCbH, nRCOOR, nRSR, nPO4 and 'Cl-090', with positive contributions to the dependent variable (negative decimal logarithm of median lethal concentration at 96-h). The Random Forest (RF) regression model was superior amongst the five ML models. We observed higher values of R2 (0.812) and lower values of RMSE (0.595) and MAE (0.462) in the cross-validation training set and external validation set. Similarly, this study had a high level of fitness and was internally robust and externally predictive compared to models presented in similar studies. The results suggest that the developed QSTR models are suitable for reliably predicting the aquatic toxicity of structurally diverse pesticides and can be used for screening, prioritising new pesticides, filling data gaps and overcoming the limitations of in vivo and in vitro tests.

IFPTML Mapping of Drug Graphs with Protein and Chromosome Structural Networks vs. Pre-Clinical Assay Information for Discovery of Antimalarial Compounds.

The parasite species of genus Plasmodium causes Malaria, which remains a major global health problem due to parasite resistance to available Antimalarial drugs and increasing treatment costs. Consequently, computational prediction of new Antimalarial compounds with novel targets in the proteome of Plasmodium sp. is a very important goal for the pharmaceutical industry. We can expect that the success of the pre-clinical assay depends on the conditions of assay per se, the chemical structure of the drug, the structure of the target protein to be targeted, as well as on factors governing the expression of this protein in the proteome such as genes (Deoxyribonucleic acid, DNA) sequence and/or chromosomes structure. However, there are no reports of computational models that consider all these factors simultaneously. Some of the difficulties for this kind of analysis are the dispersion of data in different datasets, the high heterogeneity of data, etc. In this work, we analyzed three databases ChEMBL (Chemical database of the European Molecular Biology Laboratory), UniProt (Universal Protein Resource), and NCBI-GDV (National Center for Biotechnology Information-Genome Data Viewer) to achieve this goal. The ChEMBL dataset contains outcomes for 17,758 unique assays of potential Antimalarial compounds including numeric descriptors (variables) for the structure of compounds as well as a huge amount of information about the conditions of assays. The NCBI-GDV and UniProt datasets include the sequence of genes, proteins, and their functions. In addition, we also created two partitions (cassayj = caj and cdataj = cdj) of categorical variables from theChEMBL dataset. These partitions contain variables that encode information about experimental conditions of preclinical assays (caj) or about the nature and quality of data (cdj). These categorical variables include information about 22 parameters of biological activity (ca0), 28 target proteins (ca1), and 9 organisms of assay (ca2), etc. We also created another partition of (cprotj = cpj) including categorical variables with biological information about the target proteins, genes, and chromosomes. These variables cover32 genes (cp0), 10 chromosomes (cp1), gene orientation (cp2), and 31 protein functions (cp3). We used a Perturbation-Theory Machine Learning Information Fusion (IFPTML) algorithm to map all this information (from three databases) into and train a predictive model. Shannon's entropy measure Shk (numerical variables) was used to quantify the information about the structure of drugs, protein sequences, gene sequences, and chromosomes in the same information scale. Perturbation Theory Operators (PTOs) with the form of Moving Average (MA) operators have been used to quantify perturbations (deviations) in the structural variables with respect to their expected values for different subsets (partitions) of categorical variables. We obtained three IFPTML models using General Discriminant Analysis (GDA), Classification Tree with Univariate Splits (CTUS), and Classification Tree with Linear Combinations (CTLC). The IFPTML-CTLC presented the better performance with Sensitivity Sn(%) = 83.6/85.1, and Specificity Sp(%) = 89.8/89.7 for training/validation sets, respectively. This model could become a useful tool for the optimization of preclinical assays of new Antimalarial compounds vs. different proteins in the proteome of Plasmodium.

Computational MitoTarget Scanning Based on Topological Vacancies of Single-Walled Carbon Nanotubes with the Human Mitochondrial Voltage-Dependent Anion Channel (hVDAC1).

We present an in silico approach for modeling the noncovalent interactions between the human mitochondrial voltage-dependent anion channel (hVDAC1) and a family of single-walled carbon nanotubes (SWCNTs) with a defined pattern of topological vacancies ( v = 1-16), obtained by removing atoms from the SWCNT surface. The general results showed more stable docking interaction complexes (SWCNT-hVDAC1), with more negative Gibbs free energy of binding affinity values, and a strong dependence on the vacancy number ( R2 = 0.93) and vacancy formation energy ( R2 = 0.96). In addition, for most of the SWCNT vacancies that were analyzed, the interatomic distances for the interactions of the SWCNT-hVDAC1 complex with the functional catalytic residues (i.e., Pro7, Gln199, Gln182, Phe181, Val20, Asp19, Lys15, Gly14, Asp12, Ala11, and Arg18) that form the hVDAC1 active site (i.e., the voltage-sensing N-terminal α-helix segment) were very similar to or shorter than the interatomic distances of these residues for ATP-hVDAC1 interactions. In particular, the hVDAC1 residues that can be phosphorylated like Tyr10, Tyr198, and Se16 were significantly perturbed by the interactions with SWCNT with at least nine vacancies. In addition, the SWCNT vacancy family members can affect the flexibility properties of the hVDAC1 N-terminal α-helix segment inducing different patterns of local perturbations in inter-residue communication. Finally, vacancy quantitative structure-binding relationships (V-QSBRs) were unveiled for setting up a robust model that can predict the strength of docking interactions between SWCNTs with a specific topological vacancy and hVDAC1. The developed V-QSBR model classified properly all of the SWCNTs with a different number of SWCNT vacancies with exceptional sensitivity and specificity (both equal to 100%), indicating a strong potential to unequivocally predict the influence of SWCNT vacancies on the mitochondrial channel interactions.

MitoTarget Modeling Using ANN-Classification Models Based on Fractal SEM Nano-Descriptors: Carbon Nanotubes as Mitochondrial F0F1-ATPase Inhibitors.

Recently, it has been suggested that the mitochondrial oligomycin A-sensitive F0-ATPase subunit is an uncoupling channel linked to apoptotic cell death, and as such, the toxicological inhibition of mitochondrial F0-ATP hydrolase can be an interesting mitotoxicity-based therapy under pathological conditions. In addition, carbon nanotubes (CNTs) have been shown to offer higher selectivity like mitotoxic-targeting nanoparticles. In this work, linear and nonlinear classification algorithms on structure-toxicity relationships with artificial neural network (ANN) models were set up using the fractal dimensions calculated from CNTs as a source of supramolecular chemical information. The potential ability of CNT-family members to induce mitochondrial toxicity-based inhibition of the mitochondrial H+-F0F1-ATPase from in vitro assays was predicted. The attained experimental data suggest that CNTs have a strong ability to inhibit the F0-ATPase active-binding site following the order oxidized-CNT (CNT-COOH > CNT-OH) > pristine-CNT and mimicking the oligomycin A mitotoxicity behavior. Meanwhile, the performance of the ANN models was found to be improved by including different nonlinear combinations of the calculated fractal scanning electron microscopy (SEM) nanodescriptors, leading to models with excellent internal accuracy and predictivity on external data to classify correctly CNT-mitotoxic and nonmitotoxic with specificity (Sp > 98.9%) and sensitivity (Sn > 99.0%) from ANN models compared with linear approaches (LNN) with Sp ≈ Sn > 95.5%. Finally, the present study can contribute toward the rational design of carbon nanomaterials and opens new opportunities toward mitochondrial nanotoxicology-based in silico models.

Perturbation-Theory and Machine Learning (PTML) Model for High-Throughput Screening of Parham Reactions: Experimental and Theoretical Studies.

Machine learning (ML) algorithms are gaining importance in the processing of chemical information and modeling of chemical reactivity problems. In this work, we have developed a perturbation-theory and machine learning (PTML) model combining perturbation theory (PT) and ML algorithms for predicting the yield of a given reaction. For this purpose, we have selected Parham cyclization, which is a general and powerful tool for the synthesis of heterocyclic and carbocyclic compounds. This reaction has both structural (substitution pattern on the substrate, internal electrophile, ring size, etc.) and operational variables (organolithium reagent, solvent, temperature, time, etc.), so predicting the effect of changes on substrate design (internal elelctrophile, halide, etc.) or reaction conditions on the yield is an important task that could help to optimize the reaction design. The PTML model developed uses PT operators to account for perturbations under experimental conditions and/or structural variables of all the molecules involved in a query reaction, compared to a reaction of reference. Thus, a dataset of >100 reactions has been collected for different substrates and internal electrophiles, under different reaction conditions, with a wide range of yields (0-98%). The best PTML model found using General Linear Regression (GLR) has R = 0.88 in training and R = 0.83 in external validation series for 10 000 pairs of query and reference reactions. The PTML model has a final R = 0.95 for all reactions using multiple reactions of reference. We also report a comparative study of linear versus nonlinear PTML models based on artificial neural network (ANN) algorithms. PTML-ANN models (LNN, MLP, RBF) with R ≈ 0.1-0.8 do not outperform the first PMTL model. This result confirms the validity of the linearity of the model. Next, we carried out an experimental and theoretical study of nonreported Parham reactions to illustrate the practical use of the PTML model. A 500 000-point simulation and a Hammett analysis of the reactivity space of Parham reactions are also reported.

Experimental-Computational Study of Carbon Nanotube Effects on Mitochondrial Respiration: In Silico Nano-QSPR Machine Learning Models Based on New Raman Spectra Transform with Markov-Shannon Entropy Invariants.

The study of selective toxicity of carbon nanotubes (CNTs) on mitochondria (CNT-mitotoxicity) is of major interest for future biomedical applications. In the current work, the mitochondrial oxygen consumption (E3) is measured under three experimental conditions by exposure to pristine and oxidized CNTs (hydroxylated and carboxylated). Respiratory functional assays showed that the information on the CNT Raman spectroscopy could be useful to predict structural parameters of mitotoxicity induced by CNTs. The in vitro functional assays show that the mitochondrial oxidative phosphorylation by ATP-synthase (or state V3 of respiration) was not perturbed in isolated rat-liver mitochondria. For the first time a star graph (SG) transform of the CNT Raman spectra is proposed in order to obtain the raw information for a nano-QSPR model. Box-Jenkins and perturbation theory operators are used for the SG Shannon entropies. A modified RRegrs methodology is employed to test four regression methods such as multiple linear regression (LM), partial least squares regression (PLS), neural networks regression (NN), and random forest (RF). RF provides the best models to predict the mitochondrial oxygen consumption in the presence of specific CNTs with R2 of 0.998-0.999 and RMSE of 0.0068-0.0133 (training and test subsets). This work is aimed at demonstrating that the SG transform of Raman spectra is useful to encode CNT information, similarly to the SG transform of the blood proteome spectra in cancer or electroencephalograms in epilepsy and also as a prospective chemoinformatics tool for nanorisk assessment. All data files and R object models are available at https://dx.doi.org/10.6084/m9.figshare.3472349 .

A study of the Immune Epitope Database for some fungi species using network topological indices.

In the last years, the encryption of system structure information with different network topological indices has been a very active field of research. In the present study, we assembled for the first time a complex network using data obtained from the Immune Epitope Database for fungi species, and we then considered the general topology, the node degree distribution, and the local structure of this network. We also calculated eight node centrality measures for the observed network and compared it with three theoretical models. In view of the results obtained, we may expect that the present approach can become a valuable tool to explore the complexity of this database, as well as for the storage, manipulation, comparison, and retrieval of information contained therein.

Data Analysis in Chemistry and Bio-Medical Sciences.

n/a.

Self-Assembled Binary Nanoscale Systems: Multioutput Model with LFER-Covariance Perturbation Theory and an Experimental-Computational Study of NaGDC-DDAB Micelles.

Studies of the self-aggregation of binary systems are of both theoretical and practical importance. They provide an opportunity to investigate the influence of the molecular structure of the hydrophobe on the nonideality of mixing. On the other hand, linear free energy relationship (LFER) models, such as Hansch's equations, may be used to predict the properties of chemical compounds such as drugs or surfactants. However, the task becomes more difficult once we want to predict simultaneaously the effect over multiple output properties of binary systems of perturbations under multiple input experimental boundary conditions (b(j)). As a consequence, we need computational chemistry or chemoinformatics models that may help us to predict different properties of the autoaggregation process of mixed surfactants under multiple conditions. In this work, we have developed the first model that combines perturbation theory (PT) and LFER ideas. The model uses as input covariance PT operators (CPTOs). CPTOs are calculated as the difference between covariance ΔCov((i)µ(k)) functions before and after multiple perturbations in the binary system. In turn, covariances calculated as the product of two Box-Jenkins operators (BJO) operators. BJOs are used to measure the deviation of the structure of different chemical compounds from a set of molecules measured under a given subset of experimental conditions. The best CPT-LFER model found predicted the effects of 25,000 perturbations over 9 different properties of binary systems. We also reported experimental studies of different experimental properties of the binary system formed by sodium glycodeoxycholate and didodecyldimethylammonium bromide (NaGDC-DDAB). Last, we used our CPT-LFER model to carry out a 1000 data point simulation of the properties of the NaGDC-DDAB system under different conditions not studied experimentally.

Multi-output model with Box-Jenkins operators of linear indices to predict multi-target inhibitors of ubiquitin-proteasome pathway.

The ubiquitin-proteasome pathway (UPP) plays an important role in the degradation of cellular proteins and regulation of different cellular processes that include cell cycle control, proliferation, differentiation, and apoptosis. In this sense, the disruption of proteasome activity leads to different pathological states linked to clinical disorders such as inflammation, neurodegeneration, and cancer. The use of UPP inhibitors is one of the proposed approaches to manage these alterations. On other hand, the ChEMBL database contains >5,000 experimental outcomes for >2,000 compounds tested as possible proteasome inhibitors using a large number of pharmacological assay protocols. All these assays report a large number of experimental parameters of biological activity like EC50, IC50 percent of inhibition, and many others that have been determined under many different conditions, targets, organisms, etc. Although this large amount of data offers new opportunities for the computational discovery of proteasome inhibitors, the complexity of these data represents a bottleneck for the development of predictive models. In this work, we used linear molecular indices calculated with the software TOMOCOMD-CARDD and Box-Jenkins moving average operators to develop a multi-output model that can predict outcomes for 20 experimental parameters in >450 assays carried out under different conditions. This generated multi-output model showed values of accuracy, sensitivity, and specificity above 70% for training and validation series. Finally, this model is considered multi-target and multi-scale, because it predicts the inhibition of the UPP for drugs against 22 molecular or cellular targets of different organisms contained in the ChEMBL database.

A QSPR-like model for multilocus genotype networks of Fasciola hepatica in Northwest Spain.

Fasciola hepatica is a parasitic trematode that infects wild and domesticated mammals, particularly cattle and sheep, and causes significant economic losses to global livestock production. In the present study, we used codominant genetic markers to define and build, for the first time, complex genotype networks for F. hepatica isolated from cattle and sheep in NW Spain. We generated three types of random networks with a number of nodes and edges as close as possible to the observed networks, and we then calculated 14 node centrality measures for both observed and random networks. Finally, using Linear Discriminant Analysis (LDA) and these measures as inputs, we constructed a quantitative structure-property relationship (QSPR)-like model able to predict the propensity of a specific genotype of F. hepatica to infect different infrapopulations, farms and/or host species. The accuracy, sensitivity and specificity of the model were >90% for both training and cross-validation series. We also assessed the applicability domain of the model. This type of QSPR model is a potentially powerful tool for epidemiological studies and could be used to manage and prevent the spread of fasciolosis.

Markov mean properties for cell death-related protein classification.

The cell death (CD) is a dynamic biological function involved in physiological and pathological processes. Due to the complexity of CD, there is a demand for fast theoretical methods that can help to find new CD molecular targets. The current work presents the first classification model to predict CD-related proteins based on Markov Mean Properties. These protein descriptors have been calculated with the MInD-Prot tool using the topological information of the amino acid contact networks of the 2423 protein chains, five atom physicochemical properties and the protein 3D regions. The Machine Learning algorithms from Weka were used to find the best classification model for CD-related protein chains using all 20 attributes. The most accurate algorithm to solve this problem was K*. After several feature subset methods, the best model found is based on only 11 variables and is characterized by the Area Under the Receiver Operating Characteristic Curve (AUROC) of 0.992 and the true positive rate (TP Rate) of 88.2% (validation set). 7409 protein chains labeled with "unknown function" in the PDB Databank were analyzed with the best model in order to predict the CD-related biological activity. Thus, several proteins have been predicted to have CD-related function in Homo sapiens: 3DRX-involved in virus-host interaction biological process, protein homooligomerization; 4DWF-involved in cell differentiation, chromatin modification, DNA damage response, protein stabilization; 1IUR-involved in ATP binding, chaperone binding; 1J7D-involved in DNA double-strand break processing, histone ubiquitination, nucleotide-binding oligomerization; 1UTU-linked with DNA repair, regulation of transcription; 3EEC-participating to the cellular membrane organization, egress of virus within host cell, class mediator resulting in cell cycle arrest, negative regulation of ubiquitin-protein ligase activity involved in mitotic cell cycle and apoptotic process. Other proteins from bacteria predicted as CD-related are 2G3V - a CAG pathogenicity island protein 13 from Helicobacter pylori, 4G5A - a hypothetical protein in Bacteroides thetaiotaomicron, 1YLK-involved in the nitrogen metabolism of Mycobacterium tuberculosis, and 1XSV - with possible DNA/RNA binding domains. The results demonstrated the possibility to predict CD-related proteins using molecular information encoded into the protein 3D structure. Thus, the current work demonstrated the possibility to predict new molecular targets involved in cell-death processes.

Modeling complex metabolic reactions, ecological systems, and financial and legal networks with MIANN models based on Markov-Wiener node descriptors.

The use of numerical parameters in Complex Network analysis is expanding to new fields of application. At a molecular level, we can use them to describe the molecular structure of chemical entities, protein interactions, or metabolic networks. However, the applications are not restricted to the world of molecules and can be extended to the study of macroscopic nonliving systems, organisms, or even legal or social networks. On the other hand, the development of the field of Artificial Intelligence has led to the formulation of computational algorithms whose design is based on the structure and functioning of networks of biological neurons. These algorithms, called Artificial Neural Networks (ANNs), can be useful for the study of complex networks, since the numerical parameters that encode information of the network (for example centralities/node descriptors) can be used as inputs for the ANNs. The Wiener index (W) is a graph invariant widely used in chemoinformatics to quantify the molecular structure of drugs and to study complex networks. In this work, we explore for the first time the possibility of using Markov chains to calculate analogues of node distance numbers/W to describe complex networks from the point of view of their nodes. These parameters are called Markov-Wiener node descriptors of order k(th) (W(k)). Please, note that these descriptors are not related to Markov-Wiener stochastic processes. Here, we calculated the W(k)(i) values for a very high number of nodes (>100,000) in more than 100 different complex networks using the software MI-NODES. These networks were grouped according to the field of application. Molecular networks include the Metabolic Reaction Networks (MRNs) of 40 different organisms. In addition, we analyzed other biological and legal and social networks. These include the Interaction Web Database Biological Networks (IWDBNs), with 75 food webs or ecological systems and the Spanish Financial Law Network (SFLN). The calculated W(k)(i) values were used as inputs for different ANNs in order to discriminate correct node connectivity patterns from incorrect random patterns. The MIANN models obtained present good values of Sensitivity/Specificity (%): MRNs (78/78), IWDBNs (90/88), and SFLN (86/84). These preliminary results are very promising from the point of view of a first exploratory study and suggest that the use of these models could be extended to the high-throughput re-evaluation of connectivity in known complex networks (collation).

ANN multiscale model of anti-HIV drugs activity vs AIDS prevalence in the US at county level based on information indices of molecular graphs and social networks.

This work is aimed at describing the workflow for a methodology that combines chemoinformatics and pharmacoepidemiology methods and at reporting the first predictive model developed with this methodology. The new model is able to predict complex networks of AIDS prevalence in the US counties, taking into consideration the social determinants and activity/structure of anti-HIV drugs in preclinical assays. We trained different Artificial Neural Networks (ANNs) using as input information indices of social networks and molecular graphs. We used a Shannon information index based on the Gini coefficient to quantify the effect of income inequality in the social network. We obtained the data on AIDS prevalence and the Gini coefficient from the AIDSVu database of Emory University. We also used the Balaban information indices to quantify changes in the chemical structure of anti-HIV drugs. We obtained the data on anti-HIV drug activity and structure (SMILE codes) from the ChEMBL database. Last, we used Box-Jenkins moving average operators to quantify information about the deviations of drugs with respect to data subsets of reference (targets, organisms, experimental parameters, protocols). The best model found was a Linear Neural Network (LNN) with values of Accuracy, Specificity, and Sensitivity above 0.76 and AUROC > 0.80 in training and external validation series. This model generates a complex network of AIDS prevalence in the US at county level with respect to the preclinical activity of anti-HIV drugs in preclinical assays. To train/validate the model and predict the complex network we needed to analyze 43,249 data points including values of AIDS prevalence in 2,310 counties in the US vs ChEMBL results for 21,582 unique drugs, 9 viral or human protein targets, 4,856 protocols, and 10 possible experimental measures.

Computational tool for risk assessment of nanomaterials: novel QSTR-perturbation model for simultaneous prediction of ecotoxicity and cytotoxicity of uncoated and coated nanoparticles under multiple experimental conditions.

Nanomaterials have revolutionized modern science and technology due to their multiple applications in engineering, physics, chemistry, and biomedicine. Nevertheless, the use and manipulation of nanoparticles (NPs) can bring serious damages to living organisms and their ecosystems. For this reason, ecotoxicity and cytotoxicity assays are of special interest in order to determine the potential harmful effects of NPs. Processes based on ecotoxicity and cytotoxicity tests can significantly consume time and financial resources. In this sense, alternative approaches such as quantitative structure-activity/toxicity relationships (QSAR/QSTR) modeling have provided important insights for the better understanding of the biological behavior of NPs that may be responsible for causing toxicity. Until now, QSAR/QSTR models have predicted ecotoxicity or cytotoxicity separately against only one organism (bioindicator species or cell line) and have not reported information regarding the quantitative influence of characteristics other than composition or size. In this work, we developed a unified QSTR-perturbation model to simultaneously probe ecotoxicity and cytotoxicity of NPs under different experimental conditions, including diverse measures of toxicities, multiple biological targets, compositions, sizes and conditions to measure those sizes, shapes, times during which the biological targets were exposed to NPs, and coating agents. The model was created from 36488 cases (NP-NP pairs) and exhibited accuracies higher than 98% in both training and prediction sets. The model was used to predict toxicities of several NPs that were not included in the original data set. The results of the predictions suggest that the present QSTR-perturbation model can be employed as a highly promising tool for the fast and efficient assessment of ecotoxicity and cytotoxicity of NPs.

Prediction of multi-target networks of neuroprotective compounds with entropy indices and synthesis, assay, and theoretical study of new asymmetric 1,2-rasagiline carbamates.

In a multi-target complex network, the links (L(ij)) represent the interactions between the drug (d(i)) and the target (t(j)), characterized by different experimental measures (K(i), K(m), IC50, etc.) obtained in pharmacological assays under diverse boundary conditions (c(j)). In this work, we handle Shannon entropy measures for developing a model encompassing a multi-target network of neuroprotective/neurotoxic compounds reported in the CHEMBL database. The model predicts correctly >8300 experimental outcomes with Accuracy, Specificity, and Sensitivity above 80%-90% on training and external validation series. Indeed, the model can calculate different outcomes for >30 experimental measures in >400 different experimental protocolsin relation with >150 molecular and cellular targets on 11 different organisms (including human). Hereafter, we reported by the first time the synthesis, characterization, and experimental assays of a new series of chiral 1,2-rasagiline carbamate derivatives not reported in previous works. The experimental tests included: (1) assay in absence of neurotoxic agents; (2) in the presence of glutamate; and (3) in the presence of H2O2. Lastly, we used the new Assessing Links with Moving Averages (ALMA)-entropy model to predict possible outcomes for the new compounds in a high number of pharmacological tests not carried out experimentally.