Search

[Display omitted]

ABSTRACTGenetic Programming (GP) is a technique which is able to solve different problems through the evolution of mathematical expressions. However, in order to be applied, its tendency to overfit the data is one of its main issues. The use of a validation dataset is a common alternative to prevent overfitting in many Machine Learning (ML) techniques, including GP. But, there is one key point which differentiates GP and other ML techniques: instead of training a single model, GP evolves a population of models. Therefore, the use of the validation dataset has several possibilities because any of those evolved models could be evaluated. This work explores the possibility of using the validation dataset not only on the training-best individual but also in a subset with the training-best individuals of the population. The study has been conducted with 5 well-known databases performing regression or classification tasks. In most of the cases, the results of the study point out to an improvement when the validation dataset is used on a subset of the population instead of only on the training-best individual, which also induces a reduction on the number of nodes and, consequently, a lower complexity on the expressions.

Microemulsions combine the advantages of emulsions with those of nanocarriers, overcoming the stability problems of the former and providing facile scalable systems with compartments adequate for high drug loadings. Recently, microemulsions are gaining attention in the formulation of anticancer drugs not only for topical treatment, but also for systemic delivery as well as for the development of theranostic systems. The aim of this paper is two-fold. First, an updated review about general features, preparation, characterization and pharmaceutical applications, with a special focus on colorectal cancer, is provided. Second, a case study of formulation of methotrexate in microemulsions is presented. Various essential oils (menthol, trans-anethole, α-tocopherol) and surfactants (TPGS-1000, Maxemul 6112, Noigen RN-20) were investigated for the preparation of o/w microemulsions for the delivery of methotrexate, and the ability of methotrexate-loaded microemulsions to inhibit cancer cell growth was then evaluated. Disregarding the surfactants used, menthol and trans-anethole led to cytotoxic microemulsions, whereas α-tocopherol based-formulations induced cell proliferation. These findings highlight the role that the oily component may play in the efficacy and safety of the microemulsions.

We can use Artificial Neural Networks (ANNs) and graph Topological Indices (TIs) to seek structure-property relationship. Balabans’ J index is one of the classic TIs for chemo-informatics studies. We used here Markov chains to generalize the J index and apply it to bioinformatics, systems biology, and social sciences. We seek new ANN models to show the discrimination power of the new indices at node level in three proof-of-concept experiments. First, we calculated more than 1,000,000 values of the new Balaban-Markov centralities Jk(i) and other indices for all nodes in >100 complex networks. In the three experiments, we found new MIANN models with >80% of Specificity (Sp) and Sensitivity (Sn) in train and validation series for Metabolic Reactions of Networks (MRNs) for 42 organisms (bacteria, yeast, nematode and plants), 73 Biological Interaction Webs or Networks (BINs), and 43 sub-networks of U.S. Supreme court citations in different decades from 1791 to 2005. This work may open a new route for the application of TIs to unravel hidden structure-property relationships in complex bio-molecular, ecological, and social networks.

Complex systems and networks appear in almost all areas of reality. We find then from proteins residue networks to Protein Interaction Networks (PINs). Chemical reactions form Metabolic Reactions Networks (MRNs) in living beings or Atmospheric reaction networks in planets and moons. Network of neurons appear in the worm C. elegans, in Human brain connectome, or in Artificial Neural Networks (ANNs). Infection spreading networks exist for contagious outbreaks networks in humans and in malware epidemiology for infection with viral software in internet or wireless networks. Social-legal networks with different rules evolved from swarm intelligence, to hunter-gathered societies, or citation networks of U.S. Supreme Court. In all these cases, we can see the same question. Can we predict the links based on structural information? We propose to solve the problem using Quantitative Structure-Property Relationship (QSPR) techniques commonly used in chemo-informatics. In so doing, we need software able to transform all types of networks/graphs like drug structure, drug-target interactions, protein structure, protein interactions, metabolic reactions, brain connectome, or social networks into numerical parameters. Consequently, we need to process in alignment-free mode multitarget, multiscale, and multiplexing, information. Later, we have to seek the QSPR model with Machine Learning techniques. MI-NODES is this type of software. Here we review the evolution of the software from chemoinformatics to bioinformatics and systems biology. This is an effort to develop a universal tool to study structure-property relationships in complex systems.

The nucleotide binding proteins are involved in many important cellular processes, such as transmission of genetic information or energy transfer and storage. Therefore, the screening of new peptides for this biological function is an important research topic. The current study proposes a mixed methodology to obtain the first classification model that is able to predict new nucleotide binding peptides, using only the amino acid sequence. Thus, the methodology uses a Star graph molecular descriptor of the peptide sequences and the Machine Learning technique for the best classifier. The best model represents a Random Forest classifier based on two features of the embedded and non‐embedded graphs. The performance of the model is excellent, considering similar models in the field, with an Area Under the Receiver Operating Characteristic Curve (AUROC) value of 0.938 and true positive rate (TPR) of 0.886 (test subset). The prediction of new nucleotide binding peptides with this model could be useful for drug target studies in drug development.

The molecular information encoding into molecular descriptors is the first step into in silico Chemoinformatics methods in Drug Design. The Machine Learning methods are a complex solution to find prediction models for specific biological properties of molecules. These models connect the molecular structure information such as atom connectivity (molecular graphs) or physical-chemical properties of an atom/group of atoms to the molecular activity (Quantitative Structure - Activity Relationship, QSAR). Due to the complexity of the proteins, the prediction of their activity is a complicated task and the interpretation of the models is more difficult. The current review presents a series of 11 prediction models for proteins, implemented as free Web tools on an Artificial Intelligence Model Server in Biosciences, Bio-AIMS (http://bio-aims.udc.es/TargetPred.php). Six tools predict protein activity, two models evaluate drug - protein target interactions and the other three calculate protein - protein interactions. The input information is based on the protein 3D structure for nine models, 1D peptide amino acid sequence for three tools and drug SMILES formulas for two servers. The molecular graph descriptor-based Machine Learning models could be useful tools for in silico screening of new peptides/proteins as future drug targets for specific treatments.

Lectins (Ls) play an important role in many diseases such as different types of cancer, parasitic infections and other diseases. Interestingly, the Protein Data Bank (PDB) contains +3000 protein 3D structures with unknown function. Thus, we can in principle, discover new Ls mining non‐annotated structures from PDB or other sources. However, there are no general models to predict new biologically relevant Ls based on 3D chemical structures. We used the MARCH‐INSIDE software to calculate the Markov‐Shannon 3D electrostatic entropy parameters for the complex networks of protein structure of 2200 different protein 3D structures, including 1200 Ls. We have performed a Linear Discriminant Analysis (LDA) using these parameters as inputs in order to seek a new Quantitative Structure‐Activity Relationship (QSAR) model, which is able to discriminate 3D structure of Ls from other proteins. We implemented this predictor in the web server named LECTINPred, freely available at http://bio‐aims.udc.es/LECTINPred.php. This web server showed the following goodness‐of‐fit statistics: Sensitivity=96.7 % (for Ls), Specificity=87.6 % (non‐active proteins), and Accuracy=92.5 % (for all proteins), considering altogether both the training and external prediction series. In mode 2, users can carry out an automatic retrieval of protein structures from PDB. We illustrated the use of this server, in operation mode 1, performing a data mining of PDB. We predicted Ls scores for +2000 proteins with unknown function and selected the top‐scored ones as possible lectins. In operation mode 2, LECTINPred can also upload 3D structural models generated with structure‐prediction tools like LOMETS or PHYRE2. The new Ls are expected to be of relevance as cancer biomarkers or useful in parasite vaccine design.

There are several different types of medical imaging modalities, among others magnetic resonance imaging (MRI), positron emission tomography (PET), ultrasound, computed tomography (CT) or two-dimensional electrophoresis images (2D-electrophoresis). The number of images is increasing rapidly and the development of automatic image processing systems is necessary in order to aid in diagnostic decisions and therapy assessments. One of the most important features in an image is texture, thus it is one of the central concepts in computer vision and should always be taken into account as an innate property. There are various methods of extracting textural features from images; this work considers statistical methods for texture analysis. Those methods analyze the spatial distribution of gray values by computing local features. Depending on the number of pixels, statistical methods can be classified into first- (one pixel), second- (two pixels) and high-order (three or more pixels). Second- and high-order statistics estimate properties of two or more pixel values occurring at specific locations relative to each other. This paper is focused on the high-order statistics texture analysis of CT, MRI, PET and 2D-electrophoresis images.

The study of complex systems such as proteins/DNA/RNA or dynamics of tax law systems can be carried out with the complex network theory. This allows the numerical quantification of the significant information contained by the sequences of amino acids, nucleotides or types of tax laws. In this paper we describe S2SNet, a new Python tool with a graphical user interface that can transform any sequence of characters or numbers into series of invariant star network topological indices. The application is based on Python reusable processing procedures that perform different functions such as reading sequence data, transforming numerical series into character sequences, changing letter codification of strings and drawing the star networks of each sequence using Graphviz package as graphical back-end. S2SNet was previously used to obtain classification models for natural/random proteins, breast/colon/prostate cancer-related proteins, DNA sequences of mycobacterial promoters and for early detection of diseases and drug-induced toxicities using the blood serum proteome mass spectrum. In order to show the extended practical potential of S2SNet, this work presents several examples of application for proteins, DNA/RNA, blood proteome mass spectra and time evolution of the financial law recurrence. The obtained topological indices can be used to characterize systems by creating classification models, clustering or pattern search with statistical, Neural Network or Machine Learning methods. The free availability of S2SNet, the flexibility of analyzing diverse systems and the Python portability make it an ideal tool in fields such as Bioinformatics, Proteomics, Genomics, and Biomedicine or Social, Economic and Political Sciences.

In recent years, in the post genomic era, more and more data is being generated by biological high throughput technologies, such as proteomics and transcriptomics. This omics data can be very useful, but the real challenge is to analyze all this data, as a whole, after integrating it. Biomedical data integration enables making queries to different, heterogeneous and distributed biomedical data sources. Data integration solutions can be very useful not only in the context of drug design, but also in biomedical information retrieval, clinical diagnosis, system biology, etc. In this review, we analyze the most common approaches to biomedical data integration, such as federated databases, data warehousing, multi-agent systems and semantic technology, as well as the solutions developed using these approaches in the past few years.

Reducing costs in terms of time, animal sacrifice, and material resources with computational methods has become a promising goal in Medicinal, Biological, Physical and Organic Chemistry. There are many computational techniques that can be used in this sense. In any case, almost all these methods focus on few fundamental aspects including: type (1) methods to quantify the molecular structure, type (2) methods to link the structure with the biological activity, and others. In particular, MARCH-INSIDE (MI), acronym for Markov Chain Invariants for Networks Simulation and Design, is a well-known method for QSAR analysis useful in step (1). In addition, the bio-inspired Artificial-Intelligence (AI) algorithms called Artificial Neural Networks (ANNs) are among the most powerful type (2) methods. We can combine MI with ANNs in order to seek QSAR models, a strategy which is called herein MIANN (MI & ANN models). One of the first applications of the MIANN strategy was in the development of new QSAR models for drug discovery. MIANN strategy has been expanded to the QSAR study of proteins, protein-drug interactions, and protein-protein interaction networks. In this paper, we review for the first time many interesting aspects of the MIANN strategy including theoretical basis, implementation in web servers, and examples of applications in Medicinal and Biological chemistry. We also report new applications of the MIANN strategy in Medicinal chemistry and the first examples in Physical and Organic Chemistry, as well. In so doing, we developed new MIANN models for several self-assembly physicochemical properties of surfactants and large reaction networks in organic synthesis. In some of the new examples we also present experimental results which were not published up to date.

The study of the nervous system of human beings is an arduous task. The reasons are that it is very complex and it is internal to the organism. The nervous system is comprised not only of neuronal networks but also of different types of cells that constitute the glial system. Astrocytes, a type of glial cells, have traditionally been considered as passive, supportive cells. However, through the use of neuroscientific techniques, it has recently been demonstrated that astrocytes are actively involved in the processing and regulation of synaptic information, suggesting that brain function arises from the activity of neuron-glia networks. Also in recent studies employing artificial intelligence (AI) techniques, it has been shown that adding artificial astrocytes to Artificial Neural Networks (ANNs), the effectiveness of such networks in classification tasks is markedly improved. At present, the actual impact of astrocytes in neural network function is largely unknown. Therefore, our group is placing increasing emphasis on the study of the influence that astrocytes may have on brain information processing using a rather different perspective based on the use of multielectrode arrays (MEAs). This represents a hybrid approach given that it combines a biological component (cultured cells), hardware technology (MEAs), and AI (computer simulations based on AI techniques to control the system). With this in mind, the objective of this paper is to present a review of the state of the art in the use of MEAs containing nerve cells. This review is intended as a preliminary theoretical analysis on the suitability of these devices to achieve the aforementioned future goal of fusing bioinformatics, micro/nano-technologies, and AI techniques to study these complex systems.

Sensitivity improvement in molecular genetic analysis has led to increased detection of novel sequence variants of unknown clinical significance in disease related genes. These unclassified variants (UVs) can often induce pathogenesis by mutating the protein product of the gene. However, they can also manifest non-pathogenic or neutral effects, coding for amino acid changes which do not significantly affect the protein product. Diagnostic laboratories have great difficulty to identify whether an UV is pathogenic or not. Significant characterization of such variants represents a major challenge for medical management of patients in whom they are identified. Functional assays may help to prove whether an UV cause pathogenicity, but these analyses are tedious and laborious. Conversely, in silico prediction tools are very useful to perform a fast bioinformatics analysis which can predict the pathogenicity of a variant based on the change to an amino acid. Despite the amount of in silico tools, only a small number of these are regularly used by genetic testing laboratories. Practice guidelines at the Clinical Molecular Genetics Society for analysis of UVs (UK CMGS UV guidelines) recommend the use of AGVGD, SIFT and Polyphen, but it is unknown whether these are the most useful methods. The aim of the present study was the ability assessment of several in silico bioinformatics tools to accurately predict both pathogenic and neutral missense variants.

There is a need for the study of complex diseases due to their important impact on our society. One of the solutions involves the theoretical methods which are fast and efficient tools that can lead to the discovery of new active drugs specially designed for these diseases. The Quantitative Structure - Activity Relationship models (QSAR) and the complex network theory become important solutions for screening and designing efficient pharmaceuticals by coding the chemical information of the molecules into molecular descriptors. This review presents the most recent studies on drug discovery and design using QSAR of several complex diseases in the fields of Neurology, Cardiology and Oncology.

Colorectal cancer is one of the most frequent types of cancer in the world and generates important social impact. The understanding of the specific metabolism of this disease and the transformations of the specific drugs will allow finding effective prevention, diagnosis and treatment of the colorectal cancer. All the terms that describe the drug metabolism contribute to the construction of ontology in order to help scientists to link the correlated information and to find the most useful data about this topic. The molecular components involved in this metabolism are included in complex network such as metabolic pathways in order to describe all the molecular interactions in the colorectal cancer. The graphical method of processing biological information such as graphs and complex networks leads to the numerical characterization of the colorectal cancer drug metabolic network by using invariant values named topological indices. Thus, this method can help scientists to study the most important elements in the metabolic pathways and the dynamics of the networks during mutations, denaturation or evolution for any type of disease. This review presents the last studies regarding ontology and complex networks of the colorectal cancer drug metabolism and a basic topology characterization of the drug metabolic process subontology from the Gene Ontology.

Nowadays, medical practice needs, at the patient Point-of-Care (POC), personalised knowledge adjustable in each moment to the clinical needs of each patient, in order to provide support to decision-making processes, taking into account personalised information. To achieve this, adapting the hospital information systems is necessary. Thus, there is a need of computational developments capable of retrieving and integrating the large amount of biomedical information available today, managing the complexity and diversity of these systems. Hence, this paper describes a prototype which retrieves biomedical information from different sources, manages it to improve the results obtained and to reduce response time and, finally, integrates it so that it is useful for the clinician, providing all the information available about the patient at the POC. Moreover, it also uses tools which allow medical staff to communicate and share knowledge.

The impact of cancer in the society has created the necessity of new and faster theoretical models that may allow earlier cancer detection. The present review gives the prediction of cancer by using the star graphs of the protein sequences and proteome mass spectra by building a Quantitative Protein - Disease Relationships (QPDRs), similar to Quantitative Structure Activity Relationship (QSAR) models. The nodes of these star graphs are represented by the amino acids of each protein or by the amplitudes of the mass spectra signals and the edged are the geometric and/or functional relationships between the nodes. The star graphs can be numerically described by the invariant values named topological indices (TIs). The transformation of the star graphs (graphical representation) of proteins into TIs (numbers) facilitates the manipulation of protein information and the search for structure-function relationships in Proteomics. The advantages of this method include simplicity, fast calculations and free resources such as S2SNet and MARCH-INSIDE tools. Thus, this ideal theoretical scheme can be easily extended to other types of diseases or even other fields, such as Genomics or Systems Biology.