RESUMO
Efficient identification of chemical probes for the manipulation and understanding of biological systems demands specificity for target proteins. Computational means to optimize candidate compound selection for experimental selectivity evaluation are being sought. The active learning virtual screening method has demonstrated the ability to efficiently converge on predictive models with reduced datasets, though its applicability domain to probe identification has yet to be determined. In this article, we challenge active learning's ability to predict inhibitory bioactivity profiles of selective compounds when learning from chemogenomic features found in non-selective ligand-target pairs. Comparison of controls versus multiple molecule representations de-convolutes factors contributing to predictive capability. Experiments using the matrix metalloproteinase family demonstrate maximum probe bioactivity prediction achieved from only approximately 20% of non-probe bioactivity; this data volume is consistent with prior chemogenomic active learning studies despite the increased difficulty from chemical biology experimental settings used here. Feature weight analyses are combined with a custom visualization to unambiguously detail how active learning arrives at classification decisions, yielding clarified expectations for chemogenomic modeling. The results influence tactical decisions for computational probe design and discovery.
Assuntos
Descoberta de Drogas , Aprendizado de Máquina , Relação Quantitativa Estrutura-Atividade , Algoritmos , Fenômenos Químicos , Biologia Computacional/métodos , Bases de Dados de Compostos Químicos , Técnicas de Apoio para a Decisão , Árvores de Decisões , Descoberta de Drogas/métodos , Ligantes , Modelos Teóricos , Reprodutibilidade dos TestesRESUMO
Chemogenomics is a comparatively nascent branch dealing with the effects of drugs and chemicals on molecular level systems. With the emergence of this new epoch, the quantity of data sources is also unprecedentedly increasing. Despite having a plethora of a databases, the variation in bioactivity measurement as well as bias toward specific protein studies, varied computational procedures and redundant information make data mining tedious, especially for newcomers in the field. In this chapter, we give an overview of hands-on data collection and domains of applicability from some useful Web-based chemogenomic resources that are accessible with nothing more than a Web browser. This overview can help assist users in acquiring chemogenomic datasets for their project at hand.
Assuntos
Bases de Dados de Compostos Químicos , Bases de Dados Genéticas , Genômica/métodos , Humanos , NavegadorRESUMO
Computational models for predicting the activity of small molecules against targets are now routinely developed and used in academia and industry, partially due to public bioactivity databases. While models based on bigger datasets are the trend, recent studies such as chemogenomic active learning have shown that only a fraction of data is needed for effective models in many cases. In this article, the chemogenomic active learning method is discussed and used to newly analyze public databases containing nuclear hormone receptor and cytochrome P450 enzyme family bioactivity. In addition to existing results on kinases and G-protein coupled receptors, results here demonstrate the active learning methodology's effectiveness on extracting informative ligand-target pairs in sparse data scenarios. Experiments to assess the domain of the applicability demonstrate the influence of ligand profiles of similar targets within the family.
Assuntos
Sistema Enzimático do Citocromo P-450/metabolismo , Aprendizado de Máquina , Receptores Citoplasmáticos e Nucleares/metabolismo , Bibliotecas de Moléculas Pequenas/farmacologia , Algoritmos , Inibidores das Enzimas do Citocromo P-450/química , Inibidores das Enzimas do Citocromo P-450/farmacologia , Sistema Enzimático do Citocromo P-450/química , Bases de Dados Factuais , Humanos , Ligantes , Receptores Citoplasmáticos e Nucleares/antagonistas & inibidores , Receptores Citoplasmáticos e Nucleares/química , Bibliotecas de Moléculas Pequenas/químicaRESUMO
Male-specific region of the human Y chromosome (MSY) comprises 95% of its length that is functionally active. This portion inherits in block from father to male offspring. Most of the genes in the MSY region are involved in male-specific function, such as sex determination and spermatogenesis; also contains genes probably involved in other cellular functions. However, a detailed characterization of numerous MSY-encoded proteins still remains to be done. In this study, 12 uncharacterized proteins of MSY were analyzed through bioinformatics tools for structural and functional characterization. Within these 12 proteins, a total of 55 domains were found, with DnaJ domain signature corresponding to be the highest (11%) followed by both FAD-dependent pyridine nucleotide reductase signature and fumarate lyase superfamily signature (9%). The 3D structures of our selected proteins were built up using homology modeling and the protein threading approaches. These predicted structures confirmed in detail the stereochemistry; indicating reasonably good quality model. Furthermore the predicted functions and the proteins with whom they interact established their biological role and their mechanism of action at molecular level. The results of these structure-functional annotations provide a comprehensive view of the proteins encoded by MSY, which sheds light on their biological functions and molecular mechanisms. The data presented in this study may assist in future prognosis of several human diseases such as Turner syndrome, gonadal sex reversal, spermatogenic failure, and gonadoblastoma.