RESUMEN
Machine learning analysis of neuroimaging data can accurately predict chronological age in healthy people. Deviations from healthy brain ageing have been associated with cognitive impairment and disease. Here we sought to further establish the credentials of 'brain-predicted age' as a biomarker of individual differences in the brain ageing process, using a predictive modelling approach based on deep learning, and specifically convolutional neural networks (CNN), and applied to both pre-processed and raw T1-weighted MRI data. Firstly, we aimed to demonstrate the accuracy of CNN brain-predicted age using a large dataset of healthy adults (N = 2001). Next, we sought to establish the heritability of brain-predicted age using a sample of monozygotic and dizygotic female twins (N = 62). Thirdly, we examined the test-retest and multi-centre reliability of brain-predicted age using two samples (within-scanner N = 20; between-scanner N = 11). CNN brain-predicted ages were generated and compared to a Gaussian Process Regression (GPR) approach, on all datasets. Input data were grey matter (GM) or white matter (WM) volumetric maps generated by Statistical Parametric Mapping (SPM) or raw data. CNN accurately predicted chronological age using GM (correlation between brain-predicted age and chronological age r = 0.96, mean absolute error [MAE] = 4.16 years) and raw (r = 0.94, MAE = 4.65 years) data. This was comparable to GPR brain-predicted age using GM data (r = 0.95, MAE = 4.66 years). Brain-predicted age was a heritable phenotype for all models and input data (h2 ≥ 0.5). Brain-predicted age showed high test-retest reliability (intraclass correlation coefficient [ICC] = 0.90-0.99). Multi-centre reliability was more variable within high ICCs for GM (0.83-0.96) and poor-moderate levels for WM and raw data (0.51-0.77). Brain-predicted age represents an accurate, highly reliable and genetically-influenced phenotype, that has potential to be used as a biomarker of brain ageing. Moreover, age predictions can be accurately generated on raw T1-MRI data, substantially reducing computation time for novel data, bringing the process closer to giving real-time information on brain health in clinical settings.
Asunto(s)
Envejecimiento , Encéfalo/diagnóstico por imagen , Procesamiento de Imagen Asistido por Computador/métodos , Aprendizaje Automático , Redes Neurales de la Computación , Adolescente , Adulto , Anciano , Anciano de 80 o más Años , Envejecimiento/patología , Encéfalo/patología , Femenino , Humanos , Imagen por Resonancia Magnética/métodos , Masculino , Persona de Mediana Edad , Fenotipo , Adulto JovenRESUMEN
The quest for small drug-like compounds that selectively inhibit the function of biological targets has always been a major focus in the pharmaceutical industry and in academia as well. High-throughput screening of compound libraries requires time, cost and resources. Therefore, the use of alternative methods is necessary for facilitating lead discovery. Computational techniques that dock small molecules into macromolecular targets and predict the affinity and activity of the small molecule are widely used in drug design and discovery, and have become an integral part of the industrial and academic research. In this review, we present an overview of some state-of-the-art technologies in modern drug design that have been developed for expediting the search for novel drug candidates.
Asunto(s)
Diseño Asistido por Computadora , Diseño de FármacosRESUMEN
We propose a non-parametric regression methodology, Random Forests on Distance Matrices (RFDM), for detecting genetic variants associated to quantitative phenotypes, obtained using neuroimaging techniques, representing the human brain's structure or function. RFDM, which is an extension of decision forests, requires a distance matrix as the response that encodes all pair-wise phenotypic distances in the random sample. We discuss ways to learn such distances directly from the data using manifold learning techniques, and how to define such distances when the phenotypes are non-vectorial objects such as brain connectivity networks. We also describe an extension of RFDM to detect espistatic effects while keeping the computational complexity low. Extensive simulation results and an application to an imaging genetics study of Alzheimer's Disease are presented and discussed.
Asunto(s)
Interpretación Estadística de Datos , Modelos Genéticos , Neuroimagen , Algoritmos , Enfermedad de Alzheimer/genética , Enfermedad de Alzheimer/fisiopatología , Inteligencia Artificial , Encéfalo/patología , Encéfalo/fisiopatología , Estudios de Casos y Controles , Simulación por Computador , Árboles de Decisión , Epistasis Genética , Estudios de Asociación Genética , Humanos , Tamaño de los Órganos/genética , Fenotipo , Polimorfismo de Nucleótido Simple , Curva ROCRESUMEN
BACKGROUND: Liquid Chromatography-Mass Spectrometry (LC-MS) is a commonly used technique to resolve complex protein mixtures. Visualization of large data sets produced from LC-MS, namely the chromatogram and the mass spectra that correspond to its compounds is the focus of this work. RESULTS: The in-house developed 'Brukin2D' software, built in Matlab 7.4, which is presented here, uses the compound data that are exported from the Bruker 'DataAnalysis' program, and depicts the mean mass spectra of all the chromatogram compounds from one LC-MS run, in one 2D contour/density plot. Two contour plots from different chromatograph runs can then be viewed in the same window and automatically compared, in order to find their similarities and differences. The results of the comparison can be examined through detailed mass quantification tables, while chromatogram compound statistics are also calculated during the procedure. CONCLUSION: 'Brukin2D' provides a user-friendly platform for quick, easy and integrated view of complex LC-MS data. The software is available at http://www.bioacademy.gr/bioinformatics/Brukin2d/index.html.
Asunto(s)
Cromatografía Liquida , Espectrometría de Masas , Proteómica/métodos , Programas Informáticos , Bases de Datos de Proteínas , Proteínas/análisis , Análisis de Secuencia de Proteína/métodos , Interfaz Usuario-ComputadorRESUMEN
The human face is a complex trait under strong genetic control, as evidenced by the striking visual similarity between twins. Nevertheless, heritability estimates of facial traits have often been surprisingly low or difficult to replicate. Furthermore, the construction of facial phenotypes that correspond to naturally perceived facial features remains largely a mystery. We present here a large-scale heritability study of face geometry that aims to address these issues. High-resolution, three-dimensional facial models have been acquired on a cohort of 952 twins recruited from the TwinsUK registry, and processed through a novel landmarking workflow, GESSA (Geodesic Ensemble Surface Sampling Algorithm). The algorithm places thousands of landmarks throughout the facial surface and automatically establishes point-wise correspondence across faces. These landmarks enabled us to intuitively characterize facial geometry at a fine level of detail through curvature measurements, yielding accurate heritability maps of the human face (www.heritabilitymaps.info).