MOTIVATION: Systematic analysis of connection between proteins, their cellular function and phenotypic manifestations in disease is a central problem of biological and clinical research. The solution to this problem requires the development of new approaches to link the rapidly growing dataset of gene-disease associations with the many complex and overlapping phenotypes of human disease. RESULTS: We analyze genetic skin disorders and suggest a manually designed set of elementary phenotypes whose combinations define diseases as points in a multidimensional space, providing a basis for phenotypic disease clustering. Placing the known gene-disease associations in the context of this space reveals new patterns that suggest previously unknown functional links between proteins, signaling pathways and disease phenotypes. For example, analysis of telangiectasias (spider vein diseases) reveals a previously unrecognized interplay between the TGF-beta signaling pathway and pentose phosphate pathway. This interaction may mediate glucose-dependent regulation of TGF-beta signaling, providing a clue to the known association between angiopathies and diabetes and implying new gene candidates for mutational analysis and drug targeting.

Mole pattern changes are important cues in detecting melanoma at an early stage. As a first step to automatically register mole pattern changes from skin images, this paper presents a framework to detect and label moles on skin images in the presence of clutter, occlusions, and varying imaging conditions. The input image is processed with cascaded blocks to successively discard non-mole pixels. Our method first searches the entire input image for skin regions using a non-parametric skin detection scheme, and the detected skin regions are further processed using a difference of Gaussian (DoG) filter to find possible mole candidates of varying sizes. Mole candidates are classified as moles in the final stage using a trained support vector machine. To increase the mole classification accuracy, hair is removed if present on the skin image using steerable filters and a graphical model. The performance of the designed system is evaluated with 28 test images, and the experimental results demonstrate the effectiveness of the proposed mole localization scheme.