Search

Rare diseases affect hundreds of millions of people worldwide but are hard to detect since they have extremely low prevalence rates (varying from 1/1,000 to 1/200,000 patients) and are massively underdiagnosed. How do we reliably detect rare diseases with such low prevalence rates? How to further leverage patients with possibly uncertain diagnosis to improve detection? In this paper, we propose a Complementary pattern Augmentation (CONAN) framework for rare disease detection. CONAN combines ideas from both adversarial training and max-margin classification. It first learns self-attentive and hierarchical embedding for patient pattern characterization. Then, we develop a complementary generative adversarial networks (GAN) model to generate candidate positive and negative samples from the uncertain patients by encouraging a max-margin between classes. In addition, CONAN has a disease detector that serves as the discriminator during the adversarial training for identifying rare diseases. We evaluated CONAN on two disease detection tasks. For low prevalence inflammatory bowel disease (IBD) detection, CONAN achieved .96 precision recall area under the curve (PR-AUC) and 50.1% relative improvement over the best baseline. For rare disease idiopathic pulmonary fibrosis (IPF) detection, CONAN achieves .22 PR-AUC with 41.3% relative improvement over the best baseline.

A new catalogue of extrasolar planets is presented by re-analysing a selection of published radial velocity data sets using EXOFIT (Balan & Lahav 2009). All objects are treated on an equal footing within a Bayesian framework, to give orbital parameters for 94 exoplanetary systems. Model selection (between one- and two-planet solutions) is then performed, using both a visual flagging method and a standard chi-square analysis, with agreement between the two methods for 99% of the systems considered. The catalogue is to be made available online, and this 'proof of concept' study may be maintained and extended in the future to incorporate all systems with publicly available radial velocity data, as well as transit and microlensing data.

In their simplest form, proteins essentially comprise unbranched polymer chains formed as a result of chemical bonding that takes place between the amino acid building blocks.

The last two decades have witnessed the continual and concerted effort toward the development of powerful tools which allow DFT calculations to be efficiently performed for systems containing thousands of atoms.

It is quite alarming that several publications exist in the literature raising serious questions about the applicability of DFT techniques to large-scale systems such as water clusters and proteins [1, 2, 3, 4, 5, 6].

Strain induced by antiphase boundaries (APBs) in the Si(111) 2 x 1 surface is investigated using scanning tunneling microscopy (STM), laterally resolved scanning tunneling spectroscopy (STS), and density functional theory (DFT). We determine the structure of all identified APB reconstructions and show that a band shift of states close to the Fermi energy leads to the previously observed electronic contrast. The orientation of the band shift and the observed movement of APBs within the surface are explained by surface strain resulting from the excess free energy of the boundary. We demonstrate that the location of APBs and their associated strain can be precisely manipulated, making them an ideal model system to study and control strain at the atomic scale.