… ( f k , q k , a k ) } k = 1 to K ⁠, where f k is the convolution filter size, q k is the number of
convolutional filters and a k is … ( f k , q k , a k ) (see Section 2 for explanation of notation). We drop a …

Motivation Protein solubility can be a decisive factor in both research and production efficiency,
and in silico sequence-based predictors that can accurately estimate solubility outcomes …

… The feature representations learnt by our model, such as k-mer information and frequent sets
of amino acid k-mers help in identifying discriminative features for predicting which proteins …

… where k represents a node in the regression tree, |$w^{t}_{jk}$|⁠, |$w^{t}_{jkl}$| and |$w^{t}_{jkr}$|
correspond to number of samples in node k, the left branch of k and right branch of k …

Background Disparities in the genetic risk of cancer among various ancestry groups and
populations remain poorly defined. This challenge is even more acute for Middle Eastern …

… These features can be associated with the frequencies of k-mers and sets of k-mers of
different lengths. However, it is not straightforward to pinpoint what are the specific k-mers in a …

… Khalid Kunji is a software engineer at QCRI with a background in biophysics and mathematics.
His work includes protein property prediction, family-based imputation and other work in …

… modules recovered by the top K methods. Given the top K methods, we considered the set
… From the set of trait-associated modules discovered by the top K methods, we thus derived …

… The authors also thank Yusef Kunji for valuable discussions and comments on biochemical
pathways and gene function and Fayaz Mir for the help with sample acquisition in QCBio. …

Genotype imputation is widely used in genome-wide association studies to boost variant
density, allowing increased power in association testing. Many studies currently include …