User profiles for K. Kunji
Khalid KunjiHamad Bin Khalifa University, Qatar Computing Research Institute Verified email at hbku.edu.qa Cited by 770 |
DeepSol: a deep learning framework for sequence-based protein solubility prediction
… ( 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 …
convolutional filters and a k is … ( f k , q k , a k ) (see Section 2 for explanation of notation). We drop a …
PaRSnIP: sequence-based protein solubility prediction using gradient boosting machine
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 …
and in silico sequence-based predictors that can accurately estimate solubility outcomes …
DeepCrystal: a deep learning framework for sequence-based protein crystallization prediction
… 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 …
of amino acid k-mers help in identifying discriminative features for predicting which proteins …
RGBM: regularized gradient boosting machines for identification of the transcriptional regulators of discrete glioma subtypes
… 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 …
correspond to number of samples in node k, the left branch of k and right branch of k …
Genetic predisposition to cancer across people of different ancestries in Qatar: a population-based, cohort study
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 …
populations remain poorly defined. This challenge is even more acute for Middle Eastern …
BCrystal: an interpretable sequence-based protein crystallization predictor
… 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 …
different lengths. However, it is not straightforward to pinpoint what are the specific k-mers in a …
Network-based identification of key master regulators associated with an immune-silent cancer phenotype
… 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 …
His work includes protein property prediction, family-based imputation and other work in …
Open community challenge reveals molecular network modules with key roles in diseases
… 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 …
… From the set of trait-associated modules discovered by the top K methods, we thus derived …
Validation of polygenic risk scores for Coronary Heart Disease in a Middle Eastern Cohort using whole genome sequencing
… 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. …
pathways and gene function and Fayaz Mir for the help with sample acquisition in QCBio. …
Comparison and assessment of family-and population-based genotype imputation methods in large pedigrees
Genotype imputation is widely used in genome-wide association studies to boost variant
density, allowing increased power in association testing. Many studies currently include …
density, allowing increased power in association testing. Many studies currently include …