• Publications
  • Influence
Prediction of Interactions Between HIV-1 and Human Proteins by Information Integration
TLDR
We propose a supervised learning framework to predict the global set of interactions between HIV-1 and human host cellular proteins. Expand
  • 126
  • 14
  • PDF
Semi-supervised multi-task learning for predicting interactions between HIV-1 and human proteins
TLDR
We propose a semi-supervised multi-task framework for predicting PPIs from not only labeled, but also partially labeled reference sets. Expand
  • 107
  • 5
  • PDF
Virus interactions with human signal transduction pathways
TLDR
We overlay reported pairwise human-virus PPIs on human signalling pathways and find evidence supporting the hypothesis that viruses often interact with different proteins depending on the targeted pathway. Expand
  • 11
  • 1
  • PDF
Integromic Analysis of Genetic Variation and Gene Expression Identifies Networks for Cardiovascular Disease Phenotypes
Background— Cardiovascular disease (CVD) reflects a highly coordinated complex of traits. Although genome-wide association studies have reported numerous single nucleotide polymorphisms (SNPs) to beExpand
  • 48
  • PDF
Retinal proteins as model systems for membrane protein folding.
Experimental folding studies of membrane proteins are more challenging than water-soluble proteins because of the higher hydrophobicity content of membrane embedded sequences and the need to provideExpand
  • 19
  • PDF
DeepSide: A Deep Learning Framework for Drug Side Effect Prediction
TLDR
A convolutional neural network-based model that uses only SMILES string representation of the drugs achieves the best results and provides 13.0% macro-AUC and 3.1% micro AUC improvements over the state-of-the-art. Expand
  • 6
Comparison of virus interactions with human signal transduction pathways
TLDR
We overlay reported pairwise human, virus PPI on human signaling pathways. Expand
  • 7
An Inference Attack on Genomic Data Using Kinship, Complex Correlations, and Phenotype Information
TLDR
We propose a new unifying framework to quantify the genomic privacy of individuals using all publicly available resources. Expand
  • 14
  • PDF
GLANET: genomic loci annotation and enrichment tool
TLDR
We present GLANET as a comprehensive annotation and enrichment analysis tool which implements a sampling‐based enrichment test that accounts for GC content and/or mappability biases, jointly or separately. Expand
  • 9
A utility maximizing and privacy preserving approach for protecting kinship in genomic databases
TLDR
We define two routes kinship privacy can leak and propose a technique to protect kinships privacy against these risks while maximizing the utility of shared data. Expand
  • 5
  • PDF