User-managed-events is a popular feature on social networks. Take Facebook Events as an example: over 135 million events were created in 2015 and over 550 million people use events each month. In this work, we consider the heavy sparseness in both user and event feedback history caused by short lifespans (transiency) of events and user participation patterns in a production event system. We propose to solve the resulting cold-start problems by introducing a joint representation model to project users and events into the same latent space. Our model based on parallel Convolutional Neural Networks captures semantic meaning in event text and also utilizes heterogeneous user knowledge available in the social network. By feeding the model output as user and event representation into a combiner prediction model, we show that our representation model improves the prediction accuracy over existing techniques (+6% AUC lift). Our method provides a generic way to match heterogeneous information from different domains and applies to a wide range of applications in social networks.

SUMMARY: Although the 1000 Genomes haplotypes are the most commonly used reference panel for imputation, medical sequencing projects are generating large alternate sets of sequenced samples. Imputation in African Americans using 3384 haplotypes from the Exome Sequencing Project, compared with 2184 haplotypes from 1000 Genomes Project, increased effective sample size by 8.3-11.4% for coding variants with minor allele frequency <1%. No loss of imputation quality was observed using a panel built from phenotypic extremes. We recommend using haplotypes from Exome Sequencing Project alone or concatenation of the two panels over quality score-based post-imputation selection or IMPUTE2's two-panel combination. CONTACT: [email protected]. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Genotype imputation has become an indispensible step in genome-wide association studies (GWAS). Imputation accuracy, directly influencing downstream analysis, has shown to be improved using re-sequencing-based reference panels; however, this comes at the cost of high computational burden due to the huge number of potentially imputable markers (tens of millions) discovered through sequencing a large number of individuals. Therefore, there is an increasing need for access to imputation quality information without actually conducting imputation. To facilitate this process, we have established a publicly available SNP and indel imputability database, aiming to provide direct access to imputation accuracy information for markers identified by the 1000 Genomes Project across four major populations and covering multiple GWAS genotyping platforms. RESULTS: SNP and indel imputability information can be retrieved through a user-friendly interface by providing the ID(s) of the desired variant(s) or by specifying the desired genomic region. The query results can be refined by selecting relevant GWAS genotyping platform(s). This is the first database providing variant imputability information specific to each continental group and to each genotyping platform. In Filipino individuals from the Cebu Longitudinal Health and Nutrition Survey, our database can achieve an area under the receiver-operating characteristic curve of 0.97, 0.91, 0.88 and 0.79 for markers with minor allele frequency >5%, 3-5%, 1-3% and 0.5-1%, respectively. Specifically, by filtering out 48.6% of markers (corresponding to a reduction of up to 48.6% in computational costs for actual imputation) based on the imputability information in our database, we can remove 77%, 58%, 51% and 42% of the poorly imputed markers at the cost of only 0.3%, 0.8%, 1.5% and 4.6% of the well-imputed markers with minor allele frequency >5%, 3-5%, 1-3% and 0.5-1%, respectively. AVAILABILITY: http://www.unc.edu/∼yunmli/imputability.html

Recent studies [1] -- [5] have suggested using constraints in the form of relative distance comparisons to represent domain knowledge: d(a, b)

Recent studies have suggested using relative distance comparisons as constraints to represent domain knowledge. A natural extension to relative comparisons is the combination of two comparisons defined on the same set of three instances. Constraints in this form, termed Relative Constraints, provide a unified knowledge representation for both partitional and hierarchical clusterings. But many key properties of relative constraints remain unknown. In this paper, we answer the following important questions that enable the broader application of relative constraints in general clustering problems: " Feasibility: Does there exist a clustering that satisfies a given set of relative constraints? (consistency of constraints) "Completeness: Given a set of consistent relative constraints, how can one derive a complete clustering without running into dead-ends? " Informativeness: How can one extract the most informative relative constraints from given knowledge sources? We show that any hierarchical domain knowledge can be easily represented by relative constraints. We further present a hierarchical algorithm that finds a clustering satisfying all given constraints in polynomial time. Experiments showed that our algorithm achieves significantly higher accuracy than the existing metric learning approach based on relative comparisons.

MOTIVATION: High-density SNP data of model animal resources provides opportunities for fine-resolution genetic variation studies. These genetic resources are generated through a variety of breeding schemes that involve multiple generations of matings derived from a set of founder animals. In this article, we investigate the problem of inferring the most probable ancestry of resulting genotypes, given a set of founder genotypes. Due to computational difficulty, existing methods either handle only small pedigree data or disregard the pedigree structure. However, large pedigrees of model animal resources often contain repetitive substructures that can be utilized in accelerating computation. RESULTS: We present an accurate and efficient method that can accept complex pedigrees with inbreeding in inferring genome ancestry. Inbreeding is a commonly used process in generating genetically diverse and reproducible animals. It is often carried out for many generations and can account for most of the computational complexity in real-world model animal pedigrees. Our method builds a hidden Markov model that derives the ancestry probabilities through inbreeding process without explicit modeling in every generation. The ancestry inference is accurate and fast, independent of the number of generations, for model animal resources such as the Collaborative Cross (CC). Experiments on both simulated and real CC data demonstrate that our method offers comparable accuracy to those methods that build an explicit model of the entire pedigree, but much better scalability with respect to the pedigree size.