Summary The topological landscape of molecular or functional interaction networks provides a rich source of information for inferring functional patterns of genes or proteins. However, a pressing yet unsolved challenge is how to combine multiple heterogeneous networks, each having different connectivity patterns, to achieve more accurate inference. Here we describe the Mashup framework for scalable and robust network integration. In Mashup, the diffusion in each network is first analyzed to characterize the topological context of each node. Next, the high-dimensional topological patterns in individual networks are canonically represented using low-dimensional vectors, one per gene or protein. These vectors can then be plugged into off-the-shelf machine learning methods to derive functional insights about genes or proteins. We present tools based on Mashup that achieve state-of-the-art performance in three diverse functional inference tasks: protein function prediction, gene ontology reconstruction, and genetic interaction prediction. Mashup enables deeper insights into the structure of rapidly accumulating, diverse biological network data and can be broadly applied to other network science domains.

Most sequenced genomes are currently stored in strict access-controlled repositories1–3. Free access to these data could improve the power of genome-wide association studies (GWAS) to identify disease-causing genetic variants and may aid in the discovery of new drug targets4,5. However, concerns over genetic data privacy6–9 may deter individuals from contributing their genomes to scientific studies10 and in many cases, prevent researchers from sharing data with the scientific community11. Although several cryptographic techniques for secure data analysis exist12–14, none scales to computationally intensive analyses, such as GWAS. Here we describe an end-to-end protocol for large-scale genome-wide analysis that facilitates quality control and population stratification correction in 9K, 13K, and 23K individuals while maintaining the confidentiality of underlying genotypes and phenotypes. We show the protocol could feasibly scale to a million individuals. This approach may help to make currently restricted data available to the scientific community and could potentially enable ‘secure genome crowdsourcing,’ allowing individuals to contribute their genomes to a study without compromising their privacy.

Motivation: Systematically predicting gene (or protein) function based on molecular interaction networks has become an important tool in refining and enhancing the existing annotation catalogs, such as the Gene Ontology (GO) database. However, functional labels with only a few (<10) annotated genes, which constitute about half of the GO terms in yeast, mouse and human, pose a unique challenge in that any prediction algorithm that independently considers each label faces a paucity of information and thus is prone to capture non-generalizable patterns in the data, resulting in poor predictive performance. There exist a variety of algorithms for function prediction, but none properly address this ‘overfitting’ issue of sparsely annotated functions, or do so in a manner scalable to tens of thousands of functions in the human catalog.Results: We propose a novel function prediction algorithm, clusDCA, which transfers information between similar functional labels to alleviate the overfitting problem for sparsely annotated functions. Our method is scalable to datasets with a large number of annotations. In a cross-validation experiment in yeast, mouse and human, our method greatly outperformed previous state-of-the-art function prediction algorithms in predicting sparsely annotated functions, without sacrificing the performance on labels with sufficient information. Furthermore, we show that our method can accurately predict genes that will be assigned a functional label that has no known annotations, based only on the ontology graph structure and genes associated with other labels, which further suggests that our method effectively utilizes the similarity between gene functions.Availability and implementation: https://github.com/wangshenguiuc/clusDCA.Contact: jianpeng@illinois.eduSupplementary information: Supplementary data are available at Bioinformatics online.

Large-scale single-cell RNA-sequencing (scRNA-seq) studies that profile hundreds of thousands of cells are becoming increasingly common, overwhelming existing analysis pipelines. Here, we describe how to enhance and accelerate single-cell data analysis by summarizing the transcriptomic heterogeneity within a data set using a small subset of cells, which we refer to as a geometric sketch. Our sketches provide more comprehensive visualization of transcriptional diversity, capture rare cell types with high sensitivity, and accurately reveal biological cell types via clustering. Our sketch of umbilical cord blood cells uncovers a rare subpopulation of inflammatory macrophages, which we experimentally validated in vitro. The construction of our sketches is extremely fast, which enabled us to accelerate other crucial resource-intensive tasks such as scRNA-seq data integration. We anticipate that our algorithm will become an 42 in a matter of minutes and with an asymptotic runtime that is close to linear in the size of the data 43 set. We empirically demonstrate that our algorithm produces sketches that more evenly represent 44 the transcriptional space covered by the data. We further show that our sketches enhance and 45 5 Preprint. Work in progress. accelerate downstream analyses by preserving rare cell types, producing visualizations that 46 broadly capture transcriptomic heterogeneity, facilitating the identification of cell types via 47 131 transcriptional variability within a data set, allowing researchers to more easily gain insight into 132 rarer transcriptional states. 133 Rare Cell Types Are Better Preserved Within Geometric Sketches 134 As suggested by the above results, one of the key advantages of our algorithm is that it naturally 135 increases the representation of rare cell types with sufficient transcriptomic heterogeneity in the 136 subsampled data. Using the four data sets mentioned above, which include cell type labels 137 157 clustering algorithm (Blondel et al., 2008). Then, we transferred cluster labels to the rest of the 158 data set via k-nearest-neighbor classification and assessed the agreement between our 159 unsupervised cluster labels and the biological cell type labels provided by the original studies 160

Nonlinear data-visualization methods, such as t-SNE and UMAP, summarize the complex transcriptomic landscape of single cells in 2D or 3D, but they neglect the local density of data points in the original space, often resulting in misleading visualizations where densely populated subsets of cells are given more visual space than warranted by their transcriptional diversity in the dataset. We present den-SNE and densMAP, density-preserving visualization tools based on t-SNE and UMAP, respectively, and demonstrate their ability to accurately incorporate information about transcriptomic variability into the visual interpretation of single-cell RNA-seq data. Applied to recently published datasets, our methods reveal significant changes in transcriptomic variability in a range of biological processes, including heterogeneity in transcriptomic variability of immune cells in blood and tumor, human immune cell specialization, and the developmental trajectory of C. elegans . Our methods are readily applicable to visualizing high-dimensional data in other scientific domains.

Highlights d Method to subsample massive scRNA-seq datasets while preserving rare cell states d Resulting ''sketch'' accelerates clustering, visualization, and integration analyses d Highlighting rare cells helps uncover a rare subtype of inflammatory macrophages d Sketches can boost the utility of single-cell data for labs with limited resources

Complex biological systems have been successfully modeled by biochemical and genetic interaction networks, typically gathered from high-throughput (HTP) data. These networks can be used to infer functional relationships between genes or proteins. Using the intuition that the topological role of a gene in a network relates to its biological function, local or diffusionbased "guilt-by-association" and graph-theoretic methods have had success in inferring gene functions. Here we seek to improve function prediction by integrating diffusion-based methods with a novel dimensionality reduction technique to overcome the incomplete and noisy nature of network data. In this paper, we introduce diffusion component analysis (DCA), a framework that plugs in a diffusion model and learns a low-dimensional vector representation of each node to encode the topological properties of a network. As a proof of concept, we demonstrate DCA's substantial improvement over state-of-the-art diffusion-based approaches in predicting protein function from molecular interaction networks. Moreover, our DCA framework can integrate multiple networks from heterogeneous sources, consisting of genomic information, biochemical experiments and other resources, to even further improve function prediction. Yet another layer of performance gain is achieved by integrating the DCA framework with support vector machines that take our node vector representations as features. Overall, our DCA framework provides a novel representation of nodes in a network that can be used as a plug-in architecture to other machine learning algorithms to decipher topological properties of and obtain novel insights into interactomes. 1 1 This paper was selected for oral presentation at RECOMB 2015 and an abstract is published in the conference proceedings.

While combining data from multiple entities could power life-saving breakthroughs, open sharing of pharmacological data is generally not viable due to data privacy and intellectual property concerns. To this end, we leverage modern cryptographic tools to introduce a computational protocol for securely training a predictive model of drug-target interactions (DTI) on a pooled dataset that overcomes barriers to data sharing by provably ensuring the confidentiality of all underlying drugs, targets, and observed interactions. Our protocol runs within days on a real dataset of more than a million interactions, and is more accurate than state-of-the-art DTI prediction methods. Using our protocol, we discover novel DTI that we experimentally validated via targeted assays. Our work lays a foundation for more effective and cooperative biomedical research.