Scaffold proteins drive liquid-liquid phase separation (LLPS) to form biomolecular condensates and organize various biochemical reactions in cells. Dysregulation of scaffolds can lead to aberrant condensate assembly and various complex diseases. However, bioinformatics predictors dedicated to scaffolds are still lacking and their development suffers from an extreme imbalance between limited experimentally identified scaffolds and unlabeled candidates. Here, using the joint distribution of hybrid multimodal features, we implemented a positive unlabeled (PU) learning-based framework named PULPS that combined ProbTagging and penalty logistic regression (PLR) to profile the propensity of scaffolds. PULPS achieved the best AUC of 0.8353 and showed an area under the lift curve (AUL) of 0.8339 as an estimation of true performance. Upon reviewing recent experimentally verified scaffolds, we performed a partial recovery with 2.85% increase in AUL from 0.8339 to 0.8577. In comparison, PULPS showed a 45.7% improvement in AUL compared with PLR, whereas 8.2% superiority over other existing tools. Our study first proved that PU learning is more suitable for scaffold prediction and demonstrated the widespread existence of phase separation states. This profile also uncovered potential scaffolds that co-drive LLPS in the human proteome and generated candidates for further experiments. PULPS is free for academic research at http://pulps.zbiolab.cn.

MOTIVATION: Biological and cellular systems are often modeled as graphs in which vertices represent objects of interest (genes, proteins and drugs) and edges represent relational ties between these objects (binds-to, interacts-with and regulates). This approach has been highly successful owing to the theory, methodology and software that support analysis and learning on graphs. Graphs, however, suffer from information loss when modeling physical systems due to their inability to accurately represent multiobject relationships. Hypergraphs, a generalization of graphs, provide a framework to mitigate information loss and unify disparate graph-based methodologies. RESULTS: We present a hypergraph-based approach for modeling biological systems and formulate vertex classification, edge classification and link prediction problems on (hyper)graphs as instances of vertex classification on (extended, dual) hypergraphs. We then introduce a novel kernel method on vertex- and edge-labeled (colored) hypergraphs for analysis and learning. The method is based on exact and inexact (via hypergraph edit distances) enumeration of hypergraphlets; i.e. small hypergraphs rooted at a vertex of interest. We empirically evaluate this method on fifteen biological networks and show its potential use in a positive-unlabeled setting to estimate the interactome sizes in various species. AVAILABILITY AND IMPLEMENTATION: https://github.com/jlugomar/hypergraphlet-kernels. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Machine learning methods are used to discover complex nonlinear relationships in biological and medical data. However, sophisticated learning models are computationally unfeasible for data with millions of features. Here, we introduce the first feature selection method for nonlinear learning problems that can scale up to large, ultra-high dimensional biological data. More specifically, we scale up the novel Hilbert-Schmidt Independence Criterion Lasso (HSIC Lasso) to handle millions of features with tens of thousand samples. The proposed method is guaranteed to find an optimal subset of maximally predictive features with minimal redundancy, yielding higher predictive power and improved interpretability. Its effectiveness is demonstrated through applications to classify phenotypes based on module expression in human prostate cancer patients and to detect enzymes among protein structures. We achieve high accuracy with as few as 20 out of one million features-a dimensionality reduction of 99.998 percent. Our algorithm can be implemented on commodity cloud computing platforms. The dramatic reduction of features may lead to the ubiquitous deployment of sophisticated prediction models in mobile health care applications.

Elucidating the precise molecular events altered by disease-causing genetic variants represents a major challenge in translational bioinformatics. To this end, many studies have investigated the structural and functional impact of amino acid substitutions. Most of these studies were however limited in scope to either individual molecular functions or were concerned with functional effects (e.g. deleterious vs. neutral) without specifically considering possible molecular alterations. The recent growth of structural, molecular and genetic data presents an opportunity for more comprehensive studies to consider the structural environment of a residue of interest, to hypothesize specific molecular effects of sequence variants and to statistically associate these effects with genetic disease. In this study, we analyzed data sets of disease-causing and putatively neutral human variants mapped to protein 3D structures as part of a systematic study of the loss and gain of various types of functional attribute potentially underlying pathogenic molecular alterations. We first propose a formal model to assess probabilistically function-impacting variants. We then develop an array of structure-based functional residue predictors, evaluate their performance, and use them to quantify the impact of disease-causing amino acid substitutions on catalytic activity, metal binding, macromolecular binding, ligand binding, allosteric regulation and post-translational modifications. We show that our methodology generates actionable biological hypotheses for up to 41% of disease-causing genetic variants mapped to protein structures suggesting that it can be reliably used to guide experimental validation. Our results suggest that a significant fraction of disease-causing human variants mapping to protein structures are function-altering both in the presence and absence of stability disruption.

Current sequencing methods produce large amounts of data, but genome assemblies based on these data are often woefully incomplete. These incomplete and error-filled assemblies result in many annotation errors, especially in the number of genes present in a genome. In this paper we investigate the magnitude of the problem, both in terms of total gene number and the number of copies of genes in specific families. To do this, we compare multiple draft assemblies against higher-quality versions of the same genomes, using several new assemblies of the chicken genome based on both traditional and next-generation sequencing technologies, as well as published draft assemblies of chimpanzee. We find that upwards of 40% of all gene families are inferred to have the wrong number of genes in draft assemblies, and that these incorrect assemblies both add and subtract genes. Using simulated genome assemblies of Drosophila melanogaster, we find that the major cause of increased gene numbers in draft genomes is the fragmentation of genes onto multiple individual contigs. Finally, we demonstrate the usefulness of RNA-Seq in improving the gene annotation of draft assemblies, largely by connecting genes that have been fragmented in the assembly process.

Growing transistor counts, limited power budgets, and the breakdown of voltage scaling are currently conspiring to create a utilization wall that limits the fraction of a chip that can run at full speed at one time. In this regime, specialized, energy-efficient processors can increase parallelism by reducing the per-computation power requirements and allowing more computations to execute under the same power budget. To pursue this goal, this paper introduces conservation cores. Conservation cores, or c-cores, are specialized processors that focus on reducing energy and energy-delay instead of increasing performance. This focus on energy makes c-cores an excellent match for many applications that would be poor candidates for hardware acceleration (e.g., irregular integer codes). We present a toolchain for automatically synthesizing c-cores from application source code and demonstrate that they can significantly reduce energy and energy-delay for a wide range of applications. The c-cores support patching, a form of targeted reconfigurability, that allows them to adapt to new versions of the software they target. Our results show that conservation cores can reduce energy consumption by up to 16.0x for functions and by up to 2.1x for whole applications, while patching can extend the useful lifetime of individual c-cores to match that of conventional processors.