Search

Cancer driver genes, i.e., oncogenes and tumor suppressor genes, are involved in the acquisition of important functions in tumors, providing a selective growth advantage, allowing uncontrolled proliferation and avoiding apoptosis. It is therefore important to identify these driver genes, both for the fundamental understanding of cancer and to help finding new therapeutic targets or biomarkers. Although the most frequently mutated driver genes have been identified, it is believed that many more remain to be discovered, particularly for driver genes specific to some cancer types. In this paper, we propose a new computational method called LOTUS to predict new driver genes. LOTUS is a machine-learning based approach which allows to integrate various types of data in a versatile manner, including information about gene mutations and protein-protein interactions. In addition, LOTUS can predict cancer driver genes in a pan-cancer setting as well as for specific cancer types, using a multitask learning strategy to share information across cancer types. We empirically show that LOTUS outperforms five other state-of-the-art driver gene prediction methods, both in terms of intrinsic consistency and prediction accuracy, and provide predictions of new cancer genes across many cancer types. [ABSTRACT FROM AUTHOR]

With the recent technological developments a vast amount of high-throughput data has been profiled to understand the mechanism of complex diseases. The current bioinformatics challenge is to interpret the data and underlying biology, where efficient algorithms for analyzing heterogeneous high-throughput data using biological networks are becoming increasingly valuable. In this paper, we propose a software package based on the Prize-collecting Steiner Forest graph optimization approach. The PCSF package performs fast and user-friendly network analysis of high-throughput data by mapping the data onto a biological networks such as protein-protein interaction, gene-gene interaction or any other correlation or coexpression based networks. Using the interaction networks as a template, it determines high-confidence subnetworks relevant to the data, which potentially leads to predictions of functional units. It also interactively visualizes the resulting subnetwork with functional enrichment analysis. [ABSTRACT FROM AUTHOR]

Manually curating biomedical knowledge from publications is necessary to build a knowledge based service that provides highly precise and organized information to users. The process of retrieving relevant publications for curation, which is also known as document triage, is usually carried out by querying and reading articles in PubMed. However, this query-based method often obtains unsatisfactory precision and recall on the retrieved results, and it is difficult to manually generate optimal queries. To address this, we propose a machine-learning assisted triage method. We collect previously curated publications from two databases UniProtKB/Swiss-Prot and the NHGRI-EBI GWAS Catalog, and used them as a gold-standard dataset for training deep learning models based on convolutional neural networks. We then use the trained models to classify and rank new publications for curation. For evaluation, we apply our method to the real-world manual curation process of UniProtKB/Swiss-Prot and the GWAS Catalog. We demonstrate that our machine-assisted triage method outperforms the current query-based triage methods, improves efficiency, and enriches curated content. Our method achieves a precision 1.81 and 2.99 times higher than that obtained by the current query-based triage methods of UniProtKB/Swiss-Prot and the GWAS Catalog, respectively, without compromising recall. In fact, our method retrieves many additional relevant publications that the query-based method of UniProtKB/Swiss-Prot could not find. As these results show, our machine learning-based method can make the triage process more efficient and is being implemented in production so that human curators can focus on more challenging tasks to improve the quality of knowledge bases. [ABSTRACT FROM AUTHOR]

Central questions to epigenome evolution include whether interspecies changes of histone modifications are independent of evolutionary changes of DNA, and if there is dependence whether they depend on any specific types of DNA sequence changes. Here, we present a likelihood approach for testing hypotheses on the co-evolution of genome and histone modifications. The gist of this approach is to convert evolutionary biology hypotheses into probabilistic forms, by explicitly expressing the joint probability of multispecies DNA sequences and histone modifications, which we refer to as a class of oint volutionary odel for the enome and the pigenome (JEMGE). JEMGE can be summarized as a mixture model of four components representing four evolutionary hypotheses, namely dependence and independence of interspecies epigenomic variations to underlying sequence substitutions and to underlying sequence insertions and deletions (indels). We implemented a maximum likelihood method to fit the models to the data. Based on comparison of likelihoods, we inferred whether interspecies epigenomic variations depended on substitution or indels in local genomic sequences based on DNase hypersensitivity and spermatid H3K4me3 ChIP-seq data from human and rhesus macaque. Approximately 5.5% of homologous regions in the genomes exhibited H3K4me3 modification in either species, among which approximately 67% homologous regions exhibited local-sequence-dependent interspecies H3K4me3 variations. Substitutions accounted for less local-sequence-dependent H3K4me3 variations than indels. Among transposon-mediated indels, ERV1 insertions and L1 insertions were most strongly associated with H3K4me3 gains and losses, respectively. By initiating probabilistic formulation on the co-evolution of genomes and epigenomes, JEMGE helps to bring evolutionary biology principles to comparative epigenomic studies. [ABSTRACT FROM AUTHOR]

We use reinforcement learning to train an agent for computational RNA design: given a target secondary structure, design a sequence that folds to that structure in silico. Our agent uses a novel graph convolutional architecture allowing a single model to be applied to arbitrary target structures of any length. After training it on randomly generated targets, we test it on the Eterna100 benchmark and find it outperforms all previous algorithms. Analysis of its solutions shows it has successfully learned some advanced strategies identified by players of the game Eterna, allowing it to solve some very difficult structures. On the other hand, it has failed to learn other strategies, possibly because they were not required for the targets in the training set. This suggests the possibility that future improvements to the training protocol may yield further gains in performance. [ABSTRACT FROM AUTHOR]

A common goal in data-analysis is to sift through a large data-matrix and detect any significant submatrices (i.e., biclusters) that have a low numerical rank. We present a simple algorithm for tackling this biclustering problem. Our algorithm accumulates information about 2-by-2 submatrices (i.e., ‘loops’) within the data-matrix, and focuses on rows and columns of the data-matrix that participate in an abundance of low-rank loops. We demonstrate, through analysis and numerical-experiments, that this loop-counting method performs well in a variety of scenarios, outperforming simple spectral methods in many situations of interest. Another important feature of our method is that it can easily be modified to account for aspects of experimental design which commonly arise in practice. For example, our algorithm can be modified to correct for controls, categorical- and continuous-covariates, as well as sparsity within the data. We demonstrate these practical features with two examples; the first drawn from gene-expression analysis and the second drawn from a much larger genome-wide-association-study (GWAS). [ABSTRACT FROM AUTHOR]

Pooled DNA from multiple unknown organisms arises in a variety of contexts, for example microbial samples from ecological or human health research. Determining the composition of pooled samples can be difficult, especially at the scale of modern sequencing data and reference databases. Here we propose a novel method for taxonomic profiling in pooled DNA that combines the speed and low-memory requirements of k-mer based pseudoalignment with a likelihood framework that uses base quality information to better resolve multiply mapped reads. We apply the method to the problem of classifying 16S rRNA reads using a reference database of known organisms, a common challenge in microbiome research. Using simulations, we show the method is accurate across a variety of read lengths, with different length reference sequences, at different sample depths, and when samples contain reads originating from organisms absent from the reference. We also assess performance in real 16S data, where we reanalyze previous genetic association data to show our method discovers a larger number of quantitative trait associations than other widely used methods. We implement our method in the software Karp, for k-mer based analysis of read pools, to provide a novel combination of speed and accuracy that is uniquely suited for enhancing discoveries in microbial studies. [ABSTRACT FROM AUTHOR]

We propose a novel method and software tool, Strawberry, for transcript reconstruction and quantification from RNA-Seq data under the guidance of genome alignment and independent of gene annotation. Strawberry consists of two modules: assembly and quantification. The novelty of Strawberry is that the two modules use different optimization frameworks but utilize the same data graph structure, which allows a highly efficient, expandable and accurate algorithm for dealing large data. The assembly module parses aligned reads into splicing graphs, and uses network flow algorithms to select the most likely transcripts. The quantification module uses a latent class model to assign read counts from the nodes of splicing graphs to transcripts. Strawberry simultaneously estimates the transcript abundances and corrects for sequencing bias through an EM algorithm. Based on simulations, Strawberry outperforms Cufflinks and StringTie in terms of both assembly and quantification accuracies. Under the evaluation of a real data set, the estimated transcript expression by Strawberry has the highest correlation with Nanostring probe counts, an independent experiment measure for transcript expression. Availability: Strawberry is written in C++14, and is available as open source software at under the MIT license. [ABSTRACT FROM AUTHOR]

The adaptation of the CRISPR-Cas9 system as a genome editing technique has generated much excitement in recent years owing to its ability to manipulate targeted genes and genomic regions that are complementary to a programmed single guide RNA (sgRNA). However, the efficacy of a specific sgRNA is not uniquely defined by exact sequence homology to the target site, thus unintended off-targets might additionally be cleaved. Current methods for sgRNA design are mainly concerned with predicting off-targets for a given sgRNA using basic sequence features and employ elementary rules for ranking possible sgRNAs. Here, we introduce CRISTA (CRISPR Target Assessment), a novel algorithm within the machine learning framework that determines the propensity of a genomic site to be cleaved by a given sgRNA. We show that the predictions made with CRISTA are more accurate than other available methodologies. We further demonstrate that the occurrence of bulges is not a rare phenomenon and should be accounted for in the prediction process. Beyond predicting cleavage efficiencies, the learning process provides inferences regarding patterns that underlie the mechanism of action of the CRISPR-Cas9 system. We discover that attributes that describe the spatial structure and rigidity of the entire genomic site as well as those surrounding the PAM region are a major component of the prediction capabilities. [ABSTRACT FROM AUTHOR]

The specificities of transcription factors are most commonly represented with probabilistic models. These models provide a probability for each base occurring at each position within the binding site and the positions are assumed to contribute independently. The model is simple and intuitive and is the basis for many motif discovery algorithms. However, the model also has inherent limitations that prevent it from accurately representing true binding probabilities, especially for the highest affinity sites under conditions of high protein concentration. The limitations are not due to the assumption of independence between positions but rather are caused by the non-linear relationship between binding affinity and binding probability and the fact that independent normalization at each position skews the site probabilities. Generally probabilistic models are reasonably good approximations, but new high-throughput methods allow for biophysical models with increased accuracy that should be used whenever possible. [ABSTRACT FROM AUTHOR]

Target-based screening is one of the major approaches in drug discovery. Besides the intended target, unexpected drug off-target interactions often occur, and many of them have not been recognized and characterized. The off-target interactions can be responsible for either therapeutic or side effects. Thus, identifying the genome-wide off-targets of lead compounds or existing drugs will be critical for designing effective and safe drugs, and providing new opportunities for drug repurposing. Although many computational methods have been developed to predict drug-target interactions, they are either less accurate than the one that we are proposing here or computationally too intensive, thereby limiting their capability for large-scale off-target identification. In addition, the performances of most machine learning based algorithms have been mainly evaluated to predict off-target interactions in the same gene family for hundreds of chemicals. It is not clear how these algorithms perform in terms of detecting off-targets across gene families on a proteome scale. Here, we are presenting a fast and accurate off-target prediction method, REMAP, which is based on a dual regularized one-class collaborative filtering algorithm, to explore continuous chemical space, protein space, and their interactome on a large scale. When tested in a reliable, extensive, and cross-gene family benchmark, REMAP outperforms the state-of-the-art methods. Furthermore, REMAP is highly scalable. It can screen a dataset of 200 thousands chemicals against 20 thousands proteins within 2 hours. Using the reconstructed genome-wide target profile as the fingerprint of a chemical compound, we predicted that seven FDA-approved drugs can be repurposed as novel anti-cancer therapies. The anti-cancer activity of six of them is supported by experimental evidences. Thus, REMAP is a valuable addition to the existing in silico toolbox for drug target identification, drug repurposing, phenotypic screening, and side effect prediction. The software and benchmark are available at . [ABSTRACT FROM AUTHOR]

Analyses of metagenome data (MG) and metatranscriptome data (MT) are often challenged by a paucity of complete reference genome sequences and the uneven/low sequencing depth of the constituent organisms in the microbial community, which respectively limit the power of reference-based alignment and de novo sequence assembly. These limitations make accurate protein family classification and abundance estimation challenging, which in turn hamper downstream analyses such as abundance profiling of metabolic pathways, identification of differentially encoded/expressed genes, and de novo reconstruction of complete gene and protein sequences from the protein family of interest. The profile hidden Markov model (HMM) framework enables the construction of very useful probabilistic models for protein families that allow for accurate modeling of position specific matches, insertions, and deletions. We present a novel homology detection algorithm that integrates banded Viterbi algorithm for profile HMM parsing with an iterative simultaneous alignment and assembly computational framework. The algorithm searches a given profile HMM of a protein family against a database of fragmentary MG/MT sequencing data and simultaneously assembles complete or near-complete gene and protein sequences of the protein family. The resulting program, HMM-GRASPx, demonstrates superior performance in aligning and assembling homologs when benchmarked on both simulated marine MG and real human saliva MG datasets. On real supragingival plaque and stool MG datasets that were generated from healthy individuals, HMM-GRASPx accurately estimates the abundances of the antimicrobial resistance (AMR) gene families and enables accurate characterization of the resistome profiles of these microbial communities. For real human oral microbiome MT datasets, using the HMM-GRASPx estimated transcript abundances significantly improves detection of differentially expressed (DE) genes. Finally, HMM-GRASPx was used to reconstruct comprehensive sets of complete or near-complete protein and nucleotide sequences for the query protein families. HMM-GRASPx is freely available online from . [ABSTRACT FROM AUTHOR]

Sub-cellular localisation of proteins is an essential post-translational regulatory mechanism that can be assayed using high-throughput mass spectrometry (MS). These MS-based spatial proteomics experiments enable us to pinpoint the sub-cellular distribution of thousands of proteins in a specific system under controlled conditions. Recent advances in high-throughput MS methods have yielded a plethora of experimental spatial proteomics data for the cell biology community. Yet, there are many third-party data sources, such as immunofluorescence microscopy or protein annotations and sequences, which represent a rich and vast source of complementary information. We present a unique transfer learning classification framework that utilises a nearest-neighbour or support vector machine system, to integrate heterogeneous data sources to considerably improve on the quantity and quality of sub-cellular protein assignment. We demonstrate the utility of our algorithms through evaluation of five experimental datasets, from four different species in conjunction with four different auxiliary data sources to classify proteins to tens of sub-cellular compartments with high generalisation accuracy. We further apply the method to an experiment on pluripotent mouse embryonic stem cells to classify a set of previously unknown proteins, and validate our findings against a recent high resolution map of the mouse stem cell proteome. The methodology is distributed as part of the open-source Bioconductor suite for spatial proteomics data analysis. [ABSTRACT FROM AUTHOR]

Given sufficient large protein families, and using a global statistical inference approach, it is possible to obtain sufficient accuracy in protein residue contact predictions to predict the structure of many proteins. However, these approaches do not consider the fact that the contacts in a protein are neither randomly, nor independently distributed, but actually follow precise rules governed by the structure of the protein and thus are interdependent. Here, we present PconsC2, a novel method that uses a deep learning approach to identify protein-like contact patterns to improve contact predictions. A substantial enhancement can be seen for all contacts independently on the number of aligned sequences, residue separation or secondary structure type, but is largest for β-sheet containing proteins. In addition to being superior to earlier methods based on statistical inferences, in comparison to state of the art methods using machine learning, PconsC2 is superior for families with more than 100 effective sequence homologs. The improved contact prediction enables improved structure prediction. [ABSTRACT FROM AUTHOR]