PaperPlayer biorxiv bioinformatics

Link to bioRxiv paper:

http://biorxiv.org/cgi/content/short/2020.11.19.390617v1?rss=1

Authors: Cao, C., Kwok, D., Li, Q., He, J., Guo, X., Zhang, Q., Long, Q.

Abstract:

The success of transcriptome-wide association studies (TWAS) has led to substantial research towards improving its core component of genetically regulated expression (GReX). GReX links expression information with phenotype by serving as both the outcome of genotype-based expression models and the predictor for downstream association testing. In this work, we demonstrate that current linear models of GReX inadvertently combine two separable steps of machine learning - feature selection and aggregation - which can be independently replaced to improve overall power. We show that the monolithic approach of GReX limits the adaptability of TWAS methodology and practice, especially given low expression heritability.

Copy rights belong to original authors. Visit the link for more info

Link to bioRxiv paper:

http://biorxiv.org/cgi/content/short/2020.11.17.385757v1?rss=1

Authors: Jiang, Y., Rensi, S., wang, s., Altman, R. B.

Abstract:

Massively accumulated pharmacogenomics, chemogenomics, and side effect datasets offer an unprecedented opportunity for drug response prediction, drug target identification and drug side effect prediction. Existing computational approaches limit their scope to only one of these three tasks, inevitably overlooking the rich connection among them. Here, we propose DrugOrchestra, a deep multi-task learning framework that jointly predicts drug response, targets and side effects. DrugOrchestra leverages pre-trained molecular structure-based drug representation to bridge these three tasks. Instead of directly fine-tuning on an individual task, DrugOrchestra uses deep multi-task learning to obtain a phenotype-based drug representation by simultaneously fine-tuning on drug response, target and side effect prediction. By coupling these three tasks together, DrugOrchestra is able to make predictions for unseen drugs by only knowing their molecular structures. We constructed a heterogeneous drug discovery dataset of over 21k drugs by integrating 8 datasets across three tasks. Our method obtained significant improvements in comparison to methods that were trained on a single task or a single dataset. We further revealed the transferability across 8 datasets and 3 tasks, providing novel insights for understanding drug mechanisms.

Copy rights belong to original authors. Visit the link for more info

Link to bioRxiv paper:

http://biorxiv.org/cgi/content/short/2020.11.17.387811v1?rss=1

Authors: Kang, K., Chong, H., Ning, K.

Abstract:

Motivation: Microbial community samples and sequencing data have been accumulated at a speed faster than ever, with tens of thousands of samples been sequenced each year. Mining such a huge amount of multi-source heterogeneous data is becoming more and more difficult. Among several sample mining bottlenecks, efficient and accurate search of samples is one of the most prominent: Faced with millions of samples in the data repository, traditional sample comparison and search approaches fall short in speed and accuracy. Results: Here we proposed Meta-Prism 2.0, a microbial community sample search method based on smart pair-wise sample comparison, which pushed the time and memory efficiency to a new limit, without the compromise of accuracy. Based on memory-saving data structure, time-saving instruction pipeline, and boost scheme optimization, Meta-Prism 2.0 has enabled ultra-fast, accurate and memory-efficient search among millions of samples. Meta-Prism 2.0 has been put to test on several datasets, with largest containing one million samples. Results have shown that firstly, as a distance-based method, Meta-Prism 2.0 is not only faster than other distance-based methods, but also faster than unsupervised methods. Its 0.00001s per sample pair search speed, as well as 8GB memory needs for searching against one million samples, have enabled it to be the most efficient method for sample comparison. Additionally, Meta-Prism 2.0 could achieve the comparison accuracy and search precision that are comparable or better than other contemporary methods. Thirdly, Meta-Prism 2.0 can precisely identify the original biome for samples, thus enabling sample source tracking. Conclusion: In summary, Meta-Prism 2.0 can perform accurate searches among millions of samples with very low memory cost and fast speed, enabling knowledge discovery from samples at a massive scale. It has changed the traditional resource-intensive sample comparison and search scheme to a cheap and effective procedure, which could be conducted by researchers everyday even on a laptop, for insightful sample search and knowledge discovery. Meta-Prism 2.0 could be accessed at: https://github.com/HUST-NingKang-Lab/Meta-Prism-2.0.

Copy rights belong to original authors. Visit the link for more info

Link to bioRxiv paper:

http://biorxiv.org/cgi/content/short/2020.11.18.386102v1?rss=1

Authors: Zhang, R., Luo, Y., Ma, J., Zhang, M., Wang, S.

Abstract:

Rapidly generated scRNA-seq datasets enable us to understand cellular differences and the function of each individual cell at single-cell resolution. Cell type classification, which aims at characterizing and labeling groups of cells according to their gene expression, is one of the most important steps for single-cell analysis. To facilitate the manual curation process, supervised learning methods have been used to automatically classify cells. Most of the existing supervised learning approaches only utilize annotated cells in the training step while ignoring the more abundant unannotated cells. In this paper, we proposed scPretrain, a multi-task self-supervised learning approach that jointly considers annotated and unannotated cells for cell type classification. scPretrain consists of a pre-training step and a fine-tuning step. In the pre-training step, scPretrain uses a multi-task learning framework to train a feature extraction encoder based on each dataset's pseudo-labels, where only unannotated cells are used. In the fine-tuning step, scPretrain fine-tunes this feature extraction encoder using the limited annotated cells in a new dataset. We evaluated scPretrain on 60 diverse datasets from different technologies, species and organs, and obtained a significant improvement on both cell type classification and cell clustering. Moreover, the representations obtained by scPretrain in the pre-training step also enhanced the performance of conventional classifiers such as random forest, logistic regression and support vector machines. scPretrain is able to effectively utilize the massive amount of unlabelled data and be applied to annotating increasingly generated scRNA-seq datasets.

Copy rights belong to original authors. Visit the link for more info

Link to bioRxiv paper:

http://biorxiv.org/cgi/content/short/2020.11.17.387860v1?rss=1

Authors: Gao, B., Luo, Y., Ma, J., Wang, S.

Abstract:

Tumor stratification, which aims at clustering tumors into biologically meaningful subtypes, is the key step towards personalized treatment. Large-scale profiled cancer genomics data enables us to develop computational methods for tumor stratification. However, most of the existing approaches only considered tumors from an individual cancer type during clustering, leading to the overlook of common patterns across cancer types and the vulnerability to the noise within that cancer type. To address these challenges, we proposed cancerAlign to map tumors of the target cancer type into latent spaces of other source cancer types. These tumors were then clustered in each latent space rather than the original space in order to exploit shared patterns across cancer types. Due to the lack of aligned tumor samples across cancer types, cancerAlign used adversarial learning to learn the mapping at the population level. It then used consensus clustering to integrate cluster labels from different source cancer types. We evaluated cancerAlign on 7,134 tumors spanning 24 cancer types from TCGA and observed substantial improvement on tumor stratification and cancer gene prioritization. We further revealed the transferability across cancer types, which reflected the similarity among them based on the somatic mutation profile. cancerAlign is an unsupervised approach that provides deeper insights into the heterogeneous and rapidly accumulating somatic mutation profile and can be also applied to other genome-scale molecular information.

Copy rights belong to original authors. Visit the link for more info

Link to bioRxiv paper:

http://biorxiv.org/cgi/content/short/2020.11.18.042887v1?rss=1

Authors: Vishwakarma, P., Meena, N. K., Prasad, R., Lynn, A. M., Banerjee, A.

Abstract:

In view of the multiple clinical and physiological implications of ABC transporter proteins, there is a considerable interest among researchers to characterize them functionally. However, such characterizations are based on the premise that ABC proteins are accurately identified in the genome, and their topology is correctly predicted. With this objective, we have developed ABC-finder, i.e., a Docker-based package for the identification of ABC proteins in all organisms, and visualization of the topology of ABC proteins using an interactive web browser. ABC-finder is built and deployed in a Linux container, making it scalable for many concurrent users on our servers and enabling users to download and run it locally. Overall, ABC-finder is a convenient, portable, and platform-independent tool for the identification and topology prediction of ABC proteins. ABC-finder is accessible at http://abc-finder.osdd.jnu.ac.in

Copy rights belong to original authors. Visit the link for more info

Link to bioRxiv paper:

http://biorxiv.org/cgi/content/short/2020.11.17.387548v1?rss=1

Authors: Maden, S. K., Thompson, R. F., Hansen, K. D., Nellore, A.

Abstract:

While DNA methylation (DNAm) is the most-studied epigenetic mark, few recent studies probe the breadth of publicly available DNAm array samples. We collectively analyzed 35,360 Illumina Infinium HumanMethylation450K DNAm array samples published on the Gene Expression Omnibus (GEO). We learned a controlled vocabulary of sample labels by applying regular expressions to metadata and used existing models to predict various sample properties including epigenetic age. We found approximately two-thirds of samples were from blood, one-quarter were from brain, and one-third were from cancer patients. 19% of samples failed at least one of Illumina's 17 prescribed quality assessments; signal distributions across samples suggest modifying manufacturer-recommended thresholds for failure would make these assessments more informative. We further analyzed DNAm variances in seven tissues (adipose, nasal, blood, brain, buccal, sperm, and liver) and characterized specific probes distinguishing them. Finally, we compiled DNAm array data and metadata, including our learned and predicted sample labels, into database files accessible via the recountmethylation R/Bioconductor companion package. Its vignettes walk the user through some analyses contained in this paper.

Copy rights belong to original authors. Visit the link for more info

Link to bioRxiv paper:

http://biorxiv.org/cgi/content/short/2020.11.17.387134v1?rss=1

Authors: Ernst, J., Vu, H. T.

Abstract:

Genome-wide maps of chromatin marks such as histone modifications and open chromatin sites provide valuable information for annotating the non-coding genome, including identifying regulatory elements. Computational approaches such as ChromHMM have been applied to discover and annotate chromatin states defined by combinatorial and spatial patterns of chromatin marks within the same cell type. An alternative stacked modeling approach was previously suggested, where chromatin states are defined jointly from datasets of multiple cell types to produce a single universal genome annotation based on all datasets. Despite its potential benefits for applications that are not specific to one cell type, such an approach was previously applied only for small-scale specialized purposes. Large-scale applications of stacked modeling have previously posed scalability challenges. In this paper, using a version of ChromHMM enhanced for large-scale applications, we applied the stacked modeling approach to produce a universal chromatin state annotation of the human genome using over 1000 datasets from more than 100 cell types, denoted the full-stack model. The full-stack model states show distinct enrichments for external genomic annotations, which we used in characterizing each state. Compared to cell-type-specific annotations, the full-stack annotation directly differentiates constitutive from cell-type-specific activity and is more predictive of locations of external genomic annotations. Overall, the full-stack ChromHMM model provides a universal chromatin state annotation of the genome and a unified global view of over 1000 datasets. We expect this to be a useful resource that complements existing cell-type-specific annotations for studying the non-coding human genome.

Copy rights belong to original authors. Visit the link for more info

Link to bioRxiv paper:

http://biorxiv.org/cgi/content/short/2020.11.17.386649v1?rss=1

Authors: Danciu, D., Karasikov, M., Mustafa, H., Kahles, A., Ratsch, G.

Abstract:

Since the amount of published biological sequencing data is growing exponentially, efficient methods for storing and indexing this data are more needed than ever to truly benefit from this invaluable resource for biomedical research. Labeled de Bruijn graphs are a frequently-used approach for representing large sets of sequencing data. While significant progress has been made to succinctly represent the graph itself, efficient methods for storing labels on such graphs are still rapidly evolving. In this paper, we present RowDiff, a new technique for compacting graph labels by leveraging expected similarities in annotations of nodes adjacent in the graph. RowDiff can be constructed in linear time relative to the number of nodes and labels in the graph, and the construction can be efficiently parallelized and distributed, significantly reducing construction time. RowDiff can be viewed as an intermediary sparsification step of the initial annotation matrix and can thus naturally be combined with existing generic schemes for compressed binary matrix representation. Our experiments on the Fungi subset of the RefSeq collection show that applying RowDiff sparsification reduces the size of individual annotation columns stored as compressed bit vectors by an average factor of 42. When combining RowDiff with a Multi-BRWT representation, the resulting annotation is 26 times smaller than Mantis-MST, the previously known smallest annotation representation. In addition, experiments on 10,000 RNA-seq datasets show that RowDiff combined with Multi-BRWT results in a 30% reduction in annotation footprint over Mantis-MST.

Copy rights belong to original authors. Visit the link for more info

Link to bioRxiv paper:

http://biorxiv.org/cgi/content/short/2020.11.17.385864v1?rss=1

Authors: Chevalier, A., Yang, S., Yajima, M., Campbell, J. D.

Abstract:

Mutational signatures are patterns of somatic alterations in the genome that cause carcinogenic exposures or aberrant cellular processes. We created the musicatk package to provide a comprehensive workflow for preprocessing, analysis, and visualization of mutational signatures. The musicatk package enables users to select different schemas for counting mutation types and easily combine count tables from different schemas. Several methods can be used to discover new signatures or infer the exposures for given a pre-existing set of signatures. Several visualizations are provided to facilitate exploratory analysis of signatures and exposures. These include comparison of discovered signatures to those in the COSMIC database, using UMAP to embed tumors in two dimensions, and plotting of exposure distributions across user-defined annotations. Overall, musicatk can be used to gain novel insights into the patterns of mutational signature observed in cancer.

Copy rights belong to original authors. Visit the link for more info