Biology subjects

Bilmes, J.

Publications and source records attributed to Bilmes, J..

5 recordsLinked to original sources

bioRxiv2018

Multi-scale deep tensor factorization learns a latent representation of the human epigenome

The human epigenome has been experimentally characterized by measurements of protein binding, chromatin acessibility, methylation, and histone modification in hundreds of cell types. The result is a huge compendium of data, consisting of thousands of measurements for every basepair in the human genome. These data are difficult to make sense of, not only for humans, but also for computational methods that aim to detect genes and other functional elements, predict gene expression, characterize polymorphisms, etc. To address this challenge, we propose a deep neural network tensor factorization method, Avocado, that compresses epigenomic data into a dense, information-rich representation of the human genome. We use data from the Roadmap Epigenomics Consortium to demonstrate that this learned representation of the genome is broadly useful: first, by imputing epigenomic data more accurately than previous methods, and second, by showing that machine learning models that exploit this representation outperform those trained directly on epigenomic data on a variety of genomics tasks. These tasks include predicting gene expression, promoter-enhancer interactions, replication timing, and an element of 3D chromatin architecture. Our findings suggest the broad utility of Avocados learned latent representation for computational genomics and epigenomics.

bioinformatics↗

bioRxiv2018

Joint precursor elution profile inference via regression for peptide detection in data-independent acquisition mass spectra

In data independent acquisition (DIA) mass spectrometry, precursor scans are interleaved with wide-window fragmentation scans, resulting in complex fragmentation spectra containing multiple co-eluting peptide species. In this setting, detecting the isotope distribution profiles of intact peptides in the precursor scans can be a critical initial step in accurate peptide detection and quantification. This peak detection step is particularly challenging when the isotope peaks associated with two different peptide species overlap--or interfere--with one another. We propose a regression model, called Siren, to detect isotopic peaks in precursor DIA data that can explicitly account for interference. We validate Sirens peak-calling performance on a variety of data sets by counting how many of the peaks Siren identifies are associated with confidently detected peptides. In particular, we demonstrate that substituting the Siren regression model in place of the existing peak-calling step in DIA-Umpire leads to improved overall rates of peptide detection.

bioinformatics↗

bioRxiv2017

Comprehensive statistical inference of the clonal structure of cancer from multiple biopsies

A comprehensive characterization of tumor genetic heterogeneity is critical for understanding how cancers evolve and escape treatment. Although many algorithms have been developed for capturing tumor heterogeneity, they are designed for analyzing either a single type of genomic aberration or individual biopsies. Here we present THEMIS (Tumor Heterogeneity Extensible Modeling via an Integrative System), which allows for the joint analysis of different types of genomic aberrations from multiple biopsies taken from the same patient, using a dynamic graphical model. Simulation experiments demonstrate higher accuracy of THEMIS over its ancestor, TITAN. The heterogeneity analysis results from THEMIS are validated with single cell DNA sequencing from a clinical tumor biopsy. When THEMIS is used to analyze tumor heterogeneity among multiple biopsies from the same patient, it helps to reveal the mutation accumulation history, track cancer progression, and identify the mutations related to treatment resistance. We implement our model via an extensible modeling platform, which makes our approach open, reproducible, and easy for others to extend.

bioinformatics↗

bioRxiv2017

PREDICTD: PaRallel Epigenomics Data Imputation With Cloud-based Tensor Decomposition

The Encyclopedia of DNA Elements (ENCODE) and the Roadmap Epigenomics Project have produced thousands of data sets mapping the epigenome in hundreds of cell types. However, the number of cell types remains too great to comprehensively map given current time and financial constraints. We present a method, PaRallel Epigenomics Data Imputation with Cloud-based Tensor Decomposition (PREDICTD), to address this issue by computationally imputing missing experiments in collections of epigenomics experiments. PREDICTD leverages an intuitive and natural model called \"tensor decomposition\" to impute many experiments simultaneously. Compared with the current state-of-the-art method, ChromImpute, PREDICTD produces lower overall mean squared error, and combining methods yields further improvement. We show that PREDICTD data can be used to investigate enhancer biology at non-coding human accelerated regions. PREDICTD provides reference imputed data sets and open-source software for investigating new cell types, and demonstrates the utility of tensor decomposition and cloud computing, two technologies increasingly applicable in bioinformatics.

bioinformatics↗

bioRxiv2017

Nucleotide sequence and DNaseI sensitivity are predictive of 3D chromatin architecture

Recently, Hi-C has been used to probe the 3D chromatin architecture of multiple organisms and cell types. The resulting collections of pairwise contacts across the genome have connected chromatin architecture to many cellular phenomena, including replication timing and gene regulation. However, high resolution (10 kb or finer) contact maps remain scarce due to the expense and time required for collection. A computational method for predicting pairwise contacts without the need to run a Hi-C experiment would be invaluable in understanding the role that 3D chromatin architecture plays in genome biology. We describe Rambutan, a deep convolutional neural network that predicts Hi-C contacts at 1 kb resolution using nucleotide sequence and DNaseI assay signal as inputs. Specifically, Rambutan identifies locus pairs that engage in high confidence contacts according to Fit-Hi-C, a previously described method for assigning statistical confidence estimates to Hi-C contacts. We first demonstrate Rambutans performance across chromosomes at 1 kb resolution in the GM12878 cell line. Subsequently, we measure Rambutans performance across six cell types. In this setting, the model achieves an area under the receiver operating characteristic curve between 0.7662 and 0.8246 and an area under the precision-recall curve between 0.3737 and 0.9008. We further demonstrate that the predicted contacts exhibit expected trends relative to histone modification ChlP-seq data, replication timing measurements, and annotations of functional elements such as promoters and enhancers. Finally, we predict Hi-C contacts for 53 human cell types and show that the predictions cluster by cellular function. [NOTE: After our original submission we discovered an error in our calling of statistically significant contacts. Briefly, when calculating the prior probability of a contact, we used the number of contacts at a certain genomic distance in a chromosome but divided by the total number of bins in the full genome. While we investigate what impact this had on our results, we ask that readers treat this manuscript skeptically.]

bioinformatics↗