Biology subjects

Bilmes, J. A.

Publications and source records attributed to Bilmes, J. A..

4 recordsLinked to original sources

bioRxiv2023

ChromaFold predicts the 3D contact map from single-cell chromatin accessibility

The identification of cell-type-specific 3D chromatin interactions between regulatory elements can help to decipher gene regulation and to interpret the function of disease-associated non-coding variants. However, current chromosome conformation capture (3C) technologies are unable to resolve interactions at this resolution when only small numbers of cells are available as input. We therefore present ChromaFold, a deep learning model that predicts 3D contact maps and regulatory interactions from single-cell ATAC sequencing (scATAC-seq) data alone. ChromaFold uses pseudobulk chromatin accessibility, co-accessibility profiles across metacells, and predicted CTCF motif tracks as input features and employs a lightweight architecture to enable training on standard GPUs. Once trained on paired scATAC-seq and Hi-C data in human cell lines and tissues, ChromaFold can accurately predict both the 3D contact map and peak-level interactions across diverse human and mouse test cell types. In benchmarking against a recent deep learning method that uses bulk ATAC-seq, DNA sequence, and CTCF ChIP-seq to make cell-type-specific predictions, ChromaFold yields superior prediction performance when including CTCF ChIP-seq data as an input and comparable performance without. Finally, fine-tuning ChromaFold on paired scATAC-seq and Hi-C in a complex tissue enables deconvolution of chromatin interactions across cell subpopulations. ChromaFold thus achieves state-of-the-art prediction of 3D contact maps and regulatory interactions using scATAC-seq alone as input data, enabling accurate inference of cell-type-specific interactions in settings where 3C-based assays are infeasible.

bioinformatics↗

bioRxiv2022

MS1Connect: a mass spectrometry run similarity measure

Interpretation of newly acquired mass spectrometry data can be improved by identifying, from an online repository, previous mass spectrometry runs that resemble the new data. However, this retrieval task requires computing the similarity between an arbitrary pair of mass spectrometry runs. This is particularly challenging for runs acquired using different experimental protocols. We propose a method, MS1Connect, that calculates the similarity between a pair of runs by examining only the intact peptide (MS1) scans, and we show evidence that the MS1Connect score is accurate. Specifically, we show that MS1Connect outperforms several baseline methods on the task of predicting the species from which a given proteomics sample originated. In addition, we show that MS1Connect scores are highly correlated with similarities computed from fragment (MS2) scans, even though this data is not used by MS1Connect. The MS1Connect software will be made available upon acceptance at https://github.com/bmx8177/MS1Connect.

bioinformatics↗

bioRxiv2021

Epiphany: predicting Hi-C contact maps from 1D epigenomic signals

Recent deep learning models that predict the Hi-C contact map from DNA sequence achieve promising accuracy but cannot generalize to new cell types and indeed do not capture cell-type-specific differences among training cell types. We propose Epiphany, a neural network to predict cell-type-specific Hi-C contact maps from five epigenomic tracks that are already available in hundreds of cell types and tissues: DNase I hypersensitive sites and ChIP-seq for CTCF, H3K27ac, H3K27me3, and H3K4me3. Epiphany uses 1D convolutional layers to learn local representations from the input tracks, a bidirectional long short-term memory (Bi-LSTM) layers to capture long term dependencies along the epigenome, as well as a generative adversarial network (GAN) architecture to encourage contact map realism. To improve the usability of predicted contact matrices, we trained and evaluated models using multiple normalization and matrix balancing techniques including KR, ICE, and HiC-DC+ Z-score and observed-over-expected count ratio. Epiphany is trained with a combination of MSE and adversarial (i.a., a GAN) loss to enhance its ability to produce realistic Hi-C contact maps for downstream analysis. Epiphany shows robust performance and generalization to held-out chromosomes within and across cell types and species, and its predicted contact matrices yield accurate TAD and significant interaction calls. At inference time, Epiphany can be used to study the contribution of specific epigenomic peaks to 3D architecture and to predict the structural changes caused by perturbations of epigenomic signals.

genomics↗

bioRxiv2016

A unified encyclopedia of human functional DNA elements through fully automated annotation of 164 human cell types

Semi-automated genome annotation methods such as Segway enable understanding of chromatin activity. Here we present chromatin state annotations of 164 human cell types using 1,615 genomics data sets. To produce these annotations, we developed a fully-automated annotation strategy in which we train separate unsupervised annotation models on each cell type and use a machine learning classifier to automate the state interpretation step. Using these annotations, we developed a measure of the importance of each genomic position called the \"conservation-associated activity score,\" which we use to aggregate information across cell types into a multi-cell type view. The aggregated conservation-associated activity score provides a measure of importance directly attributable to a specific activity in a specific set of cell types. In contrast to evolutionary conservation, this measure is not biased to detect only elements shared with related species. Using the conservation-associated activity score, we combined all our annotations into a single, cell type-agnostic encyclopedia that catalogs all human transcriptional and regulatory elements, enabling easy and intuitive interpretation of the effect of genome variants on phenotype, such as in disease-associated, evolutionarily conserved or positively selected loci. These resources, including cell type-specific annotations, encyclopedia, and a visualization server, are available at http://noble.gs.washington.edu/proj/encyclopedia.\n\nAuthor SummaryGenome annotation algorithms are an effective class of tools for understanding the function of the genome. These algorithms take as input a set of genome-wide measurements about the activity at each base pair in a given tissue, such as where a given protein is binding or how accessible the DNA is to being read by a protein. The genome is then partitioned and each segment is assigned a label such that positions with the same label exhibit similar patterns in the input data. Such annotations are widely used for many applications, such as to understand the mechanism of impact of a given genetic variant. Here we present, to our knowledge, the most comprehensive set of genome annotations created so far, encompassing 164 human cell types and including 1,615 genomics data sets. These comprehensive annotations are made possible by a strategy that automates the previous interpretation step. Furthermore, we present several methodological innovations that make these genome annotations more useful.

genomics↗