Biology subjects

Phuycharoen, M.

Publications and source records attributed to Phuycharoen, M..

4 recordsLinked to original sources

bioRxiv2024

Predicting cell type-specific epigenomic profiles accounting for distal genetic effects

Understanding genetic variants effects on the epigenome is crucial for interpreting genome-wide association studies (GWAS) results, yet profiling these effects across the non-coding genome remains challenging due to the scalability limits of experimental methods. This necessitates accurate computational models. Existing machine learning approaches, while progressively improving, are confined to the cell types they were trained on, limiting their applicability. Here, we propose the development of a deep learning model, Enformer Celltyping, which can both incorporate distal effects of DNA interactions, up to 100,000 base-pairs away, and predict epigenetic signals in a cell type-agnostic fashion. We demonstrate that Enformer Celltypings predictions of the epigenome out-perform the current best-in-class approach, have strong performance in a range of different cell types and biological regions and generalise to cell types assayed independently of the original training set. Finally, we propose an approach to test epigenetic models performance on genetic variant effect predictions using regulatory quantitative trait loci mapping studies, highlighting Enformer Celltypings and other genomic deep learning models limitations for this task. Our work introduces a new, accurate model for cell type-agnostic histone mark predictions and highlights the benefit of transfer learning for more efficient model development for deep learning in genomics. We make our customisable and efficient transfer learning approach for Enformer available to the community.

genomics↗

bioRxiv2023

UVAE: Integration of Heterogeneous Unpaired Data with Imbalanced Classes

We introduce the Unbiasing Variational Autoencoder (UVAE), a computational framework for the integration of unpaired biomedical data streams such as clinical flow cytometry. UVAE addresses batch effect correction and data alignment by training a semi-supervised model on partially labelled datasets, enabling simultaneous normalisation and integration of diverse data within a shared latent space. The framework implements a probabilistic model for batch effect normalisation and balances class contents during training to ensure accurate representation of underlying cell composition. We apply UVAE to integrate heterogeneous clinical flow cytometry data from COVID-19 patients. The integrated data enhances the statistical signal of cell types associated with disease severity, enables clustering of subpopulations without the impediment of batch effects, and improves the performance of longitudinal regression for predicting peak disease severity from temporal patient samples.

bioinformatics↗

bioRxiv2019

HOX paralogs selectively convert binding of ubiquitous transcription factors into tissue-specific patterns of enhancer activation

Gene expression programs determine cell fate in embryonic development and their dysregulation results in disease. Transcription factors (TFs) control gene expression by binding to enhancers, but how TFs select and activate their target enhancers is still unclear. HOX TFs share conserved homeodomains with highly similar sequence recognition properties, yet they impart the identity of different animal body parts. To understand how HOX TFs control their specific transcriptional programs in vivo, we compared HOXA2 and HOXA3 binding profiles in the mouse embryo. HOXA2 and HOXA3 directly cooperate with TALE TFs and selectively target different subsets of a broad TALE chromatin platform. Binding of HOX and tissue-specific TFs convert low affinity TALE binding into high confidence, tissue-specific binding events, which bear the mark of active enhancers. We propose that HOX paralogs, alone and in combination with tissue-specific TFs, generate tissue-specific transcriptional outputs by modulating the activity of TALE TFs at selected enhancers.

developmental biology↗

bioRxiv2019

Uncovering tissue-specific binding features from differential deep learning

MotivationTranscription factors (TFs) can bind DNA in a cooperative manner, enabling a mutual increase in occupancy. Through this type of interaction, alternative binding sites can be preferentially bound in different tissues to regulate tissue-specific expression programmes. Recently, deep learning models have become state-of-the-art in various pattern analysis tasks, including applications in the field of genomics. We therefore investigate the application of convolutional neural network (CNN) models to the discovery of sequence features determining cooperative and differential TF binding across tissues. ResultsWe analyse ChIP-seq data from MEIS, TFs which are broadly expressed across mouse branchial arches, and HOXA2, which is expressed in the second and more posterior branchial arches. By developing models predictive of MEIS differential binding in all three tissues we are able to accurately predict HOXA2 co-binding sites. We evaluate transfer-like and multitask approaches to regularising the high-dimensional classification task with a larger regression dataset, allowing for creation of deeper and more accurate models. We test the performance of perturbation and gradient-based attribution methods in identifying the HOXA2 sites from differential MEIS data. Our results show that deep regularised models significantly outperform shallow CNNs as well as k-mer methods in the discovery of tissue-specific sites bound in vivo. AvailabilityFor implementation and models please visit https://doi.org/10.5281/zenodo.2635463.

bioinformatics↗