Biology subjects

Grabowski, P.

Publications and source records attributed to Grabowski, P..

5 recordsLinked to original sources

bioRxiv2023

cudaMMC - GPU-enhanced Multiscale Monte Carlo Chromatin 3D Modelling

MotivationInvestigating the 3D structure of chromatin provides new insights into transcriptional regulation. With the advancements in 3C new-sequencing techniques such as ChiA-PET and Hi-C, there has been a substantial increase in the volume of collected data, necessitating faster algorithms for chromatin spatial modelling. This study presents the cudaMMC method, which utilises the Simulated Annealing Monte Carlo approach extended by GPU-accelerated computing to generate ensembles of chromatin 3D structures efficiently. ResultsThe cudaMMC calculations demonstrate significantly faster performance and lower (better) model scores compared to our previous method on the same workstation. cudaMMC substantially reduces the computation time required for generating ensembles of large chromatin models, making it an invaluable tool for studying chromatin spatial conformation. AvailabilityOpen-source software and manual and sample data are freely available on https://github.com/SFGLab/cudaMMC ContactDariusz.Plewczynski@pw.edu.pl

bioinformatics↗

bioRxiv2021

Effective expression analysis using gene interaction matrices and convolutional neural networks

Artificial intelligence recently experienced a renaissance with the advancement of convolutional neural networks (CNNs). CNNs require spatially meaningful matrices (e.g., image data) with recurring patterns, limiting its applicability to high-throughput omics data. We present GIM, a simple, CNN-ready framework for omics data to detect both individual and network-level entities of biological importance. Using gene expression data, we show that GIM-CNNs can outperform comparable neural networks in performance and their design facilitates network-level interpretability. GIM-CNNs provide a means to discover novel disease-relevant factors beyond individual genes and their expression, factors that are likely missed by standard differential gene expression approaches.

bioinformatics↗

bioRxiv2020

Training a neural network to learn other dimensionality reduction removes data size restrictions in bioinformatics and provides a new route to exploring data representations

High dimensionality omics and hyperspectral imaging datasets present difficult challenges for feature extraction and data mining due to huge numbers of features that cannot be simultaneously examined. The sample numbers and variables of these methods are constantly growing as new technologies are developed, and computational analysis needs to evolve to keep up with growing demand. Current state of the art algorithms can handle some routine datasets but struggle when datasets grow above a certain size. We present a training deep learning via neural networks on non-linear dimensionality reduction, in particular t-distributed stochastic neighbour embedding (t-SNE), to overcome prior limitations of these methods. One Sentence SummaryAnalysis of prohibitively large datasets by combining deep learning via neural networks with non-linear dimensionality reduction.

bioinformatics↗

bioRxiv2019

The human proteome co-regulation map reveals functional relationships between proteins

The annotation of protein function is a longstanding challenge of cell biology that suffers from the sheer magnitude of the task. Here we present ProteomeHD, which documents the response of 10,323 human proteins to 294 biological perturbations, measured by isotope-labelling mass spectrometry. Using this data matrix and robust machine learning we create a co-regulation map of the cell that reflects functional associations between human proteins. The map identifies a functional context for many uncharacterized proteins, including microproteins that are difficult to study with traditional methods. Co-regulation also captures relationships between proteins which do not physically interact or co-localize. For example, co-regulation of the peroxisomal membrane protein PEX11{beta} with mitochondrial respiration factors led us to discover a novel organelle interface between peroxisomes and mitochondria in mammalian cells. The co-regulation map can be explored at www.proteomeHD.net.

systems biology↗

bioRxiv2019

treeClust improves protein co-regulation analysis due to robust selectivity for close linear relationships

Gene co-expression analysis is a widespread method to identify the potential biological function of uncharacterised genes. Recent evidence suggests that proteome profiling may provide more accurate results than transcriptome profiling. However, it is unclear which statistical measure is best suited to detect proteins that are co-regulated. We have previously shown that expression similarities calculated using treeClust, an unsupervised machine-learning algorithm, outperformed correlation-based analysis of a large proteomics dataset. The reason for this improvement is unknown. Here we systematically explore the characteristics of treeClust similarities. Leveraging synthetic data, we find that tree-based similarities are exceptionally robust against outliers and detect only close-fitting, linear protein - protein associations. We then use proteomics data to demonstrate that both of these features contribute to the improved performance of treeClust relative to Pearson, Spearman and robust correlation. Our results suggest that, for large proteomics datasets, unsupervised machine-learning algorithms such as treeClust may significantly improve the detection of biologically relevant protein - protein associations relative to correlation metrics.

systems biology↗