bioRxiv Science⌕ Search
Home/Archive/bioRxiv

bioRxiv · 10.1101/2020.10.07.321927

DeepFoci: Deep Learning-Based Algorithm for Fast Automatic Analysis of DNA Double Strand Break Ionizing Radiation-Induced Foci

Vicar, T.·Gumulec, J.·Kolar, R.·Kopecna, O.·Pagacova, E.·Falk, M.
View original source ↗Export metadata ↓

Abstract

DNA double-strand breaks, marked by Ionizing Radiation-Induced (Repair) Foci (IRIF), are the most serious DNA lesions, dangerous to human health. IRIF quantification based on confocal microscopy represents the most sensitive and gold standard method in radiation biodosimetry and allows research of DSB induction and repair at the molecular and a single cell level. In this study, we introduce DeepFoci - a deep learning-based fully-automatic method for IRIF counting and its morphometric analysis. DeepFoci is designed to work with 3D multichannel data (trained for 53BP1 and {gamma}H2AX) and uses U-Net for the nucleus segmentation and IRIF detection, together with maximally stable extremal region-based IRIF segmentation. The proposed method was trained and tested on challenging datasets consisting of mixtures of non-irradiated and irradiated cells of different types and IRIF characteristics - permanent cell lines (NHDF, U-87) and cell primary cultures prepared from tumors and adjacent normal tissues of head and neck cancer patients. The cells were dosed with 1-4 Gy gamma-rays and fixed at multiple (0-24 h) post-irradiation times. Upon all circumstances, DeepFoci was able to quantify the number of IRIF foci with the highest accuracy among current advanced algorithms. Moreover, while the detection error of DeepFoci remained comparable to the variability between two experienced experts, the software kept its sensitivity and fidelity across dramatically different IRIF counts per nucleus. In addition, information was extracted on IRIF 3D morphometric features and repair protein colocalization within IRIFs. This allowed multiparameter IRIF categorization, thereby refining the analysis of DSB repair processes and classification of patient tumors with a potential to identify specific cell subclones. The developed software improves IRIF quantification for various practical applications (radiotherapy monitoring, biodosimetry, etc.) and opens the door to an advanced DSB focus analysis and, in turn, a better understanding of (radiation) DNA damaging and repair. HighlightsO_LINew method for DSB repair focus (IRIF) detection and multi-parameter analysis C_LIO_LITrainable deep learning-based method C_LIO_LIFully automated analysis of multichannel 3D datasets C_LIO_LITrained and tested on extremely challenging datasets (tumor primary cultures) C_LIO_LIComparable to an expert analysis and superb to available methods C_LI Graphical Abstract O_FIG O_LINKSMALLFIG WIDTH=200 HEIGHT=76 SRC="FIGDIR/small/321927v1_ufig1.gif" ALT="Figure 1"> View larger version (23K): org.highwire.dtl.DTLVardef@7a0127org.highwire.dtl.DTLVardef@1e1d3cborg.highwire.dtl.DTLVardef@117e7a7org.highwire.dtl.DTLVardef@69c620_HPS_FORMAT_FIGEXP M_FIG C_FIG

Source connections

Explore related subjects

bioinformaticsPreprint

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Vicar, T., Gumulec, J., Kolar, R., Kopecna, O., Pagacova, E., Falk, M.. 2020-10-08. DeepFoci: Deep Learning-Based Algorithm for Fast Automatic Analysis of DNA Double Strand Break Ionizing Radiation-Induced Foci. https://doi.org/10.1101/2020.10.07.321927

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related preprints

bioRxiv2026

RoDPAA: A Robust Dissimilarity-Based Principal Angle Analysis Framework for Multi-View Microbiome Data Integration

Multiview microbiome studies profile the same participants across body sites or molecular layers, but integration is hampered by sparse, compositional data, modest sample sizes and methods that recognize only exact sharing. We present RoDPAA (Robust Dissimilarity-based Principal Angle Analysis), a framework that represents each view through any data-appropriate dissimilarity, such as Bray--Curtis, without log-ratio transformation or likelihood assumptions. RoDPAA aligns view-specific signal subspaces through principal angles, captures complete and partial sharing, and tests by permutation how many components are shared, using only eigendecomposition and little tuning. In Gaussian simulations, RoDPAA matched JIVE and MOFA given true ranks, ran faster and alone recovered the shared dimension in every replicate. In two inflammatory bowel disease (IBD) cohorts with sparse, zero-inflated data, Bray--Curtis-based RoDPAA recovered shared structure that was stable to prevalence filtering, whereas log-ratio-based alternatives were not. Its leading microbiome--metabolome factors, learned without disease labels, were the only ones associated with IBD.

bioinformatics↗
bioRxiv2026

Deducing splicing events from transcript sets with splicelogic

Long-read RNA sequencing captures a greater proportion of full-length transcripts, enabling more accurate isoform identification, discovery of novel isoforms, and more precise differential transcript usage analysis. However, comparing transcripts, whether between conditions or between sets such as novel and annotated isoforms, yields complex isoform changes that are hard to manipulate, summarize, and visualize. This is compounded by vertical integration of some tools, where downstream analysis depends on the specific output of a particular upstream tool. To address this gap, we have developed splicelogic, an R/Bioconductor package that makes transcript-set comparisons biologically interpretable by turning them into discrete splicing events, such as exon skipping, alternative splice sites, intron retention, and alternative transcription start and end sites. We designed splicelogic to integrate easily with existing RNA-seq workflows and tools. The splicelogic functions are modular, readable, and extensible, making it easy for users to adapt core logic to their own custom scientific questions or novel splicing definitions. By obtaining interpretable splicing events from transcript changes, splicelogic enables downstream analyses, including annotation of RNA-binding protein recognition sites, alongside summary statistics and visualization. The splicelogic package is publicly available and distributed through Bioconductor.

bioinformatics↗
bioRxiv2026

Contrastive Learning Improves Generalization on M2OR Olfactory Binding Dataset

Olfaction-based biosensors stand to have profound impacts in fields such as medical diagnostics, national security, and drug discovery. A promising mode of vapor phase biodetection mimics volatile organic compound-olfactory receptor (VOC-OR) interactions with target-specific protein or peptide probes; however, lack of experimental coverage remains a core bottleneck. Current computational approaches aim to improve prediction of VOC-OR binding to reduce experimental burden, and current machine learning approaches fail to demonstrate a level of generalization that addresses current engineering challenges. Here, using the Molecular to Olfactory Dataset (M2OR) and Insect Olfactory Binding Protein Database (iOBPdb) datasets, data partitioning methods and their performance are evaluated on a neural network and contrastive learning framework on such VOC-OR binding datasets, varying: model training, architecture, and structure of the input data distribution. It was found that holding out certain chemical or proteomic motifs from the training data diminished model performance with a two layer neural network model. The model was able to generalize to state of the art performance (0.88 AUCROC) on every data split by applying a contrastive learning objective defined by shared molecular constituents and a stochastic sampler. This suggests the contrastive objective provides a strong inductive bias for neural networks to predict novel VOC-OR pairs. These findings highlight that model performance on pairwise biological interaction datasets can be inflated through identity leakage from constituent overlap, and emphasize the need for more robust evaluation protocols. Furthermore, we show contrastive regularization mitigates dataset degeneracy through enforcement of compatibility in the models latent geometry that may extend to other binder target-datasets where identity leakage confounds evaluation.

bioinformatics↗