Browse
Submit Data
Databases
API
Help

Dataset Information

5 Views

0 Connections

0 Citations

0 Reanalyses

0 Downloads

Omics score: 0

A self-attention model for inferring cooperativity between regulatory features.

ABSTRACT: Deep learning has demonstrated its predictive power in modeling complex biological phenomena such as gene expression. The value of these models hinges not only on their accuracy, but also on the ability to extract biologically relevant information from the trained models. While there has been much recent work on developing feature attribution methods that discover the most important features for a given sequence, inferring cooperativity between regulatory elements, which is the hallmark of phenomena such as gene expression, remains an open problem. We present SATORI, a Self-ATtentiOn based model to detect Regulatory element Interactions. Our approach combines convolutional layers with a self-attention mechanism that helps us capture a global view of the landscape of interactions between regulatory elements in a sequence. A comprehensive evaluation demonstrates the ability of SATORI to identify numerous statistically significant TF-TF interactions, many of which have been previously reported. Our method is able to detect higher numbers of experimentally verified TF-TF interactions than existing methods, and has the advantage of not requiring a computationally expensive post-processing step. Finally, SATORI can be used for detection of any type of feature interaction in models that use a similar attention mechanism, and is not limited to the detection of TF-TF interactions.

SUBMITTER: Ullah F

PROVIDER: S-EPMC8287919 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Json Xml

Similar Datasets

The interplay between cooperativity and diversity in model threshold ensembles.

Project description:The interplay between cooperativity and diversity is crucial for biological ensembles because single molecule experiments show a significant degree of heterogeneity and also for artificial nanostructures because of the high individual variability characteristic of nanoscale units. We study the cross-effects between cooperativity and diversity in model threshold ensembles composed of individually different units that show a cooperative behaviour. The units are modelled as statistical distributions of parameters (the individual threshold potentials here) characterized by central and width distribution values. The simulations show that the interplay between cooperativity and diversity results in ensemble-averaged responses of interest for the understanding of electrical transduction in cell membranes, the experimental characterization of heterogeneous groups of biomolecules and the development of biologically inspired engineering designs with individually different building blocks.

| S-EPMC4233720 | biostudies-literature

Inferring gene regulatory network from single-cell transcriptomes with graph autoencoder model.

Project description:The gene regulatory structure of cells involves not only the regulatory relationship between two genes, but also the cooperative associations of multiple genes. However, most gene regulatory network inference methods for single cell only focus on and infer the regulatory relationships of pairs of genes, ignoring the global regulatory structure which is crucial to identify the regulations in the complex biological systems. Here, we proposed a graph-based Deep learning model for Regulatory networks Inference among Genes (DeepRIG) from single-cell RNA-seq data. To learn the global regulatory structure, DeepRIG builds a prior regulatory graph by transforming the gene expression of data into the co-expression mode. Then it utilizes a graph autoencoder model to embed the global regulatory information contained in the graph into gene latent embeddings and to reconstruct the gene regulatory network. Extensive benchmarking results demonstrate that DeepRIG can accurately reconstruct the gene regulatory networks and outperform existing methods on multiple simulated networks and real-cell regulatory networks. Additionally, we applied DeepRIG to the samples of human peripheral blood mononuclear cells and triple-negative breast cancer, and presented that DeepRIG can provide accurate cell-type-specific gene regulatory networks inference and identify novel regulators of progression and inhibition.

| S-EPMC10519590 | biostudies-literature

TIANA: transcription factors cooperativity inference analysis with neural attention

Project description: Not available

| S-EPMC11342676 | biostudies-literature

Self-Sorting Governed by Chelate Cooperativity.

Project description:Self-sorting phenomena are the basis of manifold relevant (bio)chemical processes where a set of molecules is able to interact with no interference from other sets and are ruled by a number of codes that are programmed in molecular structures. In this work, we study, the relevance of chelate cooperativity as a code for achieving high self-sorting fidelities. In particular, we establish qualitative and quantitative relationships between the cooperativity of a cyclic system and the self-sorting fidelity when combined with other molecules that share identical geometry and/or binding interactions. We demonstrate that only systems displaying sufficiently strong chelate cooperativity can achieve quantitative narcissistic self-sorting fidelities either by dictating the distribution of cyclic species in complex mixtures or by ruling the competition between the intra- and intermolecular versions of a noncovalent interaction.

| S-EPMC8972263 | biostudies-literature

Intrinsic cooperativity potentiates parallel cis-regulatory evolution.

Project description:Convergent evolutionary events in independent lineages provide an opportunity to understand why evolution favors certain outcomes over others. We studied such a case where a large set of genes-those coding for the ribosomal proteins-gained cis-regulatory sequences for a particular transcription regulator (Mcm1) in independent fungal lineages. We present evidence that these gains occurred because Mcm1 shares a mechanism of transcriptional activation with an ancestral regulator of the ribosomal protein genes, Rap1. Specifically, we show that Mcm1 and Rap1 have the inherent ability to cooperatively activate transcription through contacts with the general transcription factor TFIID. Because the two regulatory proteins share a common interaction partner, the presence of one ancestral cis-regulatory sequence can 'channel' random mutations into functional sites for the second regulator. At a genomic scale, this type of intrinsic cooperativity can account for a pattern of parallel evolution involving the fixation of hundreds of substitutions.

| S-EPMC6173580 | biostudies-literature

Image classification model based on large kernel attention mechanism and relative position self-attention mechanism

Project description:The Transformer has achieved great success in many computer vision tasks. With the in-depth exploration of it, researchers have found that Transformers can better obtain long-range features than convolutional neural networks (CNN). However, there will be a deterioration of local feature details when the Transformer extracts local features. Although CNN is adept at capturing the local feature details, it cannot easily obtain the global representation of features. In order to solve the above problems effectively, this paper proposes a hybrid model consisting of CNN and Transformer inspired by Visual Attention Net (VAN) and CoAtNet. This model optimizes its shortcomings in the difficulty of capturing the global representation of features by introducing Large Kernel Attention (LKA) in CNN while using the Transformer blocks with relative position self-attention variant to alleviate the problem of detail deterioration in local features of the Transformer. Our model effectively combines the advantages of the above two structures to obtain the details of local features more accurately and capture the relationship between features far apart more efficiently on a large receptive field. Our experiments show that in the image classification task without additional training data, the proposed model in this paper can achieve excellent results on the cifar10 dataset, the cifar100 dataset, and the birds400 dataset (a public dataset on the Kaggle platform) with fewer model parameters. Among them, SE_LKACAT achieved a Top-1 accuracy of 98.01% on the cifar10 dataset with only 7.5M parameters.

| S-EPMC10280586 | biostudies-literature

Deconvolving sequence features that discriminate between overlapping regulatory annotations.

Project description:Genomic loci with regulatory potential can be annotated with various properties. For example, genomic sites bound by a given transcription factor (TF) can be divided according to whether they are proximal or distal to known promoters. Sites can be further labeled according to the cell types and conditions in which they are active. Given such a collection of labeled sites, it is natural to ask what sequence features are associated with each annotation label. However, discovering such label-specific sequence features is often confounded by overlaps between the labels; e.g. if regulatory sites specific to a given cell type are also more likely to be promoter-proximal, it is difficult to assess whether motifs identified in that set of sites are associated with the cell type or associated with promoters. In order to meet this challenge, we developed SeqUnwinder, a principled approach to deconvolving interpretable discriminative sequence features associated with overlapping annotation labels. We demonstrate the novel analysis abilities of SeqUnwinder using three examples. Firstly, SeqUnwinder is able to unravel sequence features associated with the dynamic binding behavior of TFs during motor neuron programming from features associated with chromatin state in the initial embryonic stem cells. Secondly, we characterize distinct sequence properties of multi-condition and cell-specific TF binding sites after controlling for uneven associations with promoter proximity. Finally, we demonstrate the scalability of SeqUnwinder to discover cell-specific sequence features from over one hundred thousand genomic loci that display DNase I hypersensitivity in one or more ENCODE cell lines.

| S-EPMC5663517 | biostudies-literature

Functional cooperativity between Myc and PI3K signaling for indefinite self-renewal property of embryonic stem cells

Project description:We explored the relationship between Myc activity and PI3K signaling in ESCs. Our data demonstrate that Myc and PI3K signaling function cooperatively for supporting pluripotent property of ESCs. Moreover, our data demonstrate that exposure of ESCs to 2i condition render both Myc and PI3K dispensable for preserving ESC status. Effect of PI3K inhibitor, LY4294002 on EBRTcH3 ESCs or their derivatives overexpressing c-Myc (wild-type or T58A mutant) was examined. Effect of LY4294002 on EBRTcH3 ESCs under 2i conditions was also examined. Furthermore, effect of Max expression ablation was compared between ESCs and those overexpressing p110 alpha.

2014-10-30 | E-GEOD-60344 | biostudies-arrayexpress

Functional cooperativity between Myc and PI3K signaling for indefinite self-renewal property of embryonic stem cells

2014-10-30 | GSE60344 | GEO

Cooperativity in the self-assembly of porphyrin ladders.

Project description:Cooperativity is a general feature of intermolecular interactions in biomolecular systems, but there are many different facets of the phenomenon that are not well understood. Positive cooperativity stabilizes a system as progressively more interactions are added, and the origin of the beneficial free energy may be entropic or enthalpic in origin. An "enthalpic chelate effect" has been proposed to operate through structural tightening that improves all of the functional group interactions in a complex, when it is more strongly bound. Here, we present direct calorimetric evidence that no such enthalpic effects exist in the cooperative assembly of supramolecular ladder complexes composed of metalloporphyrin oligomers coordinated to bipyridine ligands. The enthalpic contributions of the individual coordination interactions are 35 kJ.mol(-1) and constant over a range of free energies of self-assembly of -35 to -111 kJ.mol(-1). In rigid well defined systems of this type, the enthalpies of individual interactions are additive, and no enthalpic cooperative effects are apparent. The implication is that in more flexible, less well defined systems such as biomolecular assemblies, the enthalpy contributions available from specific functional group interactions are well defined and constant parameters.

| S-EPMC1413879 | biostudies-literature

OmicsDI is part of the ELIXIR infrastructure

OmicsDI is an Elixir interoperability service. Learn more ›

Tweets

OmicsDI Databases

PRIDE
PeptideAtlas
MassIVE
JPOST Repository
Physiome Model Repository

EGA
EVA
ENA
LINCS
PAXDB
Cell Collective

MetaboLights
Metabolomics Workbench
MetabolomeExpress
GNPS
BioModels
FAIRDOMHub

ArrayExpress
dbGaP
ExpressionAtlas
GEO
NODE

Information

Databases
Help
API
Contact us
Code on GitHub
Terms of use
Submit Data