Explainability in transformer models for functional genomics.
Ontology highlight
ABSTRACT:
SUBMITTER: Clauwaert J
PROVIDER: S-EPMC8425421 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:Neisseria meningitidis is a harmless commensal bacterium finely adapted to humans. Unfortunately, under "privileged" conditions, it adopts a "devious" lifestyle leading to uncontrolled behavior characterized by the unleashing of molecular weapons causing potentially lethal disease such as sepsis and acute meningitis. Indeed, despite the lack of a classic repertoire of virulence genes in N. meningitidis separating commensal from invasive strains, molecular epidemiology and functional genomics studies suggest that carriage and invasive strains belong to genetically distinct populations characterized by an exclusive pathogenic potential. In the last few years, "omics" technologies have helped scientists to unwrap the framework drawn by N. meningitidis during different stages of colonization and disease. However, this scenario is still incomplete and would benefit from the implementation of physiological tissue models for the reproduction of mucosal and systemic interactions in vitro. These emerging technologies supported by recent advances in the world of stem cell biology hold the promise for a further understanding of N. meningitidis pathogenesis.
| S-EPMC5531161 | biostudies-other
Project description:Genetic tools and mutagenesis strategies based on transposable elements are currently under development with a vision to link primary DNA sequence information to gene functions in vertebrate models. By virtue of their inherent capacity to insert into DNA, transposons can be developed into powerful tools for chromosomal manipulations. Transposon-based forward mutagenesis screens have numerous advantages including high throughput, easy identification of mutated alleles, and providing insight into genetic networks and pathways based on phenotypes. For example, the Sleeping Beauty transposon has become highly instrumental to induce tumors in experimental animals in a tissue-specific manner with the aim of uncovering the genetic basis of diverse cancers. Here, we describe a battery of mutagenic cassettes that can be applied in conjunction with transposon vectors to mutagenize genes, and highlight versatile experimental strategies for the generation of engineered chromosomes for loss-of-function as well as gain-of-function mutagenesis for functional gene annotation in vertebrate models, including zebrafish, mice, and rats.
| S-EPMC5682939 | biostudies-literature
Project description:One of the first steps in analyzing high-dimensional functional genomics data is an exploratory analysis of such data. Cluster Analysis and Principal Component Analysis are then usually the method of choice. Despite their versatility they also have a severe drawback: they do not always generate simple and interpretable solutions. On the basis of the observation that functional genomics data often contain both informative and non-informative variation, we propose a method that finds sets of variables containing informative variation. This informative variation is subsequently expressed in easily interpretable simplivariate components.We present a new implementation of the recently introduced simplivariate models. In this implementation, the informative variation is described by multiplicative models that can adequately represent the relations between functional genomics data. Both a simulated and two real-life metabolomics data sets show good performance of the method.
| S-EPMC3116836 | biostudies-literature
Project description:The problem of reconstructing large-scale, gene regulatory networks from gene expression data has garnered considerable attention in bioinformatics over the past decade with the graphical modeling paradigm having emerged as a popular framework for inference. Analysis in a full Bayesian setting is contingent upon the assignment of a so-called structure prior-a probability distribution on networks, encoding a priori biological knowledge either in the form of supplemental data or high-level topological features. A key topological consideration is that a wide range of cellular networks are approximately scale-free, meaning that the fraction, , of nodes in a network with degree is roughly described by a power-law with exponent between and . The standard practice, however, is to utilize a random structure prior, which favors networks with binomially distributed degree distributions. In this paper, we introduce a scale-free structure prior for graphical models based on the formula for the probability of a network under a simple scale-free network model. Unlike the random structure prior, its scale-free counterpart requires a node labeling as a parameter. In order to use this prior for large-scale network inference, we design a novel Metropolis-Hastings sampler for graphical models that includes a node labeling as a state space variable. In a simulation study, we demonstrate that the scale-free structure prior outperforms the random structure prior at recovering scale-free networks while at the same time retains the ability to recover random networks. We then estimate a gene association network from gene expression data taken from a breast cancer tumor study, showing that scale-free structure prior recovers hubs, including the previously unknown hub SLC39A6, which is a zinc transporter that has been implicated with the spread of breast cancer to the lymph nodes. Our analysis of the breast cancer expression data underscores the value of the scale-free structure prior as an instrument to aid in the identification of candidate hub genes with the potential to direct the hypotheses of molecular biologists, and thus drive future experiments.
| S-EPMC2974640 | biostudies-literature
Project description:The aim of this work is to apply an integrated systems approach to understand the biological underpinnings of hip osteoarthritis that culminates in the need for total joint replacement (TJR). This study is a feasibility pilot that integrates functional genomics data from diseased and non-diseased tissues of OA patients who have undergone TJR. For each tissue, we characterised epigenetic marks (methylation), gene transcription (RNASeq) and expression (quantitative proteomics). We also generated genotype data on the HumanCoreExome array for each individual. This data is part of a pre-publication release.
2018-05-14 | PXD006673 | Pride
Project description:Genome-scale network reconstructions are useful tools for understanding cellular metabolism, and comparisons of such reconstructions can provide insight into metabolic differences between organisms. Recent efforts toward comparing genome-scale models have focused primarily on aligning metabolic networks at the reaction level and then looking at differences and similarities in reaction and gene content. However, these reaction comparison approaches are time-consuming and do not identify the effect network differences have on the functional states of the network. We have developed a bilevel mixed-integer programming approach, CONGA, to identify functional differences between metabolic networks by comparing network reconstructions aligned at the gene level. We first identify orthologous genes across two reconstructions and then use CONGA to identify conditions under which differences in gene content give rise to differences in metabolic capabilities. By seeking genes whose deletion in one or both models disproportionately changes flux through a selected reaction (e.g., growth or by-product secretion) in one model over another, we are able to identify structural metabolic network differences enabling unique metabolic capabilities. Using CONGA, we explore functional differences between two metabolic reconstructions of Escherichia coli and identify a set of reactions responsible for chemical production differences between the two models. We also use this approach to aid in the development of a genome-scale model of Synechococcus sp. PCC 7002. Finally, we propose potential antimicrobial targets in Mycobacterium tuberculosis and Staphylococcus aureus based on differences in their metabolic capabilities. Through these examples, we demonstrate that a gene-centric approach to comparing metabolic networks allows for a rapid comparison of metabolic models at a functional level. Using CONGA, we can identify differences in reaction and gene content which give rise to different functional predictions. Because CONGA provides a general framework, it can be applied to find functional differences across models and biological systems beyond those presented here.
| S-EPMC3359066 | biostudies-literature
Project description:Alzheimer's disease (AD) is a complex and multifactorial neurodegenerative disease. Due to its long clinical course and lack of an effective treatment, AD has become a major public health problem in the USA and worldwide. Due to variation in age-at-onset, AD is classified into early-onset (< 60 years) and late-onset (≥ 60 years) forms with early-onset accounting for only 5-10% of all cases. With the exception of a small number of early-onset cases that are afflicted because of high penetrant single gene mutations in APP, PSEN1, and PSEN2 genes, AD is genetically heterogeneous, especially the late-onset form having a polygenic or oligogenic risk inheritance. Since the identification of APOE as the most significant risk factor for late-onset AD in 1993, the path to the discovery of additional AD risk genes had been arduous until 2009 when the use of large genome-wide association studies opened up the discovery gateways that led the identification of ~ 95 additional risk loci from 2009 to early 2022. This article reviews the history of AD genetics followed by the potential molecular pathways and recent application of functional genomics methods to identify the causal AD gene(s) among the many genes that reside within a single locus. The ultimate goal of integrating genomics and functional genomics is to discover novel pathways underlying the AD pathobiology in order to identify drug targets for the therapeutic treatment of this heterogeneous disorder.
| S-EPMC9130391 | biostudies-literature
Project description:The established approach to unsupervised protein contact prediction estimates coevolving positions using undirected graphical models. This approach trains a Potts model on a Multiple Sequence Alignment. Increasingly large Transformers are being pretrained on unlabeled, unaligned protein sequence databases and showing competitive performance on protein contact prediction. We argue that attention is a principled model of protein interactions, grounded in real properties of protein family data. We introduce an energy-based attention layer, factored attention, which, in a certain limit, recovers a Potts model, and use it to contrast Potts and Transformers. We show that the Transformer leverages hierarchical signal in protein family databases not captured by single-layer models. This raises the exciting possibility for the development of powerful structured models of protein family databases.
| S-EPMC8752338 | biostudies-literature
Project description:MotivationWe explored how explainable artificial intelligence (XAI) can help to shed light into the inner workings of neural networks for protein function prediction, by extending the widely used XAI method of integrated gradients such that latent representations inside of transformer models, which were finetuned to Gene Ontology term and Enzyme Commission number prediction, can be inspected too.ResultsThe approach enabled us to identify amino acids in the sequences that the transformers pay particular attention to, and to show that these relevant sequence parts reflect expectations from biology and chemistry, both in the embedding layer and inside of the model, where we identified transformer heads with a statistically significant correspondence of attribution maps with ground truth sequence annotations (e.g. transmembrane regions, active sites) across many proteins.Availability and implementationSource code can be accessed at https://github.com/markuswenzel/xai-proteins.
| S-EPMC10950482 | biostudies-literature
Project description:The bias in protein structure and function space resulting from experimental limitations and targeting of particular functional classes of proteins by structural biologists has long been recognized, but never continuously quantified. Using the Enzyme Commission and the Gene Ontology classifications as a reference frame, and integrating structure data from the Protein Data Bank (PDB), target sequences from the structural genomics projects, structure homology derived from the SUPERFAMILY database, and genome annotations from Ensembl and NCBI, we provide a quantified view, both at the domain and whole-protein levels, of the current and projected coverage of protein structure and function space relative to the human genome. Protein structures currently provide at least one domain that covers 37% of the functional classes identified in the genome; whole structure coverage exists for 25% of the genome. If all the structural genomics targets were solved (twice the current number of structures in the PDB), it is estimated that structures of one domain would cover 69% of the functional classes identified and complete structure coverage would be 44%. Homology models from existing experimental structures extend the 37% coverage to 56% of the genome as single domains and 25% to 31% for complete structures. Coverage from homology models is not evenly distributed by protein family, reflecting differing degrees of sequence and structure divergence within families. While these data provide coverage, conversely, they also systematically highlight functional classes of proteins for which structures should be determined. Current key functional families without structure representation are highlighted here; updated information on the "most wanted list" that should be solved is available on a weekly basis from http://function.rcsb.org:8080/pdb/function_distribution/index.html.
| S-EPMC1188274 | biostudies-literature