1
|
Ma J, Song J, Young ND, Chang BCH, Korhonen PK, Campos TL, Liu H, Gasser RB. 'Bingo'-a large language model- and graph neural network-based workflow for the prediction of essential genes from protein data. Brief Bioinform 2023; 25:bbad472. [PMID: 38152979 PMCID: PMC10753293 DOI: 10.1093/bib/bbad472] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/13/2023] [Revised: 10/22/2023] [Accepted: 11/28/2023] [Indexed: 12/29/2023] Open
Abstract
The identification and characterization of essential genes are central to our understanding of the core biological functions in eukaryotic organisms, and has important implications for the treatment of diseases caused by, for example, cancers and pathogens. Given the major constraints in testing the functions of genes of many organisms in the laboratory, due to the absence of in vitro cultures and/or gene perturbation assays for most metazoan species, there has been a need to develop in silico tools for the accurate prediction or inference of essential genes to underpin systems biological investigations. Major advances in machine learning approaches provide unprecedented opportunities to overcome these limitations and accelerate the discovery of essential genes on a genome-wide scale. Here, we developed and evaluated a large language model- and graph neural network (LLM-GNN)-based approach, called 'Bingo', to predict essential protein-coding genes in the metazoan model organisms Caenorhabditis elegans and Drosophila melanogaster as well as in Mus musculus and Homo sapiens (a HepG2 cell line) by integrating LLM and GNNs with adversarial training. Bingo predicts essential genes under two 'zero-shot' scenarios with transfer learning, showing promise to compensate for a lack of high-quality genomic and proteomic data for non-model organisms. In addition, the attention mechanisms and GNNExplainer were employed to manifest the functional sites and structural domain with most contribution to essentiality. In conclusion, Bingo provides the prospect of being able to accurately infer the essential genes of little- or under-studied organisms of interest, and provides a biological explanation for gene essentiality.
Collapse
Affiliation(s)
- Jiani Ma
- Department of Veterinary Biosciences, Melbourne Veterinary School, The University of Melbourne, Parkville, Victoria 3010, Australia
- School of Information and Control Engineering, China University of Mining and Technology, Xuzhou 221116, China
| | - Jiangning Song
- Department of Veterinary Biosciences, Melbourne Veterinary School, The University of Melbourne, Parkville, Victoria 3010, Australia
- Monash Biomedicine Discovery Institute and Department of Biochemistry and Molecular Biology, Monash University, Melbourne, Victoria 3800, Australia
| | - Neil D Young
- Department of Veterinary Biosciences, Melbourne Veterinary School, The University of Melbourne, Parkville, Victoria 3010, Australia
| | - Bill C H Chang
- Department of Veterinary Biosciences, Melbourne Veterinary School, The University of Melbourne, Parkville, Victoria 3010, Australia
| | - Pasi K Korhonen
- Department of Veterinary Biosciences, Melbourne Veterinary School, The University of Melbourne, Parkville, Victoria 3010, Australia
| | - Tulio L Campos
- Department of Veterinary Biosciences, Melbourne Veterinary School, The University of Melbourne, Parkville, Victoria 3010, Australia
- Bioinformatics Core Facility, Instituto Aggeu Magalhaes, Fundaçao Oswaldo Cruz (IAM-Fiocruz), Recife, Pernambuco, Brazil
| | - Hui Liu
- School of Information and Control Engineering, China University of Mining and Technology, Xuzhou 221116, China
| | - Robin B Gasser
- Department of Veterinary Biosciences, Melbourne Veterinary School, The University of Melbourne, Parkville, Victoria 3010, Australia
| |
Collapse
|
2
|
Vekris A, Pilalis E, Chatziioannou A, Petry KG. A Computational Pipeline for the Extraction of Actionable Biological Information From NGS-Phage Display Experiments. Front Physiol 2019; 10:1160. [PMID: 31607941 PMCID: PMC6769401 DOI: 10.3389/fphys.2019.01160] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.6] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/23/2018] [Accepted: 08/28/2019] [Indexed: 12/20/2022] Open
Abstract
Phage Display is a powerful method for the identification of peptide binding to targets of variable complexities and tissues, from unique molecules to the internal surfaces of vessels of living organisms. Particularly for in vivo screenings, the resulting repertoires can be very complex and difficult to study with traditional approaches. Next Generation Sequencing (NGS) opened the possibility to acquire high resolution overviews of such repertoires and thus facilitates the identification of binders of interest. Additionally, the ever-increasing amount of available genome/proteome information became satisfactory regarding the identification of putative mimicked proteins, due to the large scale on which partial sequence homology is assessed. However, the subsequent production of massive data stresses the need for high-performance computational approaches in order to perform standardized and insightful molecular network analysis. Systems-level analysis is essential for efficient resolution of the underlying molecular complexity and the extraction of actionable interpretation, in terms of systemic biological processes and pathways that are systematically perturbed. In this work we introduce PepSimili, an integrated workflow tool, which performs mapping of massive peptide repertoires on whole proteomes and delivers a streamlined, systems-level biological interpretation. The tool employs modules for modeling and filtering of background noise due to random mappings and amplifies the biologically meaningful signal through coupling with BioInfoMiner, a systems interpretation tool that employs graph-theoretic methods for prioritization of systemic processes and corresponding driver genes. The current implementation exploits the Galaxy environment and is available online. A case study using public data is presented, with and without a control selection.
Collapse
Affiliation(s)
| | - Eleftherios Pilalis
- Metabolic Engineering and Bioinformatics Program, Institute of Chemical Biology, National Hellenic Research Foundation, Athens, Greece.,eNIOS Applications P.C., Athens, Greece
| | - Aristotelis Chatziioannou
- Metabolic Engineering and Bioinformatics Program, Institute of Chemical Biology, National Hellenic Research Foundation, Athens, Greece.,eNIOS Applications P.C., Athens, Greece
| | | |
Collapse
|
3
|
Reif DM, Israel MA, Moore JH. Exploratory Visual Analysis of statistical results from microarray experiments comparing high and low grade glioma. Cancer Inform 2007; 5:19-24. [PMID: 19390666 PMCID: PMC2666953] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/25/2022] Open
Abstract
The biological interpretation of gene expression microarray results is a daunting challenge. For complex diseases such as cancer, wherein the body of published research is extensive, the incorporation of expert knowledge provides a useful analytical framework. We have previously developed the Exploratory Visual Analysis (EVA) software for exploring data analysis results in the context of annotation information about each gene, as well as biologically relevant groups of genes. We present EVA as a flexible combination of statistics and biological annotation that provides a straightforward visual interface for the interpretation of microarray analyses of gene expression in the most commonly occurring class of brain tumors, glioma. We demonstrate the utility of EVA for the biological interpretation of statistical results by analyzing publicly available gene expression profiles of two important glial tumors. The results of a statistical comparison between 21 malignant, high-grade glioblastoma multiforme (GBM) tumors and 19 indolent, low-grade pilocytic astrocytomas were analyzed using EVA. By using EVA to examine the results of a relatively simple statistical analysis, we were able to identify tumor class-specific gene expression patterns having both statistical and biological significance. Our interactive analysis highlighted the potential importance of genes involved in cell cycle progression, proliferation, signaling, adhesion, migration, motility, and structure, as well as candidate gene loci on a region of Chromosome 7 that has been implicated in glioma. Because EVA does not require statistical or computational expertise and has the flexibility to accommodate any type of statistical analysis, we anticipate EVA will prove a useful addition to the repertoire of computational methods used for microarray data analysis. EVA is available at no charge to academic users and can be found at http://www.epistasis.org.
Collapse
Affiliation(s)
- David M. Reif
- Graduate Student, Computational Genetics Laboratory, Dartmouth-Hitchcock Medical Center, Lebanon, NH 03756
| | - Mark A. Israel
- Professor of Pediatrics and Genetics, Director, Norris-Cotton Cancer Center, Dart-mouth-Hitchcock Medical Center, Lebanon, NH 03756
| | - Jason H. Moore
- Frank Lane Research Scholar in Computational Genetics, Associate Professor of Genetics, 706 Rubin Building HB 7937; Dartmouth-Hitchcock Medical Center, One Medical Center Drive, Lebanon,Correspondence: Jason H. Moore, Dartmouth-Hitchcock Medical Center, One Medical Center Drive, Lebanon, NH 03756. Tel: 603-653-9939; Fax: 603-653-9900;
| |
Collapse
|