Identifying essential genes across eukaryotes by machine learning

Beder, Thomas; Aromolaran, Olufemi; Dönitz, Jürgen; Tapanelli, Sofia; Adedeji, Eunice O.; Adebiyi, Ezekiel; Bucher, Gregor; Koenig, Rainer

doi:10.1093/nargab/lqab110

Cited by 12 publications

(6 citation statements)

References 74 publications

(85 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although finding similar works in the literature to compare our results was difficult due to our focus on context-specificity, we considered some of them to generally evaluate the goodness of the measures and consolidate the effectiveness of HELP. In [22], the authors proposed an ML method across six model eukaryotes, called CLEARER, that on human cell lines obtained results comparable to HELP (ROC-AUC=0.955±0.018) using many more features (CLEARER: 41635; HELP: 3456 (Kidney) and 3455 (Lung) Bio+CCcfs+N2V). By embedding the human PPI network, [31] reported BA lower than ours (BA=0.783).…”

Section: Resultsmentioning

confidence: 99%

“…As EGs are genes strongly involved in physical and functional interactions, we considered four interactions-based attributes: "BIOGRID", the number of interactions annotated for each query gene [21]; "UCSC TFBS", the count of predicted transcription factors binding sites (TFBSs) from the UCSC TFBS; "CCBeder" is a set of attributes describing the GO characterisation of the query gene, also considering those of its April 12, 2024 4/20 neighbours in the PPI. They were obtained by performing, for each gene set, a Fisher's exact test for the enrichment of interaction partners through the code made available by [22]. The GO-CC terms were downloaded from the g:Profiler web service as GMT files [23].…”

Section: Data: Multi-omics Featuresmentioning

confidence: 99%

See 1 more Smart Citation

HELP: A computational framework for labelling and predicting human context-specific essential genes

Granata,

Maddalena,

Manzo

et al. 2024

Preprint

View full text Add to dashboard Cite

Machine learning-based approaches are particularly suitable for identifying essential genes as they allow the generation of predictive models trained on features from multi-source data. Gene essentiality is neither binary nor static but determined by the context. The databases for essential gene annotation do not permit the personalisation of the context, and their update can be slower than the publication of new experimental data. We propose HELP (Human Gene Essentiality Labelling & Prediction), a computational framework for labelling and predicting essential genes. Its double scope allows for identifying genes based on dependency or not on experimental data. The effectiveness of the labelling method was demonstrated by comparing it with other approaches in overlapping the state-of-the-art EG annotations, where HELP demonstrated the best compromise between false and true positive rates. The gene attributes, including multi-omics and network embedding features, lead to high-performance prediction of EGs while confirming the existence of essentiality nuances.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Data: Multi-omics Featuresmentioning

confidence: 99%

HELP: A computational framework for labelling and predicting human context-specific essential genes

Granata,

Maddalena,

Manzo

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…The procedure for feature generation was similar as published earlier for essential gene prediction (54, 55, 78). Each gene served as a sample in the machine learning procedure, either labelled as HDF or non-HDF, or was not used for training the classifiers.…”

Section: Methodsmentioning

confidence: 99%

Machine learning on large scale perturbation screens for SARS-CoV-2 host factors identifies β-catenin/CBP inhibitor PRI-724 as a potent antiviral

Kelch

Vera-Guapi

Beder

et al. 2023

Preprint

Self Cite

View full text Add to dashboard Cite

Expanding antiviral treatment options against SARS-CoV-2 remains crucial as the virus evolves rapidly and drug resistant strains have emerged. Broad spectrum host-directed antivirals (HDA) are promising therapeutic options, however the robust identification of relevant host factors by CRISPR/Cas9 or RNA interference screens remains challenging due to low consistency in the resulting hits. To address this issue, we employed machine learning based on experimental data from knockout screens and a drug screen. As gold standard, we assembled perturbed genes reducing virus replication or protecting the host cells. The machines based their predictions on features describing cellular localization, protein domains, annotated gene sets from Gene Ontology, gene and protein sequences, and experimental data from proteomics, phospho-proteomics, protein interaction and transcriptomic profiles of SARS-CoV-2 infected cells. The models reached a remarkable performance with a balanced accuracy of 0.82 (knockout based classifier) and 0.71 (drugs screen based classifier), suggesting patterns of intrinsic data consistency. The predicted host dependency factors were enriched in sets of genes particularly coding for development, morphogenesis, and neural related processes. Focusing on development and morphogenesis-associated gene sets, we found β-catenin to be central and selected PRI-724, a canonical β-catenin/CBP disruptor, as a potential HDA. PRI-724 limited infection with SARS-CoV-2 variants, SARS-CoV-1, MERS-CoV and IAV in different cell line models. We detected a concentration-dependent reduction in CPE development, viral RNA replication, and infectious virus production in SARS-CoV-2 and SARS-CoV-1-infected cells. Independent of virus infection, PRI-724 treatment caused cell cycle deregulation which substantiates its potential as a broad spectrum antiviral. Our proposed machine learning concept may support focusing and accelerating the discovery of host dependency factors and the design of antiviral therapies.

show abstract

“…The procedure for feature generation was similar as published earlier for essential gene prediction ( Acencio and Lemke, 2009 ; Aromolaran et al, 2020 ; Beder et al, 2021 ). Each gene served as a sample in the machine learning procedure, either labeled as HDF or non-HDF, or was not used for training the classifiers.…”

Section: Methodsmentioning

confidence: 99%

Machine learning on large scale perturbation screens for SARS-CoV-2 host factors identifies β-catenin/CBP inhibitor PRI-724 as a potent antiviral

et al. 2023

Self Cite

View full text Add to dashboard Cite

Expanding antiviral treatment options against SARS-CoV-2 remains crucial as the virus evolves under selection pressure which already led to the emergence of several drug resistant strains. Broad spectrum host-directed antivirals (HDA) are promising therapeutic options, however the robust identification of relevant host factors by CRISPR/Cas9 or RNA interference screens remains challenging due to low consistency in the resulting hits. To address this issue, we employed machine learning, based on experimental data from several knockout screens and a drug screen. We trained classifiers using genes essential for virus life cycle obtained from the knockout screens. The machines based their predictions on features describing cellular localization, protein domains, annotated gene sets from Gene Ontology, gene and protein sequences, and experimental data from proteomics, phospho-proteomics, protein interaction and transcriptomic profiles of SARS-CoV-2 infected cells. The models reached a remarkable performance suggesting patterns of intrinsic data consistency. The predicted HDF were enriched in sets of genes particularly encoding development, morphogenesis, and neural processes. Focusing on development and morphogenesis-associated gene sets, we found β-catenin to be central and selected PRI-724, a canonical β-catenin/CBP disruptor, as a potential HDA. PRI-724 limited infection with SARS-CoV-2 variants, SARS-CoV-1, MERS-CoV and IAV in different cell line models. We detected a concentration-dependent reduction in cytopathic effects, viral RNA replication, and infectious virus production in SARS-CoV-2 and SARS-CoV-1-infected cells. Independent of virus infection, PRI-724 treatment caused cell cycle deregulation which substantiates its potential as a broad spectrum antiviral. Our proposed machine learning concept supports focusing and accelerating the discovery of host dependency factors and identification of potential host-directed antivirals.

show abstract

Identifying essential genes across eukaryotes by machine learning

Cited by 12 publications

References 74 publications

HELP: A computational framework for labelling and predicting human context-specific essential genes

HELP: A computational framework for labelling and predicting human context-specific essential genes

Machine learning on large scale perturbation screens for SARS-CoV-2 host factors identifies β-catenin/CBP inhibitor PRI-724 as a potent antiviral

Machine learning on large scale perturbation screens for SARS-CoV-2 host factors identifies β-catenin/CBP inhibitor PRI-724 as a potent antiviral

Contact Info

Product

Resources

About