Essential gene prediction in Drosophila melanogaster using machine learning approaches based on sequence and functional features

Aromolaran, Olufemi; Beder, Thomas; Oswald, Marcus; Oyelade, Jelili; Adebiyi, Ezekiel; Koenig, Rainer

doi:10.1016/j.csbj.2020.02.022

Cited by 31 publications

(31 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Essentiality predictions were shown to be reliable based on threshold-independent metrics (ROC-AUC and PR-AUC), consistently achieving nearly perfect classification (∼1) by ROC-AUC and improving the PR-AUC by at least 2-fold compared with previously published studies ( 26 , 27 ). Overall, the ensemble-based ML methods (XGB, GBM and RF) achieved the best accuracy and consistency.…”

Section: Discussionmentioning

confidence: 71%

“…A recent study ( 27 ) achieved an improved prediction of essential genes in D. melanogaster by integrating sequence, network and subcellular localization features. The genes included (441 essential and 11 788 non-essential) obtained from essentiality databases; 339 genes were from the Database of Essential Genes (DEG) ( 54 ) and 13 852 from the Online GEne Essentiality database (OGEE) ( 55 ).…”

Section: Discussionmentioning

confidence: 99%

“…In addition, such datasets are limited or unavailable for non-model organisms. Additionally, although sequence-derived features alone have proven useful for essential gene predictions, their performance is still suboptimal, even if combined with PPI network features ( 26 , 27 ).…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Combined use of feature engineering and machine-learning to predict essential genes in Drosophila melanogaster

Campos

Korhonen

Hofmann

et al. 2020

NAR Genomics and Bioinformatics

View full text Add to dashboard Cite

Characterizing genes that are critical for the survival of an organism (i.e. essential) is important to gain a deep understanding of the fundamental cellular and molecular mechanisms that sustain life. Functional genomic investigations of the vinegar fly, Drosophila melanogaster, have unravelled the functions of numerous genes of this model species, but results from phenomic experiments can sometimes be ambiguous. Moreover, the features underlying gene essentiality are poorly understood, posing challenges for computational prediction. Here, we harnessed comprehensive genomic-phenomic datasets publicly available for D. melanogaster and a machine-learning-based workflow to predict essential genes of this fly. We discovered strong predictors of such genes, paving the way for computational predictions of essentiality in less-studied arthropod pests and vectors of infectious diseases.

show abstract

Section: Discussionmentioning

confidence: 71%

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Combined use of feature engineering and machine-learning to predict essential genes in Drosophila melanogaster

Campos

Korhonen

Hofmann

et al. 2020

NAR Genomics and Bioinformatics

View full text Add to dashboard Cite

show abstract

“…A gene ontology (GO) enrichment analysis for D. melanogaster members within these conserved arthropod orthogroups without A. lycopersici members revealed that N-acetylglucosamine metabolic process (GO:0006044), transferase activity (GO:0016740) and Golgi apparatus (GO:000579) were the most highly significantly enriched GO terms within the Biological Process, Molecular Function and Cellular Component GO categories, respectively ( Supplementary file 1 — ‘Table S9’ Tab). Lastly, we found that 427 D. melanogaster essential genes ( Aromolaran et al, 2020 ) coded for members of 390 orthogroups. Forty-eight of these essential orthogroups did not have members within the Acariformes, the mite superorder comprising A. lycopersici , D. pteronyssinus, and T. urticae , while 21 (5.4%) orthogroups were absent in A. lycopersici but present in other acariform mites ( Supplementary file 1 — ‘Table S10’ Tab).…”

Section: Resultsmentioning

confidence: 85%

“…An ORA was performed for each GO category (Biological Process, Molecular Function and Cellular Component) using default settings (and ‘genome protein coding’ as reference set) and a Benjamini-Hochberg multiple testing correction (false discovery rate, FDR, of 0.05). In addition, we also identified those orthogroups that contain purported D. melanogaster essential genes, using the list of 427 essential genes provided in the respective study’s first supplementary data table ( Aromolaran et al, 2020 ).…”

Section: Methodsmentioning

confidence: 99%

Genome streamlining in a minute herbivore that manipulates its host plant

Greenhalgh

Dermauw

Glas

et al. 2020

eLife

View full text Add to dashboard Cite

The tomato russet mite, Aculops lycopersici, is among the smallest animals on earth. It is a worldwide pest on tomato and can potently suppress the host's natural resistance. We sequenced its genome, the first of an eriophyoid, and explored whether there are genomic features associated with the mite's minute size and lifestyle. At only 32.5 Mb, the genome is the smallest yet reported for any arthropod and, reminiscent of microbial eukaryotes, exceptionally streamlined. It has few transposable elements, tiny intergenic regions, and is remarkably intron-poor, as more than 80% of coding genes are intronless. Furthermore, in accordance with ecological specialization theory, this defense-suppressing herbivore has extremely reduced environmental response gene families such as those involved in chemoreception and detoxification. Other losses associate with this species' highly derived body plan. Our findings accelerate the understanding of evolutionary forces underpinning metazoan life at the limits of small physical and genome size.

show abstract