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

Inference of Essential Genes of the Parasite Haemonchus contortus via Machine Learning

Over the years, comprehensive explorations of the model organisms Caenorhabditis elegans (elegant worm) and Drosophila melanogaster (vinegar fly) have contributed substantially to our understanding of complex biological processes and pathways in multicellular organisms generally. Extensive functional genomic-phenomic, genomic, transcriptomic, and proteomic data sets have enabled the discovery and characterisation of genes that are crucial for life, called 'essential genes'. Recently, we investigated the feasibility of inferring essential genes from such data sets using advanced bioinformatics and showed that a machine learning (ML)-based workflow could be used to extract or engineer features from DNA, RNA, protein, and/or cellular data/information to underpin the reliable prediction of essential genes both within and between C. elegans and D. melanogaster. As these are two distantly related species within the Ecdysozoa, we proposed that this ML approach would be particularly well suited for species that are within the same phylum or evolutionary clade. In the present study, we cross-predicted essential genes within the phylum Nematoda (evolutionary clade V)-between C. elegans and the pathogenic parasitic nematode H. contortus-and then ranked and prioritised H. contortus proteins encoded by these genes as intervention (e.g., drug) target candidates. Using strong, validated predictors, we inferred essential genes of H. contortus that are involved predominantly in crucial biological processes/pathways including ribosome biogenesis, translation, RNA binding/processing, and signalling and which are highly transcribed in the germline, somatic gonad precursors, sex myoblasts, vulva cell precursors, various nerve cells, glia, or hypodermis. The findings indicate that this in silico workflow provides a promising avenue to identify and prioritise panels/groups of drug target candidates in parasitic nematodes for experimental validation in vitro and/or in vivo.

Essential genes identification model based on sequence feature map and graph convolutional neural network

BACKGROUND

Essential genes encode functions that play a vital role in the life activities of organisms, encompassing growth, development, immune system functioning, and cell structure maintenance. Conventional experimental techniques for identifying essential genes are resource-intensive and time-consuming, and the accuracy of current machine learning models needs further enhancement. Therefore, it is crucial to develop a robust computational model to accurately predict essential genes.

RESULTS

In this study, we introduce GCNN-SFM, a computational model for identifying essential genes in organisms, based on graph convolutional neural networks (GCNN). GCNN-SFM integrates a graph convolutional layer, a convolutional layer, and a fully connected layer to model and extract features from gene sequences of essential genes. Initially, the gene sequence is transformed into a feature map using coding techniques. Subsequently, a multi-layer GCN is employed to perform graph convolution operations, effectively capturing both local and global features of the gene sequence. Further feature extraction is performed, followed by integrating convolution and fully-connected layers to generate prediction results for essential genes. The gradient descent algorithm is utilized to iteratively update the cross-entropy loss function, thereby enhancing the accuracy of the prediction results. Meanwhile, model parameters are tuned to determine the optimal parameter combination that yields the best prediction performance during training.

CONCLUSIONS

Experimental evaluation demonstrates that GCNN-SFM surpasses various advanced essential gene prediction models and achieves an average accuracy of 94.53%. This study presents a novel and effective approach for identifying essential genes, which has significant implications for biology and genomics research.

'Bingo'-a large language model- and graph neural network-based workflow for the prediction of essential genes from protein data

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.

Heuristic-enabled active machine learning: A case study of predicting essential developmental stage and immune response genes in Drosophila melanogaster

Computational prediction of absolute essential genes using machine learning has gained wide attention in recent years. However, essential genes are mostly conditional and not absolute. Experimental techniques provide a reliable approach of identifying conditionally essential genes; however, experimental methods are laborious, time and resource consuming, hence computational techniques have been used to complement the experimental methods. Computational techniques such as supervised machine learning, or flux balance analysis are grossly limited due to the unavailability of required data for training the model or simulating the conditions for gene essentiality. This study developed a heuristic-enabled active machine learning method based on a light gradient boosting model to predict essential immune response and embryonic developmental genes in Drosophila melanogaster. We proposed a new sampling selection technique and introduced a heuristic function which replaces the human component in traditional active learning models. The heuristic function dynamically selects the unlabelled samples to improve the performance of the classifier in the next iteration. Testing the proposed model with four benchmark datasets, the proposed model showed superior performance when compared to traditional active learning models (random sampling and uncertainty sampling). Applying the model to identify conditionally essential genes, four novel essential immune response genes and a list of 48 novel genes that are essential in embryonic developmental condition were identified. We performed functional enrichment analysis of the predicted genes to elucidate their biological processes and the result evidence our predictions. Immune response and embryonic development related processes were significantly enriched in the essential immune response and embryonic developmental genes, respectively. Finally, we propose the predicted essential genes for future experimental studies and use of the developed tool accessible at http://heal.covenantuniversity.edu.ng for conditional essentiality predictions.

Whole-organism phenotypic screening methods used in early-phase anthelmintic drug discovery

Diseases caused by parasitic helminths (worms) represent a major global health burden in both humans and animals. As vaccines against helminths have yet to achieve a prominent role in worm control, anthelmintics are the primary tool to limit production losses and disease due to helminth infections in both human and veterinary medicine. However, the excessive and often uncontrolled use of these drugs has led to widespread anthelmintic resistance in these worms - particularly of animals - to almost all commercially available anthelmintics, severely compromising control. Thus, there is a major demand for the discovery and development of new classes of anthelmintics. A key component of the discovery process is screening libraries of compounds for anthelmintic activity. Given the need for, and major interest by the pharmaceutical industry in, novel anthelmintics, we considered it both timely and appropriate to re-examine screening methods used for anthelmintic discovery. Thus, we reviewed current literature (1977-2021) on whole-worm phenotypic screening assays developed and used in academic laboratories, with a particular focus on those employed to discover nematocides. This review reveals that at least 50 distinct phenotypic assays with low-, medium- or high-throughput capacity were developed over this period, with more recently developed methods being quantitative, semi-automated and higher throughput. The main features assessed or measured in these assays include worm motility, growth/development, morphological changes, viability/lethality, pharyngeal pumping, egg hatching, larval migration, CO₂- or ATP-production and/or enzyme activity. Recent progress in assay development has led to the routine application of practical, cost-effective, medium- to high-throughput whole-worm screening assays in academic or public-private partnership (PPP) contexts, and major potential for novel high-content, high-throughput platforms in the near future. Complementing this progress are major advances in the molecular data sciences, computational biology and informatics, which are likely to further enable and accelerate anthelmintic drug discovery and development.

Cross-species prediction of essential genes in insects

MOTIVATION

Insects possess a vast phenotypic diversity and key ecological roles. Several insect species also have medical, agricultural and veterinary importance as parasites and disease vectors. Therefore, strategies to identify potential essential genes in insects may reduce the resources needed to find molecular players in central processes of insect biology. However, most predictors of essential genes in multicellular eukaryotes using machine learning rely on expensive and laborious experimental data to be used as gene features, such as gene expression profiles or protein-protein interactions, even though some of this information may not be available for the majority of insect species with genomic sequences available.

RESULTS

Here, we present and validate a machine learning strategy to predict essential genes in insects using sequence-based intrinsic attributes (statistical and physicochemical data) together with the predictions of subcellular location and transcriptomic data, if available. We gathered information available in public databases describing essential and non-essential genes for Drosophila melanogaster (fruit fly, Diptera) and Tribolium castaneum (red flour beetle, Coleoptera). We proceeded by computing intrinsic and extrinsic attributes that were used to train statistical models in one species and tested by their capability of predicting essential genes in the other. Even models trained using only intrinsic attributes are capable of predicting genes in the other insect species, including the prediction of lineage-specific essential genes. Furthermore, the inclusion of RNA-Seq data is a major factor to increase classifier performance.

AVAILABILITY AND IMPLEMENTATION

The code, data and final models produced in this study are freely available at https://github.com/g1o/GeneEssentiality/.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Harnessing model organism genomics to underpin the machine learning-based prediction of essential genes in eukaryotes - Biotechnological implications

The availability of high-quality genomes and advances in functional genomics have enabled large-scale studies of essential genes in model eukaryotes, including the 'elegant worm' (Caenorhabditis elegans; Nematoda) and the 'vinegar fly' (Drosophila melanogaster; Arthropoda). However, this is not the case for other, much less-studied organisms, such as socioeconomically important parasites, for which functional genomic platforms usually do not exist. Thus, there is a need to develop innovative techniques or approaches for the prediction, identification and investigation of essential genes. A key approach that could enable the prediction of such genes is machine learning (ML). Here, we undertake an historical review of experimental and computational approaches employed for the characterisation of essential genes in eukaryotes, with a particular focus on model ecdysozoans (C. elegans and D. melanogaster), and discuss the possible applicability of ML-approaches to organisms such as socioeconomically important parasites. We highlight some recent results showing that high-performance ML, combined with feature engineering, allows a reliable prediction of essential genes from extensive, publicly available 'omic data sets, with major potential to prioritise such genes (with statistical confidence) for subsequent functional genomic validation. These findings could 'open the door' to fundamental and applied research areas. Evidence of some commonality in the essential gene-complement between these two organisms indicates that an ML-engineering approach could find broader applicability to ecdysozoans such as parasitic nematodes or arthropods, provided that suitably large and informative data sets become/are available for proper feature engineering, and for the robust training and validation of algorithms. This area warrants detailed exploration to, for example, facilitate the identification and characterisation of essential molecules as novel targets for drugs and vaccines against parasitic diseases. This focus is particularly important, given the substantial impact that such diseases have worldwide, and the current challenges associated with their prevention and control and with drug resistance in parasite populations.

Cross-Predicting Essential Genes between Two Model Eukaryotic Species Using Machine Learning

Experimental studies of Caenorhabditis elegans and Drosophila melanogaster have contributed substantially to our understanding of molecular and cellular processes in metazoans at large. Since the publication of their genomes, functional genomic investigations have identified genes that are essential or non-essential for survival in each species. Recently, a range of features linked to gene essentiality have been inferred using a machine learning (ML)-based approach, allowing essentiality predictions within a species. Nevertheless, predictions between species are still elusive. Here, we undertake a comprehensive study using ML to discover and validate features of essential genes common to both C. elegans and D. melanogaster. We demonstrate that the cross-species prediction of gene essentiality is possible using a subset of features linked to nucleotide/protein sequences, protein orthology and subcellular localisation, single-cell RNA-seq, and histone methylation markers. Complementary analyses showed that essential genes are enriched for transcription and translation functions and are preferentially located away from heterochromatin regions of C. elegans and D. melanogaster chromosomes. The present work should enable the cross-prediction of essential genes between model and non-model metazoans.

A Computational Framework Based on Ensemble Deep Neural Networks for Essential Genes Identification

Essential genes contain key information of genomes that could be the key to a comprehensive understanding of life and evolution. Because of their importance, studies of essential genes have been considered a crucial problem in computational biology. Computational methods for identifying essential genes have become increasingly popular to reduce the cost and time-consumption of traditional experiments. A few models have addressed this problem, but performance is still not satisfactory because of high dimensional features and the use of traditional machine learning algorithms. Thus, there is a need to create a novel model to improve the predictive performance of this problem from DNA sequence features. This study took advantage of a natural language processing (NLP) model in learning biological sequences by treating them as natural language words. To learn the NLP features, a supervised learning model was consequentially employed by an ensemble deep neural network. Our proposed method could identify essential genes with sensitivity, specificity, accuracy, Matthews correlation coefficient (MCC), and area under the receiver operating characteristic curve (AUC) values of 60.2%, 84.6%, 76.3%, 0.449, and 0.814, respectively. The overall performance outperformed the single models without ensemble, as well as the state-of-the-art predictors on the same benchmark dataset. This indicated the effectiveness of the proposed method in determining essential genes, in particular, and other sequencing problems, in general.