Prediction Of Essential Genes Research Articles

Robust evaluation of deep learning-based representation methods for survival and gene essentiality prediction on bulk RNA-seq data

Deep learning (DL) has shown potential to provide powerful representations of bulk RNA-seq data in cancer research. However, there is no consensus regarding the impact of design choices of DL approaches on the performance of the learned representation, including the model architecture, the training methodology and the various hyperparameters. To address this problem, we evaluate the performance of various design choices of DL representation learning methods using TCGA and DepMap pan-cancer datasets and assess their predictive power for survival and gene essentiality predictions. We demonstrate that baseline methods achieve comparable or superior performance compared to more complex models on survival predictions tasks. DL representation methods, however, are the most efficient to predict the gene essentiality of cell lines. We show that auto-encoders (AE) are consistently improved by techniques such as masking and multi-head training. Our results suggest that the impact of DL representations and of pretraining are highly task- and architecture-dependent, highlighting the need for adopting rigorous evaluation guidelines. These guidelines for robust evaluation are implemented in a pipeline made available to the research community.

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.

GPT-4 as a biomedical simulator

BackgroundComputational simulation of biological processes can be a valuable tool for accelerating biomedical research, but usually requires extensive domain knowledge and manual adaptation. Large language models (LLMs) such as GPT-4 have proven surprisingly successful for a wide range of tasks. This study provides proof-of-concept for the use of GPT-4 as a versatile simulator of biological systems. MethodsWe introduce SimulateGPT, a proof-of-concept for knowledge-driven simulation across levels of biological organization through structured prompting of GPT-4. We benchmarked our approach against direct GPT-4 inference in blinded qualitative evaluations by domain experts in four scenarios and in two quantitative scenarios with experimental ground truth. The qualitative scenarios included mouse experiments with known outcomes and treatment decision support in sepsis. The quantitative scenarios included prediction of gene essentiality in cancer cells and progression-free survival in cancer patients. ResultsIn qualitative experiments, biomedical scientists rated SimulateGPT's predictions favorably over direct GPT-4 inference. In quantitative experiments, SimulateGPT substantially improved classification accuracy for predicting the essentiality of individual genes and increased correlation coefficients and precision in the regression task of predicting progression-free survival. ConclusionThis proof-of-concept study suggests that LLMs may enable a new class of biomedical simulators. Such text-based simulations appear well suited for modeling and understanding complex living systems that are difficult to describe with physics-based first-principles simulations, but for which extensive knowledge is available as written text. Finally, we propose several directions for further development of LLM-based biomedical simulators, including augmentation through web search retrieval, integrated mathematical modeling, and fine-tuning on experimental data.

Review and meta-analysis of the genetic Minimal Cut Set approach for gene essentiality prediction in cancer metabolism.

Cancer metabolism is a marvellously complex topic, in part, due to the reprogramming of its pathways to self-sustain the malignant phenotype in the disease, to the detriment of its healthy counterpart. Understanding these adjustments can provide novel targeted therapies that could disrupt and impair proliferation of cancerous cells. For this very purpose, genome-scale metabolic models (GEMs) have been developed, with Human1 being the most recent reconstruction of the human metabolism. Based on GEMs, we introduced the genetic Minimal Cut Set (gMCS) approach, an uncontextualized methodology that exploits the concepts of synthetic lethality to predict metabolic vulnerabilities in cancer. gMCSs define a set of genes whose knockout would render the cell unviable by disrupting an essential metabolic task in GEMs, thus, making cellular proliferation impossible. Here, we summarize the gMCS approach and review the current state of the methodology by performing a systematic meta-analysis based on two datasets of gene essentiality in cancer. First, we assess several thresholds and distinct methodologies for discerning highly and lowly expressed genes. Then, we address the premise that gMCSs of distinct length should have the same predictive power. Finally, we question the importance of a gene partaking in multiple gMCSs and analyze the importance of all the essential metabolic tasks defined in Human1. Our meta-analysis resulted in parameter evaluation to increase the predictive power for the gMCS approach, as well as a significant reduction of computation times by only selecting the crucial gMCS lengths, proposing the pertinency of particular parameters for the peak processing of gMCS.

Integration of graph neural networks and genome-scale metabolic models for predicting gene essentiality

Genome-scale metabolic models are powerful tools for understanding cellular physiology. Flux balance analysis (FBA), in particular, is an optimization-based approach widely employed for predicting metabolic phenotypes. In model microbes such as Escherichia coli, FBA has been successful at predicting essential genes, i.e. those genes that impair survival when deleted. A central assumption in this approach is that both wild type and deletion strains optimize the same fitness objective. Although the optimality assumption may hold for the wild type metabolic network, deletion strains are not subject to the same evolutionary pressures and knock-out mutants may steer their metabolism to meet other objectives for survival. Here, we present FlowGAT, a hybrid FBA-machine learning strategy for predicting essentiality directly from wild type metabolic phenotypes. The approach is based on graph-structured representation of metabolic fluxes predicted by FBA, where nodes correspond to enzymatic reactions and edges quantify the propagation of metabolite mass flow between a reaction and its neighbours. We integrate this information into a graph neural network that can be trained on knock-out fitness assay data. Comparisons across different model architectures reveal that FlowGAT predictions for E. coli are close to those of FBA for several growth conditions. This suggests that essentiality of enzymatic genes can be predicted by exploiting the inherent network structure of metabolism. Our approach demonstrates the benefits of combining the mechanistic insights afforded by genome-scale models with the ability of deep learning to infer patterns from complex datasets.

Computational analysis of genes with lethal knockout phenotype and prediction of essential genes in archaea.

The identification of microbial genes essential for survival as those with lethal knockout phenotype (LKP) is a common strategy for functional interrogation of genomes. However, interpretation of the LKP is complicated because a substantial fraction of the genes with this phenotype remains poorly functionally characterized. Furthermore, many genes can exhibit LKP not because their products perform essential cellular functions but because their knockout activates the toxicity of other genes (conditionally essential genes). We analyzed the sets of LKP genes for two archaea, Methanococcus maripaludis and Sulfolobus islandicus, using a variety of computational approaches aiming to differentiate between essential and conditionally essential genes and to predict at least a general function for as many of the proteins encoded by these genes as possible. This analysis allowed us to predict the functions of several LKP genes including previously uncharacterized subunit of the GINS protein complex with an essential function in genome replication and of the KEOPS complex that is responsible for an essential tRNA modification as well as GRP protease implicated in protein quality control. Additionally, several novel antitoxins (conditionally essential genes) were predicted, and this prediction was experimentally validated by showing that the deletion of these genes together with the adjacent genes apparently encoding the cognate toxins caused no growth defect. We applied principal component analysis based on sequence and comparative genomic features showing that this approach can separate essential genes from conditionally essential ones and used it to predict essential genes in other archaeal genomes.IMPORTANCEOnly a relatively small fraction of the genes in any bacterium or archaeon is essential for survival as demonstrated by the lethal effect of their disruption. The identification of essential genes and their functions is crucial for understanding fundamental cell biology. However, many of the genes with a lethal knockout phenotype remain poorly functionally characterized, and furthermore, many genes can exhibit this phenotype not because their products perform essential cellular functions but because their knockout activates the toxicity of other genes. We applied state-of-the-art computational methods to predict the functions of a number of uncharacterized genes with the lethal knockout phenotype in two archaeal species and developed a computational approach to predict genes involved in essential functions. These findings advance the current understanding of key functionalities of archaeal cells.

Recent advances in the characterization of essential genes and development of a database of essential genes.

Over the past few decades, there has been a significant interest in the study of essential genes, which are crucial for the survival of an organism under specific environmental conditions and thus have practical applications in the fields of synthetic biology and medicine. An increasing amount of experimental data on essential genes has been obtained with the continuous development of technological methods. Meanwhile, various computational prediction methods, related databases and web servers have emerged accordingly. To facilitate the study of essential genes, we have established a database of essential genes (DEG), which has become popular with continuous updates to facilitate essential gene feature analysis and prediction, drug and vaccine development, as well as artificial genome design and construction. In this article, we summarized the studies of essential genes, overviewed the relevant databases, and discussed their practical applications. Furthermore, we provided an overview of the main applications of DEG and conducted comprehensive analyses based on its latest version. However, it should be noted that the essential gene is a dynamic concept instead of a binary one, which presents both opportunities and challenges for their future development.

'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.

Synthetic lethality in large-scale integrated metabolic and regulatory network models of human cells

Synthetic lethality (SL) is a promising concept in cancer research. A wide array of computational tools has been developed to predict and exploit synthetic lethality for the identification of tumour-specific vulnerabilities. Previously, we introduced the concept of genetic Minimal Cut Sets (gMCSs), a theoretical approach to SL developed for genome-scale metabolic networks. The major challenge in our gMCS framework is to go beyond metabolic networks and extend existing algorithms to more complex protein-protein interactions. In this article, we take a step further and incorporate linear regulatory pathways into our gMCS approach. Extensive algorithmic modifications to compute gMCSs in integrated metabolic and regulatory models are presented in detail. Our extended approach is applied to calculate gMCSs in integrated models of human cells. In particular, we integrate the most recent genome-scale metabolic network, Human1, with 3 different regulatory network databases: Omnipath, Dorothea and TRRUST. Based on the computed gMCSs and transcriptomic data, we discovered new essential genes and their associated synthetic lethal for different cancer cell lines. The performance of the different integrated models is assessed with available large-scale in-vitro gene silencing data. Finally, we discuss the most relevant gene essentiality predictions based on published literature in cancer research.

Construction and application of the genome-scale metabolic model of Streptomyces radiopugnans.

Geosmin is one of the most common earthy-musty odor compounds, which is mainly produced by Streptomyces. Streptomyces radiopugnans was screened in radiation-polluted soil, which has the potential to overproduce geosmin. However, due to the complex cellular metabolism and regulation mechanism, the phenotypes of S. radiopugnans were hard to investigate. A genome-scale metabolic model of S. radiopugnans named iZDZ767 was constructed. Model iZDZ767 involved 1,411 reactions, 1,399 metabolites, and 767 genes; its gene coverage was 14.1%. Model iZDZ767 could grow on 23 carbon sources and five nitrogen sources, which achieved 82.1% and 83.3% prediction accuracy, respectively. For the essential gene prediction, the accuracy was 97.6%. According to the simulation of model iZDZ767, D-glucose and urea were the best for geosmin fermentation. The culture condition optimization experiments proved that with D-glucose as the carbon source and urea as the nitrogen source (4g/L), geosmin production could reach 581.6ng/L. Using the OptForce algorithm, 29 genes were identified as the targets of metabolic engineering modification. With the help of model iZDZ767, the phenotypes of S. radiopugnans could be well resolved. The key targets for geosmin overproduction could also be identified efficiently.

Identify essential genes based on clustering based synthetic minority oversampling technique

Prediction of essential genes in a life organism is one of the central tasks in synthetic biology. Computational predictors are desired because experimental data is often unavailable. Recently, some sequence-based predictors have been constructed to identify essential genes. However, their predictive performance should be further improved. One key problem is how to effectively extract the sequence-based features, which are able to discriminate the essential genes. Another problem is the imbalanced training set. The amount of essential genes in human cell lines is lower than that of non-essential genes. Therefore, predictors trained with such imbalanced training set tend to identify an unseen sequence as a non-essential gene. Here, a new over-sampling strategy was proposed called Clustering based Synthetic Minority Oversampling Technique (CSMOTE) to overcome the imbalanced data issue. Combining CSMOTE with the Z curve, the global features, and Support Vector Machines, a new protocol called iEsGene-CSMOTE was proposed to identify essential genes. The rigorous jackknife cross validation results indicated that iEsGene-CSMOTE is better than the other competing methods. The proposed method outperformed λ-interval Z curve by 35.48% and 11.25% in terms of Sn and BACC, respectively.

Prediction of essential genes using single nucleotide compositional features in genomes of bacteria: a machine learning-based analysis

Prediction of essential genes using single nucleotide compositional features in genomes of bacteria: a machine learning-based analysis

Prediction of essential genes using single nucleotide compositional features in genomes of bacteria: a machine learning-based analysis

Essential genes are crucial for understanding the cellular processes of an organism. In this article, we have done an extensive machine learning-based analysis of single nucleotide composition in 35 bacterial genomes across several phylogenetic groups. With an objective of classifying essential genes from the remaining genes, we have used seven machine learning-based classifiers - logistic regression, Gaussian Naïve Bayes, k-nearest neighbours, decision tree, random forest, extreme gradient boosting and support vector machine. Random forest classifier was a better performer among the seven classifiers and achieved an AUC score of at least 70% for thirteen organisms. Higher AUC scores were achieved for several organisms such as Salmonella enterica, Sphingomonas wittichii, Bacillus thuringiensis, and Streptococcus pyogenes. Prediction result obtained in general from the machine learning-based analysis suggests that the single nucleotide compositional features may be useful in predicting gene essentiality in some bacteria species though not universally.

Evaluation of machine learning classifiers for predicting essential genes in Mycobacterium tuberculosis strains.

Accurate investigation and prediction of essential genes from bacterial genome is very important as it might be explored in effective targets for antimicrobial drugs and understanding biological mechanism of a cell. A subset of key features data obtained from 14 genome sequence-based features of 20 strains of Mycobacterium tuberculosis bacteria whose essential gene information was downloaded from ePath and NCBI database for mapping and matching essential genes by using a genome extraction program. The selection of key features was performed by using Genetic Algorithm. For each of three classifiers, 80%, 10% and 10% of subset key features were used for training, validation and testing, respectively. Experimental results (10-f-cv) illustrated that DNN (proposed), DT, and SVM achieved AUC of 0.98, 0.88 and 0.82, respectively. DNN (proposed) outperformed DT and SVM. The higher prediction accuracy of classifiers was observed because of using only key features which also justified better generalizability of classifiers and efficiency of key features related to gene essentiality. Besides, DNN (proposed) also showed best prediction performance while compared with other predictors used in previous studies. The genome extraction program was developed for mapping and matching of essential genes between ePath and NCBI database.

Predicting stress response and improved protein overproduction in Bacillus subtilis

Bacillus subtilis is a well-characterized microorganism and a model for the study of Gram-positive bacteria. The bacterium can produce proteins at high densities and yields, which has made it valuable for industrial bioproduction. Like other cell factories, metabolic modeling of B. subtilis has discovered ways to optimize its metabolism toward various applications. The first genome-scale metabolic model (M-model) of B. subtilis was published more than a decade ago and has been applied extensively to understand metabolism, to predict growth phenotypes, and served as a template to reconstruct models for other Gram-positive bacteria. However, M-models are ill-suited to simulate the production and secretion of proteins as well as their proteomic response to stress. Thus, a new generation of metabolic models, known as metabolism and gene expression models (ME-models), has been initiated. Here, we describe the reconstruction and validation of a ME model of B. subtilis, iJT964-ME. This model achieved higher performance scores on the prediction of gene essentiality as compared to the M-model. We successfully validated the model by integrating physiological and omics data associated with gene expression responses to ethanol and salt stress. The model further identified the mechanism by which tryptophan synthesis is upregulated under ethanol stress. Further, we employed iJT964-ME to predict amylase production rates under two different growth conditions. We analyzed these flux distributions and identified key metabolic pathways that permitted the increase in amylase production. Models like iJT964-ME enable the study of proteomic response to stress and the illustrate the potential for optimizing protein production in bacteria.

Comprehensive meta-analysis and machine learning approaches identified the role of novel drought specific genes in Oryza sativa

Rice is a major food crop and provides nutrition for half of the world's population. Rice production is majorly affected by drought at different developmental stages and accounted for annual yield loss depending on the intensity of drought. Hence, the need to study the molecular mechanism in a holistic manner behind drought tolerance is a prerequisite to mitigating this problem. Therefore, in the current study, the drought tolerance mechanism of rice plants was elucidated through a meta-analysis on the publically available transcriptomic datasets by integrating these datasets using a R package to remove the batch effects and applying machine learning approaches for prediction robustness and accuracy. Thus, the classifier model identified 128 essential genes through feature selection algorithms and classification methods on training datasets. The comprehensive study revealed that Naïve Bayes classification and correlation-based feature selection was robust in the prediction of essential genes. The accuracy and performance of the classification model was validated with the independent test dataset and the prediction accuracy of the classifier was 93% with ROC (0.972) and F-measures (0.927). Further, the biological significance of the identified genes in drought tolerance was assessed. The current analysis highlighted the regulatory roles of novel genes such as Os01g0844300, Os06g0246500, Os05g03733900, Os05g0550600 Os08g0442900, Os08g0104400, Os01g0256500, Os02g0259900 and Os05g0572700 in the enhancement of drought tolerance mechanisms. Thus the identified genes might be the potential targets for molecular breeding of drought-tolerant rice cultivars.

Analysis of lineage-specific protein family variability in prokaryotes combined with evolutionary reconstructions

BackgroundEvolutionary rate is a key characteristic of gene families that is linked to the functional importance of the respective genes as well as specific biological functions of the proteins they encode. Accurate estimation of evolutionary rates is a challenging task that requires precise phylogenetic analysis. Here we present an easy to estimate protein family level measure of sequence variability based on alignment column homogeneity in multiple alignments of protein sequences from Clade-Specific Clusters of Orthologous Genes (csCOGs).ResultsWe report genome-wide estimates of variability for 8 diverse groups of bacteria and archaea and investigate the connection between variability and various genomic and biological features. The variability estimates are based on homogeneity distributions across amino acid sequence alignments and can be obtained for multiple groups of genomes at minimal computational expense. About half of the variance in variability values can be explained by the analyzed features, with the greatest contribution coming from the extent of gene paralogy in the given csCOG. The correlation between variability and paralogy appears to originate, primarily, not from gene duplication, but from acquisition of distant paralogs and xenologs, introducing sequence variants that are more divergent than those that could have evolved in situ during the lifetime of the given group of organisms. Both high-variability and low-variability csCOGs were identified in all functional categories, but as expected, proteins encoded by integrated mobile elements as well as proteins involved in defense functions and cell motility are, on average, more variable than proteins with housekeeping functions. Additionally, using linear discriminant analysis, we found that variability and fraction of genomes carrying a given gene are the two variables that provide the best prediction of gene essentiality as compared to the results of transposon mutagenesis in Sulfolobus islandicus.ConclusionsVariability, a measure of sequence diversity within an alignment relative to the overall diversity within a group of organisms, offers a convenient proxy for evolutionary rate estimates and is informative with respect to prediction of functional properties of proteins. In particular, variability is a strong predictor of gene essentiality for the respective organisms and indicative of sub- or neofunctionalization of paralogs.

Exploration of Streptococcus core genome to reveal druggable targets and novel therapeutics against S. pneumoniae.

Streptococcus pneumoniae (S. pneumoniae), the major etiological agent of community-acquired pneumonia (CAP) contributes significantly to the global burden of infectious diseases which is getting resistant day by day. Nearly 30% of the S. pneumoniae genomes encode hypothetical proteins (HPs), and better understandings of these HPs in virulence and pathogenicity plausibly decipher new treatments. Some of the HPs are present across many Streptococcus species, systematic assessment of these unexplored HPs will disclose prospective drug targets. In this study, through a stringent bioinformatics analysis of the core genome and proteome of S. pneumoniae PCS8235, we identified and analyzed 28 HPs that are common in many Streptococcus species and might have a potential role in the virulence or pathogenesis of the bacteria. Functional annotations of the proteins were conducted based on the physicochemical properties, subcellular localization, virulence prediction, protein-protein interactions, and identification of essential genes, to find potentially druggable proteins among 28 HPs. The majority of the HPs are involved in bacterial transcription and translation. Besides, some of them were homologs of enzymes, binding proteins, transporters, and regulators. Protein-protein interactions revealed HP PCS8235_RS05845 made the highest interactions with other HPs and also has TRP structural motif along with virulent and pathogenic properties indicating it has critical cellular functions and might go under unconventional protein secretions. The second highest interacting protein HP PCS8235_RS02595 interacts with the Regulator of chromosomal segregation (RocS) which participates in chromosome segregation and nucleoid protection in S. pneumoniae. In this interacting network, 54% of protein members have virulent properties and 40% contain pathogenic properties. Among them, most of these proteins circulate in the cytoplasmic area and have hydrophilic properties. Finally, molecular docking and dynamics simulation demonstrated that the antimalarial drug Artenimol can act as a drug repurposing candidate against HP PCS8235_RS 04650 of S. pneumoniae. Hence, the present study could aid in drugs against S. pneumoniae.

ELIMINATOR: essentiality analysis using multisystem networks and integer programming

A gene is considered as essential when it is indispensable for cells to grow and replicate in a certain environment. However, gene essentiality is not a structural property but rather a contextual one, which depends on the specific biological conditions affecting the cell. This circumstantial essentiality of genes is what brings the attention of scientist since we can identify genes essential for cancer cells but not essential for healthy cells. This same contextuality makes their identification extremely challenging. Huge experimental efforts such as Project Achilles where the essentiality of thousands of genes is measured together with a plethora of molecular data (transcriptomics, copy number, mutations, etc.) in over one thousand cell lines can shed light on the causality behind the essentiality of a gene in a given environment. Here, we present an in-silico method for the identification of patient-specific essential genes using constraint-based modelling (CBM). Our method expands the ideas behind traditional CBM to accommodate multisystem networks. In essence, it first calculates the minimum number of lowly expressed genes required to be activated by the cell to sustain life as defined by a set of requirements; and second, it performs an exhaustive in-silico gene knockout to find those that lead to the need of activating additional lowly expressed genes. We validated the proposed methodology using a set of 452 cancer cell lines derived from the Cancer Cell Line Encyclopedia where an exhaustive experimental large-scale gene knockout study using CRISPR (Achilles Project) evaluates the impact of each removal. We also show that the integration of different essentiality predictions per gene, what we called Essentiality Congruity Score, reduces the number of false positives. Finally, we explored our method in a breast cancer patient dataset, and our results showed high concordance with previous publications. These findings suggest that identifying genes whose activity is fundamental to sustain cellular life in a patient-specific manner is feasible using in-silico methods. The patient-level gene essentiality predictions can pave the way for precision medicine by identifying potential drug targets whose deletion can induce death in tumour cells.