Network perturbation analysis of gene transcriptional profiles reveals protein targets and mechanism of action of drugs and influenza A viral infection

Noh, Heeju; Shoemaker, Jason E.

doi:10.1093/nar/gkx1314

Cited by 45 publications

(42 citation statements)

References 72 publications

(109 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Following the steps used in a previous study (19) and the provided code To test our model, the gene expression profiles of these 123 compounds were excluded from the training dataset to avoid any potential information leakage. The remaining data were then used to train our model and predict targets for these 123 compounds according to the pipeline shown in Figure 3.…”

Section: Model Performance and Analysis Using The External Test Set Imentioning

confidence: 99%

“…For example, the LINCS L1000 dataset (17) is a comprehensive resource of gene expression changes observed in human cell lines perturbed with small molecules and genetic constructs. Several computational methods that involve the exploration of differential expression patterns have been proposed (18)(19)(20)(21)(22)(23)(24)(25)(26)(27), and the strategies used in these methods mainly include comparative analysis, network-based analysis, and machine learning-based analysis (28). The comparative analysis-based methods infer targets based on gene signature similarities (17,24,26).…”

Section: Introductionmentioning

confidence: 99%

“…An example is Connectivity Map (CMap), which assigns the target/MOA information of the most similar reference chemical/genetic perturbations to the new molecule by querying its gene expression signature against the reference L1000 library (17). The network-based approach systematically integrates gene expression profiles with cellular networks (19,20,(29)(30)(31)(32). For example, ProTINA applies a dynamic model to infer drug targets from differential gene expression profiles by creating a cell type-specific protein-gene regulatory network and provides improved prediction results compared with similar methods.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Computational target fishing by mining transcriptional data using a novel Siamese spectral-based graph convolutional network

Zhong

et al. 2020

Preprint

View full text Add to dashboard Cite

Computational target fishing aims to investigate the mechanism of action or the side effects of bioactive small molecules. Unfortunately, conventional ligand-based computational methods only explore a confined chemical space, and structure-based methods are limited by the availability of crystal structures. Moreover, these methods cannot describe cellular contextdependent effects and are thus not useful for exploring the targets of drugs in specific cells. To address these challenges, we propose a novel Siamese spectral-based graph convolutional 2 network (SSGCN) model for inferring the protein targets of chemical compounds from gene transcriptional profiles. Although the gene signature of a compound perturbation only provides indirect clues of the interacting targets, the SSGCN model was successfully trained to learn from known compound-target pairs by uncovering the hidden correlations between compound perturbation profiles and gene knockdown profiles. Using a benchmark set, the model achieved impressive target inference results compared with previous methods such as Connectivity Map and ProTINA. More importantly, the powerful generalization ability of the model observed with the external LINCS phase II dataset suggests that the model is an efficient target fishing or repositioning tool for bioactive compounds.

show abstract

Section: Model Performance and Analysis Using The External Test Set Imentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Computational target fishing by mining transcriptional data using a novel Siamese spectral-based graph convolutional network

Zhong

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…Network-based approaches have been used to identify drug-target interactions by using gene expression profiles to infer the mechanisms of drug action based upon the perturbation of gene regulatory and protein-protein interaction networks. Detecting Mechanism of Action by Network Dysregulation (DeMAND) and Protein Target Inference by Network Analysis (ProTINA) are two network-based methods that infer drug-target interactions from gene expression profiles [82,83]. These two methods were compared, and ProTINA exhibited superiority over DeMAND for predicting known targets of drugs across three datasets: NCI-DREAM drug synergy challenge [84], a genotoxicity study [85], and a chromosome drug targeting study [86].…”

Section: Boolean Network Analysesmentioning

confidence: 99%

Boolean network modeling in systems pharmacology

Bloomingdale

Nguyen

Niu

et al. 2018

J Pharmacokinet Pharmacodyn

View full text Add to dashboard Cite

Quantitative systems pharmacology (QSP) is an emerging discipline that aims to discover how drugs modulate the dynamics of biological components in molecular and cellular networks and the impact of those perturbations on human pathophysiology. The integration of systems-based experimental and computational approaches is required to facilitate the advancement of this field. QSP models typically consist of a series of ordinary differential equations (ODE). However, this mathematical framework requires extensive knowledge of parameters pertaining to biological processes, which is often unavailable. An alternative framework that does not require knowledge of system-specific parameters, such as Boolean network modeling, could serve as an initial foundation prior to the development of an ODE-based model. Boolean network models have been shown to efficiently describe, in a qualitative manner, the complex behavior of signal transduction and gene/protein regulatory processes. In addition to providing a starting point prior to quantitative modeling, Boolean network models can also be utilized to discover novel therapeutic targets and combinatorial treatment strategies. Identifying drug targets using a network-based approach could supplement current drug discovery methodologies and help to fill the innovation gap across the pharmaceutical industry. In this review, we discuss the process of developing Boolean network models and the various analyses that can be performed to identify novel drug targets and combinatorial approaches. An example for each of these analyses is provided using a previously developed Boolean network of signaling pathways in multiple myeloma. Selected examples of Boolean network models of human (patho-)physiological systems are also reviewed in brief.

show abstract

“…Although there are a number of cases where GRN inference has been successfully applied to solve biological questions [7,8,10,20], network analysis has historically struggled with a set of problems. First, the results of network inference are often dependent on the underlying quality of data, with factors such as correlated regulators posing a problem for most algorithms [21][22][23].…”

Section: Introductionmentioning

confidence: 99%

LiPLike: Towards gene regulatory network predictions of high-certainty

Magnusson

Gustafsson

2019

Preprint

View full text Add to dashboard Cite

Motivation: Reverse engineering of gene regulatory networks has for years struggled with high correlation in expression between regulatory elements. If two regulators have matching expression patterns it is impossible to differentiate between the two, and thus false positive identifications are abundant. Results: To allow for gene regulation predictions of high confidence, we propose a novel method, LiPLike, that assumes a regression model and iteratively searches for interactions that cannot be replaced by a linear combination of other predictors. To compare the performance of LiPLike with other available inference methods, we benchmarked LiPLike using three independent datasets from the previous DREAM5 challenge. We found that LiPLike could be used to stratify predictions of other inference tools, and when applied to the predictions of DREAM5 participants we observed the accuracy to on average be improved >140% compared to individual methods. Furthermore, we observed that LiPLike independently predicted networks better than all DREAM5 participants when applied to biological data. When predicting the Escherichia coli network, LiPLike had an accuracy of 0.38 for the top-ranked 100 interactions, whereas the corresponding DREAM5 consensus model yielded an accuracy of 0.11. Availability: We made LiPLike available to the community as a Python toolbox, available at https://gitlab.com/Gustafsson-lab/liplike. We believe that LiPLike will be used for high confidence predictions in studies where individual model interactions are of high importance, and that LiPLike will be used to remove false positive predictions made by other state-of-the-art gene-gene regulation prediction tools.

show abstract

Network perturbation analysis of gene transcriptional profiles reveals protein targets and mechanism of action of drugs and influenza A viral infection

Cited by 45 publications

References 72 publications

Computational target fishing by mining transcriptional data using a novel Siamese spectral-based graph convolutional network

Computational target fishing by mining transcriptional data using a novel Siamese spectral-based graph convolutional network

Boolean network modeling in systems pharmacology

LiPLike: Towards gene regulatory network predictions of high-certainty

Contact Info

Product

Resources

About