Systems Biology: Applications in Drug Discovery

Ekins, Sean; Bugrim, Andrej; Nikolsky, Yuri; Nikolskaya, Tatiana

doi:10.1002/9780470571224.pse005

Cited by 7 publications

(5 citation statements)

References 238 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Providing the user with some confidence in the prediction has only been partially addressed by the efforts at providing an applicability domain using Tanimoto similarity, PCA, clustering, Mahalanobis distance, etc. (28)(29)(30)(31)(32)(33)(34)(35)(36).…”

Section: The Universementioning

confidence: 99%

“…What would it take to bring in some of the data modelers, data miners, computer animators, interface developers (from other industries), defense industries or simulator designers to provide help with pharmaceutical-derived cheminformatics data visualization? Bringing together those skilled in chemistry and informatics or these other disciplines may be analogous to the field of systems biology (33,34), which tries to integrate those skilled in mathematics, engineering, biology, etc. It is important that there is a common language that connects researchers from different backgrounds to aid in integration (35).…”

Section: The Red Dwarfmentioning

confidence: 99%

See 1 more Smart Citation

Chemical Space: Missing Pieces in Cheminformatics

et al. 2010

Self Cite

View full text Add to dashboard Cite

Cheminformatics is at a turning point, the pharmaceutical industry benefits from using the various methods developed over the last twenty years, but in our opinion we need to see greater development of novel approaches that non-experts can use. This will be achieved by more collaborations between software companies, academics and the evolving pharmaceutical industry. We suggest that cheminformatics should also be looking to other industries that use high performance computing technologies for inspiration. We describe the needs and opportunities which may benefit from the development of open cheminformatics technologies, mobile computing, the movement of software to the cloud and precompetitive initiatives.

show abstract

Section: The Universementioning

confidence: 99%

Section: The Red Dwarfmentioning

confidence: 99%

Chemical Space: Missing Pieces in Cheminformatics

et al. 2010

Self Cite

View full text Add to dashboard Cite

show abstract

“…After the model was trained, the entire dataset was encoded with the perturbation barcodes learned from the training set. Targets for 149 of the compounds were found to be annotated in Chembl (Gaulton, Bellis et al 2012) or Metabase (Ekins, Bugrim et al 2005) databases, only those targets affected with potencies <1µM were considered. For each target, distances between profiles derived from distinct compounds sharing the target were compared to a sample not sharing the target via a t statistic.…”

Section: Lincs Consortium Datamentioning

confidence: 99%

Representing high throughput expression profiles via perturbation barcodes reveals compound targets

et al. 2017

View full text Add to dashboard Cite

High throughput mRNA expression profiling can be used to characterize the response of cell culture models to perturbations such as pharmacologic modulators and genetic perturbations. As profiling campaigns expand in scope, it is important to homogenize, summarize, and analyze the resulting data in a manner that captures significant biological signals in spite of various noise sources such as batch effects and stochastic variation. We used the L1000 platform for large-scale profiling of 978 representative genes across thousands of compound treatments. Here, a method is described that uses deep learning techniques to convert the expression changes of the landmark genes into a perturbation barcode that reveals important features of the underlying data, performing better than the raw data in revealing important biological insights. The barcode captures compound structure and target information, and predicts a compound’s high throughput screening promiscuity, to a higher degree than the original data measurements, indicating that the approach uncovers underlying factors of the expression data that are otherwise entangled or masked by noise. Furthermore, we demonstrate that visualizations derived from the perturbation barcode can be used to more sensitively assign functions to unknown compounds through a guilt-by-association approach, which we use to predict and experimentally validate the activity of compounds on the MAPK pathway. The demonstrated application of deep metric learning to large-scale chemical genetics projects highlights the utility of this and related approaches to the extraction of insights and testable hypotheses from big, sometimes noisy data.

show abstract

“…As such, a new science known as systems biology has emerged. Systems biology can be described as the science resulting from the integration of omics such as genomic, proteomic, transcriptomic, and metabonomic data using computational methodologies and mathematical modeling followed by simulation to mimic the natural biological systems in silico [35] .…”

Section: Systems Biology In Drug Discoverymentioning

confidence: 99%

“…Induced abnormalities in the functioning of these models can also help in the understanding of the role of various factors in the progression of disorders and diseases such as hypertension, cancers, and Alzheimer disease. Indirectly, a chance is offered to predict abnormalities in the human body or a disease causing organism, and, hence, a valuable opportunity to validate therapeutic targets and outcomes [35] . A pipeline of systems biology in drug discovery and ADMET/Tox [37] is represented in Figure 18.6 .…”

Section: Simulation Modelsmentioning

confidence: 99%

In Silico and Ultrahigh‐Throughput Screenings (uHTS) in Drug Discovery: An Overview

Barh

Ahmad

Bhattacharjee

2012

Pharmaceutical Biotechnology

View full text Add to dashboard Cite

18 in Drug Discovery: an Overview 18.1.2 Ensuring Quality, Quantity, and Cost Effectiveness Using Integrated ApproachesWith the increases in library size over time, in addition to the increase in the number of molecular targets, assay miniaturization, automation, and quality concerns with respect to screening have become relevant. This has created a huge shift in the time process of HTS in terms of assay development, tool production, adaptation, detection tools, counter and selective screening, quality assurance, hit -to -lead, and lead optimization, and so on. The technical and process evolution of HTS over the last 15 years is represented in Figure 18.2 . Figure 18.

show abstract

Systems Biology: Applications in Drug Discovery

Cited by 7 publications

References 238 publications

Chemical Space: Missing Pieces in Cheminformatics

Chemical Space: Missing Pieces in Cheminformatics

Representing high throughput expression profiles via perturbation barcodes reveals compound targets

In Silico and Ultrahigh‐Throughput Screenings (uHTS) in Drug Discovery: An Overview

Contact Info

Product

Resources

About