A comprehensive analysis of drug repurposing workflows published by Insilico Medicine


Credit: Insilico Medicine

  • An international group of expert scientists led by Insilico Medicine published a paper, "Design of efficient computational workflows for in silico drug repurposing" in one of the most prestigious journals in the field, Drug Discovery Today.
  • The paper presents a comprehensive overview of the current status of in silico repurposing methods by establishing links between current technological trends, data availability and characteristics of the algorithms used in these methods.
  • The authors summarize the advantages and disadvantages of the 3D structure-based, similarity-based, inference-based and machine learning (ML)-based methods to emphasize the current technical challenges in the drug repurposing field.
  • The paper highlights the possibilities offered by incorporation of deep learning approaches into the modular drug repurposing workflows.
  • Reference: Vanhaelen et al., (2016) "Design of efficient computational workflows for in silico drug repurposing", Drug Discovery Today, DOI: 10.1016/j.drudis.2016.09.019, http://www.sciencedirect.com/science/article/pii/S1359644616303439

Wednesday, October 12, Baltimore, MD – Insilico Medicine, Inc. announced the publication of a research paper presenting a comprehensive overview of the current status of in silico drug repurposing methods. Currently, pharmaceutical companies face a challenging economical and societal environment that requires them to continuously look for strategies to improve their capacities to develop original drugs at reduced cost. Within this context, the pharmaceutical community considers that finding novel indications and targets for already existing drugs, a method called 'drug repurposing', first discussed by Ashburn and Thor in 2004, can compensate for the lack of technical efficiency of the traditional drug discovery approaches that results in a high failure rate and continual decline in the number of new approved small-molecular entities released by pharmaceutical industry pipelines. The major advantages of a drug-repurposing approach are that the preclinical, pharmacokinetic, pharmacodynamic and toxicity profiles of the drug are already known, reducing the risk of compound development. Thus, the compound can rapidly translate into Phase II and III clinical studies, resulting in a decreased development cost, a better return on investment and an accelerated development.

Earlier this year Insilico Medicine published two seminal papers on applying deep learning methods to drug discovery and biomarker development. The first paper titled "Deep Learning Applications for Predicting Pharmacological Properties of Drugs and Drug Repurposing Using Transcriptomic Data" in Molecular Pharmaceutics, received the American Chemical Society Editors' Choice Award. It described the first application of transcriptional response data used to predict the therapeutic class of the molecules and for drug repurposing. Increased interest in applications of computational techniques and specifically deep learning for drug repurposing motivated the R&D team at Insilico to prepare a comprehensive analysis of the many techniques used in this field and make the report open to the community.

"Drug repurposing is performed either by using an experimental approach, called 'activity-based drug repositioning', or by making use of a specific computational method. The latter approach, named 'in silico drug repurposing', is one of the latest application areas of computational pharmacology, a larger field that encompasses in silico-based methods developed to investigate how drugs affect biological systems. From a technical perspective, the development of efficient algorithms for in silico drug repurposing is made possible by two technological trends. The first is the accumulation of various high-throughput data generated from different research areas, such as proteomics, genomics, chemoproteomics and phenomics. The second technological trend is the progress made in computational and mathematical sciences combined with increasingly powerful computational resources" said Quentin Vanhaelen, PhD, simulations director at Insilico Medicine, Inc, the first author on the manuscript.

The study describes the major advances in the field and the approaches to incorporate various methods into comprehensive pipeline for drug repurposing. To introduce the main steps of the in silico repurposing procedure, application to identifying fasudil as a new autophagy enhancer serves as a case study. A special attention is given to the deep neural networks based approaches for the drug repurposing problems. "Deep learning methods make their first steps in the field, but already demonstrate very promising results" said Ivan Ozerov, PhD, drug repurposing expert at Insilico Medicine, Inc.

A prospective field for drug repurposing application is looking for the alternative candidates for anti-aging therapies. Recently Insilico Medicine announced the publication of a research paper describing the applications of its human signaling pathway-centric GeroScope platform for scoring human tissue-specific geroprotective properties of compounds implicated in the aging of model organisms.

"We at Insilico Medicine understand how useful the drug repurposing methods can be, when searching for the novel anti-aging interventions. The use of deep learning technologies has significantly expanded our capabilities in this area" concluded Alex Aliper, the President of Insilico Medicine.


Journal reference: Vanhaelen et al., (2016) "Design of efficient computational workflows for in silico drug repurposing", Drug Discovery Today, DOI: 10.1016/j.drudis.2016.09.019, http://www.sciencedirect.com/science/article/pii/S1359644616303439

About Insilico Medicine

Insilico Medicine, Inc. is a bioinformatics company located at the Emerging Technology Centers at the Johns Hopkins University Eastern campus in Baltimore with R&D resources in Belgium, Russia and Poland hiring talent through hackathons and competitions. It utilizes advances in genomics, big data analysis and deep learning for in silico drug discovery and drug repurposing for aging and age-related diseases. The company pursues internal drug discovery programs in cancer, Parkinson's, Alzheimer's, sarcopenia and geroprotector discovery. Through its Pharma.AI division the company provides advanced machine learning services to biotechnology, pharmaceutical and skin care companies. Brief company video: https://www.youtube.com/watch?v=l62jlwgL3v8

Media Contact

Qingsong Zhu
[email protected]


%d bloggers like this: