Biomedical Informatics Solutions for Drug Discovery in Biopharma
Target ID and Repurposing Consultative Solution: TaRCoS
BioInfi believes that every biotech company should have access to expert
target selection and repurposing guidance. We are here to help your succeed.
Successful target selection decisions require:
leveraging the biotech's competitive edge and strategy
an in-depth understanding of the platform and therapeutic area
interpretation of the relevant genetics and literature data
experience making target prioritization decisions that foreshadow future challenges
These early decisions are crucial to your success.
Our proprietary analytical platform helps you rapidly prioritize
across targets using our data integration, analytics, and expert
Our comprehensive approach improves your probability of success.
We also help you exercise the necessary due diligence to consider broader types and sources of information before committing millions of dollars on a project and target.
Please email us to initiate a discussion. We are available to present a seminar on our approach.
The TaRCoS approach is backed by our
in high-impact journals.
We have extensive experience with a variety of techniques
and data types.
We carefully select the most effective methods and data sources to
use in each project.
Our published work demonstrates the success of
We are committed to staying current with the
latest state-of-the-art methods in order to provide the best possible
service to our clients.
Key publications spanning multiple techniques and data
types used in TaRCoS: ...
Connectivity Map, Indication Expansion, Validation: Reisdorf W., , Agarwal P. Preclinical evaluation of EPHX2 inhibition as a novel treatment for inflammatory bowel disease. PLoS One. 2019 Apr 19;14(4):e0215033.
AI, Strategy, OpinionVijayan V, Rouillard A, Rajpal D, Agarwal P. Could Artificial Intelligence provide the new paradigm for data integration in drug discovery? Expert Opin Drug Discov. 2019.
Machine Learning, Expression: Rouillard A, Hurle MR, Agarwal P. Systematic interrogation of diverse Omic data reveals interpretable, robust, and generalizable transcriptomic features of clinically successful therapeutic targets. PLoS Computational Biology 2018: 14 (5), e1006142.
Networks, Pitfalls: Ji X, Freudenberg J, Agarwal P. Integrating biological networks for drug target prediction and prioritization. Methods Mol Biol. 2019; 1903:203-218.
AI, Pitfalls: Yao J, Hurle MR, Nelson MR, Agarwal P. Predicting clinically promising therapeutic hypotheses using tensor factorization. BMC Bioinformatics. 2019: 20:69.
Genetics, Pathways: Jhamb D, Magid-Slav M, Hurle M, Agarwal P. Pathway analysis of GWAS loci identifies novel drug targets and repurposing opportunities. Drug Discovery Today 24 (6), 1232-1236.
Indication Expansion, Validation: Middleton SA, …, Agarwal P, Kumar V. BET Inhibition Improves NASH and Liver Fibrosis. Sci Rep. 201; 8: 17257.
Open Targets: Khaladkar M, Koscielny G, Hasan S, Agarwal P, Dunham I, Rajpal D, Sanseau P. Uncovering novel repositioning opportunities using the Open Targets platform. Drug Discov Today. 2017 Dec;22(12):1800-1807.
Public data, Strategy, Opinion: Reisdorf WC, Chhugani N, Sanseau P, Agarwal P. Harnessing public domain data to discover and validate therapeutic targets. Expert Opin Drug Discov. 2017 Jul;12(7):687-693.
Genetics, Strategy: Hurle MR, Nelson MR, Agarwal P, Cardon LR. Trial watch: Impact of genetically supported target selection on R&D productivity. Nat Rev Drug Discov. 2016: 15 (9), 596-7.
Strategy, Novelty: P. Agarwal, P. Sanseau, L.R. Cardon. Novelty in the target landscape of the pharmaceutical industry. Nat Rev Drug Discov. 2013 Aug;12(8):575-6. doi: 10.1038/nrd4089.
Review, Methodology: M.R. Hurle, L. Yang, D.K. Rajpal, P. Sanseau, P. Agarwal. Computational drug repositioning: from data to therapeutics. Clin Pharmacol Ther. 2013 Apr;93(4):335-41.
Genetics, Indication Expansion: P. Sanseau, P. Agarwal, M.R. Barnes, T. Pastinen, J.B. Richards, L.R. Cardon, V. Mooser. Use of Genome-Wide Association Studies for Drug Repositioning. Nat. Biotech. 2012 Apr 10;30(4):317-20.
Clinical, Indication Expansion: L. Yang, P. Agarwal. Systematic Drug Repositioning based on Clinical Side-Effects. PLoS One. 2011;6(12):e28025.
EHRs, Indication Expansion: L.Yao, Y. Zhang, Y. Li, P. Sanseau, P. Agarwal. Electronic health records: Implications for drug discovery. Drug Discov Today. 2011 Jul;16(13-14):594-9.
Indication evaluation and expansion for your (pre)clinical asset.
Evaluation of molecular biomarkers for an indication.
Pharmacodynamic biomarkers for your drug.
Recruiting the impossible to find scientist or physician based on their science.
Each of these is supported by proprietary data builds, analytics, and
consulting to provide clean solutions to biotech challenges. We
specialize in non-oncology indications and rare diseases.
Our business model offers flexible, flat-fee pricing based on your
specific objectives. With decades of industry experience across a
wide range of diseases, platforms, and therapeutic modalities, we
are well-equipped to provide actionable guidance for your project.
Our comprehensive service
a custom data build
inclusion of your target-related, disease-specific, and bespoke requests
prioritization of targets and repurposing opportunities
joint assessment of results with workshopped consulting support
customer owns all target rights
BioInfi retains rights to our data and analytics IP
risk-sharing options with milestone-based payments available
AI-based Healthcare Experts and Physician Recruiting
Human capital is an important element for healthcare and drug discovery. Surprisingly, there are few resources that connect medical and scientific talent to patients, drug discoverers, and biotechs. We have developed two solutions:
We have a data-driven solution to biomedical recruitment that
will connect you by email with impossible to find specialized
physicians. Email us to discuss your job descriptions from attending
physicians to Department Heads. We will provide you a competitive
edge in finding doctors with high-degree of expertise, response
rate, and with ties to the region.
These solutions leverage and vastly expand on the technologies we published:
P. Agarwal, D.B Searls. Can Literature Analysis Identify Innovation Drivers in Drug Discovery? Nat Rev Drug Discov. 2009 Nov;8(11):865-78.
P. Agarwal, D.B Searls. Literature Mining in Support of Drug Discovery. Brief Bioinform. 2008; doi: 10.1093/bib/bbn035.
The principal, Dr. Pankaj Agarwal, has 25+ years strategic and tactical experience utilizing bioinformatics to enable drug discovery and create pipeline value. He has collaborated extensively with numerous pharmaceutical project teams, academic/biotech partners, and top informatics talent. Dr. Agarwal has 50+ publications in top journals, including Nature Rev Drug Discovery, Nature Biotechnology, and Clinical Pharmacology & Therapeutics, and multiple methodological and gene patents. In 2016, he was among a group of select few scientists appointed as Senior Fellows at GSK. Dr. Agarwal has also served on NSF, NIH, FDA and PhRMA panels. He possesses a B.Tech. in Computer Science & Engineering from IIT, Delhi and a Ph.D. in Computer Science from the Courant Institute of Mathematical Sciences at NYU. He is a founder and senior member of the International Society for Computational Biology (ISCB). Most importantly, Dr. Agarwal is passionate about drug discovery, rare diseases, and helping patients.
Our engagements at BioInfi include:
Multiple due dilligences on AI drug discovery companies on the behest of the
Gates Foundation, Investment Companies, and Biotechs.
Target identification for a series B startup.
Indication Expansion for a clinical asset for a biotech
Strategic plan for a disease area for mid-size pharma (including
targets, biomarkers, clinical discovery and repurposing)
Medical recruitment for an hospital (identifying specialized
medical experts and contact protocol design)
Strategic evaluation and alignment of a biomarker application
Advice and Implementation of Recommended UTI Antbiotics based
on RT-PCR assays
Dr. Agarwal's projects and accomplishments during his tenure at GSK include:
Led numerous target identification projects using the best-in-class tools with clear actionable shortlist of targets. Collaborated with bioinformaticians, disease biologists, and phenotypic screening experts on these projects.
Led an internal biotech for repurposing: Systematic Drug Repositioning (SyDR), which developed multiple computational techniques, assessed all internal pipeline molecules and experimentally validated the most promising hypotheses across 10+ disease areas.
Analyzed the potential for setting up a rare disease unit within GSK and identified the seed portfolio of repurposing and target opportunties.
Collaborated with multiple disease areas on due diligences, in-licensing, and suitable target identification using multiple drug modalities.
Identified and actioned six rare to common drug targets based
on agnostic evaluation of their genetics, biology, literature, and druggability.
Led a comprehensive evaluation of targets for gene therapy.
Led the training of the Bioinformatics team in deep learning and AI. Within a month, the team was using sophisticated Tensorflow methods directly on drug discovery projects. A team member discovered that phase 3 target success could be predicted using an Autoencoder on GTEx data.
Collaborated on a machine learning project to predict oncology response biomarkers and combinations for pipeline and marketed drugs.
Comprehensively discovered and patented numerous gene targets first from ESTs and then the human genome using automated overnight computes. This was enabled by extensive collaborations with top gene-finding experts and joint publications.
Invented and patented the first gene set enrichment method and extended it to work across multiple genetic loci from the precursor to GWAS studies. Established a comprehensive collection of gene sets across public domain and private data.
Developed the largest collection of protein interaction data
through licenses with early providers establishing a large
biomedical knowledge graph. Co-built and published a
network algorithm to mine it.
Led the design and development of a comprehensive portal and toolkit with over a 1000 internal pharmaceutical users with gene, disease and Omic tools.
Led the comprehensive analysis of scientific innovation in disease areas for the Head of R&D. The results of this project were used to scientifically redesign R&D. Selected results were published in Nature Reviews Drug Discovery.
The above project included a strategy for identifying KOLs and potential hires in each area as well as an in-licensing analysis and strategy.