Discovery Workflow












Data Resources - RESTful API Access



In-house Discovery & Collaborative Partnerships



    • Identification of novel biomarkers from healthy versus disease metabolomics patient datasets for bladder cancer and Crohn's disease.
    • Identification of non-toxic novel molecular targets for colorectal cancer from medical literature & healthy versus disease transcriptomics datasets.
    • Identification of novel molecular targets from breast cancer phenotypic screening datasets.
    • Identification of novel indications for drug repurposing from transcriptomics datasets for cancer and rare disease.


BioX Discovery Research Workbench




    • Open Access Abstracts, Full Text and Figure Images & Ontologies
    • Hypothesis generation with network visualization
    • Direct Knowledge Generation & Reports
    • Recommendations for test hypotheses validation assays
    • Intelligent Search Engine with Automated Thesaurus




  • Ingest Proprietary or Third Party Text, Image & Omics Data
  • 50+ integrated ontologies with automated thesauri & menu filtering
  • 250+ selected life science data repositories
  • Secure private cloud for cross-team experimental data discussion

        & internal project collaboration


           USE CASES


    • Identifying non-toxic gene targets in colorectal, breast and bladder cancer
    • Determining the prevalence of antibiotics resistance genes and gene variants
    • Interpretation of transcriptomics & metabolomics datasets to identify novel gene and metabolite biomarkers
    • Identify novel gene targets in neuronal cell populations in Epilepsy
    • Identification of novel therapeutic indications for gene targets in drug repurposing
    • A global cross-site global R&D workbench for research data analysis & sharing
    • Search engine with automated thesaurus for clinical trials data



Access via Software License and/or RESTful API


BioX Experiment Design Engine




The Engine works by enabling users to evaluate experimental protocols, tools  & results from figure images for genes, proteins, diseases, molecular functions, biological processes, anatomic regions, cellular components, species, tissues, or pathways and match them with plasmids, shRNAs, siRNAs, antibodies, crispr & ZFN sequences, cell lines, proteins and kits, bioactive small molecules, animal models, software and instruments.



  • Identify optimal cell lines and gene promoters for crispr engineering
  • Identify optimal antibodies in specific cancer cell types
  • Identifying disease specific cell lines and animal models for gene targets
  • eCommerce Gene Search platform integration for tools vendors
  • Identify optimal instrument protocols



Access via Software License and/or RESTful API




Submitting Form...

The server encountered an error.

Form received.


Meet The Team





Background in emerging biotechnology & bio-medical research with over a decade of commercial experience in the life science research market. Previously, associate director at Merck KgaA leading the emerging biotechnology initiative in Europe. Mark co-founded Curogenix, a European commercial agency for in vitro & in vivo contract research services, and prior to that worked at Sigma-Aldrich as a field  applications specialist for emerging technologies.




Pavel has a background in computer science, software engineering &  applied bioinformatics. He has particular expertise in biological patterns, data classification and recognition, machine learning approaches using GPGPU based predictive modeling, code conversion & optimization, general-purpose computations on graphical processors & java technologies as well as R, C/C++, java, verilog, python, bash (linux shell), visual basic, perl, and tcl.




Background in economics & finance from Kemmy business school at University of Limerick. Anna has worked in the Life Science, Food & Banking industries, & brings over 10 years expertise in  project management ,  operations & finance to the team.  She has previously founded a company in the food industry, after working in RBS global markets in the US. Anna has also won a management award while at Aramark.


Metabolomics & Cheminformatics

Michael has a PhD in analytical chemistry & is a  lecturer in biostatistics. He has a background in cheminformatics and data science with 10 years of experience in machine learning, pattern recognition and biomarker discovery. His specialist interest is in  developing tools to interrogate metabolomics datasets leading to the non-invasive diagnosis of cancers and diseases.  Michael is skilled in statistical programming using R & Matlab.


Digital Marketing

& Design

Background in digital marketing with a proven track record in digital design, search engine optimisation, social media & automated marketing. Colum also has graphic design  & animation experience for generating online media content. He is currently interested in developing skills in print design, including infographics & posters. He has several certifications in design, digital marketing & animation.


Genomics & Transcriptomics

Niranjan has a background in molecular biology & applied bioinformatics. He has expertise in handling NGS HiSeq data, quality control and filtering of NGS data: de novo or reference based using assemblers,   reference based genome alignment, detection of genomic variation, RNA-seq  differential expression analysis, and identification of sequence binding motifs using ChIP-seq.

We are actively looking for specialists in AI, NLP, Imaging & Bioinformatics to work with us


Investment Support & Program Finalists



User Feedback

 “the genes that have come out of BioXplor are extremely relevant. In fact, the top two genes are the subject of my manuscripts! One gene is what I'm working on for publication this week! So very nice!!”


“This is exactly the tool we need to accelerate our Drug Repurposing work. Currently we have 6 senior scientists sitting in a room manually reading through Scientific Papers, whereas this tool can do in minutes & hours what takes us days, weeks & months… “


" BioXplor is more advanced than IBM Watson in terms of Ontologies, Mining Figure Images & Full Text Papers, and it is very clever that you built the platform with these important factors in mind from the beginning…”


“Unstructured text is a MAJOR pain point in Pharma R&D today, your tool has a lot of value in solving that problem”


“This is a great platform for validating outputs from our omics based discovery pipeline by combining with literature based screening optimized for oncology”


“We have been trying to build this type of tool internally but only managed to do individual tasks due to the time & complexity involved. It’s particularly important that you automatically update your database with each newly published scientific paper”


" This is an ideal platform to analyse and share our R&D data combined with literature based insights right across our global R&D organisation."

2017 Copyright Bioxplor Ltd.