Skip to main content

Pharmas and biotechs are united by a common goal: discovery.

Whether seeking new treatments, improved patient outcomes, or more efficient and effective processes, their efforts are trained on illuminating connections between chemistry and biology that would otherwise remain concealed.

Each discovery attempt is a long shot. It depends on successfully identifying a target and selecting a viable compound to progress to clinical trials. Thousands of potential paths narrow to one. Decisions are made about which routes are valid and which are not. These decisions depend on data.

Quantitative and qualitative data is analyzed and subjected to predictive simulations to produce hypotheses for testing. In theory, the more data a model uses, the better its predictions should be. But the sheer volume of data creates a problem – identifying which pieces are applicable to the objective and which are redundant or likely to mislead the model into erroneous conclusions. Not only that, but the data must be consistently structured and tagged to be usable by the system. With data drawn from hundreds of disconnected sources, that’s a more significant challenge than it might appear, and drug discovery programs risk being bottlenecked by the problem of standardization.

Structuring data for drug discovery

At Excelra, our mission is to accelerate your discovery journey by making the path shorter, simpler, and more clearly signposted.

We do this in many creative and innovative ways. We start from a unique principle: that scientific expertise and technical infrastructure are two sides of the same discovery coin, and must be joined – not separated – on the journey. Our teams include biologists, medicinal chemists, pharmacologists, and engineers working at the intersection of science and technology to create an interdisciplinary community that speaks our customers’ language, whatever it is.

Next, we avoid the problem of polluted, ineffectual data by sourcing it ourselves. Our datasets are rich, relevant, and carefully curated by scientific experts to meet FAIR criteria: findability, accessibility, interoperability, and reusability. Our ability to extract, transform, and load data creates demonstrable value that all life sciences companies respect.

Finally, we make the data the hero of the drug discovery process. We build semantic models, automated pipelines, search tools, and visualizations that simplify the data analytics processes and produce clear, precise results to empower our customers’ decision-making and accelerate their discovery.

  • Whatever discovery means to you
    Target identification, treatment application, drug repurposing – we help you make it.
  • Whichever data you need to make your discovery
    Toxicity, structure-activity relationship, key opinion leaders – we will select and analyze it to ensure maximum suitability.
  • Wherever it comes from
    Clinical trials, journal articles, public domain databases – we source, normalize, and deliver it in any form you require.
  • However it needs to be analyzed
    In the cloud, along custom pipelines, across multiple applications and programs – we develop powerful products and bespoke service solutions that save time, money, and energy.

Actively accelerating discovery for 15 of the top 20 pharmas

One of our large pharma partners sought to improve their internal drug discovery program and derive value from their OMICS data by establishing an enterprise-wide R&D-IT ecosystem specific to the early discovery and translational function.

Requiring experts who could integrate scientific knowledge with technological innovation, the company approached Excelra. We were tasked with developing an end-to-end pipeline for processing cryogenic electron microscopy (Cryo-EM) images to learn more about protein structures and their conformational and compositional heterogeneity.

Cryo-EM is a highly specialized technique, but our team had significant experience within the field and clearly understood the requirements. The technique produces 2D maps containing several particles. These maps are low resolution, randomly oriented, and intrinsically heterogeneous, making analysis difficult.

To overcome this difficulty, we designed a pipeline incorporating cutting-edge AI/ML technologies to transform the original micrographs into high-resolution 3D structures.

The successful deployment of the pipeline has dramatically saved time, reduced cost, and improved outcomes for protein target credentialling. It has improved the analysis of structures that are essential in therapy development.

This is what we mean by accelerating discovery and creating value.

Our ability to combine deep scientific knowledge and cutting-edge technology impressed the customer, and we now have a team of 70 experts embedded with them to support their objectives.

Our inputs have resulted in some outstanding solutions that have helped accelerate the customer’s discovery journey:

Accurately annotated data, curated to avoid pollution or irrelevance and transformed to become usable within their existing systems.

A powerful sample workflow management system that’s now in use across the whole organization, integrated with the cryo-EM pipeline and routinely benchmarked and tested to ensure impeccable performance.

Configuration of job schedulers like Apache Airflow, NextFlow, and SnakeMake, for batch processing on Azure, AWS, and GCP

Biomedical search and cataloging tools that expedite the retrieval of internal studies enhanced with public data.

Automation of ETL and AI/ML pipelines, and development and deployment of OMICS data analysis pipelines on platforms like DNANexus and Seven Bridges.

Semantic data modeling that’s transformed legacy datasets from donor samples and clinical trials.

These deliverables and more were achieved thanks to strict adherence to our intradisciplinary principles and our commitment to excellence across domain expertise and technology solutions.

The clients are in no doubt of the value we’ve added to their discovery journey:

“Because of your hard work, we have a product that has created such an organic following of senior stakeholders that we now officially have the president of R&D using the product”

Unlocking your potential

To open the door of discovery, you need the right key in the appropriate lock. Excelra provides data curation, bioinformatics expertise, infrastructure development, and the unique ability to bridge the gap between domain expertise and technical development. We provide the key and empower you to use it.

This is how we create value from the promise of data.

This is how we accelerate discovery.

Ready to get more from data?

Tell us about your objectives. We’ll help get you there.

"*" indicates required fields

Country **
This field is for validation purposes and should be left unchanged.

Please fill the form

"*" indicates required fields

This will close in 0 seconds