<strong>World leader in machine reading the pharma conversation</strong>

We are the world leader in developing and deploying machine reading technology to synthesize action-ready insights from unstructured text. Our team consists of artificial intelligence and natural language processing visionaries who deliver state-of-the-science computing solutions focused on pharma’s needs. We use artificial intelligence to read public and proprietary data with the accuracy of an expert – at machine scale.


We support innovators in the pharmaceutical industry with identifying and optimizing product value. Our customers need to access and assemble evidence in real time in a number of areas, such as medical excellence, customer value and real-world evidence (RWE), market development and access, health economics and outcomes research (HEOR) and health technology assessment (HTA), patient journey and advocacy, and competitive intelligence. In all of these cases, it’s essential to understand the views of the stakeholders – patients, health-care practitioners, payers, competitors – in multiple markets around the globe. We are convinced that a deep, data-driven understanding of these voices unleashes genuine innovation in decision-making, accelerating both our customers’ contributions to health care and their competitive advantages.

Passion for Technology

We use state-of-the-science semantic computing to unlock the value of human-created data for pharma

Our cutting-edge natural language processing (NLP) technologies automatically extract key insights from natural language data, such as health-center patient (HCP) surveys and focus group transcripts, medical affairs communications, electronic health records (EHRs), and patient forums. Awareness, judgments, emotions, and more are linked to key entities in a knowledge graph, which ensures insights are correctly contextualized.
Our robust and flexible approach to analyzing language lets you discover relevant insights by using machine learning to induce rules from training data. Not only do we look for expected patterns such as efficacy, prescription intention, and unmet needs for insights; we also extract unexpected commonalities to discover unknown unknowns.
We rely on ontologies and semantic technologies to capture relevant domain knowledge that allows us to contextualize analyses and support disambiguation. These methods ensure high accuracy and harmonization across data sources, enabling us to generate coherent insights that matter.
Our pharma Knowledge Graphs (networked databases) are the foundation of our interpretive power and are built on relations that exist between things such as clinical studies, drug products, conditions, and guidelines as well as their associations as expressed in text with subjective experiences, thoughts, and feelings. This contextualization allows us to deliver consistent and uniform analytics. Knowledge graphs are the foundation upon which algorithms understand the pharma business.

Understanding the Why

We help you understand the why – that is, the reasons behind how physicians, patients, payers, and regulators perceive the value of pharmaceuticals. These views inform the narratives and decisions that drive the health-care industry to develop new opportunities, maximize available resources, and pivot to the strategies that promote both brand and consumer health.

Developing Powerful Value Narratives

We provide insights that enable pharma companies to calibrate their value propositions and market values to serve the needs of the market.

Understanding Perceptions

We provide clear answers to specific questions, helping to explain the main drivers that affect value perception.

Getting 360° Evidence

Get comprehensive evidence of value perception. Across data sources. Across stakeholders. Across geographies. Across time.

Moving ahead of Competitors

Move quickly – no more quarterly, manually compiled, and outdated reports. Get insights instantly and in real time.

Fostering Collaboration

Our systematic approach to capturing value perception fosters collaboration across departments and business units.

Our Story

Founded in 2015 as a spin-off of the Semantic Computing Research Group at CITEC – the Cluster of Excellence Cognitive Interaction Technology at Bielefeld University, Germany – by 2018, we had grown from a handful of employees to a diverse team more than 60 internationally recruited colleagues, with connections to leading researchers and top pharmaceutical companies worldwide. Highly specialized experts drive our progress in key technologies such as machine learning, deep learning, knowledge graphs, natural language processing, machine reading, predictive analytics, statistical inference, and data visualization.

Between 2015 and 2018, we completed over 25 projects with clients from the pharmaceutical industry with a total volume of EUR 2.8 million. Currently, we are launching Pharos®, a platform that ingests information from various pharma-relevant sources to explain the global conversation around drug product and brand value in real time. Pharos® provides a comprehensive overview by analyzing the voices of multiple stakeholders, including pharmaceutical companies, patients, HCPs, and regulators.

Our rapid growth and successful business model have attracted a seed investment of EUR 1 million from several venture capital investors and business angels.

Semalytix has been featured in

Wirtschaftswoche / Economy 4.0
The Hundert
Neue Westfälische



2016: Winner of international award for best-performing sentiment analysis system (ESWC)
2016: Winner of best research transfer project award at Semantics, Leipzig
2017: Participant in the Bertelsmann-funded Start-Up Accelerator program
2018: Finalist in the BARC start-up award
2018: Awarded funding by the European Commission for multilingual text analytics for RWE in pharma
2018: Recognized by The Hundert as one of the top 10 most innovative start-ups in Germany