Thunken Inc. Thunken

Natural language processing meets

  • financial statements.
  • patents.
  • public records.
  • scholarly publications.
  • your data.^2000

About Thunken

Thunken offers software engineering and consulting services in natural language processing, machine learning, and data science.

We are on a mission to bridge gaps between scientific data and business intelligence. We specialize in extracting high-quality information from complex documents such as patents, scholarly publications, clinical trial filings, and financial statements.

We have built crawlers, search engines, and text mining tools for various clients across North America and Europe. In addition to our consulting activities, we develop Cobaltmetrics, Ironsift, and several open source libraries.



Cobaltmetrics  monitors trusted sources to index citations and hyperlinks, helping you report on all types of content.

We track references to millions of documents, including scientific publications, books, journals, patents, trademarks, clinical trials, financial statements, security vulnerabilities, tweets, etc.


Ironsift  puts public data to work instantly, allowing you to stay on top of innovation and regulations, no matter your industry.

Get access to decades of historic data. Monitor results in real time, get notifications when new records match your queries. Share alerts and reports with your team.


Software Development

We cover all stages in software development, including prototyping, productization, integration of third-party services, and performance improvements.

Machine learning

We help you work with unstructured data using methods like document labeling, semantic search, topic extraction, sentiment analysis, etc.

Business Intelligence

Turn your data into actionable insights. We help you use artificial intelligence to structure and visualize your data, and to automate your processes.


Nanomolar  has outsourced their full-stack development to us since their inception in 2017. We work on all technical aspects of the project, from data collection and text mining on patents and technology transfer documents to system administration.

MyScienceWork  outsourced their R&D to us from 2017 to 2018. We helped their team deduplicate and ingest tens of millions of documents into their databases, and we built various text mining tools to analyze scholarly publications and patents.

We have also worked with technology companies such as eRowz  and LakePharma , business schools like INSEEC , and various clients via Clarity .


Luc Boruta 

Chief Executive Officer

Damien Vannson 

Chief Technology Officer

Casey Scott McKay 

Jr. Backend Developer

Contact Us

Ask us how we can help! Email us at [email protected] to inquire about your next project with us, or just to say hello.

We are also active on LinkedIn , Medium , GitHub , and Clarity .

Email is our preferred method of communication, but snail mail can be addressed to:
Thunken, ℅ Luc Boruta, Suite 100, 1666 Connecticut Ave NW, Washington, DC 20009.