The startup develops data science software that automates the extraction of genetic evidence from biomedical text data, enabling researchers to analyze extensive scientific literature for relevant genetic factors. This platform enhances decision-making in drug development and clinical trials by providing precise insights into genetic connections.
Funding
$15M raised to dateRaised to date based on public sources. This may differ from the amount the company actually raised and is based only on what is publicly available on the internet.
Founders
Product
Problem
Biomedical researchers face challenges in efficiently extracting and analyzing genetic evidence from the rapidly expanding volume of scientific literature. Legacy systems and fragmented data sources hinder the discovery of critical relationships between biomedical concepts, leading to wasted search time and missed opportunities for drug discovery.
Solution
Tellic provides a data science platform that leverages large language models (LLMs), natural language processing (NLP), and knowledge graphs to automate the extraction of genetic evidence from biomedical text data. The platform creates a unified source of truth for biomedical concepts by processing unstructured data from research papers, grants, preprints, clinical trials, patents, and proprietary research. This enables researchers to efficiently explore and validate connections critical to drug discovery, generate hypotheses, and make informed decisions in target selection and clinical trial design. Tellic's patented biomedical language processing, powered by machine learning and big data, accelerates the time to insight and helps unlock critical relationships from biomedical data.
Target Audience
The primary target audience includes pharmaceutical and biotechnology companies, as well as researchers and analysts involved in drug discovery, clinical trials, and target selection.
Features
- Biomedical NLP pipelines purpose-built for processing unstructured biomedical text data at scale
- Concept search that increases the number of relevant search results by 4X
- Knowledge graph construction from extracted biomedical concepts and relationships
- Detection of biomedical concepts in text data with high accuracy
- Linking of biomedical concepts to preferred ontologies using machine learning
- Context-driven relevance ranking to surface the most important research
- Support for evolving vernacular, ontologies, and identifiers