Documentation
- Query Refinement
- Research Lenses
- AI-Powered Semantic Search
- Unbiased Computational Analysis
- Research Landscape
- Research Landscape Synthesis
- Trends and Momentum
- AI Research Assistant
- Citation-Grounded Answers
- Hypothesis Generation
- Methodology Generation
- Network Analysis
- Foundational Papers
- Hub Papers
- Bridge Papers
- Novel Leads
- PDF Export
Documentation
AI-Powered Semantic Search
Go beyond keywords to search by biological concepts and relationships. Distill millions of publications into a core, statistically-backed evidence set. Surface novel connections and hidden patterns in the literature.
How Semantic Search Works
Unlike traditional keyword search, semantic search understands the meaning behind your query:
- Query Understanding: Your natural language query is processed by the Semantic Scholar Graph API, which uses advanced neural models trained on hundreds of millions of scientific papers
- Relevance Scoring: The system uses Semantic Scholar's relevance ranking algorithm to find papers that match your query conceptually, not just by keywords
- Ranking: Papers are ranked by semantic relevance, ensuring you find papers that discuss the same concepts even if they use different terminology
- Filtering: Additional filters (year range, open access, citations) are applied to refine results
Advantages Over Keyword Search
Semantic search provides several key advantages:
- Concept understanding: Finds papers discussing the same biological concepts even when different terms are used (e.g., "tumor suppressor" vs "p53")
- Synonym recognition: Automatically handles synonyms, abbreviations, and alternative naming conventions
- Context awareness: Understands the relationship between concepts (e.g., pathways, regulatory mechanisms, disease associations)
- Comprehensive coverage: Powered by Semantic Scholar's index of over 200 million academic papers with rich citation and metadata information
Writing Effective Queries
To get the best results from semantic search:
- Use natural language: Write your query as you would describe your research question (e.g., "How does cytokine signaling regulate T-cell activation?")
- Include context: Provide biological context (cell type, disease, pathway) to narrow results
- Be specific: More specific queries yield more focused results (e.g., "BRCA1 mutations in triple-negative breast cancer" vs "breast cancer")
- Use biological terminology: The system understands scientific terms, so use them naturally
Search Filters
Use filters to refine your search results:
- Year Range: Focus on recent publications or explore historical research
- Open Access: Filter to papers with freely available full text
- Citation Count: Find papers with minimum citation counts to identify influential work
- Relevance Score: Adjust the minimum score threshold to control result relevance
Under the Hood
BioSkepsis leverages the Semantic Scholar Graph API for semantic search. Semantic Scholar is a free, AI-powered research tool developed by the Allen Institute for AI that indexes over 200 million academic papers across all fields of science.
The API uses advanced neural language models to understand your query and match it against paper abstracts, titles, and other metadata. This enables intelligent matching based on concepts and meaning rather than exact keyword matches.