Papedex Search Guide

Get the best results from AI-powered semantic search across 19M+ PubMed articles.

How Papedex Search Works

Papedex uses a multi-channel search engine that combines two fundamentally different approaches to find relevant papers:

Semantic Search (AI-powered)

Your query is converted into a mathematical representation (embedding) and compared against pre-computed embeddings of every title and abstract in PubMed. This finds papers that are conceptually similar to your query, even if they use different words. For example, searching "heart attack" will also find papers about "myocardial infarction" and "acute coronary syndrome."

Keyword Search (BM25)

Simultaneously, your query is matched against titles and abstracts using traditional keyword matching (BM25 ranking). This ensures papers that use your exact terminology are always found.

Author Search

If your query looks like an author name, Papedex searches the author index directly. See Searching for Authors for details.

Fusion

Results from all channels are merged using Reciprocal Rank Fusion (RRF), which combines rankings from different sources into a single ranked list. A paper that ranks well across multiple channels (e.g., both semantically and by keywords) gets boosted to the top. Recent papers receive a gentle boost, reflecting that newer research is often more relevant.

Writing Effective Queries

Key insight: Papedex benefits from descriptive queries. Unlike PubMed, which auto-expands short queries using its controlled vocabulary (MeSH), Papedex relies on the words you provide to understand what you're looking for. More specific queries produce more specific results.

Be Descriptive

Instead ofTryWhy
diabetes type 2 diabetes insulin resistance mechanisms Gives the semantic model more context to understand what you actually want
cancer pancreatic cancer immunotherapy checkpoint inhibitors Narrows from 3M+ papers to your specific area
CRISPR CRISPR-Cas9 gene editing therapeutic applications Distinguishes from CRISPR review papers, bacterial biology, etc.

Use Natural Language

Semantic search understands concepts, not just keywords. You can search in a more natural way:

QueryWhat it finds
how does sleep affect memory consolidation Papers on sleep-dependent memory processes, even if they don't use these exact words
proteins that cause Alzheimer's disease Amyloid-beta, tau, presenilin papers without needing to know those terms
side effects of mRNA vaccines Adverse events, reactogenicity, safety profiles of COVID-19 and other mRNA vaccines

Combine Approaches

You can mix natural language with exact terminology and field-specific syntax:

QueryEffect
gut microbiome depression journal:nature Semantic search for concept + journal filter
author:doudna CRISPR delivery year:2022-2025 Author + topic + date range
"gut-brain axis" AND inflammation Exact phrase + boolean AND

Search Syntax Reference

Field-Specific Search

Prefix a term with a field name and colon to restrict the search to that field:

SyntaxDescriptionExample
title:term Search titles only title:CRISPR
author:name Search authors only author:doudna
abstract:term Search abstracts only abstract:neuroplasticity
journal:name Filter by journal journal:nature
year:range Filter by year or year range year:2020-2025 or year:2024

Field prefixes can be combined with free text: author:hattar melanopsin circadian

Exact Phrase Search

Wrap a phrase in double quotes to find exact matches:

SyntaxEffect
"gut-brain axis" Finds papers with this exact phrase in title or abstract
"machine learning" radiology Exact phrase + free keyword

Searching for Authors

Papedex automatically detects author names and routes to a dedicated author search. This works best with clear name formats:

FormatExampleNotes
First Last Jennifer Doudna Capitalized names detected automatically
Last Initials Bhatt DL Citation format (as seen in references)
Last Initial hattar s Short format works for any case
author: prefix author:doudna Explicit author search (most reliable)
Tip: For common names (e.g., "Zhang F" matches thousands of researchers), combine with a topic to narrow results: author:zhang CRISPR or Feng Zhang CRISPR gene editing

Author + Topic

Search for a specific author's work on a topic by combining a capitalized name with keywords:

QueryEffect
Samer Hattar melanopsin Papers by Hattar related to melanopsin
author:doudna CRISPR delivery Doudna's papers on CRISPR delivery (using field prefix)

Limitations

Papedex does not currently have author disambiguation. If you search for "Smith J," you'll get papers by every "J. Smith" in PubMed. Use topic terms to narrow results, or use the author: prefix combined with specific keywords.

Boolean Operators

Use AND, OR, and NOT (case-insensitive) to combine terms:

OperatorExampleEffect
AND CRISPR AND cancer Results must match both terms (each searched independently, results intersected)
OR Alzheimer OR dementia Results can match either term (results merged)
NOT diabetes NOT type 1 Results for first term, excluding papers mentioning second term

Boolean operators must be uppercase or will be treated as regular search terms. Multi-word boolean queries search each side as a full phrase.

Filters and Sorting

Year Filters

Use the filter panel (click "Show Filters") or the year: syntax:

  • year:2024 — Papers from 2024 only
  • year:2020-2025 — Papers from 2020 through 2025

Journal Filter

Use the filter panel or journal: syntax. Partial matches work:

  • journal:nature — Nature, Nature Medicine, Nature Genetics, etc.
  • journal:cell — Cell, Cancer Cell, Molecular Cell, etc.

Sort Options

  • Relevance (default) — Multi-channel fusion score with recency boost
  • Newest First — Most recent publications first
  • Oldest First — Earliest publications first

Results Count

Use the slider to adjust how many results are returned (5 to 100). More results take slightly longer but cover a wider range.

Papedex vs PubMed

Papedex and PubMed have different strengths. Understanding these helps you get the best results from each:

AspectPapedexPubMed
Search method Semantic (AI embeddings) + keyword (BM25), fused Keyword + MeSH controlled vocabulary + ML ranking
Short queries Less effective — add context for better results Strong — auto-expands using MeSH synonyms
Descriptive queries Excellent — semantic model uses all context Good, but may over-weight certain MeSH terms
Concept discovery Strong — finds papers using different terminology for the same concept Moderate — limited to MeSH term relationships
Author search Name matching (no disambiguation for common names) Disambiguated via ORCID and MeSH Author IDs
Recency Gentle recency boost (~3%/year decay) Strong recency signal in "Best Match"
Try the comparison: Check "Compare with PubMed" on the search page to see results from both engines side-by-side. Shared results are highlighted with a green border.

When to Use Papedex Over PubMed

  • Exploring a new topic using natural language descriptions
  • Finding papers that discuss a concept without using standard terminology
  • Searching across multiple dimensions (author + topic + date) in one query
  • When PubMed's MeSH mapping sends you down the wrong path

When PubMed May Be Better

  • Very short, well-defined searches (single MeSH-mapped terms)
  • Searching for a common author name without topic context
  • When you need publication type filters (clinical trials, reviews, etc.)

Best Practices

1. Start Descriptive, Then Narrow

Begin with a detailed query describing what you're looking for, then use filters and field syntax to refine:

  1. gut microbiome influence on depression and anxiety
  2. Add a year filter: year:2020-2025
  3. Narrow to a journal: journal:nature

2. Use Quotes for Exact Phrases

When you need a specific phrase, quote it: "gut-brain axis" ensures those words appear together.

3. Combine Author + Topic for Disambiguation

Instead of just Zhang F, use author:zhang CRISPR or Feng Zhang gene editing to find the right researcher.

4. Check the Comparison View

Enable "Compare with PubMed" to see if important papers appear in one engine but not the other. This is especially useful when evaluating your search strategy.

5. Adjust Result Count for Broad Searches

For exploratory searches, increase the results slider to 50-100. For targeted searches, 10-25 is usually sufficient.