Menu
Request Demo
AI-powered peer reviewer matching

Find the right
peer reviewer
in seconds.
Not Hours.

Reviewer Select uses AI to understand your manuscript and match it with experts based on real research alignment, not keyword overlap. Built for publishers, editors, and research teams who need speed without compromising on quality.

Book a demo See how it works
reviewer-select / manuscript-3742
Live
Manuscript
CRISPR-Cas9 modulation in glioblastoma microenvironments
CRISPR-Cas9 glioblastoma tumor microenvironment gene editing immunotherapy +8
EM
Dr. Elena Marquez
94.6 /100
ETH Z rich Oncology and gene therapy
Semantic
Citations
Integrity
DOI 10.1038/s41586-024- 12 supporting works
KO
Prof. Kenji Ohara
91.2 /100
Kyoto U. Tumor immunology
Semantic
Citations
Integrity
AP
Dr. Aisha Patel
87.4/100
MIT Broad Institute Genome editing
Milvus index 8.4M reviewers
Model
0 -Tier
Semantic scoring
Latency
<0 s
Abstract ? ranked list
Method
0%
Concept-driven matching
Provenance
DOI
Evidence-based matching
— The problem we solve

Peer review is
slowing down

Submission volumes are rising. Reviewer availability isnt. Editors are spending too much time searching, relying on the same networks, and still missing the best-fit experts.

01 / Time
30+ min

per manuscript
Manual reviewer search slows down editorial workflows. What should take seconds takes 30 minutes or more.

median per submission
02 / Fatigue
? 42%

Reviewer fatigue is increasing
The same experts are invited repeatedly, leading to lower acceptance rates and slower turnaround.

vs. five years ago
03 / Search
keyword blind

Keyword search misses real expertise
Terminology changes. Disciplines overlap. Keyword-based tools fail to capture true subject alignment.

boolean ? expertise
04 / Integrity
opaquesignals

Critical signals are hard to access
Conflict checks, retractions, and affiliations are not visible when decisions are made.

risk you can't audit
— What makes us different

Purpose-built for peer review,
transparent by design.

Six pillars set Reviewer Select apart from general-purpose recommendation engines. Powered end-to-end by the Milvus vector database.

See exactly why a reviewer is recommended

Every match is broken down concept by concept. You can see how your manuscript aligns with a reviewers work, with clear similarity scores. No black box. Every decision is explainable.

Backed by real research, not assumptions

Each recommendation is supported by DOI-linked articles. You can review the actual publications behind every match before making a decision.

Score breakdown Dr. E. Marquez
94.6
Semantic concept overlap0.96
Citation graph proximity0.88
Methodological alignment0.91
Integrity and conflict screenpassed
10.1038/s41586-024-07129-zGlioblastoma vector therapy
10.1126/sciadv.adk9012CRISPR-Cas9 immunology
10.1016/j.cell.2023.11.044Tumor microenvironment
You stay in control of the search

Review and validate extracted concepts before running the search. Refine inputs if needed. The results reflect your intent, not just the AI's first pass.

Critical signals at the moment of decision

Retractions, affiliations, and co-authorship data are visible directly on each reviewer card. No separate checks needed.

Editorial weights
Policy · Cell Biology Q3
Semantic match— 1.4
Author seniority floorpost-doc+
Geographic diversitybalance
Retraction screenstrict
Live exclusions: Inst. of Oncology Geneva — 3 prior co-authors
Matches based on meaning, not keywords

The system understands relationships between topics, even when terminology differs. This helps surface relevant experts across disciplines.

Expertise comes before reputation

Reviewers are ranked based on alignment with your manuscript. Not seniority. Not institutional prestige. Just relevance.

Concept vector space 2D projection
Milvus IVF_FLAT
manuscript gene editing immunology
1024
dim space
8.4 M
reviewer vectors
k = 50
ann recall
— How it works

From manuscript abstract to ranked reviewers in three steps.

01
Step One

Enter manuscript details

Paste the title, abstract, and optional keywords. Better input leads to better matches.

NEW SUBMISSIONstep 1/3
[Title] CRISPR-Cas9 modulation of glioblastoma microenvironments
[Abstract] We report a programmable Cas9 delivery vehicle that selectively disables
1.2 KB — pasted
02
Step Two

Review extracted concepts

Check what the AI has understood. Adjust if needed before running the search.

EXTRACTED 14 CONCEPTSstep 2/3
CRISPR-Cas9 ? glioblastoma ? microenvironment ? gene editing ? stem cells + delivery vectors
edited by editor
03
Step Three

Check recommended reviewers

View and shortlist reviewers Get a ranked reviewer list with scores, evidence, and key signals. Everything you need in one place.

SHORTLIST 12 OF 8.4Mstep 3/3
E. Marquez94.6
K. Ohara91.2
A. Patel87.4
3 invited 2 accepted
— Reviewer card

Everything on one
reviewer card.

Six layers of intelligence collapsed into a single, auditable artefact your editorial team can act on in seconds.

AI concept extraction
Understand what your manuscript is really about before searching.
Input

"We report a programmable Cas9 delivery vehicle that selectively disables"

Concepts
CRISPR-Cas9 glioblastoma delivery vector tumor immunology microenvironment
Semantic matching
Find reviewers based on true research alignment, not keywords.
8.4 M
indexed reviewer vectors
across 220+ disciplines
Three-tier ranking
Clear prioritization of relevance, depth, and coverage.
Semantic alignmenttier 1
Bibliometric proximitytier 2
Integrity signalstier 3
Integrity signals
Change retraction record to Retraction history
Retraction recordclear
Co-author proximity2 of 12
Conflict declarationsnone
Editorial blacklistpass
DOI-linked evidence
Validate every recommendation with real publications.
10.1038/s41586-024-07129
10.1126/sciadv.adk9012
10.1016/j.cell.2023.11
Affiliation history
Check conflicts and reviewer background instantly.
  1. ETH Zrich
    2019 . present
  2. Broad Institute
    2014 . 2019
— Use cases

Built for teams who take reviewer quality seriously.

For publishers

Publishers and editors

Cut handling time across portfolios, surface fresh reviewer voices, and standardise integrity checks across every imprint.

  • Reduce reviewer search time drastically
  • Maintain consistent match quality
  • Expand beyond existing networks
For funders

Research funding agencies

Assemble defensible peer reviewer panels for grant programs, scale across funding rounds, and document selection rationale end-to-end.

  • Identify independent reviewers
  • Improve evaluation integrity
  • Process higher application volumes
For universities

University research offices

Source external reviewers for tenure files, dissertation defenses, and internal program evaluations with documented impartiality.

  • Support internal review processes
  • Discover cross-domain experts
  • Scale evaluations efficiently
— Quick answers

Quick
answers.

Have more questions? Check out our FAQ or schedule a call with our team.

How is this different from keyword search?
It matches meaning, not words. This helps surface better and broader expertise.
Does it handle interdisciplinary work?
Yes. You can see exactly which parts of your manuscript each reviewer covers.
What if the search yields no reviewer are recommendations?
Check the unmatched results or refine your input for better alignment.
Does ranking consider seniority?
No. Ranking is based purely on expertise and relevance.
Live in production with editorial partners

Transform reviewer
selection with semantic AI.

Reduce reviewer search from 30 minutes to under 60 seconds without sacrificing rigour, transparency, or editorial control.

Request a demo Contact us