Technology · EMX

Biomedical entity recognition, without a neural network

EMX is the entity matcher we built for Atlas. It finds genes, diseases, drugs and seven other entity types in scientific text, links each mention to the vocabularies that define it, and does it on a CPU in milliseconds, with the same output every time.

Example project: KRAS G12C · non-small cell lung canceremx 0.1.0, lexicon v42 · benchmarks of 2 Nov 2026
median per full-text article, on CPU, with identifiers
55 ms
F1 on tmVar v3 genes with identifier (HunFlair2: 76.75)
76.8
entity types, against 5 for HunFlair2
10
vocabularies, 71.2 million concepts
13

What is biomedical entity normalization?

Biomedical entity normalization finds the genes, diseases, chemicals and other entities named in a text and links each one to an identifier in a reference vocabulary, such as NCBI Gene, MONDO or MeSH. It is what lets a system know that LY3537982 and olomorasib are the same molecule, or that two papers discuss the same gene under different names. It usually takes two steps and a trained model; EMX does both in one pass, from a compiled lexicon.

With Atlas

  • One pass: each mention comes with its position and every candidate identifier
  • Ten entity types, from genes to procedures
  • Byte-identical output from one run to the next
  • Runs on CPU, with no GPU and no external API

Why we built it

Atlas first extracted entities by sending each document to a general-purpose language model. It worked, with four costs: about four seconds per abstract, a bill for every document, results that can change between two runs, and entity names without identifiers, which leaves the linking across papers to another step.

Entity recognition is a task where most of the knowledge already exists, in the vocabularies the field maintains. We wanted to use it directly: fast, deterministic, with identifiers from the start, and keep language models for what they do better, such as reading results, relations and contradictions.

How it works

EMX is written in Rust. It compiles 71.2 million concepts and 51.8 million written forms from 13 scientific vocabularies, among them NCBI Gene, MONDO and MeSH, into a lexical index searched with an Aho-Corasick automaton, then applies deterministic context rules.

Each mention keeps its exact position, its type and its candidate identifiers in the vocabularies. Nothing is learned, so an error is fixed in the lexicon or in a rule, and the fix can be measured.

Entity types: gene / protein, disease, chemical / drug, cell type, cell line, organism, anatomy, cellular component, procedure, phenomenon.

Benchmarks: recognition quality

F1 scores (0 to 100) against human-annotated public corpora and one internal full-text set. A mention counts as correct only if both its boundaries and its type are exact. The “setting” column says where a system was trained on the corpus, which makes its score an upper bound rather than a fair comparison.

DatasetSettingEMXHunFlair2scispaCyDeepSeek v4.1 flash
tmVar v3, genes + identifierHunFlair2 figure as published by Sänger et al. (2024); DeepSeek returns no identifierHunFlair2's own cross-corpus evaluation76.876.75——
tmVar v3, gene recognitionSame corpus, recognition only84.087.9—52.4
BC5CDR testOut of domain for EMX and HunFlair2; in domain for scispaCy81.681.175.774.6
NCBI Disease testIn domain for HunFlair275.393.157.774.9
GNormPlusIn domain for HunFlair273.081.3——
Atlas full-text gold, 5 shared typesGold built by a consensus of language models, not human experts; DeepSeek received the guideline used to build it150 passages of recent full-text articles, rebuilt without DeepSeek's vote74.068.532.775.5
Quaero (French)Out of domain for all; none is built for French26.720.217.3—

On the task that matters for Atlas, finding a gene and identifying it, EMX matches HunFlair2 on the corpus its authors chose for their own cross-corpus evaluation (76.8 against 76.75). HunFlair2 still finds more genes, and wins clearly on the corpora it was trained on.

Benchmarks: speed

Median and 95th-percentile time per full-text article, on the same 500 articles (10 used for warm-up). Each system runs on the hardware where it is fastest.

SystemTaskHardwareMedianp95
EMXRecognition + identifiersCPU, 4 threads (cloud)55 ms216 ms
EMXRecognition + identifiersCPU, 4 threads (Intel i7-7700)59 ms192 ms
scispaCyRecognitionCPU (Intel i7-7700)1.6 s4.7 s
HunFlair2RecognitionGPU NVIDIA L45.5 s17.5 s
DeepSeek v4.1 flashRecognition, chunks sent in parallelAPI20.4 s38.5 s
HunFlair2Recognition + normalization (100 articles)GPU NVIDIA L435 s93 s

At equal task, recognition and identifiers on the same cloud machine, EMX is about 640 times faster than HunFlair2 on a full-text article and about 1,700 times faster on an abstract (3.6 ms against 6.1 s), with no GPU. On an abstract, DeepSeek answers in 3.3 to 4.0 seconds through its API, without identifiers.

Where EMX is not better

Method and caveats

Status in Atlas

EMX is being integrated into Atlas. Once in production, it will identify entities in the papers and trials of each project, and language models will work on top of its identifiers. The sources Atlas reads are listed on data sources, and what the entities become in a project on the knowledge graph page.

References

See what Atlas does with these entities

We set up a project on your disease and target with you, and walk through the papers, trials and evidence it finds.

Request a demo

Benchmarks of 2 Nov 2026, emx 0.1.0, lexicon v42. Speed measured on an AWS g6.2xlarge (NVIDIA L4 GPU, 8 vCPU AMD EPYC 7R13) and on an Intel Core i7-7700; quality measured on the same machine with the same scorer for every system, except where a published figure is cited.