Back

Curation at Scale with EPITOME: Extraction Pipeline for Immunological Texts and Open-Source Multimodal Enquiry

Richardson, E.; Lischwe, P.; Bennett, J.; Blazeska, N.; Greenbaum, J.; Harlan, B.; Lallmamode, N.; Marrama, D.; Talbott, M.; Vita, R.; Sette, A.; Kuether, K.; Peters, B.

2026-01-09 bioinformatics
10.64898/2026.01.08.698331 bioRxiv
Show abstract

The Immune Epitope Database (IEDB, iedb.org) has manually curated epitope data from over 26,000 publications across two decades. With PubMed adding [~]5,000 articles daily, traditional curation methods face scalability challenges. Given the multimodality of data contained in scientific papers, we have sought to build an open-source vision language model (VLM)-based tool that human curators can use to speed up and automate biological data curation. Here we present a multimodal document ingestion and Question-Answering (QnA) pipeline that ties traditional Optical Character Recognition (OCR) and text matching with Vision-Language Model (VLM) capabilities. The system, which we call EPITOME, implements three-stage processing: regex-based epitope and MHC molecule identification, visual element extraction from PDFs, and contextual indexing that links peptide sequences, MHC molecules, and assays to their locations across text, tables, and figures. This indexing is used to supply context for further VLM QnA. Our preliminary results from EPITOME demonstrate promising zero-shot performance of open-source VLMs that suggest promise for accelerating biocuration through a curator-in-the-loop process, with our evaluation identifying strategic points where curator-in-the-loop intervention can enhance overall system accuracy.

Matching journals

The top 7 journals account for 50% of the predicted probability mass.

1
Nucleic Acids Research
◐ 1281 papers in training set
Top 1%
12.2%
Similar papers in this journal
2
Bioinformatics
◐ 1204 papers in training set
Top 2%
11.5%
Similar papers in this journal
3
Scientific Data
○ 209 papers in training set
Top 0.3%
7.6%
Similar papers in this journal
4
Patterns
○ 78 papers in training set
Top 0.1%
6.5%
Similar papers in this journal
5
Database
◐ 61 papers in training set
Top 0.1%
6.0%
Similar papers in this journal
6
GigaScience
◐ 212 papers in training set
Top 0.6%
5.0%
7
Briefings in Bioinformatics
◐ 354 papers in training set
Top 2%
3.9%
50% of probability mass above
8
Nature Communications
○ 5641 papers in training set
Top 34%
3.3%
9
NAR Genomics and Bioinformatics
◐ 242 papers in training set
Top 1%
3.3%
10
Scientific Reports
○ 3612 papers in training set
Top 35%
3.1%
11
mAbs
○ 32 papers in training set
Top 0.2%
3.0%
12
Bioinformatics Advances
◐ 203 papers in training set
Top 2%
3.0%
13
Nature Methods
○ 385 papers in training set
Top 3%
2.5%
14
Computational and Structural Biotechnology Journal
● 242 papers in training set
Top 2%
2.5%
15
BMC Bioinformatics
○ 457 papers in training set
Top 3%
2.3%
16
Genome Biology
○ 637 papers in training set
Top 5%
2.0%
17
Nature Protocols
○ 33 papers in training set
Top 0.3%
1.7%
18
PLOS Computational Biology
● 1863 papers in training set
Top 15%
1.6%
19
iScience
○ 1154 papers in training set
Top 22%
1.4%
20
Cell Reports Methods
○ 165 papers in training set
Top 2%
1.4%
21
Journal of Proteome Research
● 234 papers in training set
Top 1%
1.3%
22
Cell Systems
○ 201 papers in training set
Top 4%
1.0%
23
Frontiers in Bioinformatics
○ 49 papers in training set
Top 1%
1.0%
24
PLOS ONE
● 5266 papers in training set
Top 60%
0.8%
25
Molecular Systems Biology
○ 162 papers in training set
Top 3%
0.8%
26
BioData Mining
○ 22 papers in training set
Top 0.7%
0.8%
27
Journal of Molecular Biology
○ 232 papers in training set
Top 4%
0.8%
28
Protein Science
○ 246 papers in training set
Top 4%
0.8%
29
eLife
● 5828 papers in training set
Top 68%
0.8%
30
Nature Biotechnology
○ 172 papers in training set
Top 5%
0.6%

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.