@inproceedings{kondadadi-ortega-2026-beyond,
title = "Beyond Knowledge Graphs: {P}ub{M}ed{BERT} Embeddings as a Competitive Standalone Modality for Drug Re-purposing",
author = "Kondadadi, Rishik and
Ortega, John E.",
editor = "Demner-Fushman, Dina and
Ananiadou, Sophia and
Roberts, Kirk and
Tsujii, Junichi",
booktitle = "{B}io{NLP} 2026",
month = jul,
year = "2026",
address = "San Diego, California",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.bionlp-1.13/",
pages = "135--140",
ISBN = "979-8-89176-434-7",
abstract = "Drug repurposing methods rely heavily on knowledge graph (KG) embeddings, but building and curating these graphs takes considerable effort. We present two findings on the Hetionet drug-disease benchmark and an epilepsy ranking task. First, PubMedBERT text embeddings, fed through the same downstream classifiers and identical 10-fold splits as four re-trained KG baselines (TransE, ComplEx, DistMult, RotatE), reach AUROC {\$}0.910{\$}, above all four (best: RotatE, {\$}0.854{\$}); a Random Forest on the same vectors scores {\$}0.880{\$}. The comparison is asymmetric in one important way: PubMedBERT was pretrained on the literature Hetionet was curated from, so the result is best read as ``text-with-literature-supervision vs.graph-only,'' and a head-to-head with text-augmented KG methods (KG-BERT, TxGNN) is left as follow-up. Second, across all seven combinations of text, molecular (ECFP4), and gene expression (LINCS L1000) features, cross-attention fusion of weaker modalities into text consistently degrades performance, despite a gated mechanism intended to suppress unhelpful modalities; the residual path forces the strong modality to absorb noise. The model also ranks proconvulsants (amoxapine, flumazenil) near the top, because text embeddings encode strength of association with a disease but not its direction."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kondadadi-ortega-2026-beyond">
<titleInfo>
<title>Beyond Knowledge Graphs: PubMedBERT Embeddings as a Competitive Standalone Modality for Drug Re-purposing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rishik</namePart>
<namePart type="family">Kondadadi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">John</namePart>
<namePart type="given">E</namePart>
<namePart type="family">Ortega</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>BioNLP 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dina</namePart>
<namePart type="family">Demner-Fushman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sophia</namePart>
<namePart type="family">Ananiadou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kirk</namePart>
<namePart type="family">Roberts</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junichi</namePart>
<namePart type="family">Tsujii</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-434-7</identifier>
</relatedItem>
<abstract>Drug repurposing methods rely heavily on knowledge graph (KG) embeddings, but building and curating these graphs takes considerable effort. We present two findings on the Hetionet drug-disease benchmark and an epilepsy ranking task. First, PubMedBERT text embeddings, fed through the same downstream classifiers and identical 10-fold splits as four re-trained KG baselines (TransE, ComplEx, DistMult, RotatE), reach AUROC $0.910$, above all four (best: RotatE, $0.854$); a Random Forest on the same vectors scores $0.880$. The comparison is asymmetric in one important way: PubMedBERT was pretrained on the literature Hetionet was curated from, so the result is best read as “text-with-literature-supervision vs.graph-only,” and a head-to-head with text-augmented KG methods (KG-BERT, TxGNN) is left as follow-up. Second, across all seven combinations of text, molecular (ECFP4), and gene expression (LINCS L1000) features, cross-attention fusion of weaker modalities into text consistently degrades performance, despite a gated mechanism intended to suppress unhelpful modalities; the residual path forces the strong modality to absorb noise. The model also ranks proconvulsants (amoxapine, flumazenil) near the top, because text embeddings encode strength of association with a disease but not its direction.</abstract>
<identifier type="citekey">kondadadi-ortega-2026-beyond</identifier>
<location>
<url>https://aclanthology.org/2026.bionlp-1.13/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>135</start>
<end>140</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Beyond Knowledge Graphs: PubMedBERT Embeddings as a Competitive Standalone Modality for Drug Re-purposing
%A Kondadadi, Rishik
%A Ortega, John E.
%Y Demner-Fushman, Dina
%Y Ananiadou, Sophia
%Y Roberts, Kirk
%Y Tsujii, Junichi
%S BioNLP 2026
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California
%@ 979-8-89176-434-7
%F kondadadi-ortega-2026-beyond
%X Drug repurposing methods rely heavily on knowledge graph (KG) embeddings, but building and curating these graphs takes considerable effort. We present two findings on the Hetionet drug-disease benchmark and an epilepsy ranking task. First, PubMedBERT text embeddings, fed through the same downstream classifiers and identical 10-fold splits as four re-trained KG baselines (TransE, ComplEx, DistMult, RotatE), reach AUROC $0.910$, above all four (best: RotatE, $0.854$); a Random Forest on the same vectors scores $0.880$. The comparison is asymmetric in one important way: PubMedBERT was pretrained on the literature Hetionet was curated from, so the result is best read as “text-with-literature-supervision vs.graph-only,” and a head-to-head with text-augmented KG methods (KG-BERT, TxGNN) is left as follow-up. Second, across all seven combinations of text, molecular (ECFP4), and gene expression (LINCS L1000) features, cross-attention fusion of weaker modalities into text consistently degrades performance, despite a gated mechanism intended to suppress unhelpful modalities; the residual path forces the strong modality to absorb noise. The model also ranks proconvulsants (amoxapine, flumazenil) near the top, because text embeddings encode strength of association with a disease but not its direction.
%U https://aclanthology.org/2026.bionlp-1.13/
%P 135-140
Markdown (Informal)
[Beyond Knowledge Graphs: PubMedBERT Embeddings as a Competitive Standalone Modality for Drug Re-purposing](https://aclanthology.org/2026.bionlp-1.13/) (Kondadadi & Ortega, BioNLP 2026)
ACL