MétaCan
Menu
Back to cohort
Record W4410516993 · doi:10.1038/s43856-025-00903-w

Hidden challenges in evaluating spillover risk of zoonotic viruses using machine learning models

2025· article· en· W4410516993 on OpenAlex

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

fundA Canadian funder is recorded on the work.
no affNo Canadian affiliation: this work is invisible to an affiliation-only frame.
No Canadian affiliation. An affiliation-only frame, the usual design, would never have seen this work. It is one of the works that make the case for inverting the frame.

Bibliographic record

VenueCommunications Medicine · 2025
Typearticle
Languageen
FieldMedicine
TopicZoonotic diseases and public health
Canadian institutionsnot available
FundersPrecursory Research for Embryonic Science and TechnologyJapan Society for the Promotion of ScienceInstitute of GeneticsUniversity of TokyoMinistry of Education, Culture, Sports, Science and Technology
KeywordsSpillover effectComputer scienceArtificial intelligenceVirologyMachine learningBiologyEconomics

Abstract

fetched live from OpenAlex

Machine learning models have been deployed to assess the zoonotic spillover risk of viruses by identifying their potential for human infectivity. However, the lack of comprehensive datasets for viral infectivity poses a major challenge, limiting the predictable range of viruses. In this study, we address this limitation through two key strategies: constructing expansive datasets across 26 viral families and developing the BERT-infect model, which leverages large language models pre-trained on extensive nucleotide sequences. Here we show that our approach substantially boosts model performance. This enhancement is particularly notable in segmented RNA viruses, which are involved with severe zoonoses but have been overlooked due to limited data availability. Our model also exhibits high predictive performance even with partial viral sequences, such as high-throughput sequencing reads or contig sequences from de novo sequence assemblies, indicating the model’s applicability for mining zoonotic viruses from virus metagenomic data. Furthermore, models trained on data up to 2018 demonstrate robust predictive capability for most viruses identified post-2018. Nonetheless, high-resolution evaluation based on phylogenetic analysis reveals general limitations in current machine learning models: the difficulty in alerting the human infectious risk in specific zoonotic viral lineages, including SARS-CoV-2. Our study provides a comprehensive benchmark for viral infectivity prediction models and highlights unresolved issues in fully exploiting machine learning to prepare for future zoonotic threats. To prepare for future pandemics caused by animal-derived viruses, there is a growing need for computational models that can predict whether a virus might infect humans. We constructed extensive datasets covering information about different viruses, including key human pathogens. We developed computational models using these datasets, which outperformed existing approaches across many virus types. However, we also revealed that current models share the same unresolved challenges when assessing whether specific viruses will infect humans, including SARS-CoV-2. These findings suggest that current models may fail to identify animal viruses that can infect humans, which underscores the urgent need for improved predictive models to strengthen pandemic preparedness. Kawasaki et al. construct a dataset covering 26 viral families and use large language models pre-trained on nucleotide sequences to identify zoonotic viruses with human infectivity potential. High predictive performance was obtained, even with partial viral sequences, but not all zoonotic lineages could be identified.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.002
metaresearch head score (Gemma)0.003
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.934
Threshold uncertainty score0.508

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0020.003
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0010.000
Bibliometrics0.0000.001
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0000.000
Research integrity0.0000.001
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.333
GPT teacher head0.445
Teacher spread0.112 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it