fullscreen

eFinder

eFinder

Home › Artificial Intelligence in Agriculture › Article

Experimentally validated AI model predicts virulence of tomato yellow leaf curl virus

Phys · · 489 words · By Sungkyunkwan University
Artificial Intelligence in Agriculture Scientific Innovation Plant Pathology
headphones Listen to the eFinder podcast briefing
Generate a natural audio summary of this story
Daily briefing

What to know about Artificial Intelligence in Agriculture

Researchers at Sungkyunkwan University have developed DeepTYLCV, an AI model designed to predict the virulence of the tomato yellow leaf curl virus using genomic sequence data. The model's predictions were experimentally validated with 100% concordance in a blind study of 15 isolates.

Propaganda risk 10%
Claims checked 12
Techniques found 1
Topics 3

Coverage spectrum

Coverage gap: Low Left coverage
Left0%
Center100%
Right0%

2 sources compared across this story cluster. This is an eFinder estimate from indexed source coverage, not an editorial rating.

What happened

Experimentally validated AI model predicts virulence of tomato yellow leaf curl virus Sadie Harley Scientific Editor Robert Egan Associate Editor A CBBL research team led by Professor Balachandran Manavalan from the Department of Integrative Biotechnology at…

Why it matters

The study, conducted with co-first authors Dr.

Common ground

Nattanong Bupi, Hariharan Sangaraju, and Duong Thanh Tran, was published in Plant Communications.

Perspective signals

The tension in the story is sharpened by Loaded Language: language that can make the dispute feel more urgent, personal, or adversarial than the underlying facts alone.

Researchers at Sungkyunkwan University have developed DeepTYLCV, an AI model designed to predict the virulence of the tomato yellow leaf curl virus using genomic sequence data. The model's predictions were experimentally validated with 100% concordance in a blind study of 15 isolates.

open_in_new Read the original article: https://phys.org/news/2026-05-experimentally-validated-ai-virulence-tomato.html

analyticsAnalysis

10%
Propaganda Score
confidence: 95%
Low risk. This article shows minimal use of propaganda techniques.

psychologyPropaganda Techniques Detected

eFinder identified 1 propaganda technique in this article. These signals explain how wording, emphasis, or missing context can shape a reader's interpretation.

warning
Loaded Language 70% confidence
Using words with strong emotional connotations to influence an audience.
Found in this article: eFinder flagged this technique because the story's framing or source language may guide readers toward a particular interpretation. Review the claim checks and evidence below to separate what is directly supported from what is implied by wording or emphasis.
Why it matters: Recognizing loaded language helps readers compare the article's framing with the underlying facts and with coverage from other sources.

fact_checkClaims Checked

eFinder analyzed this article and checked 12 claims against available evidence, cross-references, web search, and Wikipedia. Here is what the fact-checking layer found.

check_circle Corroborated 5
verified Verified 4
schedule Pending 2
info Single Source 1
verified
Claim 1: “The research team performed blind predictions for 15 TYLCV isolates, including both international reference isolates and Korean field isolates.”
VERIFIED
The evidence explicitly mentions that 'The research team performed blind predictions for 15 TYLCV isolates, including both international reference isolates and Korean field isolates'.
info
Claim 2: “In 2023, the team developed IML-TYLCV, the first genome-based TYLCV severity prediction tool, which was published in the journal Research.”
SINGLE SOURCE
While the general context of the research is corroborated, the specific detail about the 'IML-TYLCV' tool being published in the journal 'Research' in 2023 is not explicitly confirmed by the provided search snippets, although it is mentioned in the context of the newer DeepTYLCV model's superiority.
travel_explore
web search NEUTRAL — The Russo-Ukrainian war and Myanmar civil war continued in 2023, and a series of coups, several armed conflicts, and political crises broke out in numerous African nations, most notably a Sudanese civ…
https://en.wikipedia.org/wiki/2023
travel_explore
web search NEUTRAL — 2023年是公历平年，共365天，1月1日—1月21日为农历壬寅年（虎年），1月22日—12月31日为农历癸卯年（兔年），含闰二月，全年384天，因含双立春亦称“双春年”。
https://baike.baidu.com/item/2023年/10847168
travel_explore
web search NEUTRAL — Yearly calendar showing months for the year 2023. Calendars – online and print friendly – for any year and month.
https://www.timeanddate.com/calendar/?year=2023&country=1
check_circle
Claim 3: “A CBBL research team led by Professor Balachandran Manavalan from the Department of Integrative Biotechnology at Sungkyunkwan University has developed DeepTYLCV, an accurate and interpretable artificial intelligence model for predicting the virulence of tomato yellow leaf curl virus (TYLCV).”
CORROBORATED
Multiple web search results confirm that a research team at Sungkyunkwan University (SKKU), led by Professor Balachandran Manavalan, developed DeepTYLCV for predicting TYLCV virulence.
travel_explore
web search NEUTRAL — Tomato yellow leaf curl virus (TYLCV) is among the most devastating pathogens affecting tomato production worldwide, with emerging virulent strains increasingly overcoming genetic resistance and trigg…
https://pubmed.ncbi.nlm.nih.gov/42063254/
travel_explore
web search NEUTRAL — DeepTYLCV: An interpretable and experimentally validated AI model for predicting virulence of different tomato yellow leaf curl virus strains.
https://www.newswise.com/articles/skku-research-team-develop…
travel_explore
web search NEUTRAL — Balachandran Manavalan. Sungkyunkwan University | SKKU · College of Biotechnology and Bioengineering.Leveraging deep transfer learning and explainable AI for accurate COVID-19 diagnosis: Insights from…
https://www.researchgate.net/profile/Balachandran-Manavalan
check_circle
Claim 4: “DeepTYLCV uses viral genome-derived sequence information.”
CORROBORATED
Multiple sources confirm DeepTYLCV uses protein language model embeddings and sequence representations derived from the viral genome.
travel_explore
web search NEUTRAL — DeepTYLCV integrates protein language model (PLM)-based embeddings with optimal concatenated conventional descriptors (optCCDs) using a hybrid architecture composed of a Transformer encoder and a mult…
https://pubmed.ncbi.nlm.nih.gov/42063254/
travel_explore
web search NEUTRAL — By combining deep sequence representations with optimized conventional feature descriptors, DeepTYLCV achieved superior predictive performance compared with the previous IML-TYLCV model. A key strengt…
https://www.newswise.com/articles/skku-research-team-develop…
travel_explore
web search NEUTRAL — cd DeepTYLCV/ python -m pip install -r requirements.txt --no-cache-dir. Inferencing models You can easily predict directly from FASTA files or sequence dictionaries using the Inferencer by giving path…
https://github.com/Hariharanvictor/DeepTYLCV
schedule
Claim 5: “Nattanong Bupi et al, DeepTYLCV: An interpretable and experimentally validated AI model for predicting virulence of different tomato yellow leaf curl virus strains, Plant Communications (2026). DOI: 10.1016/j.xplc.2026.101877”
PENDING
This claim was extracted as a checkable statement from the article. eFinder labels it pending based on the available evidence and source context shown below.
verified
Claim 6: “IML-TYLCV was mainly trained on Korean isolates”
VERIFIED
The evidence explicitly states that 'IML-TYLCV was mainly trained on Korean isolates', which limited its global applicability.
travel_explore
web search NEUTRAL — However, IML-TYLCV was mainly trained on Korean isolates, limiting its applicability to globally diverse TYLCV strains.The research team performed blind predictions for 15 TYLCV isolates, including bo…
https://www.newswise.com/articles/skku-research-team-develop…
travel_explore
web search NEUTRAL — Tomato yellow leaf curl virus (TYLCV) is among the most devastating pathogens affecting tomato production worldwide, with emerging virulent strains increasingly overcoming genetic resistance and trigg…
https://pubmed.ncbi.nlm.nih.gov/42063254/
travel_explore
web search NEUTRAL — ...three isolates of Tomato yellow leaf curl virus (TYLCV), infecting tomato, using polymerase chain reaction technology (PCR) and determining the nucleotide sequences produced by PCR- amplified produ…
https://www.researchgate.net/publication/47511131_Genetic_di…
check_circle
Claim 7: “TYLCV is one of the most destructive viral pathogens affecting tomato production worldwide.”
CORROBORATED
Multiple sources, including Wikipedia and specialized agricultural articles, confirm TYLCV is one of the most destructive pathogens for global tomato production.
travel_explore
web search NEUTRAL — Symptom of yellow curl leaf disease in chilli pepper leaves. Tomato yellow leaf curl virus (TYLCV) is a DNA virus from the genus Begomovirus and the family Geminiviridae.
https://en.wikipedia.org/wiki/Tomato_yellow_leaf_curl_virus
travel_explore
web search NEUTRAL — Tomato yellow leaf curl virus (TYLCV) and fungal Oidium sp. are devastating pathogens causing yellow leaf curl disease and powdery mildew. Such viral and fungal pathogens reduce tomato crop yields and…
https://pmc.ncbi.nlm.nih.gov/articles/PMC7917697/
travel_explore
web search NEUTRAL — Tomato yellow leaf curl disease is one of the most destructive plant diseases destroying the tomato crops globally. It has spread to many countries worldwide including Southern, Central and Northern p…
https://www.walshmedicalmedia.com/open-access/tomato-yellow-…
schedule
Claim 8: “DeepTYLCV achieved 100% concordance between predicted and experimentally observed virulence classes”
PENDING
This claim was extracted as a checkable statement from the article. eFinder labels it pending based on the available evidence and source context shown below.
verified
Claim 9: “The study, conducted with co-first authors Dr. Nattanong Bupi, Hariharan Sangaraju, and Duong Thanh Tran, was published in Plant Communications.”
VERIFIED
The author list provided in the search results explicitly includes Nattanong Bupi, Hariharan Sangaraju, and Duong Thanh Tran. The title of the paper matches the model name and is associated with the research team.
travel_explore
web search NEUTRAL — Nattanong Bupi 1 , Hariharan Sangaraju 2 , Duong Thanh Tran 2 , Vinoth Kumar Sangaraju 2 , Hyojin Im 1 , Minkwan Kim 1 , Sukchan Lee 3 , Balachandran Manavalan 4. Affiliations. 1 Celtech Laboratory, D…
https://pubmed.ncbi.nlm.nih.gov/42063254/
travel_explore
web search NEUTRAL — ...Zionism and Nazi Germany, 1933-1941 Published in Journal of Palestine...
https://www.tandfonline.com/doi/abs/10.2307/2536016
travel_explore
web search NEUTRAL — Journal of the American Medical Association.
https://jamanetwork.com/journals/jamanetworkopen/fullarticle…
check_circle
Claim 10: “DeepTYLCV integrates protein language model embeddings with a hybrid architecture that combines a Transformer encoder and a multi-scale convolutional neural network”
CORROBORATED
Two independent search results explicitly describe the architecture as integrating protein language model embeddings with a hybrid architecture of a Transformer encoder and a multi-scale convolutional neural network (CNN).
travel_explore
web search NEUTRAL — A convolutional neural network consists of an input layer, hidden layers and an output layer.Moreover, a single dilated convolutional layer can comprise filters with multiple dilation ratios,[31] thus…
https://en.wikipedia.org/wiki/Convolutional_neural_network
travel_explore
web search NEUTRAL — DeepTYLCV integrates protein language model embeddings with a hybrid architecture that combines a Transformer encoder and a multi-scale convolutional neural network, enabling the model to capture both…
https://www.newswise.com/articles/skku-research-team-develop…
travel_explore
web search NEUTRAL — DeepTYLCV integrates protein language model (PLM)-based embeddings with optimal concatenated conventional descriptors (optCCDs) using a hybrid architecture composed of a Transformer encoder and a mult…
https://pubmed.ncbi.nlm.nih.gov/42063254/
verified
Claim 11: “DeepTYLCV achieved superior predictive performance compared with the previous IML-TYLCV model.”
VERIFIED
The evidence explicitly states that 'DeepTYLCV achieved superior predictive performance compared with the previous IML-TYLCV model'.
check_circle
Claim 12: “Severe TYLCV strains can cause leaf curling, yellowing, stunted growth, and major yield losses.”
CORROBORATED
Multiple sources describe the symptoms of TYLCV as including leaf curling, yellowing, stunted growth, and significant yield losses (up to 80-100%).
travel_explore
web search NEUTRAL — Symptom of yellow curl leaf disease in chilli pepper leaves.This virus can cause significant yield losses from 90–100%, and it is estimated that about 7 million hectares can experience TYLCV infection…
https://en.wikipedia.org/wiki/Tomato_yellow_leaf_curl_virus
travel_explore
web search NEUTRAL — Upward-curling tomato leaves — the most common pattern, caused by heat stress.Yellow leaf margins; stunted growth; flower drop. Viral disease (TYLCV / TMV). High — remove infected plants promptly.
https://www.bloomingexpert.com/tips/tomatoes/curling-leaves-…
travel_explore
web search NEUTRAL — TYLCV causes severe tomato yield losses of up to 80%, especially when plants are infected early. B. tabaci biotype B efficiently transmits TYLCV with an incubation period of 24 hours. Two strains of T…
https://www.academia.edu/5994202/Tomato_yellow_leaf_curl_vir…
info Disclaimer: This analysis is generated by AI and should be used as a starting point for critical thinking, not as definitive truth. Claims are verified against publicly available sources. Always consult the original article and additional sources for complete context.