fullscreen

eFinder

eFinder

Home › Article

Are the chemicals around you safe? Researchers are using AI to find out

Phys · · 815 words · By Camryn Haines
headphones Listen to the eFinder podcast briefing
Ready to play
Daily briefing

What to know about Are the chemicals around you safe? Researchers are using AI to find out

Researchers at Texas A&M University are developing AI and machine learning models to predict chemical toxicity and estimate the reliability of those predictions. This approach aims to address the data gap in chemical safety testing by identifying high-risk substances and directing regulatory focus more efficiently.

Propaganda risk 10%
Claims checked 11
Techniques found 0
Topics 0

Coverage spectrum

Coverage gap: Low Left coverage
Left0%
Center75%
Right25%

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

What happened

Researchers are using AI to find out Lisa Lock Scientific Editor Robert Egan Associate Editor People are exposed to thousands of chemicals every day—through the products they use, the food they eat and the environments they live in—but only a fraction of…

Why it matters

Researchers at the Texas A&M College of Veterinary Medicine and Biomedical Sciences (VMBS) are turning to artificial intelligence to help close that gap, using new tools to predict chemical toxicity and determine how much those predictions can be trusted.

Common ground

The work builds on a recent study published in Nature Communications that explores how artificial intelligence can predict chemical toxicity while also estimating how reliable those predictions are.

Perspective signals

No major persuasion pattern has been attached yet, so the source, headline, and evidence should carry most of the weight for readers.

Researchers at Texas A&M University are developing AI and machine learning models to predict chemical toxicity and estimate the reliability of those predictions. This approach aims to address the data gap in chemical safety testing by identifying high-risk substances and directing regulatory focus more efficiently.

open_in_new Read the original article: https://phys.org/news/2026-05-chemicals-safe-ai.html

analyticsAnalysis

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

fact_checkClaims Checked

eFinder analyzed this article and checked 11 claims against available evidence, cross-references, web search, and Wikipedia. Here is what the fact-checking layer found.

check_circle Corroborated 5
info Single Source 4
help Insufficient Evidence 1
schedule Pending 1
check_circle
Claim 1: “Chiu and collaborators expanded this work to include so-called "uncertainty-aware" machine learning, an approach that estimates how reliable each prediction is.”
CORROBORATED
EurekAlert!, Texas A&M news, and a PMC paper all confirm the development of 'uncertainty-aware' machine learning models to estimate the reliability of toxicity predictions.
menu_book
wikipedia NEUTRAL — Historic treatment of rail ties in the Houston, Texas Fifth Ward and Kashmere Gardens neighborhoods has exposed residents to cancer-causing soil contamination. Creosote and its extenders were used in…
https://en.wikipedia.org/wiki/Creosote_contamination_in_Hous…
travel_explore
web search NEUTRAL — Dr. Weihsueh Chiu of Texas A&M University’s College of Veterinary Medicine and Biomedical Sciences is developing artificial intelligence tools to improve chemical toxicity prediction and risk assessme…
https://www.eurekalert.org/news-releases/1129816
travel_explore
web search NEUTRAL — Dr. Weihsueh Chiu. Chemical toxicity prediction is advancing through new artificial intelligence research at Texas A&M University, where scientists are developing tools that can estimate both the pote…
https://www.processingmagazine.com/news-notes/news/55381311/…
+ 1 more evidence source
info
Claim 2: “The work builds on a recent study published in Nature Communications that explores how artificial intelligence can predict chemical toxicity while also estimating how reliable those predictions are.”
SINGLE SOURCE
While the general research is corroborated, the specific mention of a 'Nature Communications' study is not explicitly detailed in the provided search snippets, although the research topic matches the corroborated findings.
menu_book
wikipedia NEUTRAL — Generative artificial intelligence (GenAI) is a subfield of artificial intelligence (AI) that uses generative models to generate text, images, videos, audio, software code (vibe coding) or other forms…
https://en.wikipedia.org/wiki/Generative_AI
menu_book
wikipedia NEUTRAL — Second Nature, founded in Israel in 2018, is a company that offers professional training software that uses artificial intelligence: software for sales, customer support, and other training use cases.…
https://en.wikipedia.org/wiki/Second_Nature_(AI_Company)
menu_book
wikipedia NEUTRAL — The environmental impact of the design, training, deployment and use of artificial intelligence includes the greenhouse gas emissions from generating electricity for data centres and computing hardwar…
https://en.wikipedia.org/wiki/Environmental_impact_of_AI
+ 3 more evidence sources
check_circle
Claim 3: “Traditionally, for scientists to determine whether a chemical is safe, they have relied on animal studies or human epidemiological research”
CORROBORATED
Multiple sources (PMC-NIH and WHO Toolkit) confirm that traditional chemical risk assessment relies on animal testing and epidemiological studies.
travel_explore
web search NEUTRAL — Finally, the Animal Welfare Act (1966) required study designs involving animal models to be reviewed and approved in advance by an institutional animal care ...
https://pmc.ncbi.nlm.nih.gov/articles/PMC3114808/
travel_explore
web search NEUTRAL — In those cases, a quantitative evaluation of toxicity based on laboratory animal models or epidemiological studies may be required. That type of assessment ...
https://www.who.int/docs/default-source/documents/human-heal…
travel_explore
web search NEUTRAL — Traditional chemical-specific risk assessment based on animal testing may be insufficient and the lack of toxicological studies on chemical mixtures remains ...
https://www.sciencedirect.com/science/article/abs/pii/S02786…
help
Claim 4: “Certain groups of chemicals—including metals, polychlorinated compounds and PFAS—showed higher levels of uncertainty”
INSUFFICIENT EVIDENCE
No evidence was provided in the search results that specifically mentions metals, polychlorinated compounds, or PFAS showing higher levels of uncertainty in these models.
check_circle
Claim 5: “Dr. Weihsueh Chiu, a professor in VMBS' Department of Veterinary Physiology and Pharmacology, is leading efforts to advance these tools and apply them to better understand chemical safety and risk.”
CORROBORATED
Both EurekAlert! and Texas A&M news sources explicitly identify Dr. Weihsueh Chiu as the lead researcher from the College of Veterinary Medicine and Biomedical Sciences working on these AI tools.
menu_book
wikipedia NEUTRAL — Historic treatment of rail ties in the Houston, Texas Fifth Ward and Kashmere Gardens neighborhoods has exposed residents to cancer-causing soil contamination. Creosote and its extenders were used in…
https://en.wikipedia.org/wiki/Creosote_contamination_in_Hous…
travel_explore
web search NEUTRAL — May 14, 2026 · Dr. Andy Yen is an internal medicine physician with over 7 years of clinical experience serving patients in the Lake Stevens, WA area. He completed his medical training at Other and has…
https://ourhealthnetwork.com/doctor/andy-yen-md-1043879133
travel_explore
web search NEUTRAL — Dr. Floyd is a Board Certified Podiatrist and Foot and Ankle Surgeon and is a Diplomate of the American Board of Podiatric Surgery, and Fellow of the American College of Foot and Ankle Surgeons.
https://www.aafcclinic.com/about/
+ 1 more evidence source
check_circle
Claim 6: “Researchers at the Texas A&M College of Veterinary Medicine and Biomedical Sciences (VMBS) are turning to artificial intelligence to help close that gap, using new tools to predict chemical toxicity and determine how much those predictions can be trusted.”
CORROBORATED
Multiple independent web sources (EurekAlert! and a Texas A&M specific news report) confirm that Dr. Weihsueh Chiu at the Texas A&M College of Veterinary Medicine and Biomedical Sciences is developing AI tools to predict chemical toxicity and the reliability of those predictions.
menu_book
wikipedia NEUTRAL — Texas A&M University (Texas A&M, A&M, TA&M, or TAMU) is a public land-grant research university in College Station, Texas, United States. It was founded in 1876 and became the flagship institution of …
https://en.wikipedia.org/wiki/Texas_A&M_University
menu_book
wikipedia NEUTRAL — The Texas A&M University College of Veterinary Medicine & Biomedical Sciences is the veterinary school of Texas A&M University, a public research university in College Station, Texas. It was founded i…
https://en.wikipedia.org/wiki/Texas_A&M_University_School_of…
menu_book
wikipedia NEUTRAL — The Texas A&M University System is a state university system in Texas and is one of the state's seven independent university systems. The Texas A&M University System is one of the largest systems of h…
https://en.wikipedia.org/wiki/Texas_A&M_University_System
+ 3 more evidence sources
schedule
Claim 7: “Kerstin von Borries et al, Uncertainty-aware machine learning to predict non-cancer human toxicity for the global chemicals market, Nature Communications (2026). DOI: 10.1038/s41467-025-67374-4”
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.
info
Claim 8: “Chiu has previously helped address this issue through a two-stage machine learning framework designed to make predictions more interpretable.”
SINGLE SOURCE
The evidence confirms Dr. Chiu's work on uncertainty-aware ML, but the specific detail about a 'two-stage framework' for interpretability is not explicitly detailed in the provided snippets.
menu_book
wikipedia NEUTRAL — Historic treatment of rail ties in the Houston, Texas Fifth Ward and Kashmere Gardens neighborhoods has exposed residents to cancer-causing soil contamination. Creosote and its extenders were used in…
https://en.wikipedia.org/wiki/Creosote_contamination_in_Hous…
travel_explore
web search NEUTRAL — Uncertainty-aware machine learning models predict human toxicity for more than 100,000 chemicals, highlighting potency and uncertainty hotspots to guide safer ...
https://pmc.ncbi.nlm.nih.gov/articles/PMC12816579/
travel_explore
web search NEUTRAL — Dec 13, 2023 · Imputation machine learning (ML) surpasses traditional approaches in modeling toxicity data. The method was tested on an open-source data set.
https://pubs.acs.org/doi/10.1021/acs.jcim.3c01695
+ 1 more evidence source
info
Claim 9: “specifically, instead of relying on abstract molecular descriptors, the model uses familiar, real-world properties—such as water solubility, biodegradability and toxicity indicators”
SINGLE SOURCE
The provided evidence for this claim consists of irrelevant search results about doctors in Lake Stevens, WA, and does not mention the specific properties used in Dr. Chiu's model.
travel_explore
web search NEUTRAL — May 14, 2026 · Dr. Andy Yen is an internal medicine physician with over 7 years of clinical experience serving patients in the Lake Stevens, WA area. He completed his medical training at Other and has…
https://ourhealthnetwork.com/doctor/andy-yen-md-1043879133
travel_explore
web search NEUTRAL — Dr. Floyd is a Board Certified Podiatrist and Foot and Ankle Surgeon and is a Diplomate of the American Board of Podiatric Surgery, and Fellow of the American College of Foot and Ankle Surgeons.
https://www.aafcclinic.com/about/
travel_explore
web search NEUTRAL — There are 94 hospitals near Lake Stevens, WA with affiliated Family Medicine specialists, including Providence Regional Medical Center Everett, Skagit Valley Hospital and Swedish Edmonds Campus.
https://www.healthgrades.com/family-practice-directory/wa-wa…
check_circle
Claim 10: “researchers have spent the past decade developing machine learning models—known as quantitative structure-activity relationship (QSAR) models—that use a chemical's structure to estimate safe exposure levels.”
CORROBORATED
Multiple search results confirm that QSAR (Quantitative Structure-Activity Relationship) models are used in toxicology to predict effects based on chemical structure.
travel_explore
web search NEUTRAL — To enable a better understanding of the state-of-the-art, this study presents a narrative review of the different QSAR approaches to predict mixture effects ...
https://www.sciencedirect.com/science/article/pii/S246811132…
travel_explore
web search NEUTRAL — Using 5 machine learning algorithms and 3 types of chemical fingerprints, 15 QSAR models were developed for each PubChem assay dataset. These models showed ...
https://pmc.ncbi.nlm.nih.gov/articles/PMC10134506/
travel_explore
web search NEUTRAL — This machine learning-based QSAR model serves as a valuable tool for predicting drug plasma half-lives and extralabel withdrawal intervals in 6 common food ...
https://academic.oup.com/toxsci/article/203/1/52/7762650
info
Claim 11: “When applied to more than 126,000 chemicals, these models revealed important patterns—not just in toxicity, but also in uncertainty.”
SINGLE SOURCE
A PMC paper mentions predicting toxicity for 'more than 100,000 chemicals', which is close to the claim's 126,000, but the specific number and the patterns of uncertainty are not explicitly detailed in the snippets provided.
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.