Countless chemical substances, including fertilisers and pesticides but also pharmaceutical substances and industrial products, leak into groundwater, lakes and rivers. “We want to know what the impact of these chemicals is on aquatic species, and whether they are toxic or not,” says Marco Baity-Jesi, Head of the Eawag Data Science Group. To do this, fish are typically exposed to a substance at different concentrations in different tanks. These animal experiments, which are fatal for the fish, are ethically controversial and also costly. “Instead of conducting such experiments, we want to predict the effect of chemicals on fish using machine learning methods,” explains Baity-Jesi, a physicist. For this project, his team is collaborating with the group lead by Kristin Schirmer, which is developing experimental alternatives to animal tests with fish using fish cell lines.

For the source material, the researchers accessed the database of the US Environmental Protection Agency. This contains the results of experiments with almost 2,200 chemicals tested on 345 different fish species. In all, the researchers were able to use around 20,000 entries. “It’s not a huge dataset, but it’s enough for our purposes,” says the physicist. After analysing and setting up the data, his team wrote the software for various machine learning models suitable for the prepared input. The researchers used most of the data as training material to feed their models, but kept a small portion as a test dataset so they could check how accurately the machine’s calculated predictions matched the experimental results.

Precise predictions

The researchers have now published their results in an initial study. Based on the learned patterns, the models can predict in a second whether a chemical is more or less toxic for a fish species. The computer’s predictions proved to be more than 90-per cent correct. “The model predictions can’t be completely perfect,” explains Baity-Jesi. “Because the experiments aren’t either.” For example, one often finds conflicting data on experiments with a particular substance and fish species. “If you perform an experiment with the same chemical twice, it may end up in two different categories of toxicity,” the researcher says. “But the models can’t be better than the data they learn from.”

The authors of the paper were surprised to find that a new model, which has been successful in human toxicology, did not produce results that were more accurate than the standard models used. “Overall, our outcome looks very good,” comments Baity-Jesi. “But although our models are online and anyone can use them, many more tests are needed before the machine can be deployed as an alternative to animal testing and chemical regulation.”

From fish to invertebrates and algae

For instance, the current results represent only a fraction of all possible chemicals and organisms to test. To expand the scope of the models, a broader range of data is needed both for training the algorithms and for testing them. So next, besides fish, the research group wants to include invertebrates and algae in its work. In addition, data from experiments with fish cell lines should also support the models in the future. The success of this work by Schirmer’s group was demonstrated last year when the OECD recognised the fish cell line assay developed at Eawag as a new guideline in the approval procedures of chemicals.

“The more data you present to the models, the better they get,” explains Baity-Jesi. Moreover, care must be taken to ensure that the models are trained where they will be used. If chemicals or organisms deviate too much from those tested in the experiments, the accuracy of the machine learning also drops; therefore limits to its reliability must be identified.

In the future, computer predictions will probably still need to be confirmed by testing in some cases. “Therefore, it is unlikely that machine learning alone will soon be able to completely replace animal testing, but it can certainly make it possible to reduce it tremendously,” the researchers write. And even at the current stage of development, Baity-Jesi sees an important use for the computer algorithms: “For example, if you only have resources for five experiments but thousands of chemicals and animal species, our models can tell you which substances and animals should be tested first.” In this way, machine learning helps prioritise environmental research.

Cover picture: Trout are often used in experiments. Machine learning could be an alternative to fish testing. (Image: istock, edited by Eawag)

Wu, J.; D’Ambrosi, S.; Ammann, L.; Stadnicka-Michalak, J.; Schirmer, K.; Baity-Jesi, M. (2022) Predicting chemical hazard across taxa through machine learning, Environment International, 163, 107184 (15 pp.), doi: 10.1016/j.envint.2022.107184 , Institutional Repository

TECH NEWS RELATED

Climate change, ozone pollution to reduce global crop yields by a fifth, with South Asia most at risk, study shows

Global food crop yields could fall by a fifth by 2050 due to ground-level ozone pollution and climate change, a new study has found. South Asia is likely to bear the brunt of the impact, producing up to 40 per cent less rice by the end of the century. ...

View more: Climate change, ozone pollution to reduce global crop yields by a fifth, with South Asia most at risk, study shows

Limiting global warming to 1.5 degrees Celsius would reduce risks to humans by up to 85%

Flooding in Key Haven caused by hurricane Wilma on 10/24/2005. Credit: Marc Averette/Wikipedia New research led by the University of East Anglia (UEA) quantifies the benefits of limiting global warming to 1.5 degrees Celsius and identifies the hotspot regions for climate change risk in the future. The study calculates ...

View more: Limiting global warming to 1.5 degrees Celsius would reduce risks to humans by up to 85%

Ukraine, climate, hunger: the G7 action plans

The world’s top industrialised nations wrapped up a three-day summit dominated by talks on how they can bolster Ukraine in repelling Russia’s invasion while minimising the international fallout. Here are the main plans drawn up by the leaders of Britain, Canada, France, Germany, Italy, Japan and the United States ...

View more: Ukraine, climate, hunger: the G7 action plans

Oceans key to global warming fight: US climate envoy

Safeguarding the world’s oceans will be fundamental to tackling global warming, US climate envoy John Kerry told AFP on Tuesday, warning that war in Ukraine and its economic fallout meant efforts to curb dangerous carbon pollution were facing “powerful headwinds”. The interview, on the margins of the UN Ocean ...

View more: Oceans key to global warming fight: US climate envoy

Climate tech firm to launch scaled-up plant sucking CO2 from air

Construction is due to begin on Wednesday on what could become the world’s biggest plant to capture carbon dioxide from the air and deposit it underground, the company behind the nascent green technology said. Swiss start-up Climeworks AG said its second large-scale direct air capture (DAC) plant will be ...

View more: Climate tech firm to launch scaled-up plant sucking CO2 from air

Warmer Climate, Possible Threat to Antarctica’s Only Native Insect Population Despite Its Ability to Endure Extreme Conditions

(Photo : Pexels/Egor Kamelev) To avoid damage to internal tissue by icy crystals, overwintering larvae are losing up to 70 percent of their body fluids. A recent study showed that the Antarctic midge has evolved to survive in extreme conditions, yet a warming climate could endanger its existence. The ...

View more: Warmer Climate, Possible Threat to Antarctica’s Only Native Insect Population Despite Its Ability to Endure Extreme Conditions

Chesapeake Bay 'dead zone' predicted to be 13% lower than average this summer

Satellite (Landsat) picture of Chesapeake Bay (center) and Delaware Bay (upper right) – and Atlantic coast of the central-eastern United States. Credit: Landsat/NASA, Public Domain, via Wikimedia Commons This summer’s Chesapeake Bay “dead zone” is expected to be smaller than the long-term average, according to a forecast released today ...

View more: Chesapeake Bay 'dead zone' predicted to be 13% lower than average this summer

Study shows chemical's extent in the Fairbanks winter air

Credit: Pixabay/CC0 Public Domain A chemical compound discovered in 2019 in the wintertime air of Fairbanks, Alaska accounts for a significant portion of the community’s fine particulate pollution, according to new research that seeks to better understand the causes and makeup of the dirty air. The finding is the ...

View more: Study shows chemical's extent in the Fairbanks winter air

Nearly 1 in 4 globally at risk from severe flooding: study

Climate change is shrinking and fragmenting salmon habitat

Flooding exacerbates pollution exposure in at-risk urban communities

Understanding earthquakes triggered by wastewater injection

New study shows how the ancient world adapted to climate change

California's Dixie Fire shows impact of legacy effects, prescribed burns

Climate change is altering the chemistry of wine

Drones and DNA tracking: How these high-tech tools are helping nature heal

Increasing heat waves affect up to half a billion people

Climate protection: CO2 turned into methanol

Modeling the climate-energy consumption link in Tibet

Insights into Cenozoic environmental change and ecosystem evolution

OTHER TECH NEWS

Top Car News Car News