A pioneering machine-learning approach has identified powerful new types of antibiotic from a pool of more than 100 million molecules -- including one that works against a wide range of bacteria, including tuberculosis and strains considered untreatable. The researchers say the antibiotic, called halicin, is the first discovered with artificial intelligence (AI). Although AI has been used to aid parts of the antibiotic-discovery process before, they say that this is the first time it has identified completely new kinds of antibiotic from scratch, without using any previous human assumptions. The work, led by synthetic biologist Jim Collins at the Massachusetts Institute of Technology in Cambridge, is published in Cell1. The study is remarkable, says Jacob Durrant, a computational biologist at the University of Pittsburgh, Pennsylvania. The team didn't just identify candidates, but also validated promising molecules in animal tests, he says.

At the annual meeting of the Scientific Advisory Committee on Alternative Toxicological Methods (SACATM; see sidebar), committee members enthusiastically supported advances in new nonanimal testing technologies, such as computational tools and microphysiological systems (MPS), also known as tissue chips. The committee urged regulators to provide clear guidance on how these technologies should be used and what data from them would be accepted. Members also stressed the importance of having high-quality reference data from both human and animal tests to clearly demonstrate the ability of new methods to identify toxic chemicals. Experts from academia, industry, and animal welfare organizations debated how best to use these new technologies in the Sept. 19-20 meeting. The committee meets annually to advise the Interagency Coordinating Committee on the Validation of Alternative Methods (ICCVAM).

THURSDAY, Sept. 27, 2018 (HealthDay News) -- Machine learning of toxological big data can predict the toxicity of chemicals, and may be more reliable than animal testing, according to a study published in the September issue of Toxicological Sciences. Noting that the probability that an OECD guideline animal test would output the same result in a repeat test was 78 to 96 percent, with sensitivity of 50 to 87 percent, Tom Luechtefeld, M.D., from the Johns Hopkins University Bloomberg School of Public Health in Baltimore, and colleagues used an expanded database with more than 866,000 chemical properties/hazards as training data. Read-across structure activity relationship (RASAR) models were constructed using binary fingerprints and Jaccard distance to define chemical similarity. This similarity metric was used to construct a large chemical similarity adjacency matrix, which was used to derive feature vectors for supervised learning. Results were demonstrated on nine health hazards from a "simple" and a "data fusion" RASAR.

Earlier we created a chemical hazard database via natural language processing of dossiers submitted to the European Chemical Agency with approximately 10 000 chemicals. We identified repeat OECD guideline tests to establish reproducibility of acute oral and dermal toxicity, eye and skin irritation, mutagenicity and skin sensitization. Based on 350–700 chemicals each, the probability that an OECD guideline animal test would output the same result in a repeat test was 78%–96% (sensitivity 50%–87%). An expanded database with more than 866 000 chemical properties/hazards was used as training data and to model health hazards and chemical properties. The constructed models automate and extend the read-across method of chemical classification. The novel models called RASARs (read-across structure activity relationship) use binary fingerprints and Jaccard distance to define chemical similarity. A large chemical similarity adjacency matrix is constructed from this similarity metric and is used ...

As cold-blooded and inhuman as it may sound, animal tests are an integral part of modern-day drug and chemical compounds development and approval procedures. Scientists can't still reliably predict the properties of new chemicals, let alone how these compounds might interact with living cells. But a new paper published in the research journal Toxicological Sciences shows that it is possible to predict the attributes of new compounds using the data we already have about past tests and experiments. The artificially intelligent system was trained to predict the toxicity of tens of thousands of unknown chemicals, based on previous animal tests, and the results are, in some cases, more accurate and reliable than real animal tests. Using AI in the drug development process is nothing new.

Most consumers would be dismayed with how little we know about the majority of chemicals. Only 3 percent of industrial chemicals – mostly drugs and pesticides – are comprehensively tested. Most of the 80,000 to 140,000 chemicals in consumer products have not been tested at all or just examined superficially to see what harm they may do locally, at the site of contact and at extremely high doses. I am a physician and former head of the European Center for the Validation of Alternative Methods of the European Commission (2002-2008), and I am dedicated to finding faster, cheaper and more accurate methods of testing the safety of chemicals. To that end, I now lead a new program at Johns Hopkins University to revamp the safety sciences.

A new computer system could spell the end for animal testing. The new system offers up more accurate results than animal testing, predicting the toxicity of a substance almost immediately. It is also less expensive, less time-consuming, and poses much less of an ethical dilemma. "These results are a real eye-opener, they suggest that we can replace many animal tests with computer-based prediction and get more reliable results," Professor Thomas Hartung, the lead designer of the system, told the Financial Times. Hartung and his team of researchers used artificial intelligence to analyze the results of 800,000 tests on 10,000 different chemicals, held on a database.

Can I get a diagnosis? AI [artificial intelligence] is handling it now? You mean I just go online and see the results of my tests and read the diagnosis and pick up my drugs outside my front door? As AI creeps and crawls into the realm of medical diagnosis and treatment, and as it spreads under the banner of "more precise care for the patient," remember that AI embeds false data more firmly than any human doctor can. Once it's in there, how do you get rid of it?

Computer programs can, in some cases, predict chemical toxicity as well as tests done on rats and other animals.Credit: Coneyl Jay/SPL Machine-learning software trained on masses of chemical-safety data is so good at predicting some kinds of toxicity that it now rivals -- and sometimes outperforms -- expensive animal studies, researchers report. Computer models could replace some standard safety studies conducted on millions of animals each year, such as dropping compounds into rabbits' eyes to check if they are irritants, or feeding chemicals to rats to work out lethal doses, says Thomas Hartung, a toxicologist at Johns Hopkins University in Baltimore, Maryland. "The power of big data means we can produce a tool more predictive than many animal tests." In a paper published in Toxicological Sciences1 on 11 July, Hartung's team reports that its algorithm can accurately predict toxicity for tens of thousands of chemicals -- a range much broader than other published models achieve -- across nine kinds of test, from inhalation damage to harm to aquatic ecosystems. The paper "draws attention to the new possibilities of big data", says Bennard van Ravenzwaay, a toxicologist at the chemicals firm BASF in Ludwigshafen, Germany.