Predicting potential pharma side effects

March 8, 2016

A computer program that can predict whether or not a given pharmaceutical will have worrying side effects has been developed by researchers in the USA. Md Jamiul Jahid and Jianhua Ruan of the Department of Computer Science, at the University of Texas at San Antonio, have developed the "in silico" testing system for drugs in the early stage of drug development.

Similar programs have been attempted before with varying degrees of success but the new takes an "ensemble approach" to assessing the of a drug molecule. It can thus determine whether key sub-structures are present in the molecule that are known to give rise to in other drugs.

The team has tested the new program on almost 900 drugs against a database of 1385 side effects and demonstrated that it outstrips earlier software. The software has now been used to "test" compounds in the DrugBank database. The system could be used to alert the regulatory authorities and healthcare workers as to what side effects might occur when a new drug enters late-stage clinical trials and is ultimately brought to market. After using the software to screen 2883 small molecule uncharacterized drugs, the team was able to predict a large variety of side-effects, notably ones that were missed by other methods. "Based on drug side- information from different sources, we verify that the prediction by our approach is indeed correct," the team reports in the journal.

The team points out that more than 2 million people are affected by adverse reactions to their medication each year in the USA alone and of those around 100,000 die from problems associated with the side effects. Of course, many of those people are seriously ill and there are many factors that mean the side effects may not necessarily be entirely to blame for the deaths. Nevertheless, software that can flag potential problems through computer screening in this way could reduce that number.

In addition to predicting side effects the identification of substructures that are associated with particular side effects could be used to help medicinal chemists understand the underlying mechanism by which that side effect arises and also then design out that character from their molecules in future, reducing the number of drugs that go through the R&D pipeline and then fail at in clinical trials because side effects appear.

Explore further: Researchers are on their way to predicting what side effects you'll experience from a drug

More information: Md Jamiul Jahid et al. Structure-based prediction of drug side effects using a novel classification algorithm, International Journal of Computational Biology and Drug Design (2016). DOI: 10.1504/IJCBDD.2016.074985

Related Stories

Researchers are on their way to predicting what side effects you'll experience from a drug

November 2, 2015
Researchers at the University of California, San Diego have developed a model that could be used to predict a drug's side effects on different patients. The proof of concept study is aimed at determining how different individuals ...

Improving the drug withdrawal process could reduce number of deaths

February 4, 2015
The number of deaths associated with drugs that were subsequently withdrawn from the market could have been reduced had there been fewer delays in the withdrawal process, according to research published in the open access ...

Supercomputers link proteins to drug side effects

October 20, 2014
New medications created by pharmaceutical companies have helped millions of Americans alleviate pain and suffering from their medical conditions. However, the drug creation process often misses many side effects that kill ...

Medicine agency: Roche did not report side effects

June 22, 2012
(AP) — The European Medicines Agency is investigating "deficiencies" in the way drug maker Roche reported possible side effects in patients in the U.S., though it said there was no evidence patients are at risk.

New drug could be safer, non-addictive alternative to morphine

January 28, 2016
Researchers at Tulane University and Southeast Louisiana Veterans Health Care System have developed a painkiller that is as strong as morphine but isn't likely to be addictive and with fewer side effects, according to a new ...

Recommended for you

Baby-boomers and millennials more afflicted by the opioid epidemic

November 21, 2017
Baby-boomers, those born between 1947 and 1964, experienced an excess risk of prescription opioid overdose death and heroin overdose death, according to latest research at Columbia University's Mailman School of Public Health. ...

Sensor-equipped pill raises technological, ethical questions

November 17, 2017
The first drug with a sensor embedded in a pill that alerts doctors when patients have taken their medications was approved by the Food and Drug Administration, raiding issues involving privacy, cost, and whether patients ...

New painkillers reduce overdose risk

November 16, 2017
Scientists on the Florida campus of The Scripps Research Institute (TSRI) have developed new opioid pain relievers that reduce pain on par with morphine but do not slow or stop breathing—the cause of opiate overdose.

Separating side effects could hold key for safer opioids

November 16, 2017
Opioid pain relievers can be extremely effective in relieving pain, but can carry a high risk of addiction and ultimately overdose when breathing is suppressed and stops. Scientists have discovered a way to separate these ...

US regulators approve first digital pill to track patients

November 14, 2017
U.S. regulators have approved the first drug with a sensor that alerts doctors when the medication has been taken, offering a new way of monitoring patients but also raising privacy concerns.

Introduction is different, but top medications for opioid addiction equally effective

November 14, 2017
With opioid addiction officially declared a public health emergency in the U.S., medical intervention to treat the illness is increasingly important in responding to the epidemic. Now, a new study concludes that two of the ...

0 comments

Please sign in to add a comment. Registration is free, and takes less than a minute. Read more

Click here to reset your password.
Sign in to get notified via email when new comments are made.