Supercomputers can predict drugs’ side effects

Drug production

Credit: FDA

Scientists have found they can use supercomputers to identify proteins that cause adverse drug reactions.

The team noted that, during the drug development process, researchers often miss side effects that kill at least 100,000 patients a year.

In PLOS ONE, Montiago LaBute, PhD, of Lawrence Livermore National Laboratory in California, and his colleagues explained how we might use high-performance computers to solve this problem.

Side effects go undetected during drug development

A typical drug discovery process begins with identifying which proteins are associated with a specific disease. Candidate drug compounds are combined with target proteins to determine the drug’s efficacy and toxicity.

While this method allows researchers to identify side effects with many target proteins, there are myriad unknown, off-target proteins that may bind to the candidate drug and could cause unanticipated side effects.

Because it is cost-prohibitive to experimentally test a drug candidate against a potentially large set of proteins—and the list of possible off-targets is not known ahead of time—pharmaceutical companies usually only test a minimal set of off-target proteins during the early stages of drug discovery.

So certain adverse drug reactions remain undetected through the later stages of drug development, and the drugs may make it to the marketplace before these reactions are detected.

There have been several highly publicized medications with off-target protein side effects that have reached the marketplace. For example, Avandia, an anti-diabetic drug, caused heart attacks in some patients.

And Vioxx, an anti-inflammatory medication, caused heart attacks and strokes in certain patient populations. Both drugs were recalled because of their side effects.

“There were no indications of side effects of these medications in early testing or clinical trials,” Dr LaBute said. “We need a way to determine the safety of such therapeutics before they reach patients. Our work can help direct such drugs to patients who will benefit the most from them with the least amount of side effects.”

Supercomputers predict adverse drug reactions

Dr LaBute and colleagues tackled the problem by using supercomputers and information from public databases of drug compounds and proteins.

The databases included DrugBank, UniProt, and Protein Data Bank (PDB), as well as drug databases from the US Food and Drug Administration (FDA) and SIDER, which contain FDA-approved drugs with adverse drug reactions.

The team examined 4020 off-target proteins from DrugBank and UniProt. Those proteins were indexed against the PDB, which whittled the number down to 409 off-proteins that have high-quality 3D crystallographic X-ray diffraction structures essential for analysis in a computational setting.

The researchers fed the 409 off-target proteins into high-performance computer software known as VinaLC, along with 906 FDA-approved drug compounds. VinaLC used a molecular docking matrix that bound the drugs to the proteins. A score was given to each combination to assess whether effective binding occurred.

The team fed binding scores into another computer program and combined them with 560 FDA-approved drugs with known side effects. They used an algorithm to determine which proteins were associated with certain side effects.

In two categories of disorders—vascular disorders and neoplasms—the researchers’ computational model of predicting side effects was more predictive than current statistical methods that do not include binding scores.

In addition, the team’s calculations predicted new potential side effects. For example, they predicted a connection between a protein normally associated with cancer metastasis to vascular disorders like aneurysms.

“We have discovered a very viable way to find off-target proteins that are important for side effects,” Dr LaBute said. “This approach using [high-powered computers] and molecular docking to find [adverse drug reactions] never really existed before.”

The team’s findings provide drug companies with a cost-effective and reliable method to screen for side effects, according to Dr LaBute. Now, his group’s goal is to expand their computational pharmaceutical research to include more off-target proteins for testing and eventually screen every protein in the body.

“If we can do that, the drugs of tomorrow will have less side effects that can potentially lead to fatalities,” Dr Labute said. “Optimistically, we could be a decade away from our ultimate goal. However, we need help from pharmaceutical companies, healthcare providers, and the FDA to provide us with patient and therapeutic data.”

Drug production

Credit: FDA

Scientists have found they can use supercomputers to identify proteins that cause adverse drug reactions.

The team noted that, during the drug development process, researchers often miss side effects that kill at least 100,000 patients a year.

In PLOS ONE, Montiago LaBute, PhD, of Lawrence Livermore National Laboratory in California, and his colleagues explained how we might use high-performance computers to solve this problem.

Side effects go undetected during drug development

A typical drug discovery process begins with identifying which proteins are associated with a specific disease. Candidate drug compounds are combined with target proteins to determine the drug’s efficacy and toxicity.

While this method allows researchers to identify side effects with many target proteins, there are myriad unknown, off-target proteins that may bind to the candidate drug and could cause unanticipated side effects.

Because it is cost-prohibitive to experimentally test a drug candidate against a potentially large set of proteins—and the list of possible off-targets is not known ahead of time—pharmaceutical companies usually only test a minimal set of off-target proteins during the early stages of drug discovery.

So certain adverse drug reactions remain undetected through the later stages of drug development, and the drugs may make it to the marketplace before these reactions are detected.

There have been several highly publicized medications with off-target protein side effects that have reached the marketplace. For example, Avandia, an anti-diabetic drug, caused heart attacks in some patients.

And Vioxx, an anti-inflammatory medication, caused heart attacks and strokes in certain patient populations. Both drugs were recalled because of their side effects.

“There were no indications of side effects of these medications in early testing or clinical trials,” Dr LaBute said. “We need a way to determine the safety of such therapeutics before they reach patients. Our work can help direct such drugs to patients who will benefit the most from them with the least amount of side effects.”

Supercomputers predict adverse drug reactions

Dr LaBute and colleagues tackled the problem by using supercomputers and information from public databases of drug compounds and proteins.

The databases included DrugBank, UniProt, and Protein Data Bank (PDB), as well as drug databases from the US Food and Drug Administration (FDA) and SIDER, which contain FDA-approved drugs with adverse drug reactions.

The team examined 4020 off-target proteins from DrugBank and UniProt. Those proteins were indexed against the PDB, which whittled the number down to 409 off-proteins that have high-quality 3D crystallographic X-ray diffraction structures essential for analysis in a computational setting.

The researchers fed the 409 off-target proteins into high-performance computer software known as VinaLC, along with 906 FDA-approved drug compounds. VinaLC used a molecular docking matrix that bound the drugs to the proteins. A score was given to each combination to assess whether effective binding occurred.

The team fed binding scores into another computer program and combined them with 560 FDA-approved drugs with known side effects. They used an algorithm to determine which proteins were associated with certain side effects.

In two categories of disorders—vascular disorders and neoplasms—the researchers’ computational model of predicting side effects was more predictive than current statistical methods that do not include binding scores.

In addition, the team’s calculations predicted new potential side effects. For example, they predicted a connection between a protein normally associated with cancer metastasis to vascular disorders like aneurysms.

“We have discovered a very viable way to find off-target proteins that are important for side effects,” Dr LaBute said. “This approach using [high-powered computers] and molecular docking to find [adverse drug reactions] never really existed before.”

The team’s findings provide drug companies with a cost-effective and reliable method to screen for side effects, according to Dr LaBute. Now, his group’s goal is to expand their computational pharmaceutical research to include more off-target proteins for testing and eventually screen every protein in the body.

“If we can do that, the drugs of tomorrow will have less side effects that can potentially lead to fatalities,” Dr Labute said. “Optimistically, we could be a decade away from our ultimate goal. However, we need help from pharmaceutical companies, healthcare providers, and the FDA to provide us with patient and therapeutic data.”

Drug production

Credit: FDA

Scientists have found they can use supercomputers to identify proteins that cause adverse drug reactions.

The team noted that, during the drug development process, researchers often miss side effects that kill at least 100,000 patients a year.

In PLOS ONE, Montiago LaBute, PhD, of Lawrence Livermore National Laboratory in California, and his colleagues explained how we might use high-performance computers to solve this problem.

Side effects go undetected during drug development

A typical drug discovery process begins with identifying which proteins are associated with a specific disease. Candidate drug compounds are combined with target proteins to determine the drug’s efficacy and toxicity.

While this method allows researchers to identify side effects with many target proteins, there are myriad unknown, off-target proteins that may bind to the candidate drug and could cause unanticipated side effects.

Because it is cost-prohibitive to experimentally test a drug candidate against a potentially large set of proteins—and the list of possible off-targets is not known ahead of time—pharmaceutical companies usually only test a minimal set of off-target proteins during the early stages of drug discovery.

So certain adverse drug reactions remain undetected through the later stages of drug development, and the drugs may make it to the marketplace before these reactions are detected.

There have been several highly publicized medications with off-target protein side effects that have reached the marketplace. For example, Avandia, an anti-diabetic drug, caused heart attacks in some patients.

And Vioxx, an anti-inflammatory medication, caused heart attacks and strokes in certain patient populations. Both drugs were recalled because of their side effects.

“There were no indications of side effects of these medications in early testing or clinical trials,” Dr LaBute said. “We need a way to determine the safety of such therapeutics before they reach patients. Our work can help direct such drugs to patients who will benefit the most from them with the least amount of side effects.”

Supercomputers predict adverse drug reactions

Dr LaBute and colleagues tackled the problem by using supercomputers and information from public databases of drug compounds and proteins.

The databases included DrugBank, UniProt, and Protein Data Bank (PDB), as well as drug databases from the US Food and Drug Administration (FDA) and SIDER, which contain FDA-approved drugs with adverse drug reactions.

The team examined 4020 off-target proteins from DrugBank and UniProt. Those proteins were indexed against the PDB, which whittled the number down to 409 off-proteins that have high-quality 3D crystallographic X-ray diffraction structures essential for analysis in a computational setting.

The researchers fed the 409 off-target proteins into high-performance computer software known as VinaLC, along with 906 FDA-approved drug compounds. VinaLC used a molecular docking matrix that bound the drugs to the proteins. A score was given to each combination to assess whether effective binding occurred.

The team fed binding scores into another computer program and combined them with 560 FDA-approved drugs with known side effects. They used an algorithm to determine which proteins were associated with certain side effects.

In two categories of disorders—vascular disorders and neoplasms—the researchers’ computational model of predicting side effects was more predictive than current statistical methods that do not include binding scores.

In addition, the team’s calculations predicted new potential side effects. For example, they predicted a connection between a protein normally associated with cancer metastasis to vascular disorders like aneurysms.

“We have discovered a very viable way to find off-target proteins that are important for side effects,” Dr LaBute said. “This approach using [high-powered computers] and molecular docking to find [adverse drug reactions] never really existed before.”

The team’s findings provide drug companies with a cost-effective and reliable method to screen for side effects, according to Dr LaBute. Now, his group’s goal is to expand their computational pharmaceutical research to include more off-target proteins for testing and eventually screen every protein in the body.

“If we can do that, the drugs of tomorrow will have less side effects that can potentially lead to fatalities,” Dr Labute said. “Optimistically, we could be a decade away from our ultimate goal. However, we need help from pharmaceutical companies, healthcare providers, and the FDA to provide us with patient and therapeutic data.”