Publisher Health

The journey between identifying a potential therapeutic compound and Food and Drug Administration approval of a new drug can take well over a decade and cost upwards of a billion dollars. A research team at the CUNY Graduate Center has created an artificial intelligence model that could significantly improve the accuracy and reduce the time and cost of the drug development process. Described in a newly published paper in Nature Machine Intelligence, the new model, called CODE-AE, can screen novel drug compounds to accurately predict efficacy in humans. In tests, it was also able to theoretically identify personalized drugs for over 9,000 patients that could better treat their conditions. Researchers expect the technique to significantly accelerate drug discovery and precision medicine.
Accurate and robust prediction of patient-specific responses to a new chemical compound is critical to discover safe and effective therapeutics and select an existing drug for a specific patient. However, it is unethical and infeasible to do early efficacy testing of a drug in humans directly. Cell or tissue models are often used as a surrogate of the human body to evaluate the therapeutic effect of a drug molecule. Unfortunately, the drug effect in a disease model often does not correlate with the drug efficacy and toxicity in human patients. This knowledge gap is a major factor in the high costs and low productivity rates of drug discovery.
“Our new machine learning model can address the translational challenge from disease models to humans,” said Lei Xie, a professor of computer science, biology and biochemistry at the CUNY Graduate Center and Hunter College and the paper’s senior author. “CODE-AE uses biology-inspired design and takes advantage of several recent advances in machine learning. For example, one of its components uses similar techniques in Deepfake image generation.”
The new model can provide a workaround to the problem of having sufficient patient data to train a generalized machine learning model, said You Wu, a CUNY Graduate Center Ph.D. student and co-author of the paper. “Although many methods have been developed to utilize cell-line screens for predicting clinical responses, their performances are unreliable due to data incongruity and discrepancies,” Wu said. “CODE-AE can extract intrinsic biological signals masked by noise and confounding factors and effectively alleviated the data-discrepancy problem.”
As a result, CODE-AE significantly improves accuracy and robustness over state-of-the-art methods in predicting patient-specific drug responses purely from cell-line compound screens.
The research team’s next challenge in advancing the technology’s use in drug discovery is developing a way for CODE-AE to reliably predict the effect of a new drug’s concentration and metabolization in human bodies. The researchers also noted that the AI model could potentially be tweaked to accurately predict human side effects to drugs.
This work was supported by the National Institute of General Medical Sciences and the National Institute on Aging.
Story Source:
Materials provided by The Graduate Center, CUNY. Note: Content may be edited for style and length.

Omnipose, a deep learning software, is helping to solve the challenge of identifying varied and miniscule bacteria in microscopy images. It has gone beyond this initial goal to identify several other types of tiny objects in micrographs.
The UW Medicine microbiology lab of Joseph Mougous and the University of Washington physics and bioengineering lab of Paul A. Wiggins tested the tool. It was developed by University of Washington physics graduate student Kevin J. Cutler and his team.
Mougous said that Cutler, as a physics student, “demonstrated an unusual interest in immersing himself in a biology environment so that he could learn first-hand about problems in need of solution in this field. He came over to my lab and quickly found one that he solved in spectacular fashion.”
Their results are reported in the Oct. 17 edition of Nature Methods.
The scientists found that Omnipose, trained on a large database of bacterial images, performed well in characterizing and quantifying the myriad of bacteria in mixed microbial cultures and eliminated some of the errors that can occur in its predecessor, Cellpose.
Moreover, the software wasn’t easily fooled by extreme changes in a cell’s shape due to antibiotic treatment or antagonism by chemicals produced during interbacterial aggression. In fact, the program showed that it could even detect cell intoxication in a trial using E. coli.
In addition, Omnipose did well in overcoming recognition problems due to differences in the optical characteristics across diverse bacteria.

UVA Health researchers have discovered a molecule in the brain responsible for orchestrating the immune system’s responses to Alzheimer’s disease and multiple sclerosis (MS), potentially allowing doctors to supercharge the body’s ability to fight those and other devastating neurological diseases.
The molecule the researchers identified, called a kinase, is crucial to both removing plaque buildup associated with Alzheimer’s and preventing the debris buildup that causes MS, the researchers found. It does this, the researchers showed, by directing the activity of brain cleaners called microglia. These immune cells were once largely ignored by scientists but have, in recent years, proved vital players in brain health.
UVA’s important new findings could one day let doctors augment the activity of microglia to treat or protect patients from Alzheimer’s, MS and other neurodegenerative diseases, the researchers report.
“Unfortunately, medical doctors do not currently possess effective treatments to target the root causes of most neurodegenerative diseases, such as Alzheimer’s, Parkinson’s or ALS [amyotrophic lateral sclerosis, commonly called Lou Gehrig’s disease]. In our studies, we have discovered a master controller of the cell type and processes that are required to protect the brain from these disorders,” said senior researcher John Lukens, PhD, of the University of Virginia School of Medicine and its Center for Brain Immunology and Glia (BIG), as well as the Carter Immunology Center and the UVA Brain Institute. “Our work further shows that targeting this novel pathway provides a potent strategy to eliminate the toxic culprits that cause memory loss and impaired motor control in neurodegenerative disease.”
Toxic Brain Buildup
Many neurodegenerative diseases, including Alzheimer’s and MS, are thought to be caused by the brain’s inability to cleanse itself of toxic buildup. Recent advances in neuroscience research have shed light on the importance of microglia in removing harmful debris from the brain, but UVA’s new discovery offers practical insights into how this cleaning process occurs — and the dire consequences when it doesn’t.

For around 40 years, scientists all over the world have been unsuccessfully trying to find a cure for HIV, but now a team of researchers from Aarhus University and Aarhus University Hospital have apparently found an important element in the equation.
So says Dr. Ole Schmeltz Søgaard, Professor of Translational Viral Research at Aarhus University, who is the senior author of an innovative study that has just been published in the journal Nature Medicine.
“This study is one of the first to be carried out on human beings in which we have demonstrated a way to strengthen the body’s own ability to fight HIV — even when today’s standard treatment is paused. We thus regard the study as an important step in the direction of a cure,” he says.
The study was conducted in close collaboration with researchers from the UK, USA, Spain and Canada.
Virus in hiding
While it has not been possible to find a cure for or a protective vaccine against HIV, today’s standard treatment is very effective at keeping the disease at bay.

Pregnant smokers reduced their smoking by an average of one cigarette per day before becoming aware they were pregnant, reports a new Northwestern Medicine study of more than 400 pregnant people. Then, in the month after learning of their pregnancy, participants reduced smoking by another four cigarettes per day.
“Our findings suggest that pregnancy could curb smokers’ desire to smoke before they are even aware of having conceived,” said the study’s lead author and principal investigator, Dr. Suena Huang Massey, associate professor of psychiatry and behavioral sciences and medical social sciences at Northwestern University Feinberg School of Medicine and a Northwestern Medicine psychiatrist.
“While recognition of pregnancy is a common motivation to reduce or quit smoking, if biological processes in early pregnancy are also involved as suggested by this study, identifying precisely what these processes are can lead to the development of new smoking-cessation medications.”
The study was published Oct. 17 in Addiction Biology.
The overwhelming majority of research in this field focuses on the impact of a person’s smoking on the pregnancy and the baby. This study examines, instead, the impact of pregnancy on a person’s smoking behavior.
While reduction in smoking during pregnancy is well established, no prior study has determined precisely when reduction in pregnancy smoking begins — and, especially, whether it begins before individuals are aware of the pregnancy.

It has been more than a decade since Gartner Research identified the Internet of Things — physical objects with sensors, processing ability and software that connect and exchange data through the Internet and communications networks — as an emerging technology.
Nowadays, connected devices are indispensable to commercial industries, health care and consumer products. Data analytics firm Statista forecasts a near tripling of the number of connected devices worldwide from 9.7 billion in 2020 to more than 29 billion in 2030.
The sensors embedded in devices are largely passive, transmitting signals to networked computers that process and return meaningful data to the device. Kyusang Lee, an assistant professor of materials science and engineering and electrical and computer engineering at the University of Virginia School of Engineering and Applied Science, is working on a way to make the sensors smart.
His smart sensor will sit at the edge of a device, which itself sits at the outer reaches of a wireless network. The smart sensor system also stores and processes data — an emerging area of research he calls artificial intelligence of things, a research strength of the Charles L. Brown Department of Electrical and Computer Engineering.
“Given the exponential growth in the Internet of Things, we anticipate data bottlenecks and lags in data processing and return signaling. The sensor’s output will be less reliable,” Lee said.
The constant pulsing of data through wireless and computer networks also eats up energy and increases the risk of exposing sensitive data to accidental or unauthorized disclosure and misuse.

Depression has long been associated with an increased risk of dementia, and now a new study provides evidence that timely treatment of depression could lower the risk of dementia in specific groups of patients.
Over 55 million people worldwide live with dementia, a disabling neurocognitive condition that mainly affects older adults. No effective treatment for dementia exists but identifying ways to help minimize or prevent dementia would help to lessen the burden of the disease.
The study, led by Jin-Tai Yu, MD, PhD, Huashan Hospital, Shanghai Medical College, Fudan University, and Wei Cheng, PhD, Institute of Science and Technology for Brain-Inspired Intelligence, Fudan University, Shanghai, China, appears in Biological Psychiatry, published by Elsevier.
Professor Yu and Professor Cheng used data collected by the UK Biobank, a population-based cohort of over 500,000 participants. The current study included more than 350,000 participants, including 46,280 participants with depression. During the course of the study, 725 of the depressed patients developed dementia.
Previous studies examining whether depression therapies such as pharmacotherapy and psychotherapy could lower the risk for dementia produced mixed results, leaving the question unresolved. “Older individuals appear to experience different depression patterns over time,” said Professor Yu. “Therefore, intra-individual variability in symptoms might confer different risk of dementia as well as heterogeneity in effectiveness of depression treatment in relation to dementia prevention.”
To address that heterogeneity, the researchers then categorized participants into one of four courses of depression: increasing course, in which mild initial symptoms steadily increase; decreasing course, starting with moderate- or high-severity symptoms but subsequently decreasing; chronically high course of ongoing severe depressive symptoms; and chronically low course, where mild or moderate depressive symptoms are consistently maintained.
As expected, the study found that depression elevated the risk of dementia — by a striking 51% compared to non-depressed participants. However, the degree of risk depended on the course of depression; those with increasing, chronically high, or chronically low course depression were more vulnerable to dementia, whereas those with decreasing course faced no greater risk than participants without depression.
The researchers most wanted to know whether the increased risk for dementia could be lowered by receiving depression treatment. Overall, depressed participants who received treatment had reduced risk of dementia compared to untreated participants by about 30%. When the researchers separated the participants by depression course, they saw that those with increasing and chronically low courses of depression saw lower risk of dementia with treatment, but those with a chronically high course saw no benefit of treatment in terms of dementia risk.
“Once again, the course of ineffectively treated depression carries significant medical risk,” said Biological Psychiatry editor John Krystal, MD. He notes that, “in this case, symptomatic depression increases dementia risk by 51%, whereas treatment was associated with a significant reduction in this risk.”
“This indicates that timely treatment of depression is needed among those with late-life depression,” added Professor Cheng. “Providing depression treatment for those with late-life depression might not only remit affective symptoms but also postpone the onset of dementia.”
“The new findings shed some light on previous work as well,” said Professor Cheng. “The differences of effectiveness across depression courses might explain the discrepancy between previous studies.”
Story Source:
Materials provided by Elsevier. Note: Content may be edited for style and length.

Published59 minutes agoSharecloseShare pageCopy linkAbout sharingImage source, Getty ImagesBy Stephanie HegartyPopulation correspondent Life expectancy has been slow to rise again after the shock of the pandemic, according to new research.Data on registered deaths from 31 countries shows few recovering in 2021, and many seeing further declines.Countries that rolled out vaccines quickly, to all age groups, have generally bounced back faster.Life expectancy in England and Wales rose slightly in 2021, while in Scotland and Northern Ireland it fell further, the researchers say.The paper – from the University of Oxford and the Max Planck Institute for Demographic Research – is an update to research from last year, which found the pandemic caused the biggest global drop in life expectancy since World War Two.Researchers compiled data on registered deaths from 31 countries – 29 in Europe, plus Chile and the US. They found that in only four – Belgium, France, Sweden and Switzerland – has life expectancy returned to the level it was in 2019. The situation was worse in the US and in Eastern and Central Europe, which saw further declines in 2021.”The scale of the worsening losses, particularly in Eastern Europe, are really quite sad,” says Ridhi Kashyap, professor of demography at the University of Oxford’s Leverhulme Centre for Demographic Science, and one of the authors of the report.The drop in life expectancy in many of these European countries has mirrored the health and mortality crisis that followed the break-up of the Soviet Union, the researchers say. Image source, Getty ImagesThese life expectancy figures – known as “period life expectancy” – aren’t a prediction of how long a child born today will live for. They show the average age a new-born would live to if today’s death rates persisted for that child’s entire life.Before the pandemic, life expectancy was on a consistent upward trajectory almost everywhere. Lives were getting longer, on average, year on year. But that changed dramatically in 2020. In England and Wales, period life expectancy dropped from 81.7 years in 2019 to 80.7 in 2020. A year later it was up only a little – to 80.9. Period life expectancy figures for Northern Ireland and Scotland in 2021 were 80.3 and 78.5 respectively.The UK’s Office for National Statistics will publish its data on life expectancy for 2021 at the end of this year. Covid-19 in the UK: Cases, hospital admissions and deathsCovid protection may be boosted by genesOne in 20 suffer long-term Covid effects, study finds”Pre-pandemic life expectancy in the UK didn’t compare very well with much of Western Europe,” says Dr Veena Raleigh, senior fellow at UK health charity, The Kings Fund. “We were already lagging behind – we were seeing the slowest improvements in life expectancy,”We went into this virus with a health and social care system that was overstretched – long waiting lists, and fewer beds, nurses and doctors than most Western European or high-income countries.”She cautions against reading too much into comparisons between England and Wales, Scotland and Northern Ireland, as the latter nations have much smaller population sizes.In the US the drop was even higher – falling two years in 2020 and a further two months in 2021. Image source, Getty ImagesWhat struck the researchers was the age of people dying last year. As vaccines rolled out to older age groups, excess deaths dropped among the over-80s in most countries. But under-80s started contributing more to life expectancy losses.Where vaccines were rolled out earlier and to all age groups at the same time, life expectancy was more likely to bounce back. Bulgaria is a striking example. It lost a year and a half on its life expectancy in 2020 and a further two years in 2021. By the end of 2021 only one in four Bulgarians were vaccinated, and only 37% of over-60s, the lowest rate in the EU. Dr Raleigh says the regional differences between Eastern and Western Europe are particularly noteworthy. Before Covid, gaps in life expectancies between East and West were narrowing, but this study shows that the pandemic has reversed that trend. Similarly, before the pandemic, the gap between the life expectancies of men and women was narrowing: “The pandemic has opened up that gap again.” The study, published in Nature Human Behaviour, was limited to 31 countries by the quality of data available. “There have probably been countries that had much worse pandemics in terms of life expectancy losses but because of data inequalities in the world, we’re not in a position to measure that at the moment,” says Prof Kashyap. While many hope that life expectancy will recover in 2022, Prof Kashyap says the effects of Covid are still being felt in health systems all over the world: “There are worrying signs in England and Wales of excess mortality, particularly over the summer. It hasn’t been a smooth recovery.”

For men and women, the risk factors for cardiovascular disease are largely the same, an extensive global study involving University of Gothenburg researchers shows.
The study, now published in The Lancet, includes participants in both high-income and medium- and low-income countries. Cardiovascular disease is more widespread in the latter. The data were taken from the Prospective Urban Rural Epidemiological (PURE) Study.
The study comprised 155,724 individuals in 21 countries, in five continents. Aged 35-70 years, the participants had no history of cardiovascular disease when they joined the study. All cases of fatal cardiovascular disease, heart attack, stroke, and heart failure during the follow-up period, which averaged ten years, were registered.
The risk factors studied were metabolic (such as high blood pressure, obesity, and diabetes), behavioral (tobacco smoking and diet), and psychosocial (economic status and depression).
No clear gender or income divide
Metabolic risk factors were found to be similar in both sexes, except for high values of low-density lipoprotein (LDL, often known as bad cholesterol), where the association with cardiovascular disease was stronger in men. In the researchers’ opinion, however, this finding needs confirmation in more studies.

Research led by Dr. Suresh Alahari, Professor of Biochemistry at LSU Health New Orleans’ Schools of Medicine and Graduate Studies, reports a combination of a novel small inhibitory molecule and an FDA-approved chemotherapy drug suppresses the growth of triple-negative breast cancer cells synergistically. The findings are published in the Nature journal, Oncogene, available here.
After screening the National Cancer Institute’s Diversity Set IV (a collection of compounds selected for structural diversity and potential anti-tumor efficacy), the research team selected the molecule, NSC33353, as a potential anti-tumor compound against triple-negative breast cancer (TNBC). They tested it on human triple-negative breast cancer cells and found that it significantly suppressed cell proliferation, migration and invasion.
The researchers then turned their attention to using the molecule in combination. Triple-negative breast cancer cells develop resistance to doxorubicin, one of the most effective chemotherapeutic drugs against these tumors. The researchers showed that the combination of NSC33353 and doxorubicin suppresses the growth of TNBC cells synergistically, suggesting that NSC33353 enhances TNBC sensitivity to doxorubicin.
More common in younger women, triple-negative breast cancer (TNBC) accounts for 15-20% of breast cancers. It’s called triple-negative because these tumors lack estrogen and progesterone receptors and the human epidermal growth factor receptor 2 (HER2).
“Because the cancer cells don’t have these proteins, hormone therapy and drugs that target HER2 are not helpful,” notes Dr. Alahari.
Triple-negative breast cancer is aggressive and responds poorly to treatment, so therapy options are very limited.
“The discovery of new drugs will be of immense help for TNBC patients,” says Dr. Alahari. “Our data indicate that the small molecule inhibitor, NSC33353, exhibits anti-tumor activity in TNBC cells and works in a synergistic fashion with a well-known chemotherapeutic agent.”
LSU Health New Orleans co-authors also included Hassan Yousefi, Maninder Khosla, Samuel C. Okpechi, Jessie Guidry, and Drs. Lothar Lauterboeck, David Worthylake, Jone Garai, Jovanny Zabaleta, Dorota Wyczechowska, and Qinglin Yang. Mohammad Amin Zarandi and Dr. Janarthanan Jayawickramarajah from Tulane University and Dr. Joseph Kissil from the H. Lee Moffitt Cancer Center also participated in the research.
The project was supported by LSU Health New Orleans School of Medicine and the Fred G. Brazda Foundation.
Story Source:
Materials provided by Louisiana State University Health Sciences Center. Note: Content may be edited for style and length.