Positive Health Online

AI System Learns to Speak the Language of Cancer to Enable Improved Diagnosis

A computer system which harnesses the power of AI to learn the language of cancer is capable of spotting the signs of the disease in biological samples with remarkable accuracy, its developers say. An international team of AI specialists and cancer scientists are behind the breakthrough development, which can also provide reliable predictions of patient outcomes.

Currently, pathologists examine and characterise the features of tissue samples taken from cancer patients on slides under a microscope. Their observations on the tumour’s type and stage of growth help doctors determine each patient’s course of treatment and their chances of recovery.

The new system, which the researchers call ‘Histomorphological Phenotype Learning’ (HPL), could aid human pathologists to provide faster, more accurate diagnoses of the disease, potentially helping to improve cancer care in the future. The team, led by researchers from the University of Glasgow and New York University, outline how they developed and trained the HPL system in a new paper published in the journal Nature Communications.[1]

They began by collecting thousands of high-resolution images of tissue samples of lung adenocarcinoma taken from 452 patients stored in the United States National Cancer Institute’s Cancer Genome Atlas database. In many cases, the data is accompanied by additional information on how the patients’ cancers progressed.

Next, they developed an algorithm which used a training process called self-supervised deep learning to analyse the images and spot patterns based solely on the visual data in each slide.

The algorithm broke down the slide images into thousands of tiny tiles, each representing a small amount of human tissue. A deep neural network scrutinised the tiles, teaching itself in the process to recognise and classify any visual features shared across any of the cells in each tissue sample.

Dr Ke Yuan, of the University of Glasgow’s School of Computing Science, supervised the research and is the paper’s senior author. He said:

“We didn’t provide the algorithm with any insight into what the samples were or what we expected it to find. Nonetheless, it learned to spot recurring visual elements in the tiles which correspond to textures, cell properties and tissue architectures called phenotypes.

“By comparing those visual elements across the whole series of images it examined, it recognised phenotypes which often appeared together, independently picking out the architectural patterns that human pathologists had already identified in the samples.”

When the team added analysis of slides from squamous cell lung cancer to the HPL system, it was capable of correctly distinguishing between their features with 99% accuracy.

Once the algorithm had identified patterns in the samples, the researchers used it to analyse links between the phenotypes it had classified and the clinical outcomes stored in the database, including how long patients lived after having cancer surgery.The algorithm discovered that certain phenotypes, such as tumour cells which are less invasive, or lots of inflammatory cells attacking the tumour, were more common in patients who lived longer after treatment. Others, like aggressive tumour cells forming solid masses, or regions where the immune system was excluded, were more closely associated with the recurrence of tumours.

The predictions made by the HPL system correlated well with the real-life outcomes of the patients stored in the database, correctly assessing the likelihood and timing of cancer’s return 72% of the time. Human pathologists tasked with the same prediction drew the correct conclusions with 64% accuracy. When the research was expanded to include analysis of thousands of slides across 10 other types of cancers, including breast, prostate and bladder cancers, the results were similarly accurate despite the increased complexity of the task.

Professor John Le Quesne, from the University of Glasgow’s School of Cancer Sciences, is one of the co-senior authors of the paper and supervised the research. He said:

“We were surprised but very pleased by the effectiveness of machine learning to tackle this task. It takes many years to train human pathologists to identify the cancer subtypes they examine under the microscope and draw conclusions about the most likely outcomes for patients. It’s a difficult, time-consuming job, and even highly-trained experts can sometimes draw different conclusions from the same slide.

“In a sense, the algorithm at the heart of the HPL system taught itself from first principles to speak the language of cancer – to recognise the extremely complex patterns in the slides and ‘read’ what they can tell us about both the type of cancer and its potential effect on patients’ long-term health. Unlike a human pathologist, it doesn’t understand what it’s looking at, but it can still draw strikingly accurate conclusions based on mathematical analysis.

“It could prove to be an invaluable tool to aid pathologists in the future, augmenting their existing skills with an entirely unbiased second opinion. The insight provided by human expertise and AI analysis working together could provide faster, more accurate cancer diagnoses and evaluations of patients’ likely outcomes. That, in turn, could help improve monitoring and better-tailored care across each patients’ treatment.”

Dr Adalberto Claudio Quiros, a research associate in the University of Glasgow’s School of Cancer Sciences and School of Computing Science, is a co-first author of the paper. He said: “This research shows the potential that cutting-edge machine learning has to create advances in cancer science which could have significant benefits for patient care.

“This kind of self-learning algorithm will only become more accurate as additional data is added, helping it become more fluent in the language of cancer. Unlike humans, it brings no pre-conceived ideas to its work, so it may even find patterns across the datasets that haven’t been fully explored before.

“Ultimately, our aim is to provide doctors and patients with a tool that can help provide them with an improved understanding of their prognosis and treatment.”

Dr Aristotelis Tsirigos and Dr Nicolas Coudray, of New York University’s Grossman School of Medicine and Perlmutter Cancer Centre, are co-senior investigator and co-first author on the paper, respectively. Researchers from New York University, University College London and the Karolinska Institute also contributed to the paper.

 The team’s paper, titled ‘Mapping the landscape of histomorphological cancer phenotypes using self-supervised learning on unlabelled, unannotated pathology slides’, is published in Nature Communications. [1]The research was supported by funding from the Engineering and Physical Sciences Research Council (EPSRC), the Biotechnology and Biological Sciences Research Council (BBSRC), and the National Institutes of Health.

Reference

1. Claudio Quiros A, Coudray N, Yeaton A, Yang X, Liu B, Le H, Chiriboga L, Karimkhan A, Narula N, Moore DA, Park CY, Pass H, Moreira AL, Le Quesne J, Tsirigos A, Yuan K. Mapping the landscape of histomorphological cancer phenotypes using self-supervised learning on unannotated pathology slides. Nat Commun.;15(1):4596. doi: 10.1038/s41467-024-48666-7. PMID: 38862472. Jun 11 2024.

Media Contact and Further Information

For more information contact Ross Barker in the University of Glasgow External Relations team at  Ross Barker - University of Glasgow ross.barker@glasgow.ac.uk

Promising Role of Antidiabetic Drug in Cancer Control

Flinders University researchers have analysed how an antidiabetic treatment could help control the growth of tumours, potentially paving the way for the design of better cancer treatments. The new study investigated what happens when metformin, a type 2 diabetes medication, is used to treat colorectal cancer cells, in the process demonstrating that it could be exploited to develop new cancer therapies.[1]

Previous epidemiology studies show that taking metformin helps protect diabetes patients from developing some forms of cancer including bowel, or colorectal, cancer. The Flinders’ researchers sought to understand how taking metformin medication impacts cancer cells and how this could help with future cancer treatments.

“Using the latest techniques, we analysed how metformin helps to stop colorectal cancer cells from growing and multiplying by controlling certain ‘pathways’ inside the cells that help to regulate growth and division,” says lead author Dr Ayla Orang from Flinders University’s College of Medicine and Public Health.

“Importantly, our work has pinpointed that metformin uses small pieces of RNA (called microRNAs) to act as a ‘circuit breaker’ and turn off certain genes that are involved in cell growth and division, so it is possible that our findings could eventually be used to develop a new targeted cancer therapy.

“In particular, we found that metformin increases the levels of certain microRNAs, like miR-2110 and miR-132-3p, which then target specific genes and slow down the growth and progression of tumours.

“With this information we may be able to develop RNA-based therapies - new treatments for cancer that target RNA molecules (like microRNAs),” she says.

The research, Restricting Colorectal Cancer Cell Metabolism with Metformin: An Integrated Transcriptomics Study, used advanced techniques to study microRNAs, and the entire set of genes being expressed in the colon cancer cells, to help understand how metformin affects the cells.

Metformin increased the levels of certain microRNAs (miR-2110 and miR-132-3p) that target a specific gene (PIK3R3).

This process helps to slow down the growth of cancer cells and stop them from multiplying too quickly. Another gene (STMN1) was also targeted by different microRNAs, which led to slower cell growth and a delayed cell cycle.

Senior authors of the study, Associate Professor Michael Michael and Professor Janni Petersen say the results are a step forward in our understanding of the way metformin disrupts cancer cell growth and how they could be used to fight cancer.

"Our research provides new insights into the molecular mechanisms of how metformin works, and how we might be able to target genes responsible for turning normal cells cancerous,” says Associate Professor Michael.

“This is important because it shows the potential of metformin as a preventive agent for reducing the growth of cancer in the bowel, and the emergence of RNA therapeutics as a promising new avenue for exploring the clinical efficacy of these findings.

“We need to further investigate the potential therapeutic benefits of targeting specific miRNAs or pathways using RNA-based therapies for the treatment of cancer. Having used metformin to unravel metabolism in cancer cells, the next stage of research is focusing on specific cell pathways, which should lead to animal studies and then human clinical trials.”

Reference

1. Ayla Orang, Shashikanth Marri, Ross A. McKinnon, Janni Petersen and Michael Z. Michael. Restricting Colorectal Cancer Cell Metabolism with Metformin: An Integrated Transcriptomics Study Cancers 16(11): 2055; https://doi.org/10.3390/cancers16112055 DOI: 10.3390/cancers16112055. 29 May 2024.

Media Contact and Further Information

Sally Lauder, Media Advisor, Flinders University. Tel: +61 08 8432 4288 Mob: +61 (0)410 248 446  sally.lauder@flinders.edu.au   www.news.Flinders.edu.au

New Study Confirms Forever Chemicals are Absorbed through Human Skin

A study of 17 commonly used synthetic ‘forever chemicals’ has shown that these toxic substances can readily be absorbed through human skin. 

New research, published in Environment International proves for the first time that a wide range of PFAS (perfluoroalkyl substances) – chemicals which do not break down in nature – can permeate the skin barrier and reach the body’s bloodstream.[1]  

PFAS are used widely in industries and consumer products from school uniforms to personal care products because of their water and stain repellent properties. While some substances have been banned by government regulation, others are still widely used and their toxic effects have not yet been fully investigated. 

PFAS are already known to enter the body through other routes, for example being breathed in or ingested via food or drinking water, and they are known to cause adverse health effects such as a lowered immune response to vaccination, impaired liver function and decreased birth weight.  

It has commonly been thought that PFAS are unable to breach the skin barrier, although recent studies have shown links between the use of personal care products and PFAS concentrations in human blood and breast milk.  The new study is the most comprehensive assessment yet undertaken of the absorption of PFAS into human skin and confirms that most of them can enter the body via this route. 

Lead author of the study, Dr Oddný Ragnarsdóttir carried out the research while studying for her PhD at the University of Birmingham. She explained:

“The ability of these chemicals to be absorbed through skin has previously been dismissed because the molecules are ionised. The electrical charge that gives them the ability to repel water and stains was thought to also make them incapable of crossing the skin membrane. 

“Our research shows that this theory does not always hold true and that, in fact, uptake through the skin could be a significant source of exposure to these harmful chemicals.” 

The researchers investigated 17 different PFAS. The compounds selected were among those most widely used, and most widely studied for their toxic effects and other ways through which humans might be exposed to them. Most significantly, they correspond to chemicals regulated by the EU’s Drinking Water Directive.   

In their experiments the team used 3D human skin equivalent models – multi-layered laboratory grown tissues that mimic the properties of normal human skin, meaning the study could be carried out without using any animals. They applied samples of each chemical to measure what proportions were absorbed, unabsorbed, or retained within the models. 

Of the 17 PFAS tested, the team found 15 substances showed substantial dermal absorption – at least 5% of the exposure dose. At the exposure doses examined, absorption into the bloodstream of the most regulated PFAS (perfluoro octanoic acid (PFOA)) was 13.5% with a further 38% of the applied dose retained within the skin for potential longer-term uptake into the circulation. The amount absorbed seemed to correlate with the length of the carbon chain within the molecule. Substances with longer carbon chains showed lower levels of absorption, while compounds with shorter chains that were introduced to replace longer carbon chain PFAS like PFOA, were more easily absorbed. Absorption of perfluoro pentanoic acid for example was four times that of PFOA at 59%. 

Study co-author, Dr Mohamed Abdallah, said

“our study provides first insight into significance of the dermal route as pathway of exposure to a wide range of forever chemicals.  Given the large number of existing PFAS, it is important that future studies aim to assess the risk of broad ranges of these toxic chemicals, rather than focusing on one chemical at a time.”  

Study co-author, Professor Stuart Harrad, of the University of Birmingham’s School of Geography, Earth and Environmental Sciences, added:

“This study helps us to understand how important exposure to these chemicals via the skin might be and also which chemical structures might be most easily absorbed. This is important because we see a shift in industry towards chemicals with shorter chain lengths because these are believed to be less toxic – however the trade-off might be that we absorb more of them, so we need to know more about the risks involved.”  

Reference

1. Ragnarsdóttir et al. Dermal Bioavailability of Perfluoroalkyl Substances using in vitro 3D Human Skin Equivalent Models, https://www.sciencedirect.com/science/article/pii/S0160412024003581 Environment International  188: 108772  June 2024.

About the University of Birmingham

The University of Birmingham is ranked amongst the world’s top 100 institutions. Its work brings people from across the world to Birmingham, including researchers, teachers and more than 8,000 international students from over 150 countries. 

Contact and Further Information 

For media enquiries please contact Beck Lockwood, Press Office, University of Birmingham, Tel: +44 (0)781 3343348;  r.lockwood@bham.ac.uk  

Nature Time Boosts Children’s Mental Health, Especially Those From Low-Income Families

Children who spend more time in natural environments have significantly better mental health, according to new research led by the University of Glasgow. The innovative new study, which used GPS and accelerometer tracking, found that the benefits of spending time in nature were strongest for children from lower-income households.

The study, which is published in the journal Environment International,[1] supported by the Medical Research Council (MRC) and the Scottish Government Chief Scientist Office,

found that children who spent just 60 minutes daily in nature had a 50% lower risk of mental health issues. Notably, the benefits were greatest for children from disadvantaged backgrounds, particularly in terms of improved behaviour and social skills. In addition, the study found that using natural environments for light activities, such as walking, was equally as beneficial as using these spaces for more vigorous activities, such as running.

As a result of the findings, the researchers call for collaborative efforts between policymakers, local planners, community organisations, and health professionals to ensure good access to safe, high-quality natural spaces in disadvantaged areas. They also stress the importance of raising awareness about the health benefits of being in nature.

Amid rising concerns about children's mental health, and increasing urbanization, understanding how nature affects young people’s wellbeing has never been more important. However, previous studies investigating nature-health relationships in children have shown mixed results. This is because studies often measure ‘nature exposure’ as the amount of nature available near the home or based on parents’ estimates, which do not accurately measure children’s direct use of nature.

To address these issues researchers for this study – with the full consent of both participating children and their parents – used advanced GPS and accelerometer technology to measure children's actual time in nature over one week. They also determined if children were using nature for vigorous activities, like playing sports, or for more sedate and sedentary activities, like walking or sitting. Children’s mental health was then assessed via questionnaire and associated with their time in nature.

Dr Fiona Caryl, lead researcher from the University of Glasgow, said:

“Our findings suggest that encouraging children to spend more time in nature could be a simple yet effective way to support their mental health. Crucially, disadvantaged children appear to benefit more from time in nature than their advantaged peers.”

Professor Rich Mitchell, senior author, said:

"This provides compelling evidence of nature's role in reducing gaps in mental health between higher and lower income children. It suggests that natural environments might be 'equigenic', that is, they can reduce inequalities by disproportionately benefiting those from less affluent backgrounds."

Co-author Dr Paul McCrorie adds:

"Natural environments may buffer less advantaged children against increased psychosocial and environmental stressors. They also increase opportunities for improving social connection through activities like team sports."

Reference

1. Caryl F, McCrorie P, Olsen JR, Mitchell R. Use of natural environments is associated with reduced inequalities in child mental wellbeing: A cross-sectional analysis using global positioning system (GPS) data. Environ Int;190:108847. DOI: 10.1016/j.envint.2024.108847 Epub ahead of print. PMID: 38936067. Jun 22 2024.

Contact and Further Information 

For more information contact Elizabeth McMeekin or Ali Howard in the University of Glasgow Communications and Public Affairs Office on Elizabeth.mcmeekin@glasgow.ac.uk  or ali.howard@glasgow.ac.uk

Revolutionizing Cancer Treatment by Intracellular Protein Delivery Using Hybrid Nanotubes

The hybrid nanotube stamp system revolutionizes precision medicine with high efficiency and cell viability rates for cancer treatment. The intracellular delivery of proteins is an important technique for unveiling the cellular functions, protein complex structure, and therapeutics. However, the conventional delivery methods have several limitations. To address this, researchers from Japan have developed a novel hybrid nanotube (HyNT) stamp system that can deliver multiple proteins with high efficiency and viability rates. This system represents a groundbreaking advancement in intracellular protein delivery, offering precise injection of therapeutic agents into target cells.

In today's medical landscape, precision medicine and targeted therapies are gaining traction for their ability to tailor treatments to individual patients while minimizing adverse effects. Conventional methods, such as gene transfer techniques, show promise in delivering therapeutic genes directly to cells to address various diseases. However, these methods face significant drawbacks, hindering their efficacy and safety.

Intracellular protein delivery offers a promising approach for developing safer, more targeted, and effective therapies. By directly transferring proteins into target cells, this method circumvents issues such as silencing during transcription and translation and the risk of undesirable mutations from DNA insertion. Additionally, intracellular protein delivery allows for precise distribution of therapeutic proteins within target cells without causing toxicity.

A group of researchers led by Professor Takeo Miyake at Waseda University, Japan in collaboration with the Mikawa Group at the RIKEN Institute have now developed a hybrid nanotube stamp system for intracellular delivery of proteins.  This innovative technique enables the simultaneous delivery of diverse cargoes, including calcein dye, lactate oxidase (LOx) enzyme, and ubiquitin (UQ) protein, directly into adhesive cells for cancer treatment. An article describing their research was published in Analytical Chemistry on May 14, 2024.[1] This article has been co-authored by Dr Tsutomu Mikawa, Dr Masaomi Ikari, Dr Hiromasa Yagi, Dr Naoya Tochio, and Dr Takanori Kigawa from RIKEN Center for Biosystems Dynamics Research, Japan and Mr. Bowen Zhang, Mr. Bingfu Liu, Mr. Zhouji Wu, and Mr. Kazuhiro Oyama from Waseda University, Japan.

Miyake briefly explains the stamp system assembly.

“The HyNTs were synthesized through PEDOT polymerization onto Au nanotube membranes, and then assembled with a glass tube to create a stamp capable of physically inserting HyNTs into cells.”

The researchers explored the therapeutic potential of delivering LOx enzyme for cancer treatment.

“Through our innovative stamp system, we successfully delivered LOx into both healthy mesenchymal stem cells (MSC) and cancerous HeLa cells. While MSC cells remained unaffected, we observed significant cell death in HeLa cancer cells following LOx treatment with viabilities decreasing over time. Our findings highlight the promising efficacy of intracellularly delivered LOx in selectively targeting and killing cancer cells, while sparing healthy cells, offering a targeted therapeutic strategy for cancer treatment," explains Miyake.

Finally, the team successfully delivered 15N isotope-labeled UQ proteins into HeLa cells using the HyNT stamp system. This delivery allowed for the analysis of complex protein structures and interactions within the cells. In addition, optical and fluorescence imaging confirmed the presence of delivered UQ in HeLa cells, and nuclear magnetic resonance spectroscopy matched the intracellular UQ protein concentration with that of a solution containing 15N-labeled UQ. These results demonstrate the effectiveness of the stamp system in delivering target proteins for subsequent analysis.

The results demonstrate the remarkable capability of the HyNT stamp system in delivering LOx and UQ into a substantial number of adhesive cells, as required for regenerative medicine applications. The system achieved a notably high delivery efficiency of 89.9%, indicating its effectiveness in transporting therapeutic proteins into the target cells with precision. Moreover, the cell viability rate of 97.1% highlights the system's ability to maintain the health and integrity of the treated cells throughout the delivery process.

The HyNT stamp system offers transformative potential in intracellular protein delivery, with applications spanning from cancer treatment to molecular analysis. Beyond medicine, its versatility extends to agriculture and food industries, promising advancements in crop production and food product development. With precise cell manipulation and efficient delivery, the HyNT stamp system is poised to revolutionize biomedical research, clinical practice, and diverse industries, paving the way for personalized interventions and shaping the future of modern medicine.

Reference

1. Bowen Zhang^1,2, Bingfu Liu¹, Zhouji Wu¹, Kazuhiro Oyama^1,2,Masaomi Ikari², Hiromasa Yagi², Naoya Tochio², Takanori Kigawa², Tsutomu Mikawa², and Takeo Miyake¹. A Hybrid Nanotube Stamp System in Intracellular Protein Delivery for Cancer Treatment and NMR Analytical Techniques. Analytical Chemistry: 96,21,8349-8355. 14 May 2024.

 https://doi.org/10.1021/acs.analchem.3c05331

Affiliations:

¹Graduate School of Information, Production and Systems, Waseda University, Japan

²RIKEN Center for Biosystems Dynamics Research, Japan

About Waseda University

Located in the heart of Tokyo, Waseda University is a leading private research university that has long been dedicated to academic excellence, innovative research, and civic engagement at both the local and global levels since 1882. The University has produced many changemakers in its history, including nine prime ministers and many leaders in business, science and technology, literature, sports, and film. Waseda has strong collaborations with overseas research institutions and is committed to advancing cutting-edge research and developing leaders who can contribute to the resolution of complex, global social issues. The University has set a target of achieving a zero-carbon campus by 2032, in line with the Sustainable Development Goals (SDGs) adopted by the United Nations in 2015. 

To learn more about Waseda University, visit https://www.waseda.jp/top/en  

About Professor Takeo Miyake

Takeo Miyake is a Professor at the Faculty of Science and Engineering at Waseda University.  He received his Ph.D. degree in Nanoscience & Nanoengineering  from Waseda University. He is a member of the Materials Research Society, Surface Science Society of Japan, and Japan Society of Applied Physics. He received the Minister of Education, Culture, Sports, Science, and Technology Commendation Young Scientist Award in 2020. His research interests include bioiontronics, biofuel battery, bioprotonics, and bioelectronics. With over 2,763 citations, his notable achievements include pioneering work in enzymatic biofuel cells and interface science.

Media Contact and Further Information

Rishita Sachan rishita.sachan1@cactusglobal.com

https://www.waseda.jp/top/en/news/80827