Posts

Using machine-learning approaches to identify blood cancer types

Myeloproliferative Neoplasms (MPNs) are a group of blood cancers that occur when stem cells in the bone marrow develop mutations that lead to over-production of blood cells – either red blood cells in Polycythaemia Vera (PV), or platelets in Essential Thrombocythaemia (ET). This carries an increased risk of developing blood clots, such as in the legs, lungs, heart attacks or strokes.

In myelofibrosis, the most severe of the MPNs, destructive scarring (‘fibrosis’) of the bone marrow develops, leading to failure of the marrow to produce blood cells and severe symptoms. Patients with all MPNs are at higher risk of developing leukaemia, especially patients with myelofibrosis when this develops in over 1 in every 10 patients.

Unfortunately, we do not yet have any drug treatments that can cure these conditions. Treatments for ET and PV aim to control the blood counts and reduce the risk of blood clots. For myelofibrosis, targeted therapies such as ruxolitinib, a JAK inhibitor, can effectively control symptoms, but this does not alter the natural history of the disease and survival remains less than 5-10 years following diagnosis.

In the vast majority of cases, mutations are found in one of 3 genes – JAK2, CALR or MPL. Screening for these is important in MPN diagnosis, however distinguishing between the MPN subtypes requires a careful examination of blood counts and the morphological features of a bone marrow biopsy.

Unfortunately, assessment of the bone marrow is highly subjective, reliant on qualitative observations and there is great variability, even when it is done by expert haematopathologists. In particular, it is very hard to reliably distinguish between a mutation-negative MPN and a ‘reactive’ (non-cancer) bone marrow.

A more accurate method for diagnosis is very much needed, to enable selection of the most appropriate treatment strategy for patients and to determine treatment targets. Megakaryocyte cells or  ‘megas’ – the large, bone marrow cells that produce blood platelets – are very abnormal in all the MPNs and thought to play a key role in the disease pathology. Interestingly, although the gene mutations underlying all 3 MPNs lead to an over production of megas, subtle differences in the appearance and location of these cells within the bone marrow occur in the different MPN subtypes.

To try to improve MPN classification, a team lead by Jens Rittscher (Department of Engineering) and Daniel Royston (Radcliffe Department of Medicine), developed an AI approach to screen and classify MPN cases based on features of the mega cells, discovering new features in their cell size, clustering and internal complexity. Their machine learning approach revealed that there are clear differences between MPN subtypes – the platform was able to more accurately classify patients by assessing subtle morphological differences in the biopsies that could not have been identified by the naked eye.

These findings have been published in Blood Advances. Dr Beth Psaila, a clinician scientist at the MRC Weatherall Institute of Molecular Medicine and a haematology consultant specialising in MPNs said:

“It has long been recognised that a multitude of subtle differences in megakaryocyte morphology can distinguish between the MPN subtypes. However, this means that assessment of bone marrow biopsies is poorly reproducible, sometimes leading to diagnostic uncertainty and inappropriate treatment plans for patients.

“The approach developed here is really exciting for the field, as it is now possible to perform deep phenotyping of megakaryocytes and more accurate disease classification using simple H&E slides which are routinely prepared in all diagnostic facilities. This will be incredibly useful both for research aimed at better understanding the role of megakaryocytes in blood cancers as well as improving diagnosis and treatment pathways for our patients.”

The team hopes that in the future, this work can be combined with other histological assessments to optimise the clinical application of AI approaches, and create a more comprehensive quantitative description of the bone-marrow microenvironment and its cancers.

About the researchers and the study

This work was funded by the NIHR Oxford Biomedical Research Centre and is the result of collaboration between Korsuk Sirinukunwattana (Department of Engineering), Alan Aberdeen (Ground Truth Labs Ltd.), Helen Theissen (Department of Engineering), Jens Rittscher (Department of Engineering) and Daniel Royston (Radcliffe Department of Medicine [NDCLS]).

Jens Rittscher is a Principle Investigator whose research aim is to enhance our understanding of complex biological processes through the analysis of image data that has been acquired at the microscopic scale. Jens develops algorithms and methods that enable the quantification of a broad range of phenotypical alterations, the precise localisation of signalling events, and the ability to correlate such events in the context of the biological specimen.

Korsuk Sirinukunwattana is a postdoctoral research assistant in Rittscher’s group specialised in medical image analysis and computational pathology. His main research interest is the association between tissue morphology and molecular/genetic subtypes in various diseases.

Alan Aberdeen leads Oxford spinout Ground Truth Labs, a company supporting digital pathology research through on-demand analysis, biomarker discovery, and high-quality cohorts.

Helen Theissen is a doctoral research student in Rittscher’s group. Her research focuses on computational methods to characterise cellular subtypes and quantify the bone marrow microenvironment in MPNs.

Daniel Royston is a joint academic & consultant Haematopathologist at Oxford University Hospitals NHS Foundation Trust / Radcliffe Department of Medicine.

Drug target potential for myelofibrosis

A new paper led by Dr Bethan Psaila, from the Weatherall Institute of Molecular Medicine (WIMM) of the Radcliffe Department of Medicine, has revealed a potential new immunotherapy drug target in the treatment of myelofibrosis.

Myelofibrosis is an uncommon type of bone marrow cancer characterised by gene mutations acquired in blood stem cells that lead to over-production of bone marrow cells called megakaryocytes, development of scarring or ‘fibrosis’ that stops the bone marrow being able to produce blood cells in adequate numbers, low blood counts and a large spleen.

At present, bone marrow transplant is the only potentially curative treatment for myelofibrosis, but this procedure carries high risks and only a small proportion of patients are suitable candidates for this. While drug therapies including JAK inhibitors can improve symptoms and quality of life, none are curative and these do not improve the bone marrow fibrosis. Therefore, there is a need to identify new targets for therapeutic development.

In a paper recently published in Molecular Cell, Beth Psaila and her team investigated a specific aspect of myelofibrosis, which is an increased frequency of bone marrow megakaryocyte (MK) cells. MKs are the bone marrow cell responsible for the production of platelets. While they are rare cells in healthy bone marrow, a pathogenomic feature of myelofibrosis is that they are observed in high numbers, and they are recognised as the key cellular drivers of fibrosis.

In order to better understand the cellular and molecular pathways leading to over-production of Mks and their dysfunction, the team used single-cell analyses, studying over 120,000 blood stem/progenitor cells individually.

This led to two key observations: firstly, that the proportion of blood stem cells that were genetically ‘primed’ to give rise to MKs was 11-fold higher in myelofibrosis patients than in healthy donors, and secondly that MK genes were being switched on even in the most primitive stem cells in myelofibrosis, suggesting massive expansion of a ‘direct’ route for MKs to develop from stem cells in myelofibrosis, a phenomenon that was almost undetectable in healthy bone marrow.

They found that the myelofibrosis stem/progenitor cells, but not the wild-type or normal stem cells, expressed a high level of G6B, a immunoglobulin cell-surface receptor protein. They validated G6B as an exciting potential immunotherapy target that might be utilised to specifically ablate both the cancer stem cell clone and the fibrosis-driving MK cells.

Dr Beth Psaila commented:

“The finding that G6B is markedly increased in the cancer stem cells is very important, as it suggests that targeting G6B in combination with a stem cell marker may be a way of selectively targeting the cancer-driving stem cells while sparing healthy stem cells.

“Identifying ways to knock out the disease-initiating cells is crucial to make progress in this disease, as currently there are no curative treatments available to offer the majority of our patients.”

Going forward, Beth and her team will be working on further validating their targeting strategy to see if it might be translated to the clinic.

About Beth

Beth is a CRUK Advanced Clinician Scientist at the MRC Weatherall Institute of Molecular Medicine. The primary focus of her group is on megakaryocyte and platelet biology in cancer, and the application of single-cell approaches to clarify the cellular pathways by which megakaryocytes arise from haematopoietic stem cells.

She trained at Clare College, Cambridge, Imperial College London/The Hammersmith Hospital, Cornell, New York, and the National Institutes of Health, Bethesda USA, Beth is also an Honorary Consultant in Haematology in Oxford and a Senior Fellow in Medicine of New College, Oxford.

This research was conducted in collaboration with Prof Adam Mead and Dr Supat Thongjuea in the WIMM, including using data that was generated by Dr Alba Rodriguez-Meira. The work was partially funded by a Cancer Research UK Advanced Clinician Scientist Fellowship, a CRUK Innovation Award; a Wellcome Career Development Fellowship and a Medical Research Council (MRC) Senior Clinical Fellowship.

New start-up Base Genomics launches

 

About the technology

TET-assisted pyridine borane sequencing (TAPS) is a new method for measuring DNA methylation, a chemical modification on cytosine bases. DNA methylation has important regulatory roles in the cell but is frequently altered in cancer. These altered DNA methylation levels are preserved in DNA that is released into the blood from cancer cells and therefore DNA methylation has great potential as the basis for a multi-cancer blood test. However, a key limitation to achieving this aim, especially for detecting cancer at the earliest stages, is the low sensitivity of current DNA methylation technology.

One of the advantages of TAPS over the current standard methodology is the avoidance of the use of bisulphite, a harsh chemical that severely degrades DNA. TAPS is a mild reaction that preserves DNA integrity and is effective at very low DNA concentrations, which would increase the sensitivity of blood-based DNA methylation assays. TAPS also better retains sequence complexity, enabling simultaneous collection of DNA methylation and genetic data, and cutting sequencing costs in half. Read more about the potential of TAPS as the basis for a multi-cancer blood test here.

The company Base Genomics has been launched to set a new gold standard in DNA methylation detection using this TAPS technology.

 

“I am thrilled about the launch of Base Genomics and look forward to seeing the TAPS technology developed in my lab applied to new technologies for cancer detection and the advancement of a variety of fields of biomedical research,”

Dr Chunxiao Song, assistant member of the Ludwig Institute Oxford Branch, co-founder of Base Genomics, chemistry advisor to the company.

 

 “Genomic technologies with the power, simplicity and broad applicability of TAPS come along very infrequently,

“It has the potential to have an impact on epigenetics similar to that which Illumina’s SBS chemistry had on Next Generation Sequencing.”

Base Genomics CTO Dr Vincent Smith.

 

About Base Genomics

Base Genomics has a team of leading scientists and clinicians, including Dr Vincent Smith, a world-leader in genomic product development and former Illumina VP; Professor Anna Schuh, Head of Molecular Diagnostics at the University of Oxford and Principal Investigator on over 30 clinical trials; Drs Chunxiao Song and Yibin Liu, co-inventors of TAPS at the Ludwig Institute for Cancer Research, Oxford; and Oliver Waterhouse, previously an Entrepreneur in Residence at Oxford Sciences Innovation and founding team member at Zinc VC.

The company has closed an oversubscribed seed funding round of $11 million USD (£9 million GBP), led by Oxford Sciences Innovation alongside investors with industry expertise in genomics and oncology. This funding will progress development of the TAPS technology, initially focusing on developing a blood test for early-stage cancer and minimal residual disease.

 

”The ability to sequence a large amount of high-quality epigenetic information from a simple blood test could unlock a new era of preventative medicine,

“In the future, individuals will not just be sequenced once to determine their largely static genetic code, but will be sequenced repeatedly over time to track dynamic epigenetic changes caused by age, lifestyle, and disease.”

Base Genomics founder and CEO Oliver Waterhouse.

 

“In order to realise the potential of liquid biopsies for clinically meaningful diagnosis and monitoring, sensitive detection and precise quantification of circulating tumour DNA is paramount,

“Current approaches are not fit for purpose to achieve this, but Base Genomics has developed a game-changing technology which has the potential to make the sensitivity of liquid biopsies a problem of the past.”

Base Genomics CMO Professor Anna Schuh

 

For more information, see the Base Genomics press release.