Our guiding principles for data partnerships

• Dataset name: OPTIMAM
• Cancer type: Breast
• Data type: Medical images
• Company name: Gleamer
• Project title: Development and validation of an AI model to detect and characterise breast lesions
• Research summary: 

Gleamer is a France-based company that develops AI radiology solutions. The company aims to support radiologists by improving workflow efficiency and the diagnosis of patients. Gleamer has developed multiple regulatory-cleared AI medical image analysis tools that support clinicians across a range of areas, including bone trauma, musculoskeletal measurements, bone age assessments and chest conditions. 

Gleamer will use images from the OPTIMAM database to develop a novel AI software capable of detecting breast abnormalities and characterising their malignancy. The project aims to improve patient care by enabling the earlier detection of breast cancer, thereby reducing mortality and morbidity associated with breast cancer and its treatments.

• Date of partnership: July 2024

• Dataset name: CHHiP and IMRT Trials
• Cancer type: Prostate
• Data type: Clinical & Digital Pathology
• Company name: Artera Ai Inc.
• Project title: Prognostic validation of a digital pathology-based multi-modal artificial intelligence (MMAI) prostate cancer biomarker in the CHHIP & IMRT radiotherapy trials.
• Research summary: 

Artera have built an AI tool that is able to use images of the tissue from a patients tumour (digital pathology images) from prostate cancer patients to predict prognosis and the likelihood of response to various treatments. In this collaboration Artera are looking to understand the performance of the tool in the UK prostate cancer population and whether it can predict response to different courses of radiotherapy. Using the results from the analyses, Artera may further optimise and develop the algorithm to improve its performance for these patient populations.

• Date of partnership: July 2024

• Dataset name: S:CORT
• Cancer type: Colorectal
• Data type: Omics
• Company name: Immunocore
• Project title: Identification of factors that might modulate patient benefit to a novel therapy against Colorectal Cancer
• Research summary: 

T-cells are a type of immune cell that play a crucial role in destroying infected or cancerous cells. They use a protein on their cell surface, called the T-cell receptor (TCR), to determine whether other cells in the body are cancerous.  If T-cells determine a cell is abnormal, they kill the afflicted cell. Unfortunately, cancers are often able to adapt so they can escape or hide from these T-cells. Immunocore aims to overcome these immune escape methods using its ImmTAC® technology. ImmTAC molecules are soluble versions of TCRs that bind to cancer cells up to a million-fold more tightly than natural TCRs. Immunocore engineers such TCRs to recruit and potently activate a patient’s own T-cells, helping them recognise and kill cancer cells. Immunocore has validated this technology, with its first authorised product, that can improve overall survival in patients with a rare form of eye cancer that spreads to the liver and elsewhere. Immunocore plans to start a Phase 1 trial with its first ImmTAC candidate designed to treat patients with colorectal cancer (CRC). This ImmTAC candidate binds a cancer specific target on colorectal cancer cells. In parallel to the Phase 1 trial, Immunocore is seeking to better understand the make-up of tumours that express this target, to determine which patient subsets might benefit the most from this ImmTAC candidate. Access to the S:CORT Dataset is important to enable Immunocore to perform this analysis across a diverse population of colorectal cancer patients. Immunocore is performing this work in collaboration with the University of Oxford.

• Dataset name: S:CORT
• Cancer type: Colorectal
• Data type: Molecular and pathology images 
• Company name: Insitro Limited
• Project title: Using self-supervised machine learning methods to identify novel biomarkers for colorectal cancer patient stratification and drivers of the disease
• Research summary: 

The expansion of computer science and artificial intelligence approaches, such as machine learning, hold great promise for the potential to discover causes of cancer and develop new treatments. Machine learning algorithms can use clinical data to learn and make predictions about the biology of cancer. insitro is using machine learning to improve the understanding of colorectal cancer, subtypes of the disease and possible new treatments. This includes using these techniques to study data arising from clinical trials and NHS care.

In this project Insitro will use the S:CORT Data to find new ways of selecting patients likely to respond to existing therapies, find new targets for treatments, or new uses of existing treatments. To achieve these goals, Insitro will: 

1. Use the S:CORT data to improve Insitro’s existing methods to analyse pathology images, improving the impact of their future research in Colorectal cancer
2. Use these improved methods to analyse the S:CORT Data and identify new biological characteristics of the patients in the dataset.
3. With data from (2), combined with the patient outcome data, Insitro aim to find new biological signatures that could help decide:
   • which patients would benefit from treatment
   • what that treatment should be
   • if the patients tumour is still likely to be responding to treatment they are receiving
   • find new drug targets or where existing treatments could help more patients 

The outcomes from this project have the potential to benefit patients by increasing the precision of treatment decisions so that more patients receive the treatment that is most likely to work for them.

• Date or partnership: March 2024

• Dataset name: S:CORT
• Cancer type: Colorectal
• Data type: Molecular and pathology images 
• Company name: Ground Truth Labs
• Project title: AI image based molecular subtyping of colorectal cancers from the S:CORT cohort
• Research summary: 

The differing subtypes of Bowel (colorectal) cancer, defined by molecular signatures, exhibit different clinical behaviour including response to treatment and prognosis. Traditionally, molecular profiling techniques have been used to diagnose a patient’s particular sub-type of colorectal cancer but this is complex and time-consuming. However, Ground Truth Labs have found that artificial intelligence (AI) can accurately predict these signatures, specifically Consensus Molecular Subtypes (CMS), using digital pathology images, offering a faster, more efficient alternative.

The goal of this project is to create a clinical-grade AI algorithm to predict these molecular subtypes and assess their correlation with patient outcomes, starting with a CMS predictor.

• Date or partnership: March 2024

• Dataset name: S:CORT
• Cancer type: Colorectal
• Data type: Pathology images 
• Company name: Valar Labs
• Project title: Identifying novel histologic signatures associated with treatment response in colorectal cancer using artificial intelligence
• Research summary: 

As systemic treatment options for colorectal cancer have grown, medical oncologists are increasingly confronting decisions about which regimen is optimal for a patient with advanced colorectal cancer. Unfortunately, there are limited biomarkers, patterns in a patients data or tissue, available at present to help clinicians guide patients through treatment decisions where uncertainty in the medical literature exists. Valar Labs is a Stanford-based start-up company that seeks to use artificial intelligence to identify features which are not readily identifiable by the human eye in routine, diagnostic microscope slides (pathology) of tumors, but are nevertheless associated with cancer treatment responses. This project aims to use the pathology images that are collected under S:CORT to attempt to identify biomarkers for response to standard of care treatments from the digital pathology images that form part of the S:CORT cohort using Valar’s AI-enabled digital pathology platform. 

• Date or partnership: January 2024

• Dataset name: S:CORT
• Cancer type: Colorectal
• Data type: Molecular
• Company name: Turbine Simulated Cell Technologies (to support ongoing collaboration with Cancer Research Horizons)
• Project title: Validation of in silico predicted target patient groups for a CDC7 inhibitor
• Research summary:

Cancer is a heterogenous disease with distinct characteristics in every patient. These differences are largely due to the random nature of genetic mutations which allow uncontrolled growth in cancer cells, thus highlighting the importance of effectively selecting patient populations on the basis of their predicted sensitivity to specific drugs. CDC7 is a biological molecule involved in replication of cells. CDC7 is implicated in several cancer types for which there is an unmet need for additional treatments. Drugs which inhibit CDC7 activity (CDC7 inhibitors) have been widely trialled by the pharmaceutical industry. However, despite many attempts over 15 years, CDC7 inhibitor drug candidates have not been successful in clinical trials. We believe that a deeper understanding of the effects of CDC7 inhibitors on cancer biology and human genetics will greatly increase the chances of successful CDC7 inhibitor development, as it will enable us to more confidently select which patients can benefit from CDC7 inhibitors. Turbine’s Simulated Cell technology is a computational approach that is being used to understand which genetic differences make a tumour sensitive to a novel CDC7 inhibitor drug candidate that is being developed by CRH, the commercialisation and development arm of Cancer Research UK. The project now plans to compare our findings with the patient data available in the S:CORT database to help inform future experiments and patient selection strategies for CRH’s novel CDC7 inhibitors. Once we better understand this relationship between CRH’s novel CDC7 inhibitors and the genetics of tumours, we hope to use that knowledge to test the therapeutic effect of this new compound in patients that are most likely to benefit from it.

• Date of partnership: January 2024

• Dataset name: OPTIMAM
• Cancer type: Breast
• Data type: Medical images
• Company name: Clairity, Inc.
• Project title: Predicting future breast cancer risk
• Research summary: 

• Date of partnership: October 2023

• Dataset name: S:CORT
• Cancer type: Colorectal
• Data type: Multi-omics​
• Company name: Genialis
• Project title: Optimisation and validation in of predictive biomarker in gastric adenocarcinoma
• Research summary: 

Genialis has developed a proprietary machine learning framework which models disease biology with the goal to inform treatment decisions and realise personalised medicines for patients. In supporting the development of these biomarker algorithms, the company relies on access to diverse datasets to ensure the biomarkers are accurate and robust across different demographics. This collaboration provides Genialis access to a subset of S:CORT data to support the development and validation of the next generation of RNA based precision medicine solutions​

• Date of partnership: October 2023

• Dataset name: OPTIMAM
• Cancer type: Breast
• Data type: Imaging
• Company name: Screenpoint Medical BV​
• Project title: Intelligent Breast Screening​
• Research summary: 

ScreenPoint Medical develops artificial intelligence software that helps radiologists to detect breast cancer earlier and faster. This software works as an assistant to the radiologist by analysing the images to look for signs or risk of breast cancer. To ensure equal and fair support to all women, in particular those attending the UK breast cancer screening program, de-identified data from patients participating in the OPTIMAM study are used in the development and validation of these solutions.

• Date of partnership: August 2022 (2D Images), September 2023​​

• Dataset name: OPTIMAM
• Cancer type: Breast
• Data type: Medical images
• Company name: Beijing Yizhun Medical AI Technology Co. ,Ltd
• Project title: Testing the sensitivity and the specificity of an AI mammography diagnostic software
• Research summary:

• Date of partnership: July 2022
   

• Dataset name: OPTIMAM
• Cancer type: Breast
• Data type: Medical images
• Company name: Google Health UK 
• Project title: Machine learning for detection, characterisation and risk stratification of lesions in breast imaging
• Research summary:

Mammograms (breast X-rays) are a crucial part of breast cancer screening, implemented across the world as part of national breast screening initiatives. These scans are normally analysed by radiologists, but the quantity and complexity of these images means that additional tools are needed to support their interpretation. Google Health is developing tools to support the detection of breast cancer in mammograms and this collaboration provides Google with access to de-identified data from the OPTIMAM study to help support the development and validation of these tools. 

• Date of partnership: July 2022