Advanced methods for signature analysis: signature meta scoring using annotated gene sets

In transcription, the DNA sequence of a gene is copied (i.e., “expressed”) to make an RNA molecule which can be directly functional or be the intermediate template for a protein that performs a function. Gene expression data contains the expression levels of all genes in the organism. Geneset analysis is crucial for interpreting the results of such complex data.

Patient-level outlier detection using knowledge graphs

Join us in our exploratory journey to leverage healthcare data with knowledge graphs to detect outliers, improve data quality and even generate insight.

Understanding and correcting missing and erroneous data in diabetes-related time series

The purpose of this challenge is to address missing and erroneous data from RWD, in particular diabetic patients, that consists of multiple time series.

Understand changes to patients’ quality of life through the clinical workflow

Health-Related Quality of Life (HRQOL) is the perceived well-being of an individual. The clinical workflow is all the steps related to the delivery of care. Aspects such as treatment and age can influence HRQOL. In this challenge, we want to understand the change of HRQOL along with clinical workflow.

Advanced methods for signature analysis: signature metascoring using annotated gene sets

Gene set analysis is crucial for interpreting the results of RNASeq experiments. However, most signatures do not get used because of poor annotation.

Algorithms for liquid-chromatography optimization

Let’s seek powerful and flexible algorithms for computer-assisted high-throughput liquid-chromatography (HPLC).

Building an engaging and intentional data culture and data literacy concept

Crack the code of data literacy and culture as part of our team. Data and information is the heart of our future and we want to crack the code together with you.

Developing profiling and segmentation algorithms to generate insights into our diagnostic customers’ needs

Roche is one of the major players in in-vitro diagnostics, with a plethora of assays, technologies and customers. We are curious to learn from your ideas: how could we profile and segment our customers to better understand their needs?

Identification of hidden patterns in diagnostics assay data

We believe that multi-biomarker panels have the potential to enhance the diagnosis, prognosis and monitoring of a broad range of diseases effectively. We are curious to learn from your ideas: how could we identify hidden patterns in our wealth of diagnostics assay data?

Interpretable ML models for automated quality assessment of measurement results

Machine Learning is gaining ground in the development of medical and diagnostic products. However, unfolding its full potential is hampered by lack of interpretability of “black box” models. So let’s build interpretable ML models for automated quality assessment of instrument results.

Machine-readable clinical practice guidelines in oncology

Artificial Intelligence (AI) is divided into probabilistic and logics-based approaches. Machine-readable clinical practice guidelines form a prime use case for bringing these two approaches together. Only combined AI approaches enable us to understand, explain, and trust the hints and paths provided by the system which ultimately leads to better outcomes for patients.

A machine learning-based framework for digital biomarkers discovery, analysis and development

— Focus: PHC

Develop machine learning-based framework for digital biomarkers discovery: A generic platform for digital biomarkers development and analysis using patient surveys and wearables data.

Augmented patient pathways in oncology

— Focus: PHC

Real world population-level oncology data contains information that can change the way patients are treated. Do you want to pave the way to the future of healthcare?

Develop machine learning-based methods for early anomaly detection in diagnostics instrument and assay data

— Focus: PHC

Millions of patients around the world rely on the precision and accuracy of our diagnostics devices and lab instruments every day. We are curious to learn from your ideas: how could we monitor the quality of our products and detect emerging issues as early as possible?

Generating synthetic patient-reported outcomes to foster collaboration in clinical settings

— Focus: PHC

Shifting the focus to patients in the clinical workflow is key for a meaningful and patient-centric healthcare transformation. For this, we would like to explore the changes in the patient’s quality of life along with the care flow. We foresee that data sharing will be key to foster collaboration. Would you take that journey with us?

Predicting drug effects in a multimodal biological network

— PHC

The fundamental understanding of the human organism and how it is perturbed by variants and drugs forms the basis of delivering tailored care. How can we predict the specific effect a drug has on its known cellular target(s) based on its cellular interaction network?

Explore the future of sensing

— PHC

How will trends affect lives and behaviors and influence the daily lives of our patients? How connected will our world be in the future and what could that mean for the future solutions for diabetics

A deep learning-based approach for detection of neurological disease patterns using a draw-a-shape test

— PHC

Interested in machine learning, and analysing digital health datasets to uncover hidden disease progression? Want to make a tangible impact on the lives of people living with neurological diseases? Then help us apply deep learning methods to develop better digital measurements of impairment!

Non-invasive liquid level detection

— Lab Automation

Do you want to help improve the testing capacity of medical laboratories and hospitals? Do you want to have a direct impact on society’s ability to test for and thereby track diseases faster? Have a look at the data set and convince us of your solution proposal!

Graph-based Bottleneck Analysis in a complex production environment

— Process and Manufacturing Analytics

You love diving really deep into data and business topics which are linked to real value chain problems. You like to work on real, incomplete, dirty data sets, using complex methods while explaining it in simple words. Welcome to the world of enterprise data science!

Impact of checkpoint inhibitor therapies on a patients’ immunogenicity status

Are you curious about cancer immunotherapy everyone in the oncology world is talking about? Do you love using and advancing your skills to analyze complex data and shedding light on current research questions?

Computational deconvolution for patient stratification in the context of non-small cell lung cancer

Computational methods can help to unravel the complexity of the tumor microenvironment of individual patients. We ask for your help to assess such methods to enhance our understanding of cancer heterogeneity and to improve patient classification.

Development of a digital companion for breast cancer patients

Cancer patients often do not know what to do when they get their initial diagnosis and are often overwhelmed with the situation. We are curious to learn from your ideas how to enable patients to navigate through the jungle of information, challenges and hurdles, so that they can be in the driver’s seat of their patient journey inside the healthcare system.

Incorporating Natural Language Processing (NLP) Workflows into an open-source genomics cancer portal

Support clinicians in decision-making processes through easy access of mutation dependent targeted therapy options by using NLP.