Data Scientist - Heidelberg, Deutschland - Deutsches Krebsforschungszentrum

Deutsches Krebsforschungszentrum

Geprüftes Unternehmen

Heidelberg, Deutschland

vor 2 Wochen

Geschrieben von:

Lena Wagner

beBee Recruiter

Beschreibung

Position:
Data Scientist / Bioinformatician for Skin Cancer Research in full
- or part-time**
Department: Junior Research Group "Digital Biomarkers for Oncology"

Code number:

The German Cancer Research Center is the largest biomedical research institution in Germany. With more than 3,000 employees, we operate an extensive scientific program in the field of cancer research.

The Junior Research Group "Digital Biomarkers for Oncology" (headed by Dr. Titus Brinker) is seeking a data scientist or bioinformatician to work on a skin cancer research project.

Skin cancer is one of the most common cancers in Europe and malignant melanoma in particular causes the highest number of skin cancer-attributable deaths.

Melanomas are spatially heterogeneous, resulting in part from plastic changes in melanoma cells.

It is not well understood how molecular plasticity and associated heterogeneity translate into specific histological structures of melanomas, and how this plasticity affects the prognosis of patients.

In this interdisciplinary project, you will work together with an experienced molecular biologist from our team in Heidelberg and be responsible for the data science / bioinformatic part.

The team will be supported by a dermatologist.

Job description:

Within the project, you will characterize plasticity-induced spatial heterogeneity at both the gene expression and histological levels and investigate the relationship between the different levels of heterogeneity and with patient prognosis.

To this end, you will first develop methods to automatically annotate the different segments on histological sections of primary superficial spreading melanomas and investigate correlations.

You will then define areas of maximal overlap between the segments defined by the different methods and use these to train an algorithm that identifies these areas on new melanoma sections.

Hereby, you will investigate whether and, if so, how an analysis of the number and possibly area and/or distribution of these areas allows prognostic statements in the sense of a digital biomarker.

At the gene expression level, you will investigate transcriptional heterogeneity/plasticity using RNAscope in situ hybridization. Here, you determine the expression of selected genes from mesenchymal and melanocytic signatures previously described in melanoma cells.

At the histological level, you will characterize the segments using two methods:

by pathological annotation of different cell types and their subsequent automatic recognition using established pathology software (supervised learning) and by AI-based clustering without predefined classes (unsupervised learning).

You will analyze the area variation of the segments defined by the different methods and perform correlation analyses between molecular and histological properties of these segments.

Based on this, you will generate areas/segments on the sections that have the highest possible correlation between molecular and histological properties.

With these "fusion segments", you will train a Deep Learning
- based segmentation algorithm to automatically annotate the plasticity-induced spatial heterogeneity also on new, unknown H&E-stained melanoma tissue sections and relate the thus defined heterogeneity to prognosis. If, as in other cancers, a correlation between extent of heterogeneity and prognosis is evident, you will attempt to use the segmentation algorithm results to train a risk classifier that can be used as a digital prognostic biomarker to predict recurrence or mortality risk.

Requirements:

Preferably a bachelor's or master's degree in life science or data science
Deep motivation to improve outcomes for cancer patients
Background in data science or bioinformatics or related fields
Strong interest in life sciences / working in interdisciplinary teams
Selfdependent work ethic
English language skills are required

We offer:

Excellent framework conditions: stateoftheart equipment and opportunities for international networking at the highest level
Remuneration according to TV-L incl. occupational pension plan and capitalforming payments
30 days of vacation per year
Flexible working hours
Possibility of mobile work and parttime work
Familyfriendly working environment, e.g. parentchild room, advisory services caring for elderly relatives
Sustainable travel to work: subsidized Germany job ticket
Unleash your full potential: targeted offers for your personal development to further develop your talents
Our Corporate Health Management Program offers a holistic approach to your wellbeing

Important notice:

Earliest Possible Start Date:
as soon as possible

Duration:
The position is limited to 2 years.

Application Deadline:

Contact:

Dr. Titus Brinker
Phone 0151/

The DKFZ is committed to increase the proportion of women in all areas and positions in which women are underrepresented.

Qualifie