Biocurator

DeepLife is hiring!

About

DeepLife is a pre-series A startup focused on addressing the urgent need to increase drug discovery reliability by acting on the earliest step, drug target identification. This consists of identifying, a molecular target, such as a protein, that will trigger the transition from disease to healthy cells. With current methods, only 1 target in 10,000 reach the market, leading to a significant loss of time and efforts in the community.

Our approach is to leverage the recent revolution in the omics data, measuring precisely cells activity at large scale, and build foundation models to mimic cell behavior in various contexts and identify the optimal trigger to reverse disease state.

Half of the team today is dedicated to build the largest omics database, aka omics atlas, to map all human body tissues and diseases and reduce experimental biases.

We offer a research friendly environment, with 90% of the company holding a PhD, with academic collaborations and publications. The team is international and composed of +10 different nationalities. The company is remote first with most of the work is remote and regular events organized in our offices in Paris.

Job Description

Overview:

We are seeking a skilled Biocurator to join our single-cell atlas building team. This crucial role involves curating, harmonizing, and managing metadata for millions of samples across multiple omics. The ideal candidate will have expertise in the latest large language models (LLMs), omics data, biology, ontology construction, Python and database scrapping. This position is essential for building internal foundation models and supporting drug discovery use cases through collaboration with the atlas team and involvement in multi-omics foundation model training.

Key Responsibilities:

1. Metadata Curation and Harmonization: Curate and harmonize metadata for millions of samples across various omics to ensure consistency and accuracy in the single-cell atlas.

2. Ontology Construction: Develop and maintain biological ontologies to standardize data representation and facilitate cross-study comparisons.

3. Data Integration and Annotation: Collaborate with the atlas team to integrate and annotate multi-omics data, enhancing the biological insights derived from the atlas.

4. Database Scraping: Utilize Python to scrape relevant databases and collect comprehensive datasets for atlas development.

5. Collaboration with Atlas Team: Work closely with the atlas team to ensure high-quality data curation and integration, supporting the construction of comprehensive biological atlases.

6. LLM Integration: Apply expertise in state-of-the-art LLMs to automate and enhance data curation and annotation processes.

7. Foundation Model Development: Contribute to the development of internal foundation models by providing high-quality curated data for training.

8. Support Drug Discovery Use Cases: Participate in drug discovery projects by curating relevant omics data and metadata for specific use cases.

9. Continuous Improvement: Stay updated on advancements in bioinformatics, data curation, and LLMs to continuously improve curation processes.

10. Documentation and Reporting: Document curation processes and data harmonization methods to ensure reproducibility and facilitate collaboration.

Preferred Experience

Requirements (Ranked from Most Important to Least Important):

1. Expertise in metadata curation and harmonization for omics data.

2. Experience in ontology construction and data standardization in biological contexts.

3. Proficiency in working with state-of-the-art Large Language Models (LLMs).

4. Strong background in biology and understanding of multi-omics data.

5. Proficiency in Python, with experience in database scraping and data handling.

6. Ability to integrate and annotate multi-omics datasets for atlas development.

7. Experience in collaborating with cross-functional teams to build biological atlases.

8. Familiarity with data curation for training foundation models.

9. Understanding of drug discovery processes and related data requirements.

10. Excellent documentation and communication skills for clear reporting and collaboration.

Additional Information

Contract Type: Full-Time
Location: Paris
Possible full remote

Apply Now