Postdoc: Metagenomic Protein Families & AI Classification

European Molecular Biology Laboratory (EMBL); Hinxton; Hybrid; GBP 49,000 - 66,000; Full time

Benefits offered by this job

Hybrid working patterns

Private medical insurance

30 days annual leave

Relocation support for international/非

Job summary

EMBL invites applications for a postdoctoral researcher in Hinxton to co-develop scalable strategies for classifying MGnify protein databases and exploring structure-based protein families. You will work with a dynamic team on clustering, functional labelling, and expanding taxonomic information using diverse data sources.

The role involves AI-driven methods, data analysis at scale, and collaboration within an international team.

Qualifications

• PhD in the biological sciences or related field with demonstrated research excellence.
• Strong background in microbiology and/or metagenomics.
• Experience with large datasets and data analysis workflows.
• Proficient Python programming with well-documented code.
• Experience with UNIX/Linux, HPC or cloud environments.

Responsibilities

• Co-develop strategies to classify MGnify protein databases into families based on structure.
• Perform clustering, functional labelling and develop selection criteria for structures.
• Update MGnify with taxonomic information and expand biome data.
• Investigate correlations between biome, taxonomy and protein family distributions.
• Identify bacteriophage-encoded anti-defence systems and propose modes of action.
• Apply AI-based approaches to methodology and large-scale data analysis.

Skills

Python

UNIX/Linux

HPC/Cloud environments

English fluency

Collaboration

Data analysis

Education

PhD in biological sciences

Tools

Nextflow

Snakemake

Git

Relational databases

Job description

EMBL invites applications for a postdoctoral researcher in Hinxton to co-develop scalable strategies for classifying MGnify protein databases and exploring structure-based protein families. You will work with a dynamic team on clustering, functional labelling, and expanding taxonomic information using diverse data sources.

The role involves AI-driven methods, data analysis at scale, and collaboration within an international team.