Senior Bioinformatics Scientist

Job Title: Senior Bioinformatics Scientist III Location: Cambridge, MA 02141 100% onsite Duration: 2 Years Contract Shift: Monday Thru Friday (8 AM to 5 PM) - 40 Hours/Week Position Summary: The Precision Genetics group within the Data and Genome Sciences Department is seeking a skilled Contractor to join our Computational Precision Genetics team. We are looking for a data scientist who combines deep expertise in human genetic data analysis with strong machine learning capabilities and hands-on experience integrating multi-omics data, to support our target identification, patient stratification, and biomarker discovery efforts. Key Responsibilities: Data Ingestion: Query and harmonize external resources to acquire relevant genetic, genomic, and multi-omics datasets (e.g., dbSNP, 1000 Genomes Project, gnomAD, GTEx, Ensembl, Open Targets, ClinVar, GWAS Catalog, UK Biobank, Gene Expression Omnibus). Genetic/Genomic Data Analysis: Perform quality control (QC) and analysis of genetic/genomic data, including genotype imputation from array data, variant calling and annotation using state-of-the-art methods (e.g., IMPUTE, Minimac, Eagle, BEAGLE, GATK, bcftools, samtools, ANNOVAR, VEP). Statistical Genetics: Conduct genetic association analyses at scale, including GWAS/PheWAS, rare-variant burden and collapsing tests, fine-mapping, colocalization, polygenic scores, and Mendelian randomization (e.g., PLINK, REGENIE, SAIGE, GCTA, SuSiE, coloc, LDSC). QTL Analysis: Conduct QTL analysis to identify genetic loci associated with quantitative and molecular traits, including eQTL, sQTL, and pQTL mapping, utilizing tools such as tensorQTL, FastQTL, PLINK, or R/qtl. Population Genetics Analysis: Analyze genetic variation across populations, including allele frequency estimation, linkage disequilibrium, relatedness, and ancestry/population structure analysis. Machine Learning: Develop, benchmark, and validate machine learning models on high-dimensional genetic and molecular data for tasks such as variant effect prediction, patient stratification, and biomarker or treatment-response prediction; apply rigorous cross-validation, control for batch and ancestry confounding, and use interpretability methods to translate models into testable biological hypotheses (e.g., scikit-learn, XGBoost, PyTorch, SHAP). Multi-Omics Data Integration: Integrate genetic datasets with other omics layers, including transcriptomic (bulk and single-cell RNA-seq), epigenomic, proteomic (e.g., OLINK, mass spectrometry), and spatial data, to provide comprehensive insights into gene function and disease biology (e.g., DESeq2, limma, Seurat, scanpy). Documentation and Reproducibility: Prepare detailed documentation of analysis methods and results in a timely manner, and deliver version-controlled, reproducible analysis workflows (e.g., Git, Nextflow, Snakemake). Required Qualifications: Ph.D. in Genetics, Genomics, Statistical Genetics, Computational Biology, or a related field. A proven track record of over 5 years in genetic data analysis. Strong understanding of statistical methods and genetic data analysis and integration (e.g., variant analysis, GWAS and QTL mapping, population genetics, genomic annotations). Demonstrated experience applying machine learning to high-dimensional biological data, including feature engineering, model selection, validation, and avoidance of overfitting and confounding. Hands-on experience integrating multi-omics data (e.g., transcriptomics, proteomics, epigenomics) with genetic data. Proficiency in R, Python, and Bash, with the ability to establish best practices for reproducible data analyses. Experience with high-performance computing (HPC) systems and AWS Cloud Computing (e.g., IAM, S3 buckets). A collaborative and self-motivated individual with a strong work ethic, capable of managing multiple objectives in a dynamic environment and adapting to changing priorities. Excellent written and verbal communication skills. Preferred Qualifications: Experience with real-world and large-scale biobank genetic data (e.g., UK Biobank, All of Us, FinnGen, electronic health record-linked cohorts). Experience with deep learning approaches for genomics, including sequence-based and variant-effect prediction models. Familiarity with single-cell and spatial transcriptomics analysis. Experience supporting drug target identification and validation, or biomarker discovery in a pharmaceutical or biotechnology setting. Familiarity with workflow managers (e.g., Nextflow, Snakemake) and containerization (e.g., Docker, Singularity). Proficient in human genetic/human genomic data analysis tools and techniques-e.g., variant analysis, population genetics, genomic annotations. Multi-Omics Data Integration Proficiency in R, Python, and Bash. High-performance computing (HPC) systems and AWS Cloud Computing (e.g., IAM, S3 buckets). #J-18808-Ljbffr Net2Source (N2S)