We are seeking a highly talented and motivated bioinformatics scientist to join our Predictive Sciences and Infrastructure team in the Research Data Sciences Group. The successful candidate will take a lead role in developing/applying machine learning and bioinformatics methods that integrate large-multi-modal datasets (scRNA-Seq, bulk RNA-seq, WES, CRISPR, pathology, etc) to derive quantitative biological insights. This individual will be responsible for developing and employing rigorous statistical modeling and bioinformatics methods, interpreting and integrating large scale datasets to enable research objectives across therapeutics areas of oncology, inflammation, fibrosis and virology. The successful candidate will have the ability to formulate scientific questions into coherent analytical efforts and communicate analysis results and scientific findings to project teams and across different research functions.
- Develop and implement quality assessment, statistical analysis and data visualization for multi-omics datasets (e.g., , RNA-Seq, single cell sequencing, WES, WGS etc)
- Develop novel predictive models using statistical techniques and machine learning for analysis of large omics and high dimensional data from internal, publicly available, commercial, and real-world datasets to enable target identification/assessment, drug combinations, understanding of MOA, disease mechanisms, etc.
- Collaborate with cross-functional teams to analyze and interpret complex large datasets and communicate findings and recommend follow-up actions in multiple settings (including: 1:1, seminars, group, and project meetings)
- Actively identify new opportunities/questions that advanced computational methods can address and develop/evaluate solutions both independently and collaboratively
- Develop data dashboards, visualizations and analytical tools to enable data analysis and exploration by the broader Gilead Research community
- Provide expertise and technical consultation for external collaborations/partnerships in academia and industry
Knowledge, Experience and Skills:
- Hands-on experience analyzing, interpreting, and integrating large-scale biological datasets, such as genomics, transcriptomics, epigenetics, proteomics, high throughput screening, and/or molecular pathology, etc is required
- Hands on experience in high performance computing (e.g., AWS) is required.
- Expertise in developing algorithms and applications for predictive modeling, data mining and/or visualization of large scale multi-dimensional omics datasets.
- Strong statistics knowledge, such as probability theory, statistical power, univariate and/or multi-variate analysis, unsupervised and supervised analysis, regression analysis, survival analysis, and/or deep learning, etc.
- In-depth knowledge of bioinformatics algorithms, genomic and proteomic technologies and high-throughput experimental techniques, e.g. next generation sequencing technologies, single cell technologies, and/or their applications.
- Demonstrated ability to collaborate with research scientists and cross-functional teams, and to manage multiple projects in a fast-paced working environment.
- Excellent oral/written communication skills and ability to present to senior management team.
- Demonstrated the ability to synthesize scientific questions into a coherent research effort and communicate scientific findings across different functional teams
- A proactive and self-motivated individual with a strong work ethic and scientific rigor, ability to work in a dynamic environment and able to manage multiple objectives in parallel and adapt to changing priorities
- A Ph.D. in statistics, mathematics, bioinformatics, genomics, computer science or related field with strong hands-on experience in Omics, machine learning, predictive modeling. Industry experience is preferred but not required.
- Proficient in statistical and scripting programming languages, such as R, Python, etc. is required
- Extensive experience with multi-omics data and large-scale biological datasets is required
- Experience with advanced knowledge of a broad range of statistical machine learning and predictive modeling techniques is required
- Strong scientific background and in-depth understanding of genomic and proteomic technologies and high-throughput experimental techniques is required
- Hands on experience with high performance parallel computing environments and cloud computing systems, data management systems, advanced statistical software, and/or visualization tools is required
- Excellent interpersonal and communication skills that foster collaboration and teamwork