Track I Large-Scale Population Cohorts: Subtrack 5. Long-Read Multi-Omics (Long100K)(J28004)

Foundation Model

• Support reinforcement training of the Genos genomic foundation model, enhancing its disease prediction performance and mechanistic interpretation capability.
• Efficiently enable interpretation of variant pathogenic effects and discovery of disease–phenotype associations.
• Contribute to the development of a globally leading population-scale long-read pangenome and epigenome foundation model.

Vertical Applications

• 1.Predictive models and products for hematologic diseases, rare diseases, immune disorders, and other conditions.
• 2.Epigenomics-based models and products for biological age assessment, immune profiling, and disease risk evaluation.

Affiliated Branches

• Guangdong–Hong Kong–Macao Branch (Shenzhen)
• Hangzhou Branch (Hangzhou)
• Southwest Branch (Chongqing)
• Beijing Branch (Beijing)

(1) Preferred Background

Genomics, Epigenetics, Bioinformatics, Molecular Biology, or Computer Science.

(2) Core Technical Skills

Experience analyzing long-read sequencing data (PacBio/Nanopore); structural variant detection; epigenomic data processing; bioinformatics pipeline construction.

(3) Modeling Competency

Ability to integrate multi-omics data into predictive models; understanding of disease mechanism interpretation.

(4) Preferred Qualifications

Hands-on NGS data processing experience; familiarity with HPC environments; prior work in rare disease or immune disease research.

(5) Personal Traits

Mechanism-driven thinker, patient with complex biological data, and interested in bridging molecular biology with AI modeling.