We support common formats from the next-generation sequencing pipeline: FASTQ raw data, BAM/CRAM alignments, and VCF variants. Methylation data and RNA-Seq expression profiles can also be imported. The platform automatically normalizes inputs, allowing you to directly compare datasets from different sequencing devices.

Our AI models evaluate each variant based on frequency data, conservation patterns, and functional annotations. The result is a classification according to ACMG criteria with a traceable rationale. You can always see which features contributed to the classification and manually adjust the assessment.

Yes, you can store both public reference genomes and your own assemblies. The platform indexes your reference upon upload and uses it for all subsequent analyses. This is particularly useful when working with non-human organisms or specialized cell lines.

All data is encrypted during transmission and storage. You work in an isolated project environment with granular access rights that you define per team member. Pseudonymization is enabled by default, and you can specify how long datasets are retained.

Through our REST API, you can connect the platform to your existing workflow tools such as Snakemake or Nextflow. We provide client libraries for Python and R. This preserves your existing infrastructure while using our analysis functions as additional modules.

For institutes, we offer a technical contact who assists with setting up and optimizing your analysis workflows. This includes training for your team and regular updates on new algorithms. We also provide direct support for data migration or integration with your LIMS.