The study of rare diseases uses next-generation sequencing (NGS) technology to detect causative mutations in the human genome. NGS is a new approach for biomedical research, useful for the genetic diagnosis in extremely heterogeneous conditions. Nevertheless, only few publications address the problem when pooled experiments are considered, and existing tools are often inaccurate. In this work we focus on rare diseases and we describe how data are generated by NGS. We present how data are organized in the pre-processing phase, how they are filtered and features constructed in the learning phase. We compare different computational procedures to identify and classify variants potentially related to rare diseases and we biologically validate the obtained results.
展开▼
