Deep Learning for Biomarker Discovery in Cancer Genomes.

Background: Genomic data is essential for clinical decision-making in precision oncology. Bioinformatic algorithms are widely used to analyze next-generation sequencing (NGS) data, but they face two major challenges. First, these pipelines are highly complex, involving multiple steps and the integration of various tools.

Predictive value of tumor microenvironment on pathologic response to neoadjuvant chemotherapy in patients with undifferentiated pleomorphic sarcomas.

Undifferentiated pleomorphic sarcomas (UPS) represent a prevalent and aggressive subtype of soft tissue sarcomas (STS) in adults. Despite advancements in loco regional treatments, many patients with high grade STS, including UPS, develop metastatic disease. Neoadjuvant chemotherapy is a standard approach to mitigate this risk, but response variability necessitates refined patient selection strategies.

[Synthetic data in medicine: Generation, evaluation and limits].

Recent technological advances in data science hold great promise in medicine. Large-sized high-quality datasets are essential but often difficult to obtain due to privacy, cost, and practical challenges. Here, we discuss synthetic data's generation, evaluation, and regulation, highlighting its current applications and limits.

Cellular origin and clonal evolution of human dedifferentiated liposarcoma.

Dedifferentiated liposarcoma (DDLPS) is the most frequent high-grade soft tissue sarcoma subtype. It is characterized by a component of undifferentiated tumor cells coexisting with a component of well-differentiated adipocytic tumor cells. Both dedifferentiated (DD) and well-differentiated (WD) components exhibit MDM2 amplification, however their cellular origin remains elusive.