BPformer - Identify the Primary Site of Cancer

WELCOME TO BPformer

Identify The Primary Site Of Cancer

BPformer: Tracing the Origins of Unknown Tumors Using Biological Pathway-based Transformer Model

Read More

What is CUP?

Cancer metastasis, responsible for nearly 90% of cancer-related deaths, is considered the primary driver of cancer mortality. Cancer metastasis occurs when late-stage tumor cells develop the ability to detach from the primary tumor tissue, travel through the circulatory and lymphatic systems, invade distant tissues, and proliferate at new sites. Nonetheless, metastatic tumors manifest in 3-5% of cancer patients for which conventional diagnostics cannot identify the primary tumor sites, resulting in a diagnosis of Cancer of Unknown Primary (CUP). CUP denotes metastatic malignancies of undetermined primary anatomic origin, leading to notably adverse clinical prognoses.

OUR SERVICES

DATASETS

The dataset consists of transcriptomic and DNA methylation data from primary and metastatic tumor samples.

ANALYSIS

BPformer provides a comprehensive landscape for cancer tracking using multiple omics data, including transcriptome data and DNA methylation data.

TOOLS

The codes for BPformer and other methods previously used to trace the origin of cancers.

32 Cancer Types

The study included 32 cancer types, including primary and metastatic samples.

BPformer

Cancer of unknown primary (CUP) represents metastatic cancer where the primary site remains unidentified despite standard diagnostic procedures. To determine the tumor origin in such cases, we developed BPformer, a deep learning method integrating the transformer model with prior knowledge of biological pathways. Trained on transcriptomes from 10,410 primary tumors across 32 cancer types, BPformer achieved remarkable accuracy rates of 94%, 92%, and 89% in primary tumors and primary and metastatic sites of metastatic tumors, respectively, surpassing existing methods. Additionally, BPformer was validated in a retrospective study, demonstrating consistency with tumor sites diagnosed through immunohistochemistry and histopathology. Furthermore, BPformer was able to rank pathways based on their contribution to tumor origin identification, which helped to classify oncogenic signaling pathways into those that are highly conservative among different cancers versus those that are highly variable depending on their origins.

Try Now

Read Code

PathMethy

Despite advanced diagnostics, 3-5% of cases remain classified as cancer of unknown primary (CUP). DNA methylation, an important epigenetic feature, is essential for determining the origin of metastatic tumors. We presented PathMethy, a novel Transformer model integrated with functional categories and crosstalk of pathways, to accurately tracing the origin of tumors in CUPs based on DNA methylation. PathMethy outperformed seven competing methods in F1-score across nine cancer datasets and predicted accurately the molecular subtypes within 9 primary tumor types. It not only excelled at tracing the origins of both primary and metastatic tumors, but also demonstrated a high degree of agreement with previously diagnosed sites in cases of CUP. PathMethy provided biological insights by highlighting key pathways, functional categories and their interactions. Using functional categories of pathways, we gained a global understanding of biological processes.

Try Now

Read Code