Pathformer: a biological pathway informed transformer for disease diagnosis and prognosis using multi-omics data
Open Access
- 1 May 2024
- journal article
- research article
- Published by Oxford University Press (OUP) in Bioinformatics
- Vol. 40 (5)
Abstract
Motivation: Multi-omics data provide a comprehensive view of gene regulation at multiple levels, which is helpful in achieving accurate diagnosis of complex diseases like cancer. However, conventional integration methods rarely utilize prior biological knowledge and lack interpretability. Results: To integrate various multi-omics data of tissue and liquid biopsies for disease diagnosis and prognosis, we developed a biological pathway informed Transformer, Pathformer. It embeds multi-omics input with a compacted multi-modal vector and a pathway-based sparse neural network. Pathformer also leverages criss-cross attention mechanism to capture the crosstalk between different pathways and modalities. We first benchmarked Pathformer with 18 comparable methods on multiple cancer datasets, where Pathformer outperformed all the other methods, with an average improvement of 6.3%–14.7% in F1 score for cancer survival prediction, 5.1%–12% for cancer stage prediction, and 8.1%–13.6% for cancer drug response prediction. Subsequently, for cancer prognosis prediction based on tissue multi-omics data, we used a case study to demonstrate the biological interpretability of Pathformer by identifying key pathways and their biological crosstalk. Then, for cancer early diagnosis based on liquid biopsy data, we used plasma and platelet datasets to demonstrate Pathformer’s potential of clinical applications in cancer screening. Moreover, we revealed deregulation of interesting pathways (e.g. scavenger receptor pathway) and their crosstalk in cancer patients’ blood, providing potential candidate targets for cancer microenvironment study. Availability and implementation: Pathformer is implemented and freely available at https://github.com/lulab/Pathformer.Keywords
Funding Information
- National Natural Science Foundation of China (32170671, 82341101, 82371855)
- Tsinghua University Guoqiang Institute (2021GQG1020)
This publication has 43 references indexed in Scilit:
- The Cancer Genome Atlas Pan-Cancer analysis projectNature Genetics, 2013
- Modulation of Natural Killer Cell Anti-Tumor Reactivity by PlateletsJournal of Innate Immunity, 2011
- Reactome: a database of reactions, pathways and biological processesNucleic Acids Research, 2010
- PID: the Pathway Interaction DatabaseNucleic Acids Research, 2008
- A global pathway crosstalk networkBioinformatics, 2008
- A hidden oncogenic positive feedback loop caused by crosstalk between Wnt and ERK PathwaysOncogene, 2007
- Stabilin-1, a homeostatic scavenger receptor with multiple functionsJournal of Cellular and Molecular Medicine, 2006
- Colon Cancer Survival Rates With the New American Joint Committee on Cancer Sixth Edition StagingJNCI: Journal of the National Cancer Institute, 2004
- KEGG: Kyoto Encyclopedia of Genes and GenomesNucleic Acids Research, 2000
- DAP12: a key accessory protein for relaying signals by Natural Killer cell receptorsThe International Journal of Biochemistry & Cell Biology, 1999