Workshop Title
Representation Learning and Pattern Discovery for Bioinformatics and Biomedicine (RLPD-Bio)
Introduction to Workshop
We would like to propose a new workshop, Representation Learning and Pattern Discovery for Bioinformatics and Biomedicine (RLPD-Bio), at IEEE BIBM 2026.
Recent advances in high-throughput biotechnologies and biomedical data acquisition have enabled the generation of massive, heterogeneous datasets spanning genomics, transcriptomics, proteomics, metabolomics, single-cell and spatial omics, biomedical imaging, biological networks, and clinical data. These complex datasets offer unprecedented opportunities to understand biological systems and human diseases, while also posing major challenges for computational modeling, knowledge extraction, and biological interpretation.
Representation learning has emerged as a powerful paradigm for transforming high-dimensional, noisy, and multimodal biological data into informative low-dimensional embeddings. These learned representations can support a wide range of downstream tasks, including clustering, classification, subtype identification, biomarker discovery, interaction modeling, disease prediction, and therapeutic response analysis. At the same time, pattern discovery plays a critical role in uncovering hidden structures, biological modules, spatial organizations, dynamic trajectories, and disease-associated signals in complex datasets.
As deep learning, graph learning, multimodal learning, self-supervised learning, foundation models, and large language models rapidly advance, representation learning and pattern discovery are becoming increasingly central to bioinformatics and biomedicine. These advances are driving new computational methods for integrating heterogeneous data, capturing structural and semantic dependencies, and generating interpretable biological insights.
The proposed workshop aims to provide a vibrant forum for researchers at the intersection of machine learning, bioinformatics, and biomedicine to present recent advances, share novel ideas, and discuss emerging challenges and opportunities in representation learning and pattern discovery for biological and biomedical data.
Research Topics Included in the Workshop
Papers are welcome across multiple areas, including representation learning for biological and biomedical data, pattern discovery in complex omics and clinical datasets, newly developed machine learning methods for bioinformatics and biomedicine, and computational frameworks for integrative and interpretable biomedical data analysis. Papers are solicited on, but not limited to, the following topics:
- Representation learning for disease subtyping and prognosis prediction
- Statistical representation learning for biological and biomedical data
- Pattern discovery in high-dimensional, sparse biological data
- Deep learning methods for omics data analysis
- Self-supervised and contrastive learning for biomedical data
- Graph representation learning for biological networks
- Multi-omics data integration and multimodal representation learning
- Foundation models for bioinformatics and biomedicine
- Large language models for biomedical data analysis
- Interpretable learning for biomarker discovery
- Spatial pattern discovery in tissues and tumor microenvironments
- Temporal and trajectory pattern discovery in biological systems
- Learning biological representations from biomedical images
- Network-based learning and biological interaction modeling
- Knowledge-guided and biologically informed representation learning
- Transferable representation learning for biomedical applications
Workshop Style
Hybrid
Important Dates
- Sept 27, 2026 Due date for full workshop papers submission
- Oct 18, 2026 Notification of paper acceptance to authors
- Nov 8, 2026 Camera-ready of accepted papers
- Dec 1–4, 2026 Workshops
Program Chairs or Co-chairs
Program Committee Members
Invited Keynote Speakers
TBD