Call for papers:

Two tracks are available: featuring papers for workshop proceedings and posters from recent publications in top conferences like CVPR, ICCV, ECCV, NeurIPS, ICLR, and AAAI, as well as prominent journals such as Nature, Science, and Nature Methods.

The papers must follow the CVPR paper template.

The submission must go through: openreview

Dates

Paper Submission Deadline: March 17 ‘25 07:59 AM UTC

Notification of Acceptance: April 1 ‘25 07:59 AM UTC

Camera-Ready Deadline: April 7 ‘25 07:59 AM UTC

Final workshop program: May 9 ‘25 07:59 AM UTC

Workshop Date: June 12

Topics

• Spatial Transcriptomics for Drug Discovery
  • Computational methods for analyzing spatially resolved gene expression data.
  • Integration of transcriptomic data with high-dimensional image-based analysis.
  • Machine learning approaches for spatial transcriptomics in cellular microenvironments.
• Cell Painting and Morphological Profiling
  • High-content screening using Cell Painting images for phenotypic drug discovery.
  • Foundational models for analyzing morphological features in biological datasets.
  • Multi-modal integration of Cell Painting data with omics, molecular, and genomic data.
• Optical Pooled Screening and Functional Genomics
  • Computer vision techniques for high-throughput optical pooled screens.
  • Automated analysis of CRISPR/Cas9 and RNAi screening images for functional genomics.
  • AI-driven identification of gene-drug interactions in large-scale screens.
• AI for Multi-modal Biomedical Imaging
  • Fusion of diverse imaging modalities, including histology, microscopy, and genomics.
  • Representation learning is used to combine biological data from various imaging platforms.
  • Text-image and conversational AI for imaging modalities in drug discovery context.
• Explainable AI and Predictive Modeling in Drug Discovery
  • Development of interpretable models for predicting drug efficacy and toxicity.
  • AI methods for uncovering biomarkers and therapeutic targets from imaging data.
  • Model explainability and transparency in biomedical image-based drug discovery.
• Sparse Labelled Data in Drug Discovery Domain
  • Data Augmentation and Synthetic Data for Drug Discovery
  • Leveraging Foundational Model and Parameter-Efficient Finetuning Techniques to deal with sparse data
  • Synthetic biology and generative models for simulating disease and treatment responses.
• AI-driven Drug Discovery Pipelines
  • Integration of AI into end-to-end drug discovery workflows.
  • Real-time analysis of drug screening experiments using AI.
  • Challenges and future directions for applying AI in pharmaceutical development.
• Imaging Biomarkers Discovery:
  • AI-driven discovery of disease-relevant imaging biomarkers bridging the gap between diagnostics, early discovery, translational sciences, and clinical endpoints
  • Imaging Biomarkers facilitating targeted therapies such as dose painting in radiotherapy
  • Approaches combining structural and functional imaging modalities across species
• Safe and Trustworthy Computer Vision for Drug Discovery and Clinics:
  • Ethical Consideration when using data from the clinics and animals in in-vivo studies
  • Privacy when using synthetic or patient data
  • Regulatory frameworks in clinical models

back