Patient-specific Biomolecular Instruction Tuning

• URL: http://arxiv.org/abs/2509.22853v1
• Date: Fri, 26 Sep 2025 19:05:32 GMT
• Title: Patient-specific Biomolecular Instruction Tuning
• Abstract summary: We introduce CPTAC-PROTSTRUCT, the first instruction tuning for molecular understanding of oncology.<n>We also propose KRONOS, a graph-LLM framework that learns patient-specific graph representations for enhanced clinical reasoning.
• Score: 4.331279001189675
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Proteomics data is essential to pathogenic understanding of a disease phenotype. In cancer, analysis of molecular signatures enables precision medicine through the identification of biological processes that drive individualized tumor progression, therapeutic resistance, and clinical heterogeneity. Recent advances in multimodal large language models (LLMs) have shown remarkable capacity to integrate and reason across heterogeneous data modalities. However, performing multi-modal language modeling for molecular understanding of patient-specific proteomics remains a significant challenge due to two barriers: (1) the lack of instruction-tuning datasets that enable clinical interpretation from proteomics data, and (2) the absence of language modeling architectures designed to capture the rich heterogeneity of molecular data. In this work, we introduce CPTAC-PROTSTRUCT, the first instruction tuning dataset for molecular understanding of oncology, comprising over 400k open-ended examples derived from individualized proteomic profiles curated from the largest national proteomics cancer study (CPTAC). Additionally, we propose KRONOS (Knowledge Representation of patient Omics Networks in Oncology via Structured tuning), a novel graph-LLM framework that leverages molecular interaction topology with proteomics to learn patient-specific graph representations for enhanced clinical reasoning. We show that KRONOS achieves competitive performance across benchmark clinical tasks, including molecular classification, temporal trajectory modeling, and tumor stage prediction from proteomics data. Ultimately, this approach empowers LLMs to understand patient-level pathogenesis, advancing precision medicine through more accurate diagnosis, prognosis, and treatment stratification.

Related papers

• Towards Reliable Stain Transfer: An Iterative Data-Model Co-Optimization Framework Based on Multimodal Expert-Guided Assessment [55.16957949238588]
  We propose DMCoStain, a novel Data-Model Co-optimization framework for Stain transfer.<n>It iteratively co-refines training data and model capability, improving staining accuracy and interpretability in both pathological and structural consistency.<n>To support MEGFS, we construct ImmunoInstruction, the first large-scale IPE instruction-following dataset with 150K VQA samples.
  arXiv  Detail & Related papers  (2026-07-28T07:54:43Z)
• Data-Efficient Multimodal Alignment for Histopathology-based Molecular Prediction [3.229566379058554]
  We show that training a lightweight alignment module atop frozen histopathology and RNA-Seq foundation models enables open-vocabulary molecular prompting.<n>We achieve a 25-fold improvement in retrieval over baseline methods.<n>We validate clinical utility on the POSEIDON clinical trial.
  arXiv  Detail & Related papers  (2026-06-29T08:24:53Z)
• Spatial Transcriptomics-Guided Alignment Enhances Molecular Profiling in Pathology Foundation Model [43.24445461533517]
  We present a spatial transcriptomics-guided alignment framework for Molecular Profiling (STAMP)<n>STAMP applies a pathway-informed alignment strategy that aggregates transcriptomic data into biologically functional pathways.<n>The clinical utility of these augmented representations was validated through a multi-tier evaluation framework.
  arXiv  Detail & Related papers  (2026-05-29T16:41:14Z)
• Atherosclerosis through Hierarchical Explainable Neural Network Analysis [5.481707651804491]
  We develop a hierarchical graph neural network framework to leverage two characteristic modalities of a patient: clinical features within the context of the cohort, and molecular data unique to individual patients.<n>ATHENA enables mechanistically-informed patient subtype discovery through explainable AI (XAI)-driven subnetwork clustering.
  arXiv  Detail & Related papers  (2025-07-10T01:51:53Z)
• Genome-Anchored Foundation Model Embeddings Improve Molecular Prediction from Histology Images [22.274588547000352]
  PathLUPI uses transcriptomic privileged information during training to extract genome-anchored histological embeddings.<n>It achieves AUC $geq$ 0.80 in 14 of the biomarker prediction and molecular subtyping tasks and C-index $geq$ 0.70 in survival cohorts of 5 major cancer types.
  arXiv  Detail & Related papers  (2025-06-24T14:48:12Z)
• Interpretable Graph Kolmogorov-Arnold Networks for Multi-Cancer Classification and Biomarker Identification using Multi-Omics Data [36.92842246372894]
  Multi-Omics Graph Kolmogorov-Arnold Network (MOGKAN) is a deep learning framework that utilizes messenger-RNA, micro-RNA sequences, and DNA methylation samples.<n>By integrating multi-omics data with graph-based deep learning, our proposed approach demonstrates robust predictive performance and interpretability.
  arXiv  Detail & Related papers  (2025-03-29T02:14:05Z)
• MIRROR: Multi-Modal Pathological Self-Supervised Representation Learning via Modality Alignment and Retention [57.044719143401664]
  Histopathology and transcriptomics are fundamental modalities in oncology, encapsulating the morphological and molecular aspects of the disease.<n>We present MIRROR, a novel multi-modal representation learning method designed to foster both modality alignment and retention.<n>Extensive evaluations on TCGA cohorts for cancer subtyping and survival analysis highlight MIRROR's superior performance.
  arXiv  Detail & Related papers  (2025-03-01T07:02:30Z)
• Explainable AI Methods for Multi-Omics Analysis: A Survey [3.885941688264509]
  Multi-omics refers to the integrative analysis of data derived from multiple 'omes' Deep learning methods are increasingly utilized to integrate multi-omics data, offering insights into molecular interactions and enhancing research into complex diseases. These models, with their numerous interconnected layers and nonlinear relationships, often function as black boxes, lacking transparency in decision-making processes. This review explores how xAI can improve the interpretability of deep learning models in multi-omics research, highlighting its potential to provide clinicians with clear insights.
  arXiv  Detail & Related papers  (2024-10-15T05:01:17Z)
• Clustering of Disease Trajectories with Explainable Machine Learning: A Case Study on Postoperative Delirium Phenotypes [13.135589459700865]
  We propose an approach that combines supervised machine learning for personalized POD risk prediction with unsupervised clustering techniques to uncover potential POD phenotypes. We show that clustering patients in the SHAP feature importance space successfully recovers the true underlying phenotypes, outperforming clustering in the raw feature space.
  arXiv  Detail & Related papers  (2024-05-06T10:05:46Z)
• Bi-level Contrastive Learning for Knowledge-Enhanced Molecule Representations [68.32093648671496]
  We introduce GODE, which accounts for the dual-level structure inherent in molecules.<n> Molecules possess an intrinsic graph structure and simultaneously function as nodes within a broader molecular knowledge graph.<n>By pre-training two GNNs on different graph structures, GODE effectively fuses molecular structures with their corresponding knowledge graph substructures.
  arXiv  Detail & Related papers  (2023-06-02T15:49:45Z)
• Generating counterfactual explanations of tumor spatial proteomes to discover effective strategies for enhancing immune infiltration [44.99833362998488]
  The tumor microenvironment (TME) significantly impacts cancer prognosis due to its immune composition. Here, we formulate T-cell infiltration prediction as a self-supervised machine learning problem. We apply our framework to melanoma, colorectal cancer liver metastases, and breast tumor data, discovering perturbations predicted to support T-cell infiltration.
  arXiv  Detail & Related papers  (2022-11-08T05:46:02Z)
• G-MIND: An End-to-End Multimodal Imaging-Genetics Framework for Biomarker Identification and Disease Classification [49.53651166356737]
  We propose a novel deep neural network architecture to integrate imaging and genetics data, as guided by diagnosis, that provides interpretable biomarkers. We have evaluated our model on a population study of schizophrenia that includes two functional MRI (fMRI) paradigms and Single Nucleotide Polymorphism (SNP) data.
  arXiv  Detail & Related papers  (2021-01-27T19:28:04Z)
• MIA-Prognosis: A Deep Learning Framework to Predict Therapy Response [58.0291320452122]
  This paper aims at a unified deep learning approach to predict patient prognosis and therapy response. We formalize the prognosis modeling as a multi-modal asynchronous time series classification task. Our predictive model could further stratify low-risk and high-risk patients in terms of long-term survival.
  arXiv  Detail & Related papers  (2020-10-08T15:30:17Z)
• Confidence-guided Lesion Mask-based Simultaneous Synthesis of Anatomic and Molecular MR Images in Patients with Post-treatment Malignant Gliomas [65.64363834322333]
  Confidence Guided SAMR (CG-SAMR) synthesizes data from lesion information to multi-modal anatomic sequences. module guides the synthesis based on confidence measure about the intermediate results. experiments on real clinical data demonstrate that the proposed model can perform better than the state-of-theart synthesis methods.
  arXiv  Detail & Related papers  (2020-08-06T20:20:22Z)
• Lesion Mask-based Simultaneous Synthesis of Anatomic and MolecularMR Images using a GAN [59.60954255038335]
  The proposed framework consists of a stretch-out up-sampling module, a brain atlas encoder, a segmentation consistency module, and multi-scale label-wise discriminators. Experiments on real clinical data demonstrate that the proposed model can perform significantly better than the state-of-the-art synthesis methods.
  arXiv  Detail & Related papers  (2020-06-26T02:50:09Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.