Dexter Pratt

Although genetic sequencing is routine in cancer care, translating a tumor’s complex mutation profile into actionable treatment decisions remains a central challenge. MutationProjector is pretrained on a large corpus of genomic alterations across more than 30,000 tumors, integrated with extensive molecular knowledge. The resulting projection reveals a tumor’s altered molecular pathways, facilitating model interpretation, and it accurately reconstructs held-out mutations, demonstrating model generalization. When applied to predict immunotherapy or chemotherapy resistance across multiple cancer types and cohorts, MutationProjector achieves or exceeds state-of-the-art performance in all contexts. It identifies unexpected biomarkers, including KMT2D mutation in immunotherapy sensitivity and joint alteration of SMARCA4 and STK11 in immunotherapy resistance. These results establish a unifying framework for connecting tumor genotypes to biological mechanisms and therapeutic outcomes. Significance:This work describes MutationProjector, a tumor genomic foundation model pretrained on more than 30,000 tumors. It maps mutations to biological states for diagnosis and treatment, achieving state-of-the-art performance in predicting therapy resistance and identifying biomarkers such as KMT2D (sensitivity) and SMARCA4/STK11 coalterations (resistance).

Figure S1 shows mutational heterogeneity of the pre-training dataset. Figure S2 shows detailed model architecture. Figure S3 shows inferring the status of tumor infiltrating lymphocytes. Figure S4 shows the analysis of latent representations. Figure S5 shows the prediction of drug response using clinical biomarkers. Figure S6 shows the prediction of metastasis-related tasks. Figure S7 shows the method for computing feature importance. Figure S8 shows the analysis of high model attention.

Table S1 contains the similarities of interaction pairs between networks. Table S2 contains the predictive performance in pretraining tasks. Table S3 contains the feature importance scores for anti-cancer drug response tasks. Table S4 contains the gene alteration frequencies in predicted responders and non-responders in immunotherapy treated lung cancer patients. Table S5 contains gene co-alteration frequencies. Table S6 contains number of patients with tumor infiltrating lymphocyte status information. Table S7 contains the prediction performance of anti-cancer drug response tasks.

Systematic mapping of protein-protein interaction (PPI) networks and determining how causal mutations rewire them in autism spectrum disorder (ASD) provide a powerful framework for uncovering disease mechanisms and therapeutic opportunities. Using affinity purification–mass spectrometry, we systematically mapped PPIs for 100 high-confidence ASD genes, uncovering more than 1800 interactions. By assessing the impact of pathogenic missense mutations, leveraging AlphaFold, and validating key findings in human-derived model systems, we identified marked convergence onto shared protein complexes in the wild-type state and convergent PPI rewiring driven by independent mutations. For example, distinct patient-derived variants in FOXP1 disrupt its interactions with FOXP4, leading to changes in cortical neurogenesis and neural activity in brain organoids. Overall, these findings link genetic variation to protein networks and convergent neurodevelopmental dysfunction in ASD.

While genetic sequencing is routine in cancer care, translating a tumor’s complex mutation profile into actionable treatment decisions remains a central challenge. MutationProjector is pre-trained from a large corpus of genomic alterations across 30,000+ tumors, integrated with extensive molecular knowledge. The resulting projection reveals a tumor’s altered molecular pathways, facilitating model interpretation, and it accurately reconstructs held-out mutations, demonstrating model generalization. When applied to predict immunotherapy or chemotherapy resistance across multiple cancer types and cohorts, MutationProjector achieves or exceeds state-of-the-art performance in all contexts. It identifies unexpected biomarkers, including KMT2D mutation in immunotherapy sensitivity and joint alteration of SMARCA4 and STK11 in immunotherapy resistance. These results establish a unifying framework for connecting tumor genotypes to biological mechanisms and therapeutic outcomes.

Motivation: Knowledge graphs (KGs) are powerful tools for structuring and analyzing biological information due to their ability to represent data and improve queries across heterogeneous datasets. However, constructing KGs from unstructured literature remains challenging due to the cost and expertise required for manual curation. Prior works have explored text-mining techniques to automate this process, but have limitations that impact their ability to capture complex relationships fully. Traditional text-mining methods struggle with understanding context across sentences. Additionally, these methods lack expert-level background knowledge, making it difficult to infer relationships that require awareness of concepts indirectly described in the text. Large Language Models (LLMs) present an opportunity to overcome these challenges. LLMs are trained on diverse literature, equipping them with contextual knowledge that enables more accurate information extraction. Results: We present textToKnowledgeGraph, an artificial intelligence tool using LLMs to extract interactions from individual publications directly in Biological Expression Language (BEL). BEL was chosen for its compact, detailed representation of biological relationships, enabling structured, computationally accessible encoding. This work makes several contributions. (i) Development of the open-source Python textToKnowledgeGraph package (pypi.org/project/texttoknowledgegraph) for BEL extraction from scientific articles, usable from the command line and within other projects, (ii) an interactive application within Cytoscape Web to simplify extraction and exploration, (iii) a dataset of extractions that have been both computationally and manually reviewed to support future fine-tuning efforts. Availability and implementation: https://github.com/ndexbio/llm-text-to-knowledge-graph.

Motivation: Knowledge graphs (KGs) are powerful tools for structuring and analyzing biological information due to their ability to represent data and improve queries across heterogeneous datasets. However, constructing KGs from unstructured literature remains challenging due to the cost and expertise required for manual curation. Prior works have explored text-mining techniques to automate this process, but have limitations that impact their ability to capture complex relationships fully. Traditional text-mining methods struggle with understanding context across sentences. Additionally, these methods lack expert-level background knowledge, making it difficult to infer relationships that require awareness of concepts indirectly described in the text. Large Language Models (LLMs) present an opportunity to overcome these challenges. LLMs are trained on diverse literature, equipping them with contextual knowledge that enables more accurate extraction of information. Results: We present textToKnowledgeGraph, an artificial intelligence tool using LLMs to extract interactions from individual publications directly in Biological Expression Language (BEL). BEL was chosen for its compact and detailed representation of biological relationships, allowing for structured and computationally accessible encoding. This work makes several contributions. 1. Development of the open-source Python textToKnowledgeGraph package ( pypi.org/project/texttoknowledgegraph ) for BEL extraction from scientific articles, usable from the command line and within other projects, 2. An interactive application within Cytoscape Web to simplify extraction and exploration, 3. A dataset of extractions that have been both computationally and manually reviewed to support future fine-tuning efforts. Availability: https://github.com/ndexbio/llm-text-to-knowledge-graph

Digitized healthcare data, high-throughput profiling technologies, and data repositories have facilitated the emergence of a new era of cancer research. Each data stream requires specialized analysis methods for interpretation. The data-driven era of cancer research requires the development, enhancement, and sustainment of informatics technology software infrastructure, including fundamental methodology development in artificial intelligence and data science. We review current and emerging informatics technology developments for cancer research and discovery, spanning molecular and cellular characterizations, image analysis, informatics, and therapeutics. Summarizing the diverse methods and applications of informatics throughout cancer research identifies themes and emerging areas for the next generation of cancer research. This article is part of a special series: Driving Cancer Discoveries with Computational Research, Data Science, and Machine Learning/AI.

Human cells consist of a complex hierarchy of components, many of which remain unexplored^1,2. Here we construct a global map of human subcellular architecture through joint measurement of biophysical interactions and immunofluorescence images for over 5,100 proteins in U2OS osteosarcoma cells. Self-supervised multimodal data integration resolves 275 molecular assemblies spanning the range of 10⁻⁸ to 10⁻⁵ m, which we validate systematically using whole-cell size-exclusion chromatography and annotate using large language models³. We explore key applications in structural biology, yielding structures for 111 heterodimeric complexes and an expanded Rag–Ragulator assembly. The map assigns unexpected functions to 975 proteins, including roles for C18orf21 in RNA processing and DPP9 in interferon signalling, and identifies assemblies with multiple localizations or cell type specificity. It decodes paediatric cancer genomes⁴, identifying 21 recurrently mutated assemblies and implicating 102 validated new cancer proteins. The associated Cell Visualization Portal and Mapping Toolkit provide a reference platform for structural and functional cell biology.