Biology subjects

Rajesh, C.

Publications and source records attributed to Rajesh, C..

3 recordsLinked to original sources

bioRxiv2026

Overcoming Daraxonrasib Resistance: Allele-Specific Mechanisms Guide Salvage Therapy in Pancreatic Cancer

Clinical-grade RAS inhibitors raise an unresolved question as to whether KRAS-alleles impose constraints on adaptive resistance that can be exploited therapeutically. Using daraxonrasib (RMC-6236), a multi-selective RAS(ON) inhibitor, we compared resistance mechanisms between KRASG12D and KRASG12R, alleles with fundamentally different RAS network dynamics. Daraxonrasib inhibited KRASMUT primarily through steric occlusion of effector binding, while engaging RASWT only modestly ([~]20%). KRASG12R is marked by its inability to transactivate RASWT, and it was observed that daraxonrasib resistant KRASG12R PDAC cells utilize EGFR/RASWT-GTP signaling as the dominant adaptive route. In contrast, KRASG12D resistance arose through retained KRASG12D-GTP signaling, with a decrease of cyclophilin A (CypA) protein, the binding partner required for daraxonrasib activity. The shift from KRASG12R dependence to the EGFR/RASWT conferred sensitivity to trametinib. We confirmed this clinically: a KRASG12R PDAC patient who progressed after 10 months on daraxonrasib showed intratumoral EGFR/RASWT activation, and rapid 3D-bioprinted patient-derived toroid modeling predicted sensitivity to trametinib-based combination therapy. Given the aggressive disease trajectory and lack of response to the two immediately preceding lines of therapy, sixth-line trametinib-based combination therapy achieved approximately 5 months of disease control. This patient ultimately achieved 40 months of overall survival, far exceeding the 8-12 month median for metastatic PDAC. Collectively, these data establish a framework in which allele-specific RAS network topology dictates the adaptive resistance landscape, enabling rational selection of targeted therapies with meaningful clinical benefit in metastatic PDAC. STATEMENT OF SIGNIFICANCEDaraxonrasib resistance mechanisms have allele-specific routes: CypA becomes downregulated in KRASG12D and reliance on EGFR/RASWT in KRASG12R. Rapid patient-derived toroids identified sixth-line targeted therapy strategies with an overall survival of 40 months.

cancer biology↗

bioRxiv2025

A foundational model for joint sequence-function multi-species modeling at scale for long-range genomic prediction

Genomic prediction and design require models that integrate local sequence features with long-range regulatory dependencies spanning hundreds of kilobases to megabases. Existing approaches have made substantial progress along complementary axes: supervised sequence-to-function models achieve high accuracy for specific assays and organisms, self-supervised genomic foundation models learn transferable representations from large-scale sequence data, and conditional generative models enable principled sequence design guided by functional objectives. However, these strengths are typically realized in isolation--across distinct model classes, architectures, and training regimes--limiting the ability to combine long-context, base-resolution prediction, functional modeling, and controllable generation within a single efficient framework that generalizes across organisms and modalities. Here we introduce Nucleotide Transformer v3 (NTv3), a multi-species foundation model that unifies representation learning, functional-track and genome-annotation prediction, and controllable sequence generation within a common backbone. NTv3 uses a U-Net-like architecture to enable single-base tokenization and efficient modeling of contexts up to 1 Mb. We pre-train NTv3 on 9 trillion base pairs from OpenGenome2 using base-resolution masked language modeling, followed by post-training with a joint objective that integrates continued self-supervision with supervised learning on [~]16,000 functional tracks and annotation labels from 24 animal and plant species. After post-training, NTv3 achieves state-of-the-art accuracy for functional-track prediction and genome annotation across species, outperforming leading sequence-to-function and foundation-model baselines on established benchmarks and on the new NO_SCPLOWTVC_SCPLOW 3 BO_SCPLOWENCHMARKC_SCPLOW, a controlled downstream fine-tuning suite in a standardized 32 kb input / base-resolution output setting. We further show that NTv3 consolidates a shared regulatory grammar across tasks, enabling coherent long-range genome-to-function inference and variant-associated remodeling. Finally, we fine-tune NTv3 into a controllable generative model via masked diffusion language modeling and use it to design enhancer sequences with specified activity levels and promoter selectivity. We validate these designs experimentally, showing that generated enhancers recapitulate the intended activity stratification and achieve the desired promoter-specific activation in cellulo. We release the NTv3 model family together with code and practical cookbooks for long-context training, multispecies post-training, fine-tuning, interpretation, and sequence design.

genomics↗

bioRxiv2024

Interpretably deep learning amyloid nucleation by massive experimental quantification of random sequences

Protein aggregation is a pathological hallmark of more than fifty human diseases and a major problem for biotechnology. Methods have been proposed to predict aggregation from sequence, but these have been trained and evaluated on small and biased experimental datasets. Here we directly address this data shortage by experimentally quantifying the amyloid nucleation of >100,000 protein sequences. This unprecedented dataset reveals the limited performance of existing computational methods and allows us to train CANYA, a convolution-attention hybrid neural network that accurately predicts amyloid nucleation from sequence. We adapt genomic neural network interpretability analyses to reveal CANYAs decision-making process and learned grammar. Our results illustrate the power of massive experimental analysis of random sequence-spaces and provide an interpretable and robust neural network model to predict amyloid nucleation.

genomics↗