Biology subjects

Koes, D. R.

Publications and source records attributed to Koes, D. R..

10 recordsLinked to original sources

bioRxiv2026

A Cationic Amphiphilic Drug (CAD) Defense System in the Nematode Caenorhabditis elegans

Cationic Amphiphilic Drugs (CADs) severely disrupt lysosomal function, which leads to a cellular pathology characterized by excess phospholipids called phospholipidosis. Through a forward genetic screen and mining of published datasets, we discovered that CADs induce the expression of the CYP-35B family of cytochrome P450s and the PGP-13 p-glycoprotein pump via the nuclear receptors NHR-70 and NHR-107 in the nematode C. elegans. A pgp-13 fluorescent reporter revealed hundreds of human drugs that upregulate the CAD defense system in vivo. Chemoinformatic analyses indicate that the pgp-13 reporter may be useful in identifying CADs that have pathogenic potential in humans. Mutant analyses coupled to metabolomics and structural modeling show that the CYP-35Bs are necessary and sufficient for CAD metabolism, and that CYP-35B2 D311 is key in mediating electrostatic interactions with the positively charged CADs. We also show that CAD metabolites are effluxed via PGP-13 acting partially redundantly with PGP-14 and that an intact defense system is necessary to resist CAD-induced pathology. Finally, we demonstrate that bacteria that likely cohabitate with C. elegans in nature trigger the CAD defense system, providing a plausible explanation for why a pathway that protects against anthropogenic small molecules exists in nematodes.

pharmacology and toxicology↗

bioRxiv2025

InfluenceNet: Encoding Motif Influence for Interpretable Modeling of Cis-Regulatory Syntax

Cis-regulatory elements shape gene expression by recruiting transcription factors (TFs) to DNA motifs, yet how motifs cooperate or compete across distances remains poorly understood. Existing deep learning models predict TF binding with high accuracy but rely on computationally intensive post-hoc analyses to infer regulatory syntax, limiting interpretability and scalability. Here we present InfluenceNet, a transparent convolutional architecture that directly encodes motif influence-a position- and motif-specific profile quantifying how one motif modulates binding at another. Trained on ChIP-nexus data for pluripotency TFs, InfluenceNet achieves performance comparable to state-of-the-art models while providing immediate, global interpretability. The learned influence profiles recapitulate known principles of motif syntax, including Oct4-Sox2 pioneering activity and Nanogs striking 10.5-bp helical periodicity, and reveal a cooperative Nanog-Nanog grammar supported by de novo motif discovery. Integrating these results with structural and molecular-dynamics modeling, we propose that Nanog forms chain-like oligomers on DNA through asymmetric contacts between WRD (tryptophan repeat domain) and DBD (DNA-binding domain) that maintain helical phase alignment. Together, these findings establish InfluenceNet as a general framework for accurate prediction and mechanistic interpretation of cis-regulatory grammar, bridging deep learning and biophysical insight.

bioinformatics↗

bioRxiv2025

Small molecule intervention of actin-binding protein profilin1 reduces tumor angiogenesis in renal cell carcinoma

Angiogenesis plays a key role in the development and progression of renal cell carcinoma (RCC). Actin-binding protein profilin-1 (Pfn1) is overexpressed in clear cell RCC predominantly in tumor-associated vascular endothelial cells (ECs). We previously demonstrated that that EC-selective (over)expression of Pfn1 accelerates RCC progression, and conversely, genetic loss of EC-Pfn1 dramatically inhibits tumor angiogenesis impeding tumor initiation and/or progression in RCC, suggesting that Pfn1 could be an actionable therapeutic target in RCC. In this study, we demonstrate that 4,4-((4-bromophenyl)methylene)bis(3,5-dimethyl-1H-pyrazole), a small molecule that we had previously identified as an inhibitor of Pfn1-actin interaction, directly binds to Pfn1 and attenuates tumor angiogenesis when directly administered into subcutaneous RCC tumors. Next, we undertook a chemical optimization approach to design and synthesize 4,4-((4-(trifluoromethyl)phenyl)methylene)bis(3,5-dimethyl-1H-pyrazole), a structural analog of our originally identified inhibitor, that exhibits improved anti-angiogenic efficacy in vitro and in vivo. Finally, we demonstrate that Pfn1 inhibitor is amenable to lipid microbubble encapsulation and release in the tumor microenvironment (TME) by ultrasound-mediated disruption of circulating microbubbles to achieve anti-angiogenic and anti-tumor benefit. In summary, our findings suggest that tumor-localized release of Pfn1 inhibitor could be a potential therapeutic strategy in RCC.

cell biology↗

bioRxiv2025

NEMO recruitment at single cytokine-receptor complexes shows quantized dynamics independent of ligand affinity

Cells use a limited number of receptors to sense and process molecular information from their environment. In the classical view of signaling, receptor-ligand affinities determine binding kinetics, in timescales of diffusion, where their time-averaged contact duration regulates rapid cytoplasmic signaling events to coordinate cellular responses. For some cytokines, single receptor-ligand binding events can initiate large multiprotein complexes in the cytoplasm that assemble over tens of minutes, bringing to question how cytokine affinity influences the sensitivity and strength of signaling. Here, we leverage naturally occurring variation of IL-1{beta} from multiple species to determine the impact of affinity on human IL-1 receptor signaling. Using experiments and models we investigate single receptor complexes activated by ligands that vary across multiple orders of magnitude in affinity. Our results show that while the receptor-ligand affinity establishes cytokine response sensitivity, activated IL-1 receptor complexes signal as discrete, quantized packets of signaling flux independent of affinity.

systems biology↗

bioRxiv2025

Interpretable adenylation domain specificity prediction using protein language models

Natural products have long been a rich source of diverse and clinically effective drug candidates. Non-ribosomal peptides (NRPs), polyketides (PKs), and NRP-PK hybrids are three classes of natural products that display a broad range of bioactivities, including antibiotic, antifungal, anticancer, and immunosuppressant activities. However, discovering these compounds through traditional bioactivity-guided techniques is costly and time-consuming, often resulting in the rediscovery of known molecules. Consequently, genome mining has emerged as a high-throughput strategy to screen hundreds of thousands of microbial genomes to identify their potential to produce novel natural products. Adenylation domains play a key role in the biosynthesis of NRPs and NRP-PKs by recruiting substrates to incrementally build the final structure. We propose MASPR, a machine learning method that leverages protein language models for accurate and interpretable predictions of A-domain substrate specificities. MASPR demonstrates superior accuracy and generalization over existing methods and is capable of predicting substrates not present in its training data, or zero-shot classification. We use MASPR to develop Seq2Hybrid, an efficient algorithm to predict the structure of hybrid NRP-PK natural products from microbial genomes. Using Seq2Hybrid, we propose putative biosynthetic gene clusters for the orphan natural products Octaminomycin A, Dityromycin, SW-163B, and JBIR-39.

bioinformatics↗

bioRxiv2024

Sliding Window INteraction Grammar (SWING): a generalized interaction language model for peptide and protein interactions

The explosion of sequence data has allowed the rapid growth of protein language models (pLMs). pLMs have now been employed in many frameworks including variant-effect and peptide-specificity prediction. Traditionally, for protein-protein or peptide-protein interactions (PPIs), corresponding sequences are either co-embedded followed by post-hoc integration or the sequences are concatenated prior to embedding. Interestingly, no method utilizes a language representation of the interaction itself. We developed an interaction LM (iLM), which uses a novel language to represent interactions between protein/peptide sequences. Sliding Window Interaction Grammar (SWING) leverages differences in amino acid properties to generate an interaction vocabulary. This vocabulary is the input into a LM followed by a supervised prediction step where the LMs representations are used as features. SWING was first applied to predicting peptide:MHC (pMHC) interactions. SWING was not only successful at generating Class I and Class II models that have comparable prediction to state-of-the-art approaches, but the unique Mixed Class model was also successful at jointly predicting both classes. Further, the SWING model trained only on Class I alleles was predictive for Class II, a complex prediction task not attempted by any existing approach. For de novo data, using only Class I or Class II data, SWING also accurately predicted Class II pMHC interactions in murine models of SLE (MRL/lpr model) and T1D (NOD model), that were validated experimentally. To further evaluate SWINGs generalizability, we tested its ability to predict the disruption of specific protein-protein interactions by missense mutations. Although modern methods like AlphaMissense and ESM1b can predict interfaces and variant effects/pathogenicity per mutation, they are unable to predict interaction-specific disruptions. SWING was successful at accurately predicting the impact of both Mendelian mutations and population variants on PPIs. This is the first generalizable approach that can accurately predict interaction-specific disruptions by missense mutations with only sequence information. Overall, SWING is a first-in-class generalizable zero-shot iLM that learns the language of PPIs.

systems biology↗

bioRxiv2023

Structure-Infused Protein Language Models

Embeddings from protein language models (PLMs) capture intricate patterns for protein sequences, enabling more accurate and efficient prediction of protein properties. Incorporating protein structure information as direct input into PLMs results in an improvement on the predictive ability of protein embeddings on downstream tasks. In this work we demonstrate that indirectly infusing structure information into PLMs also leads to performance gains on structure related tasks. The key difference between this framework and others is that at inference time the model does not require access to structure to produce its embeddings.

synthetic biology↗

bioRxiv2023

CENsible: Interpretable Insights into Small-Molecule Binding with Context Explanation Networks

We present a novel and interpretable approach for predicting small-molecule binding affinities using context explanation networks (CENs). Given the specific structure of a protein/ligand complex, our CENsible scoring function uses a deep convolutional neural network to predict the contributions of pre-calculated terms to the overall binding affinity. We show that CENsible can effectively distinguish active vs. inactive compounds for many systems. Its primary benefit over related machine-learning scoring functions, however, is that it retains interpretability, allowing researchers to identify the contribution of each pre-calculated term to the final affinity prediction, with implications for subsequent lead optimization.

pharmacology and toxicology↗

bioRxiv2023

Interpreting Molecular Dynamics Forces as DeepLearning Gradients Improves Quality Of PredictedProtein Structures

Protein structure predictions from deep learning models like AlphaFold2, despite their remarkable accuracy, are likely insufficient for direct use in downstream tasks like molecular docking. The functionality of such models could be improved with a combination of increased accuracy and physical intuition. We propose a new method to train deep learning protein structure prediction models using molecular dynamics force fields to work toward these goals. Our custom PyTorch loss function, OpenMM-Loss, represents the potential energy of a predicted structure. OpenMM-Loss can be applied to any all-atom representation of protein structure capable of mapping into our software package, SidechainNet. We demonstrate our methods efficacy by finetuning OpenFold. We show that subsequently predicted protein structures, both before and after a relaxation procedure, exhibit comparable accuracy while displaying lower potential energy and improved structural quality as assessed by MolProbity metrics. SIGNIFICANCEWe propose a novel framework to directly incorporate forces from molecular dynamics as gradients for training deep learning models like AlphaFold2. We implement our method as a PyTorch loss function, OpenMM-Loss, which frames the potential energy of predicted protein structures as a minimization objective. When applied to OpenFold, our method demonstrates improved structural quality, lower potential energy, and comparable accuracy relative to the OpenFold baseline. Our framework may enhance the ability of deep learning models to recapitulate fundamental biophysical principles, reducing the number of structural irregularities in their predictions and paving the way for more effective downstream applications.

bioinformatics↗

bioRxiv2021

DeepFrag: A Deep Convolutional Neural Network for Fragment-based Lead Optimization

1Machine learning has been increasingly applied to the field of computer-aided drug discovery in recent years, leading to notable advances in binding-affinity prediction, virtual screening, and QSAR. Surprisingly, it is less often applied to lead optimization, the process of identifying chemical fragments that might be added to a known ligand to improve its binding affinity. We here describe a deep convolutional neural network that predicts appropriate fragments given the structure of a receptor/ligand complex. In an independent benchmark of known ligands with missing (deleted) fragments, our DeepFrag model selected the known (correct) fragment from a set over 6,500 about 58% of the time. Even when the known/correct fragment was not selected, the top fragment was often chemically similar and may well represent a valid substitution. We release our trained DeepFrag model and associated software under the terms of the Apache License, Version 2.0. A copy can be obtained free of charge from http://durrantlab.com/deepfragmodel.

pharmacology and toxicology↗