Biology subjects

McLaughlin, R. T.

Publications and source records attributed to McLaughlin, R. T..

3 recordsLinked to original sources

bioRxiv2024

tauX: A Gene Expression Ratio Strategy to Improve Machine Learning Applications in Precision Medicine

Machine learning algorithms identify patterns that would otherwise be difficult to observe in high-dimensional molecular and clinical data. For this reason, machine learning has the potential to have a profound impact on clinical decision making and drug target discovery. Nevertheless, there remain considerable technical challenges in adapting these tools for clinical use. These challenges include clinical feature engineering, model selection, and defining optimal strategies for model training. For cancer care, RNA sequencing of patient tumor biopsies has already proven to be a powerful molecular assay to characterize tumor-intrinsic and -extrinsic phenotypes influencing therapeutic response. To improve the predictive performance of RNA-sequencing data, we developed the tauX machine learning framework to refine gene expression features and improve the performance of machine learning algorithms. The tauX framework uses aggregated ratios of positively and negatively associated predictive genes to simplify the prediction task. We showed a significant improvement in predictive performance using a large database of synthetic gene expression profiles. We also show how the tauX framework can be used to elucidate the mechanisms of response and resistance to checkpoint blockade therapy using data from the Stand Up to Cancer (SU2C) Lung Response Cohort and The Cancer Genome Atlas (TCGA). The tauX strategy achieved superior predictive performance compared to models built upon established feature engineering strategies or widely used cancer gene expression signatures. The tauX framework is available as a freely deployable docker container (https://hub.docker.com/r/pfeiljx/taux).

bioinformatics↗

bioRxiv2021

Attentive deep learning-based tumor-only somatic mutation classifier achieves high accuracy agnostic of tissue type and capture kit.

In precision oncology, reliable identification of tumor-specific DNA mutations requires sequencing tumor DNA and non-tumor DNA (so-called "matched normal") from the same patient. The normal sample allows researchers to distinguish acquired (somatic) and hereditary (germline) variants. The ability to distinguish somatic and germline variants facilitates estimation of tumor mutation burden (TMB), which is a recently FDA-approved pan-cancer marker for highly successful cancer immunotherapies; in tumor-only variant calling (i.e., without a matched normal), the difficulty in discriminating germline and somatic variants results in inflated and unreliable TMB estimates. We apply machine learning to the task of somatic vs germline classification in tumor-only samples using TabNet, a recently developed attentive deep learning model for tabular data that has achieved state of the art performance in multiple classification tasks (Arik and Pfister 2019). We constructed a training set for supervised classification using features derived from tumor-only variant calling and drawing somatic and germline truth-labels from an independent pipeline incorporating the patient-matched normal samples. Our trained model achieved state-of-the-art performance on two hold-out test datasets: a TCGA dataset including sarcoma, breast adenocarcinoma, and endometrial carcinoma samples (F1-score: 88.3), and a metastatic melanoma dataset, (F1-score 79.8). Concordance between matched-normal and tumor-only TMB improves from R2 = 0.006 to 0.705 with the addition of our classifier. And importantly, this approach generalizes across tumor tissue types and capture kits and has a call rate of 100%. The interpretable feature masks of the attentive deep learning model explain the reasons for misclassified variants. We reproduce the recent finding that tumor-only TMB estimates for Black patients are extremely inflated relative to that of White patients due to the racial biases of germline databases. We show that our machine learning approach appreciably reduces this racial bias in tumor-only variant-calling.

genomics↗

bioRxiv2019

Demultiplexing overlapping signaling scaffold functions to probe lipid messenger coupling to cytoskeletal dynamics.

The coordination of lipid messenger signaling with cytoskeletal regulation is central to many organelle-specific signaling and regulatory processes. While central to many aspects of cell physiology, this coupling often depends on the function of multi-domain scaffolds that orchestrate transient interactions and dynamic feedback among a spectrum of signaling intermediates and regulatory proteins on organelles. Understanding scaffold protein functions has remained challenging given this complexity. This work employs live-cell imaging and statistical analyses to deconvolve (demultiplex) how the multi-domain scaffold IQGAP1 coordinates phosphoinositide signaling with organelle-specific actin regulation and membrane processing events. Using actin-ensconced endosomes that localize to the basal cortex of polarized epithelial cells as a model system, we demonstrate abilities to dissect how IQGAP1 transitions between different actin and endosomal-membrane tethered states. We provide evidence IQGAP1 functions as a transient inhibitor of actin growth around the endosomes in at least one of these states. While not easily distilled via standard (static) colocalization analyses or traditional pathway perturbations methods, this negative regulation was revealed via a series of dynamic correlation and multiple regression analyses. These methods also uncovered that the negative actin regulation is linked to GTPase-dependent tethering to the endosomal membrane. Moreover, the scaffold transitions underlying this control are shown to depend on the production of PIP3 lipid messengers by the lipid kinase PI3K. Overall, these methods and results provide new insights in to how IQGAP1 act as a signaling hub by orchestrating time-dependent membrane and cytoskeletal protein interactions and provide new routes to dissect scaffold-mediated pathway regulation in a variety of settings.

biophysics↗