George I. Austin

George I. Austin

Auto-generated profile, based on publicly available information

George I. Austin

Department of Biomedical Informatics, Columbia University Irving Medical Center, New York, NY, USA

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
28 November 2025 in Science Advances
Verified
Journal Article
Open access
GAGeorge I. Austin
George I. Austin
IPItsik Pe’eR
Itsik Pe’eR
TKTal Korem
Tal Korem
Cross-validation is a common method for evaluating machine learning models. “Leave-one-out cross-validation,” in which each data instance is used to test a model trained on all other instances, is often used in data-scarce regimes. As common metrics such as the R 2 score cannot be calculated for a single prediction, predictions are commonly aggregated across folds for performance evaluation. Here, we prove that this creates “distributional bias”: a negative correlation between the average label of each training fold and the label of its corresponding test instance. As machine learning models tend to regress to the mean of their training data, this bias tends to negatively affect performance evaluation and hyperparameter optimization. We demonstrate that distributional bias exists across diverse tasks, models, and evaluation approaches, and can bias against stronger regularization. To address it, we developed a generalizable rebalanced cross-validation that is robust to distributional bias in both classification and regression, and demonstrates improved performance in simulations, machine learning benchmarks, and several published analyses.

27 August 2024 in The Journal of Infectious Diseases
Verified
Journal Article
Closed access
PDF file
GAGeorge I Austin
George I Austin
TKTal Korem
Tal Korem
As investigations of low-biomass microbial communities have become more common, so too has the recognition of major challenges affecting these analyses. These challenges have been shown to compromise biological conclusions and have contributed to several controversies. Here, we review some of the most common and influential challenges in low-biomass microbiome research. We highlight key approaches to alleviate these potential pitfalls, combining experimental planning strategies and data analysis methods.

20 December 2023 in Cancer Epidemiology, Biomarkers & Prevention
Verified
Journal Article
Closed access
PDF file
QSQuinn S. Solfisburg
Quinn S. Solfisburg
FBFederico Baldini
Federico Baldini
BBBrittany Baldwin-Hunter
Brittany Baldwin-Hunter
GAGeorge I. Austin
George I. Austin
HLHarry H. Lee
Harry H. Lee
JAJulian A. Abrams
Julian A. Abrams
Background: Esophageal adenocarcinoma (EAC) is rising in incidence, and established risk factors do not explain this trend. Esophageal microbiome alterations have been associated with Barrett's esophagus (BE) and dysplasia and EAC. The oral microbiome is tightly linked to the esophageal microbiome; this study aimed to identify salivary microbiome-related factors associated with BE, dysplasia, and EAC. Methods: Clinical data and oral health history were collected from patients with and without BE. The salivary microbiome was characterized, assessing differential relative abundance of taxa by 16S rRNA gene sequencing and associations between microbiome composition and clinical features. Microbiome metabolic modeling was used to predict metabolite production. Results: A total of 244 patients (125 non-BE and 119 BE) were analyzed. Patients with high-grade dysplasia (HGD)/EAC had a significantly higher prevalence of tooth loss (P = 0.001). There were significant shifts with increased dysbiosis associated with HGD/EAC, independent of tooth loss, with the largest shifts within the genus Streptococcus. Modeling predicted significant shifts in the microbiome metabolic capacities, including increases in L-lactic acid and decreases in butyric acid and L-tryptophan production in HGD/EAC. Conclusions: Marked dysbiosis in the salivary microbiome is associated with HGD and EAC, with notable increases within the genus Streptococcus and accompanying changes in predicted metabolite production. Further work is warranted to identify the biological significance of these alterations and to validate metabolic shifts. Impact: There is an association between oral dysbiosis and HGD/EAC. Further work is needed to establish the diagnostic, predictive, and causal potential of this relationship.

20 May 2025 in mSystems
Verified
Journal Article
Open access
GAGeorge I. Austin
George I. Austin
TKTal Korem
Tal Korem
Gihawi et al. (mBio 14:e01607-23, 2023, https://doi.org/10.1128/mbio.01607-23 ) argued that the analysis of tumor-associated microbiome data by Poore et al. (Nature 579:567-574, 2020, https://doi.org/10.1038/s41586-020-2095-1 ) is invalid because features that were originally very sparse (genera with mostly zero read counts) became associated with the phenotype following batch correction. Here, we examine whether such an observation should necessarily indicate issues with processing or machine learning pipelines. We show counterexamples using the centered log ratio (CLR) transformation, which is often used for analysis of compositional microbiome data. The CLR transformation has similarities to voom-SNM, the batch-correction method brought into question by Gihawi et al., and yet is a sample-wise operation that cannot, in itself, “leak” information or invalidate downstream analyses. We show that because the CLR transformation divides each value by the geometric mean of its sample, common imputation strategies for missing or zero values result in transformed features that are associated with the geometric mean. Through analyses of both synthetic and vaginal microbiome data sets, we demonstrate that when the geometric mean is associated with a phenotype, sparse and CLR-transformed features will also become associated with it. We re-analyze features highlighted by Gihawi et al. and demonstrate that the phenomenon of sparse features becoming phenotype-associated can also be observed after a CLR transformation, which serves as a counterexample to the claim that such an observation necessarily means information leakage. While we do not intend to address other concerns regarding tumor microbiome analyses, validate Poore et al.’s results, or evaluate batch-correction pipelines, we conclude that because phenotype-associated features that were initially sparse can be created by a sample-wise transformation that cannot artifactually inflate machine learning performance, their detection is not independently sufficient to demonstrate information leakage in machine learning pipelines. Microbiome data are multivariate, and as such, a value of 0 carries a different meaning for each sample. Many transformations, including CLR and other batch-correction methods, are likewise multivariate, and, as these issues demonstrate, each individual feature should be interpreted with caution. IMPORTANCE: Gihawi et al. claim that finding that a transformation turned highly sparse (mostly zero) features into features that are associated with a phenotype is sufficient to conclude that there is information leakage and to invalidate an analysis. This claim has critical implications for both the debate regarding The Cancer Genome Atlas (TCGA) cancer microbiome analysis and for interpretation and evaluation of analyses in the microbiome field at large. We show by counterexamples and by reanalysis that such transformations can be valid.

12 February 2024 in bioRxiv
Verified
Preprint
Open access
PDF file
GAGeorge I. Austin
George I. Austin
AKAya Brown Kav
Aya Brown Kav
HPHeekuk Park
Heekuk Park
JBJana Biermann
Jana Biermann
AUAnne-Catrin Uhlemann
Anne-Catrin Uhlemann
TKTal Korem
Tal Korem
Every step in common microbiome profiling protocols has variable efficiency for each microbe. For example, different DNA extraction kits may have different efficiency for Gram-positive and -negative bacteria. These variable efficiencies, combined with technical variation, create strong processing biases, which impede the identification of signals that are reproducible across studies and the development of generalizable and biologically interpretable prediction models. “Batch-correction” methods have been used to alleviate these issues computationally with some success. However, many make strong parametric assumptions which do not necessarily apply to microbiome data or processing biases, or require the use of an outcome variable, which risks overfitting. Lastly and importantly, existing transformations used to correct microbiome data are largely non-interpretable, and could, for example, introduce values to features that were initially mostly zeros. Altogether, processing bias currently compromises our ability to glean robust and generalizable biological insights from microbiome data. Here, we present DEBIAS-M ( D omain adaptation with phenotype E stimation and B atch I ntegration A cross S tudies of the M icrobiome), an interpretable framework for inference and correction of processing bias, which facilitates domain adaptation in microbiome studies. DEBIAS-M learns bias-correction factors for each microbe in each batch that simultaneously minimize batch effects and maximize cross-study associations with phenotypes. Using benchmarks of HIV and colorectal cancer classification from gut microbiome data, and cervical neoplasia prediction from cervical microbiome data, we demonstrate that DEBIAS-M outperforms batch-correction methods commonly used in the field. Notably, we show that the inferred bias-correction factors are stable, interpretable, and strongly associated with specific experimental protocols. Overall, we show that DEBIAS-M allows for better modeling of microbiome data and identification of interpretable signals that are reproducible across studies.

2 December 2024 in bioRxiv
Verified
Preprint
Open access
PDF file
WKWilliam F. Kindschuh
William F. Kindschuh
GAGeorge I. Austin
George I. Austin
YMYoli Meydan
Yoli Meydan
HPHeekuk Park
Heekuk Park
JUJulia A. Urban
Julia A. Urban
TKTal Korem
Tal Korem
Preeclampsia is a severe obstetrical syndrome which contributes to 10-15% of all maternal deaths. Although the mechanisms underlying systemic damage in preeclampsia—such as impaired placentation, endothelial dysfunction, and immune dysregulation—are well studied, the initial triggers of the condition remain largely unknown. Furthermore, although the pathogenesis of preeclampsia begins early in pregnancy, there are no early diagnostics for this life-threatening syndrome, which is typically diagnosed much later, after systemic damage has already manifested. Here, we performed deep metagenomic sequencing and multiplex immunoassays of vaginal samples collected during the first trimester from 124 pregnant individuals, including 62 who developed preeclampsia with severe features. We identified multiple significant associations between vaginal immune factors, microbes, clinical factors, and the early pathogenesis of preeclampsia. These associations vary with BMI, and stratification revealed strong associations between preeclampsia and Bifidobacterium spp., Prevotella timonensis , and Sneathia vaginalis . Finally, we developed machine learning models that predict the development of preeclampsia using this first trimester data, collected ~5.7 months prior to clinical diagnosis, with an auROC of 0.78. We validated our models using data from an independent cohort (MOMS-PI), achieving an auROC of 0.80. Our findings highlight robust associations among the vaginal microbiome, local host immunity, and early pathogenic processes of preeclampsia, paving the way for early detection, prevention and intervention for this devastating condition.