AAAbin Abraham

Abin Abraham

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Abin Abraham has a total of 99 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Machine Learning Estimation of Gestational Age at Delivery Using Linked Mother-Infant Electronic Health Records Across Two Health Systems

    by Cosmin A. Bejan, Xiaotong Yang, Amelie Pham, Layth Qassem, Abin Abraham, Leena Choi, S. Trent Rosenbloom, Lana X. Gamire, Elizabeth J. Phillips

    Objective: This study aimed to train and evaluate supervised machine learning walgorithms using electronic health record (EHR) data to accurately estimate gestational age at delivery. Materials and Methods: We trained random forest, gradient boosting, and ensemble models on EHR data of mother-infant dyads from Vanderbilt University Medical Center(VUMC) and replicated the analyses at University of Michigan (UMich). We further analyzed EHR predictors of gestational age, assessed temporal drift in EHR data elements, and evaluated model performance stratified by delivery status. Results: The study included pregnancies corresponding to 54,344 and 34,345 mother-infant dyads at VUMC (2005-2025) and UMich (2012-2024), respectively. The gestational age predictions of the ensemble models achieved the highest agreement with the reference standard on the VUMC dataset (±1 week: 85.2%, ±2 weeks: 94.3%, MAE: 4.4 days) and demonstrated stronger generalization on the UMich dataset (±1 week: 93.1%, ±2 weeks: 97.8%, MAE: 2.8 days). Further, performance was better among pregnancies delivered in more recent years, and among full- and late-term deliveries compared with preterm deliveries. Discussion: The results indicate that supervised machine learning methods leveraging linked mother-infant EHRs can accurately estimate gestational age at delivery, while demonstrating the generalizability of the modeling approach and the portability of the analytic workflow across healthcare sites. Conclusion: This study presents a robust and generalizable machine learning framework to estimate gestational age at delivery. The framework can be reliably used to impute gestational age in large-scale, real-world clinical studies to support maternal and neonatal health research, in which accurate estimation of pregnancy onset is critical.

  • Open Access

    Discovering latent subtypes of preterm birth and genetic risk using tensor decomposition on electronic health records

    by Abin Abraham, Cosmin Bejan, Hannah Takasuka, Marina Sirota, John Anthony Capra

    Preterm birth is a syndrome that is triggered by diverse biological pathways and presents with many comorbid diseases. Although twin studies reveal a substantial heritable component, the genetic mechanisms of preterm birth remain poorly understood. We hypothesize that refining the preterm birth phenotype will reveal sub-phenotypes associated with distinct genetic risk factors and potential treatments. Here, we leverage rich longitudinal data from electronic health records (EHRs) from over 60,000 individuals from two clinical sites. Using tensor decomposition, we uncover several latent factors (LFs) that capture coherent combinations of comorbidities (e.g., metabolic, inflammatory, and mental health) and temporal trajectories of preterm and term births. Similar LFs are discovered between the two sites, underscoring their interpretability. Machine learning models trained on LFs accurately predict preterm birth and perform comparably to models trained on the full EHR data. Integrating genome-wide genotyping for >2,200 individuals, we find robust associations of preterm birth risk with high polygenic burden for cardiovascular disease, type 2 diabetes and body mass index. Using LFs, we discover that these genetic signals are strongly and specifically associated with different subsets of the preterm birth cohort. For example, the polygenic diabetes risk is associated with a LF characterized by relevant metabolic disorders. In summary, our study integrates latent phenotypes discovered from large EHR datasets with genetic data to predict preterm birth risk, uncover disease subtypes and comorbidities that drive genetic associations, and delineate the mechanisms underlying the heterogeneity of this complex trait.


  • Open Access

    GSEL: a fast, flexible python package for detecting signatures of diverse evolutionary forces on genomic regions

    by Abin Abraham, Abigail L Labella, Mary Lauren Benton, Antonis Rokas, John A Capra

    GSEL is a computational framework for calculating the enrichment of evolutionary signatures of diverse evolutionary forces in a set of genomic regions. GSEL can flexibly integrate any sequence-based evolutionary metric and analyze sets of human genomic regions identified by genome-wide assays (e.g., GWAS, eQTL, *-seq). The core of GSEL’s approach is the generation of empirical null distributions tailored to the allele frequency and linkage disequilibrium structure of the regions of interest. We illustrate the application of GSEL to variants identified from a GWAS of body mass index, a highly polygenic trait. GSEL is implemented as a fast, flexible, and user-friendly python package. It is available with demonstration data at https://github.com/abraham-abin13/gsel_vec Supplementary data are available at Bioinformatics online.


  • Open Access

    Mosaic patterns of selection in genomic regions associated with diverse human traits

    by Abin Abraham, Abigail L. LaBella, John A. Capra, Antonis Rokas

    Natural selection shapes the genetic architecture of many human traits. However, the prevalence of different modes of selection on genomic regions associated with variation in traits remains poorly understood. To address this, we developed an efficient computational framework to calculate enrichment of different evolutionary measures among regions associated with complex traits. We applied the framework to summary statistics from >900 genome-wide association studies (GWASs) and 11 evolutionary measures of sequence constraint, population differentiation, and allele age while accounting for linkage disequilibrium, allele frequency, and other potential confounders. We demonstrate that this framework yields consistent results across GWASs with variable sample sizes, numbers of trait-associated SNPs, and analytical approaches. The resulting evolutionary atlas maps diverse signatures of selection on genomic regions associated with complex human traits on an unprecedented scale. We detected positive enrichment for sequence conservation among trait-associated regions for the majority of traits (>77% of 290 high power GWASs), which was most dominant in reproductive traits. Many traits also exhibited substantial enrichment for population differentiation and recent positive selection, especially among hair, skin, and pigmentation traits. In contrast, we detected widespread negative enrichment for balancing selection (51% GWASs) and no evidence of enrichment for selection signals in regions associated with late-onset Alzheimer’s disease. These results support a pervasive role for negative selection on regions of the human genome that contribute to variation in complex traits, but also demonstrate where diverse modes of selection have shaped trait-associated loci. This atlas of signatures of different modes of natural selection across the diversity of available GWASs will enable exploration of the relationship between the genetic architecture and selection in the human genome.

  • Vascular alterations impede fragile tolerance to pregnancy in type 1 diabetes

    by Kelsey L. McNew, Abin Abraham, Daniel E. Sack, Charles Duncan Smart, Yasminye D. Pettway, Alexander C. Falk, Rolanda L. Lister, Annika B. Faucon, Cosmin A. Bejan, John A. Capra, et al.

  • Machine Learning Prediction of Kidney Stone Composition Using Electronic Health Record-Derived Features

    by Abin Abraham, Nicholas L. Kavoussi, Wilson Sui, Cosmin Bejan, John A. Capra, Ryan Hsi

    Objectives: To assess the accuracy of machine learning models in predicting kidney stone composition using variables extracted from the electronic health record (EHR). Materials and Methods: We identified kidney stone patients ( n = 1296) with both stone composition and 24-hour (24H) urine testing. We trained machine learning models (XGBoost [XG] and logistic regression [LR]) to predict stone composition using 24H urine data and EHR-derived demographic and comorbidity data. Models predicted either binary (calcium vs noncalcium stone) or multiclass (calcium oxalate, uric acid, hydroxyapatite, or other) stone types. We evaluated performance using area under the receiver operating curve (ROC-AUC) and accuracy and identified predictors for each task. Results: For discriminating binary stone composition, XG outperformed LR with higher accuracy (91% vs 71%) with ROC-AUC of 0.80 for both models. Top predictors used by these models were supersaturations of uric acid and calcium phosphate, and urinary ammonium. For multiclass classification, LR outperformed XG with higher accuracy (0.64 vs 0.56) and ROC-AUC (0.79 vs 0.59), and urine pH had the highest predictive utility. Overall, 24H urine analyte data contributed more to the models' predictions of stone composition than EHR-derived variables. Conclusion: Machine learning models can predict calcium stone composition. LR outperforms XG in multiclass stone classification. Demographic and comorbidity data are predictive of stone composition; however, including 24H urine data improves performance. Further optimization of performance could lead to earlier directed medical therapy for kidney stone patients.


  • Top Cited Papers

    Cell-programmed nutrient partitioning in the tumour microenvironment

    by Bradley I. Reinfeld, Matthew Z. Madden, Melissa M. Wolf, Anna Chytil, Jackie E. Bader, Andrew R. Patterson, Ayaka Sugiura, Allison S. Cohen, Ahmed Ali, Brian T. Do, et al.

    Cancer cells characteristically consume glucose through Warburg metabolism1, a process that forms the basis of tumour imaging by positron emission tomography (PET). Tumour-infiltrating immune cells also rely on glucose, and impaired immune cell metabolism in the tumour microenvironment (TME) contributes to immune evasion by tumour cells2,3,4. However, whether the metabolism of immune cells is dysregulated in the TME by cell-intrinsic programs or by competition with cancer cells for limited nutrients remains unclear. Here we used PET tracers to measure the access to and uptake of glucose and glutamine by specific cell subsets in the TME. Notably, myeloid cells had the greatest capacity to take up intratumoral glucose, followed by T cells and cancer cells, across a range of cancer models. By contrast, cancer cells showed the highest uptake of glutamine. This distinct nutrient partitioning was programmed in a cell-intrinsic manner through mTORC1 signalling and the expression of genes related to the metabolism of glucose and glutamine. Inhibiting glutamine uptake enhanced glucose uptake across tumour-resident cell types, showing that glutamine metabolism suppresses glucose uptake without glucose being a limiting factor in the TME. Thus, cell-intrinsic programs drive the preferential acquisition of glucose and glutamine by immune and cancer cells, respectively. Cell-selective partitioning of these nutrients could be exploited to develop therapies and imaging strategies to enhance or monitor the metabolic programs and activities of specific cell populations in the TME.


  • Open Access

    Evaluating human autosomal loci for sexually antagonistic viability selection in two large biobanks

    by Katja R Kasimatis, Abin Abraham, Peter L Ralph, Andrew D Kern, John A Capra, Patrick C Phillips

    Sex and sexual differentiation are pervasive across the tree of life. Because females and males often have substantially different functional requirements, we expect selection to differ between the sexes. Recent studies in diverse species, including humans, suggest that sexually antagonistic viability selection creates allele frequency differences between the sexes at many different loci. However, theory and population-level simulations indicate that sex-specific differences in viability would need to be very large to produce and maintain reported levels of between-sex allelic differentiation. We address this contradiction between theoretical predictions and empirical observations by evaluating evidence for sexually antagonistic viability selection on autosomal loci in humans using the largest cohort to date (UK Biobank, n = 487,999) along with a second large, independent cohort (BioVU, n = 93,864). We performed association tests between genetically ascertained sex and autosomal loci. Although we found dozens of genome-wide significant associations, none replicated across cohorts. Moreover, closer inspection revealed that all associations are likely due to cross-hybridization with sex chromosome regions during genotyping. We report loci with potential for mis-hybridization found on commonly used genotyping platforms that should be carefully considered in future genetic studies of sex-specific differences. Despite being well powered to detect allele frequency differences of up to 0.8% between the sexes, we do not detect clear evidence for this signature of sexually antagonistic viability selection on autosomal variation. These findings suggest a lack of strong ongoing sexually antagonistic viability selection acting on single locus autosomal variation in humans.


  • Open Access

    Cell Programmed Nutrient Partitioning in the Tumor Microenvironment

    by Bi Reinfeld, Matthew Z Madden, Melissa M Wolf, Anna Chytil, Je Bader, Andrew R Patterson, As Cohen, Ahmed Ali, Brian T Do, Alexander Muir, et al.

    The tumor microenvironment (TME) includes transformed cancer and infiltrating immune cells 1,2 . Cancer cells can consume large quantities of glucose through Warburg metabolism 3,4 that can be visualized with positron emission tomography (PET). While infiltrating immune cells also rely on glucose, disruptions to metabolism can contribute to tumor immunological evasion 5–9 . How immune cell metabolism is programmed or restrained by competition with cancer cells for nutrients, remains uncertain. Here we used PET tracers to measure the accessibility of glucose and glutamine to cell subsets in the TME. Surprisingly, myeloid cells including macrophages were the greatest consumers of intra-tumoral glucose, followed by T cells and cancer cells. Cancer cells, in contrast, had the highest glutamine uptake. This distinct nutrient partitioning was programmed through selective mTORC1 signaling and glucose or glutamine-related gene expression. Inhibition of glutamine uptake enhanced glucose uptake across tumor resident cell types and shifted macrophage phenotype, demonstrating glucose is not limiting in the TME. Thus, cancer cells are not the only cells in tumors which exhibit high glucose uptake in vivo and instead preferentially utilize glutamine over other cell types. We observe that intrinsic cellular programs can play a major role in the use of some nutrients. Together, these data argue cell selective partitioning of glucose and glutamine can be exploited to develop therapies and imaging strategies to alter the metabolic programs of specific cell populations in the TME.


  • Open Access

    Accounting for diverse evolutionary forces reveals mosaic patterns of selection on human preterm birth loci

    by Abigail L. LaBella, Abin Abraham, Yakov Pichkar, Sarah L. Fong, Ge Zhang, Louis J. Muglia, Patrick Abbot, Antonis Rokas, John A. Capra

    Currently, there is no comprehensive framework to evaluate the evolutionary forces acting on genomic regions associated with human complex traits and contextualize the relationship between evolution and molecular function. Here, we develop an approach to test for signatures of diverse evolutionary forces on trait-associated genomic regions. We apply our method to regions associated with spontaneous preterm birth (sPTB), a complex disorder of global health concern. We find that sPTB-associated regions harbor diverse evolutionary signatures including conservation, excess population differentiation, accelerated evolution, and balanced polymorphism. Furthermore, we integrate evolutionary context with molecular evidence to hypothesize how these regions contribute to sPTB risk. Finally, we observe enrichment in signatures of diverse evolutionary forces in sPTB-associated regions compared to genomic background. By quantifying multiple evolutionary forces acting on sPTB-associated regions, our approach improves understanding of both functional roles and the mosaic of evolutionary forces acting on loci. Our work provides a blueprint for investigating evolutionary pressures on complex traits.