CBCristian G. Bologa

Cristian G. Bologa

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

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Cristian G. Bologa has a total of 469 co-authors. Here are the top co-authors by number of shared publications:

  • Tudor Ionel Oprea

    Department of Internal Medicine, University of New Mexico, Albuquerque, NM, USA

    51 shared publications
  • Oleg Ursu

    Translational Informatics Division, Department of Internal Medicine, University of New Mexico School of Medicine, Albuquerque, NM 87131, USA

    16 shared publications
  • Larry A. Sklar

    Department of Pathology, University of New Mexico, School of Medicine, Albuquerque, NM 87131, United States

    13 shared publications
  • Anna Waller

    UNM Center for Molecular Discovery, University of New Mexico Comprehensive Cancer Center, University of New Mexico, Albuquerque, NM 87131, USA

    12 shared publications
  • Bruce S. Edwards

    Cytometry, Cancer Research and Treatment Center, University of New Mexico Health Sciences Center, Albuquerque, NM 87131, USA

    12 shared publications
  • Eric R. Prossnitz

    University of New Mexico Albuquerque USA

    11 shared publications

Latest Publications

  • Open Access

    Detecting Uncoded Self-Harm in Veterans’ Electronic Health Records Using Positive and Unlabeled Learning: Retrospective Cohort Study

    by Praveen Kumar, Alexandria D Viszolay, Rajesh Upadhayaya, Fariha Moomtaheen, Donald R Greer, Cristian G Bologa, Kristan A Schneider, Sharon E Davis, Michael E Matheny, David van der Goes, et al.

    Background: Underdiagnosis and undercoding are common across mental health conditions, particularly suicide and self-harm. This leaves health care datasets lacking reliable negative examples needed for predictive modeling, phenotype prevalence estimation, and identification of individuals at elevated risk. We use positive and unlabeled (PU) learning to address this challenge. Objective: This study aims to identify US Veterans whose self-harm events were not explicitly captured through diagnostic codes in electronic health records (EHRs) and estimate the underlying prevalence using a novel PU learning algorithm. Methods: We performed a retrospective cohort study using Veterans Health Administration EHRs (from October 1, 1999, to August 31, 2019), selecting a random 25% sample of 1,329,120 Veterans out of 5,316,480 (1,193,563 males and 135,557 females) with at least 2 years of observation. The study cohort comprised 24,625 Veterans with coded self-harm and 1,304,495 uncoded, with the mean ages of 38.39 (SD 12.17) and 48.76 (SD 15.04) years, respectively. We applied our PULSNAR (positive unlabeled learning selected not at random) algorithm to estimate the proportion of individuals with uncoded self-harm. Covariates included age, medical conditions, procedures, and clinical observations. Four experts (raters) independently reviewed charts of 97 uncoded Veterans, each selected from 1% intervals of calibrated PULSNAR probabilities from 0.01 to 0.97. Agreement was assessed among raters, PULSNAR classifications, and consensus review decisions. Post hoc calibration was used to refine prevalence estimates. Results: Of the 159,049 covariates in the dataset, PULSNAR’s Extreme Gradient Boosting (XGBoost) model identified 1302 (0.82%) as informative for classification. Only 1.85% (24,625/1,329,120) of Veterans had diagnostic codes indicating self-harm events, while PULSNAR estimated an overall prevalence of 10.46% (139,026/1,329,120) by identifying an additional α =8.77% (114,404/1,304,495) of self-harm cases among the uncoded population. Of the 97 chart-reviewed patients, 39 had documented but uncoded self-harm. PULSNAR probabilities were post hoc calibrated such that their sum over the 97 cases equaled 39, which adjusted the combined coded and imputed prevalence downward from 10.46% to 7.91% (105,133/1,329,120). By applying this calibration to shift the probabilities of all uncoded Veterans, with bootstrapping for confidence intervals, PULSNAR estimates that coded self-harm represents only 23.4% (95% CI 17.76% to 31.51%) of all documented (coded+notes) self-harm. Conclusions: Under the “selected not at random” assumption, PULSNAR provides an innovative and scalable framework for estimating the clinically documented prevalence of mental health conditions and identifying the uncoded individuals with calibrated prediction, without requiring confirmed negative labels. This method offers an alternative to time-consuming chart reviews for detecting likely cases missing structured coding capture. By addressing diagnostic undercoding of mental health conditions in EHRs, this approach has the potential to enhance the estimation of mental health prevalence and support screening, activation of automated clinical decision support, targeted intervention, better resource allocation, and research to improve outcomes in real-world settings.

  • Open Access

    Effective spectrum-based antibiotic resistance index for monitoring resistance in Gram-negative bacilli

    by M. Cristina Vazquez Guillamet, Alice Bewley, Nicole J. Tarlton, Reid Goodman, Michael J. Durkin, Michael Bernauer, Meghan Brett, Kevin Hsueh, Cristian Bologa, George Turabelidze, et al.

    Background: Antimicrobial resistance (AMR) is a growing public health threat, and we currently lack accurate measures to track and trend this resistance. We developed the antibiotic resistance index (ARI) that aggregates resistance of Gram-negative bacilli (GNB) into a single metric which can be tracked across healthcare settings and over time. Methods: Culture data were collected from adult patients who met the CDC adult sepsis event criteria across 10 Barnes-Jewish HealthCare (BJC) hospitals between January 2018 and December 2023. An antibiotic’s effective spectrum (AES) was calculated as the ratio of susceptible GNB to all identified GNB. The ARI was calculated as the sum of the AES to which the isolate was resistant. Using the 20 most common GNB and 15 most common anti-GNB antibiotics routinely tested in antibiograms, we calculated the ARI for each BJC hospital during the study years. Results: 18,854 GNB cultured from 12,803 patients meeting CDC adult sepsis event criteria were included. AES varied between 0.15 for ampicillin and 0.94 for amikacin. A. calcoaceticus-baumannii complex had the highest ARI of 6.64 (IQR 4.00–9.28). Median hospital-level ARI fluctuated between 2.12 (IQR 0.40–3.83) in 2018 to 2.20 (IQR 0.34–3.86) in 2023. The ARI trajectories over time varied by medical center. Conclusion: ARI aggregates AMR in GNB and may facilitate monitoring across locations and over time. ARI and antibiotic effective spectra redefine narrow and broad spectrum of activity and offer a starting point for antibiotic utilization metrics.

  • Open Access

    BiomarkerKB: An Integrated Knowledgebase Supporting Biomarker-Centric Exploration of Biomedical Data

    by Daniall Masood, Mariia Kim, Jeet Vora, Robel Kahsay, Patrick McNeeley, Sean Kim, Sujeet Kulkarni, Darren A Natale, Srinivasan Ramachandran, Shakti Gupta, et al.

    Biomarkers are essential tools for disease detection, risk assessment, therapeutic monitoring, and precision medicine. However, biomarker data are dispersed across heterogeneous resources, inconsistently reported in the literature, and rarely standardized for computational use. This fragmentation limits reproducibility, cross-study integration, and the discovery of novel biomarker and disease relationships. We developed BiomarkerKB, a knowledgebase designed to harmonize and integrate biomarker information under a standardized data model. The model follows the FDA-NIH BEST biomarker definition and captures both core fields (biomarker entity, disease/condition, exposure agent) and contextual metadata (specimen, biomarker role, evidence, provenance). Biomarker data and related annotations were either curated from publications or collected from public resources (e.g., OpenTargets, GWAS Catalog, ClinVar, CIViC, OncoMX) and were also contributed by the Common Fund Data Coordinating Centers and the Early Detection Research Network (EDRN). Standardization was achieved using ontologies and reference resources such as Disease Ontology, UBERON, UniProtKB, and HUGO Gene Nomenclature Committee (HGNC) gene symbols. BiomarkerKB data were ingested into a Neo4j-based knowledge graph and integrated with the Common Fund Data Ecosystem (CFDE) Knowledge Graph. The initial release of BiomarkerKB contains over 200,000 biomarker-disease associations spanning genes, proteins, metabolites, glycans, and chemical elements. The knowledge graph comprises more than 300,000 nodes and 1.2 million edges, enabling structured exploration of biomarker relationships within CFDE data as demonstrated through the knowledge graph query-based use cases presented in this study. A publicly accessible web portal ( https://biomarkerkb.org ) provides keyword search, filtering, data downloads, and access to graph visualization to support both researchers and computational analyses. BiomarkerKB addresses a critical gap in biomarker informatics by providing an integrated, FAIR (Findable, Accessible, Interoperable, and Reusable), and unified framework for biomarker knowledge exploration and discovery.


  • Open Access

    Badapple 2.0: An Empirical Predictor of Compound Promiscuity, Updated, Modernized, and Enhanced for Explainability

    by John Ringer, Christophe Lambert, Steven Bradfute, Cristian Bologa, Jeremy Yang

    Modern drug discovery and chemical biology research relies heavily on analyzing bioassay data. One of the many challenges in bioassay data analysis is identifying false trails, i.e., chemical compounds which initially appear to have desirable activity but are found to be problematic upon further investigation. Badapple (BioAssay-Data Associative Promiscuity Pattern Learning Engine) was initially released in 2012, to help researchers identify promiscuous compounds and thus avoid a common source of these false trails, and since then has been well regarded and used by the global scientific community. Through an effort involving software engineering, cheminformatics, and biomedical data science we have developed Badapple 2.0, a major update with a complete code-rewrite, updated and expanded assay datasets, enhanced functionality, scalability, and metadata, supporting improved explainability and richer bioactivity analyses. Badapple 2.0 was motivated and funded by an ongoing AI/ML-empowered anti-alphaviral discovery program, but has broad applicability for improving the efficiency of many other early-stage drug discovery campaigns.

  • Open Access

    Relationship between Rate of Hypernatremia Correction and Outcomes in Hospitalized Patients

    by Gabriela Chacon-Palma, J. Pedro Teixeira, Igor Litvinovich, Cristian G. Bologa, Maria-Eleni Roumelioti, MingAn Yang, Mark L. Unruh

    Key Points: Slow hypernatremia correction rates (≤0.50 mEq/L per hour) are associated with lower in-hospital mortality than fast rates (>0.50 mEq/L per hour). Fast hypernatremia correction is associated with lower odds of discharge to nursing facilities or hospice than slow correction. Hypernatremia severity, age, and kidney function do not modify associations between correction rates, hospital mortality, and disposition. Background: Current recommendations for limiting hypernatremia correction rates to avoid cerebral edema in adults are supported by limited evidence. We explored the associations between rate of hypernatremia correction in hospitalized adults, in-hospital mortality, and discharge disposition. Methods: Using a large, multicenter database, we analyzed 37,913 hospitalized adults with hypernatremia on admission. For the primary analysis, hypernatremia correction rates were categorized as slow (≤0.50 mEq/L per hour) or fast (>0.50 mEq/L per hour). Propensity score (PS) weighting and PS stratification were used to adjust for confounders. In secondary analyses, the results were stratified by initial sodium concentration, age, and initial eGFR. In a sensitivity analysis, correction rates were categorized as 0.60 mEq/L per hour. Results: Most (89%) patients experienced slow hypernatremia correction. In PS-weighted analyses, slow correction was associated with overall lower in-hospital mortality (adjusted odds ratio [aOR], 0.63; 95% confidence interval [CI], 0.59 to 0.67) but higher odds of discharge to hospice (aOR, 1.57; 95% CI, 1.38 to 1.78) or nursing facilities (aOR, 1.60; 95% CI, 1.52 to 1.69) than fast (reference) correction rates. After stratification by initial hypernatremia severity, age, and kidney function at admission, the associations between slow versus fast correction, in-hospital mortality, and discharge disposition were largely preserved without clear signals of effect modification by subgroup. When categorizing hypernatremia correction rates into three groups, 0.60 mEq/L per hour (analogous to slow versus fast, respectively) continued to be independently associated with lower in-hospital mortality but higher rates of discharge to nursing facilities or hospice. Conclusions: In this analysis, the rate of hypernatremia correction was independently associated with opposing effects on survival and a favorable discharge disposition. Our findings suggest that balancing the risks and benefits of different dysnatremia correction rates should consider not only mortality but also patient-centered outcomes such as discharge disposition.


  • Open Access

    KG2ML: Integrating Knowledge Graphs and Positive Unlabeled Learning for Identifying Disease-Associated Genes

    by Praveen Kumar, Vincent T. Metzger, Swastika T. Purushotham, Priyansh Kedia, Cristian G. Bologa, Christophe G. Lambert, Jeremy J. Yang

    Background: Biomedical knowledge graphs (KGs), such as the Data Distillery Knowledge Graph (DDKG), capture known relationships among entities (e.g., genes, diseases, proteins), providing valuable insights for research. However, these relationships are typically derived from prior studies, leaving potential unknown associations unexplored. Identifying such unknown associations, including previously unknown disease-associated genes, remains a critical challenge in bioinformatics and is crucial for advancing biomedical knowledge. Methods: Traditional methods, such as linkage analysis and genome-wide association studies (GWAS), can be time-consuming and resource-intensive. This highlights the need for efficient computational approaches to identify or predict new genes using known disease-gene associations. Recently, network-based methods and KGs, enhanced by advances in machine learning (ML) frameworks, have emerged as promising tools for inferring these unexplored associations. Given the technical limitations of the Neo4j Graph Data Science (GDS) machine learning pipeline, we developed a novel machine learning pipeline called KG2ML (Knowledge Graph to Machine Learning). This pipeline utilizes our Positive and Unlabeled (PU) learning algorithm, PULSNAR (Positive Unlabeled Learning Selected Not At Random), and incorporates path-based feature extraction from ProteinGraphML. Results: KG2ML was applied to 12 diseases, including Bipolar Disorder, Coronary Artery Disease, and Parkinson’s Disease, to infer disease-associated genes not explicitly recorded in DDKG. For several of these diseases, 14 out of the 15 top-ranked genes lacked prior explicit associations in the DDKG but were supported by literature and TINX (Target Importance and Novelty Explorer) evidence. Incorporating PULSNAR-imputed genes as positives enhanced XGBoost classification, demonstrating the potential of PU learning in identifying hidden gene-disease relationships. Conclusion: The observed improvement in classification performance after the inclusion of PULSNAR-imputed genes as positive examples, along with the subject matter experts’ (SME) evaluations of the top 15 imputed genes for 12 diseases, suggests that PU learning can effectively uncover disease-gene associations missing from existing knowledge graphs (KGs). By integrating KG data with ML-based inference, our KG2ML pipeline provides a scalable and interpretable framework to advance biomedical research while addressing the inherent limitations of current KGs.


  • Open Access

    Detecting Opioid Use Disorder in Health Claims Data With Positive Unlabeled Learning

    by Praveen Kumar, Fariha Moomtaheen, Scott A. Malec, Jeremy J. Yang, Cristian G. Bologa, Kristan A Schneider, Yiliang Zhu, Mauricio Tohen, Gerardo Villarreal, Douglas J. Perkins, et al.

    Accurate detection and prevalence estimation of behavioral health conditions, such as opioid use disorder (OUD), are crucial for identifying at-risk individuals, determining treatment needs, monitoring prevention and intervention efforts, and recruiting treatment-naive participants for clinical trials. The availability of extensive health data, combined with advancements in machine learning (ML) frameworks, has enabled researchers to employ various ML techniques to predict or identify OUD within patient health data. Ideally, we could directly estimate the prevalence, or the proportion of a population with a condition over time. However, underdiagnosis and undercoding of conditions in patient health records make it challenging to determine the true prevalence of these conditions and to identify at-risk patients with less severe conditions who are more likely to be missed. Consequently, patients without diagnoses may comprise positive and negative examples for a given condition. Treating all undiagnosed (uncoded) patients as negative when applying ML methods can introduce bias into models, affecting their predictive power. To address this issue, we employed Positive Unlabeled Learning Selected Not At Random (PULSNAR), a Positive and Unlabeled (PU) learning technique, to estimate the probability of a given patient having OUD during a time window and the overall population prevalence of OUD. In a sample of 3,342,044 commercially insured US patients with at least one opioid prescription filled, PULSNAR estimated that 5.08% of patients have a cumulative prevalence of OUD over a 2–5 a observation period, compared to the 1.35% with a recorded OUD diagnosis, with 73.5% of cases not diagnosed/coded. The prevalence estimates provided by PULSNAR are consistent with those reported in other studies.


  • Open Access

    TIN-X version 3: update with expanded dataset and modernized architecture for enhanced illumination of understudied targets

    by Vincent T. Metzger, Daniel C. Cannon, Jeremy J. Yang, Stephen L. Mathias, Cristian G. Bologa, Anna Waller, Stephan C. Schürer, Dušica Vidović, Keith J. Kelleher, Timothy K. Sheils, et al.

    TIN-X (Target Importance and Novelty eXplorer) is an interactive visualization tool for illuminating associations between diseases and potential drug targets and is publicly available at newdrugtargets.org. TIN-X uses natural language processing to identify disease and protein mentions within PubMed content using previously published tools for named entity recognition (NER) of gene/protein and disease names. Target data is obtained from the Target Central Resource Database (TCRD). Two important metrics, novelty and importance, are computed from this data and when plotted as log(importance) vs. log(novelty), aid the user in visually exploring the novelty of drug targets and their associated importance to diseases. TIN-X Version 3.0 has been significantly improved with an expanded dataset, modernized architecture including a REST API, and an improved user interface (UI). The dataset has been expanded to include not only PubMed publication titles and abstracts, but also full-text articles when available. This results in approximately 9-fold more target/disease associations compared to previous versions of TIN-X. Additionally, the TIN-X database containing this expanded dataset is now hosted in the cloud via Amazon RDS. Recent enhancements to the UI focuses on making it more intuitive for users to find diseases or drug targets of interest while providing a new, sortable table-view mode to accompany the existing plot-view mode. UI improvements also help the user browse the associated PubMed publications to explore and understand the basis of TIN-X’s predicted association between a specific disease and a target of interest. While implementing these upgrades, computational resources are balanced between the webserver and the user’s web browser to achieve adequate performance while accommodating the expanded dataset. Together, these advances aim to extend the duration that users can benefit from TIN-X while providing both an expanded dataset and new features that researchers can use to better illuminate understudied proteins.


  • Open Access

    Correction: Exploring DrugCentral: from molecular structures to clinical effects

    by Liliana Halip, Sorin Avram, Ramona Curpan, Ana Borota, Alina Bora, Cristian Bologa, Tudor I. Oprea

  • Open Access

    Toxicology knowledge graph for structural birth defects

    by John Erol Evangelista, Daniel J. B. Clarke, Zhuorui Xie, Giacomo B. Marino, Vivian Utti, Sherry L. Jenkins, Taha Mohseni Ahooyi, Cristian G. Bologa, Jeremy J. Yang, Jessica L. Binder, et al.

    Background: Birth defects are functional and structural abnormalities that impact about 1 in 33 births in the United States. They have been attributed to genetic and other factors such as drugs, cosmetics, food, and environmental pollutants during pregnancy, but for most birth defects there are no known causes. Methods: To further characterize associations between small molecule compounds and their potential to induce specific birth abnormalities, we gathered knowledge from multiple sources to construct a reproductive toxicity Knowledge Graph (ReproTox-KG) with a focus on associations between birth defects, drugs, and genes. Specifically, we gathered data from drug/birth-defect associations from co-mentions in published abstracts, gene/birth-defect associations from genetic studies, drug- and preclinical-compound-induced gene expression changes in cell lines, known drug targets, genetic burden scores for human genes, and placental crossing scores for small molecules. Results: Using ReproTox-KG and semi-supervised learning (SSL), we scored >30,000 preclinical small molecules for their potential to cross the placenta and induce birth defects, and identified >500 birth-defect/gene/drug cliques that can be used to explain molecular mechanisms for drug-induced birth defects. The ReproTox-KG can be accessed via a web-based user interface available at https://maayanlab.cloud/reprotox-kg. This site enables users to explore the associations between birth defects, approved and preclinical drugs, and all human genes. Conclusions: ReproTox-KG provides a resource for exploring knowledge about the molecular mechanisms of birth defects with the potential of predicting the likelihood of genes and preclinical small molecules to induce birth defects.