1
|
Chan LE, Casiraghi E, Reese J, Harmon QE, Schaper K, Hegde H, Valentini G, Schmitt C, Motsinger-Reif A, Hall JE, Mungall CJ, Robinson PN, Haendel MA. Predicting nutrition and environmental factors associated with female reproductive disorders using a knowledge graph and random forests. Int J Med Inform 2024; 187:105461. [PMID: 38643701 DOI: 10.1016/j.ijmedinf.2024.105461] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/11/2023] [Revised: 04/09/2024] [Accepted: 04/16/2024] [Indexed: 04/23/2024]
Abstract
OBJECTIVE Female reproductive disorders (FRDs) are common health conditions that may present with significant symptoms. Diet and environment are potential areas for FRD interventions. We utilized a knowledge graph (KG) method to predict factors associated with common FRDs (for example, endometriosis, ovarian cyst, and uterine fibroids). MATERIALS AND METHODS We harmonized survey data from the Personalized Environment and Genes Study (PEGS) on internal and external environmental exposures and health conditions with biomedical ontology content. We merged the harmonized data and ontologies with supplemental nutrient and agricultural chemical data to create a KG. We analyzed the KG by embedding edges and applying a random forest for edge prediction to identify variables potentially associated with FRDs. We also conducted logistic regression analysis for comparison. RESULTS Across 9765 PEGS respondents, the KG analysis resulted in 8535 significant or suggestive predicted links between FRDs and chemicals, phenotypes, and diseases. Amongst these links, 32 were exact matches when compared with the logistic regression results, including comorbidities, medications, foods, and occupational exposures. DISCUSSION Mechanistic underpinnings of predicted links documented in the literature may support some of our findings. Our KG methods are useful for predicting possible associations in large, survey-based datasets with added information on directionality and magnitude of effect from logistic regression. These results should not be construed as causal but can support hypothesis generation. CONCLUSION This investigation enabled the generation of hypotheses on a variety of potential links between FRDs and exposures. Future investigations should prospectively evaluate the variables hypothesized to impact FRDs.
Collapse
Affiliation(s)
- Lauren E Chan
- Oregon State University, College of Public Health and Human Sciences, Corvallis, OR, USA.
| | - Elena Casiraghi
- AnacletoLab, Dipartimento di Informatica, Università degli Studi di Milano, Italy; Environmental Genomics and Systems Biology Division, Lawrence Berkeley National Laboratory, Berkeley, CA, USA; European Laboratory for Learning and Intelligent Systems, ELLIS
| | - Justin Reese
- Environmental Genomics and Systems Biology Division, Lawrence Berkeley National Laboratory, Berkeley, CA, USA
| | - Quaker E Harmon
- National Institute of Environmental Health Sciences, Epidemiology Branch, Durham, NC, USA
| | - Kevin Schaper
- University of Colorado Anschutz Medical Campus, Aurora, CO, USA
| | - Harshad Hegde
- Environmental Genomics and Systems Biology Division, Lawrence Berkeley National Laboratory, Berkeley, CA, USA
| | - Giorgio Valentini
- AnacletoLab, Dipartimento di Informatica, Università degli Studi di Milano, Italy; European Laboratory for Learning and Intelligent Systems, ELLIS
| | - Charles Schmitt
- National Institute of Environmental Health Sciences, Office of Data Science, Durham, NC, USA
| | - Alison Motsinger-Reif
- National Institute of Environmental Health Sciences, Biostatistics & Computational Biology Branch, Durham, NC, USA
| | - Janet E Hall
- National Institute of Environmental Health Sciences, Clinical Research Branch, Durham, NC, USA
| | - Christopher J Mungall
- Environmental Genomics and Systems Biology Division, Lawrence Berkeley National Laboratory, Berkeley, CA, USA
| | - Peter N Robinson
- European Laboratory for Learning and Intelligent Systems, ELLIS; The Jackson Laboratory for Genomic Medicine, 10 Discovery Drive, Farmington, CT, USA
| | - Melissa A Haendel
- University of North Carolina, Dept. of Genetics, Chapel Hill, NC, USA
| |
Collapse
|
2
|
Callahan TJ, Tripodi IJ, Stefanski AL, Cappelletti L, Taneja SB, Wyrwa JM, Casiraghi E, Matentzoglu NA, Reese J, Silverstein JC, Hoyt CT, Boyce RD, Malec SA, Unni DR, Joachimiak MP, Robinson PN, Mungall CJ, Cavalleri E, Fontana T, Valentini G, Mesiti M, Gillenwater LA, Santangelo B, Vasilevsky NA, Hoehndorf R, Bennett TD, Ryan PB, Hripcsak G, Kahn MG, Bada M, Baumgartner WA, Hunter LE. An open source knowledge graph ecosystem for the life sciences. Sci Data 2024; 11:363. [PMID: 38605048 PMCID: PMC11009265 DOI: 10.1038/s41597-024-03171-w] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/26/2023] [Accepted: 03/21/2024] [Indexed: 04/13/2024] Open
Abstract
Translational research requires data at multiple scales of biological organization. Advancements in sequencing and multi-omics technologies have increased the availability of these data, but researchers face significant integration challenges. Knowledge graphs (KGs) are used to model complex phenomena, and methods exist to construct them automatically. However, tackling complex biomedical integration problems requires flexibility in the way knowledge is modeled. Moreover, existing KG construction methods provide robust tooling at the cost of fixed or limited choices among knowledge representation models. PheKnowLator (Phenotype Knowledge Translator) is a semantic ecosystem for automating the FAIR (Findable, Accessible, Interoperable, and Reusable) construction of ontologically grounded KGs with fully customizable knowledge representation. The ecosystem includes KG construction resources (e.g., data preparation APIs), analysis tools (e.g., SPARQL endpoint resources and abstraction algorithms), and benchmarks (e.g., prebuilt KGs). We evaluated the ecosystem by systematically comparing it to existing open-source KG construction methods and by analyzing its computational performance when used to construct 12 different large-scale KGs. With flexible knowledge representation, PheKnowLator enables fully customizable KGs without compromising performance or usability.
Collapse
Affiliation(s)
- Tiffany J Callahan
- Computational Bioscience Program, University of Colorado Anschutz Medical Campus, Aurora, CO, 80045, USA.
- Department of Biomedical Informatics, Columbia University Irving Medical Center, New York, NY, 10032, USA.
| | - Ignacio J Tripodi
- Computer Science Department, Interdisciplinary Quantitative Biology, University of Colorado Boulder, Boulder, CO, 80301, USA
| | - Adrianne L Stefanski
- Computational Bioscience Program, University of Colorado Anschutz Medical Campus, Aurora, CO, 80045, USA
| | - Luca Cappelletti
- AnacletoLab, Dipartimento di Informatica, Universit`a degli Studi di Milano, Via Celoria 18, 20133, Milan, Italy
| | - Sanya B Taneja
- Intelligent Systems Program, University of Pittsburgh, Pittsburgh, PA, 15260, USA
| | - Jordan M Wyrwa
- Department of Physical Medicine and Rehabilitation, School of Medicine, University of Colorado Anschutz Medical Campus, Aurora, CO, 80045, USA
| | - Elena Casiraghi
- AnacletoLab, Dipartimento di Informatica, Universit`a degli Studi di Milano, Via Celoria 18, 20133, Milan, Italy
- Division of Environmental Genomics and Systems Biology, Lawrence Berkeley National Laboratory, Berkeley, CA, 94720, USA
| | | | - Justin Reese
- Division of Environmental Genomics and Systems Biology, Lawrence Berkeley National Laboratory, Berkeley, CA, 94720, USA
| | - Jonathan C Silverstein
- Department of Biomedical Informatics, University of Pittsburgh School of Medicine, Pittsburgh, PA, 15206, USA
| | - Charles Tapley Hoyt
- Laboratory of Systems Pharmacology, Harvard Medical School, Boston, MA, 02115, USA
| | - Richard D Boyce
- Department of Biomedical Informatics, University of Pittsburgh School of Medicine, Pittsburgh, PA, 15206, USA
| | - Scott A Malec
- Division of Translational Informatics, University of New Mexico School of Medicine, Albuquerque, NM, 87131, USA
| | - Deepak R Unni
- SIB Swiss Institute of Bioinformatics, Basel, Switzerland
| | - Marcin P Joachimiak
- Division of Environmental Genomics and Systems Biology, Lawrence Berkeley National Laboratory, Berkeley, CA, 94720, USA
| | - Peter N Robinson
- Berlin Institute of Health at Charité-Universitatsmedizin, 10117, Berlin, Germany
| | - Christopher J Mungall
- Division of Environmental Genomics and Systems Biology, Lawrence Berkeley National Laboratory, Berkeley, CA, 94720, USA
| | - Emanuele Cavalleri
- AnacletoLab, Dipartimento di Informatica, Universit`a degli Studi di Milano, Via Celoria 18, 20133, Milan, Italy
| | - Tommaso Fontana
- AnacletoLab, Dipartimento di Informatica, Universit`a degli Studi di Milano, Via Celoria 18, 20133, Milan, Italy
| | - Giorgio Valentini
- AnacletoLab, Dipartimento di Informatica, Universit`a degli Studi di Milano, Via Celoria 18, 20133, Milan, Italy
- ELLIS, European Laboratory for Learning and Intelligent Systems, Milan Unit, Italy
| | - Marco Mesiti
- AnacletoLab, Dipartimento di Informatica, Universit`a degli Studi di Milano, Via Celoria 18, 20133, Milan, Italy
| | - Lucas A Gillenwater
- Computational Bioscience Program, University of Colorado Anschutz Medical Campus, Aurora, CO, 80045, USA
- Department of Biomedical Informatics, University of Colorado School of Medicine, Aurora, CO, 80045, USA
| | - Brook Santangelo
- Computational Bioscience Program, University of Colorado Anschutz Medical Campus, Aurora, CO, 80045, USA
- Department of Biomedical Informatics, University of Colorado School of Medicine, Aurora, CO, 80045, USA
| | - Nicole A Vasilevsky
- Data Collaboration Center, Critical Path Institute, 1840 E River Rd. Suite 100, Tucson, AZ, 85718, USA
| | - Robert Hoehndorf
- Computer, Electrical and Mathematical Sciences & Engineering Division, Computational Bioscience Research Center, King Abdullah University of Science and Technology, Thuwal, 23955-6900, Kingdom of Saudi Arabia
| | - Tellen D Bennett
- Department of Biomedical Informatics, University of Colorado School of Medicine, Aurora, CO, 80045, USA
- Department of Pediatrics, University of Colorado School of Medicine, Aurora, CO, 80045, USA
| | - Patrick B Ryan
- Janssen Research and Development, Raritan, NJ, 08869, USA
| | - George Hripcsak
- Department of Biomedical Informatics, Columbia University Irving Medical Center, New York, NY, 10032, USA
| | - Michael G Kahn
- Department of Biomedical Informatics, University of Colorado School of Medicine, Aurora, CO, 80045, USA
| | - Michael Bada
- Division of General Internal Medicine, University of Colorado School of Medicine, Aurora, CO, 80045, USA
| | - William A Baumgartner
- Division of General Internal Medicine, University of Colorado School of Medicine, Aurora, CO, 80045, USA.
| | - Lawrence E Hunter
- Computational Bioscience Program, University of Colorado Anschutz Medical Campus, Aurora, CO, 80045, USA.
- Department of Biomedical Informatics, University of Colorado School of Medicine, Aurora, CO, 80045, USA.
| |
Collapse
|
3
|
Valentini G. Exploring the similarity between genetic diseases improves their differential diagnosis and the understanding of their etiology. Eur J Hum Genet 2024; 32:373-374. [PMID: 38273167 PMCID: PMC10999431 DOI: 10.1038/s41431-024-01535-9] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/27/2023] [Accepted: 01/09/2024] [Indexed: 01/27/2024] Open
Affiliation(s)
- Giorgio Valentini
- AnacletoLab, Department of Computer Science, University of Milan, Via Celoria 18, Milan, Italy.
| |
Collapse
|
4
|
Cappelletti L, Rekerle L, Fontana T, Hansen P, Casiraghi E, Ravanmehr V, Mungall CJ, Yang JJ, Spranger L, Karlebach G, Caufield JH, Carmody L, Coleman B, Oprea TI, Reese J, Valentini G, Robinson PN. Node-degree aware edge sampling mitigates inflated classification performance in biomedical random walk-based graph representation learning. BIOINFORMATICS ADVANCES 2024; 4:vbae036. [PMID: 38577542 PMCID: PMC10994718 DOI: 10.1093/bioadv/vbae036] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 01/11/2023] [Revised: 01/31/2024] [Accepted: 02/29/2024] [Indexed: 04/06/2024]
Abstract
Motivation Graph representation learning is a family of related approaches that learn low-dimensional vector representations of nodes and other graph elements called embeddings. Embeddings approximate characteristics of the graph and can be used for a variety of machine-learning tasks such as novel edge prediction. For many biomedical applications, partial knowledge exists about positive edges that represent relationships between pairs of entities, but little to no knowledge is available about negative edges that represent the explicit lack of a relationship between two nodes. For this reason, classification procedures are forced to assume that the vast majority of unlabeled edges are negative. Existing approaches to sampling negative edges for training and evaluating classifiers do so by uniformly sampling pairs of nodes. Results We show here that this sampling strategy typically leads to sets of positive and negative examples with imbalanced node degree distributions. Using representative heterogeneous biomedical knowledge graph and random walk-based graph machine learning, we show that this strategy substantially impacts classification performance. If users of graph machine-learning models apply the models to prioritize examples that are drawn from approximately the same distribution as the positive examples are, then performance of models as estimated in the validation phase may be artificially inflated. We present a degree-aware node sampling approach that mitigates this effect and is simple to implement. Availability and implementation Our code and data are publicly available at https://github.com/monarch-initiative/negativeExampleSelection.
Collapse
Affiliation(s)
- Luca Cappelletti
- AnacletoLab, Dipartimento di Informatica, Università degli Studi di Milano, Milano 20133, Italy
| | - Lauren Rekerle
- The Jackson Laboratory for Genomic Medicine, CT 06032, United States
| | - Tommaso Fontana
- AnacletoLab, Dipartimento di Informatica, Università degli Studi di Milano, Milano 20133, Italy
| | - Peter Hansen
- The Jackson Laboratory for Genomic Medicine, CT 06032, United States
| | - Elena Casiraghi
- AnacletoLab, Dipartimento di Informatica, Università degli Studi di Milano, Milano 20133, Italy
- Division of Environmental Genomics and Systems Biology, Lawrence Berkeley National Laboratory, Berkeley, CA 94710, United States
| | - Vida Ravanmehr
- The Jackson Laboratory for Genomic Medicine, CT 06032, United States
| | - Christopher J Mungall
- Division of Environmental Genomics and Systems Biology, Lawrence Berkeley National Laboratory, Berkeley, CA 94710, United States
| | - Jeremy J Yang
- Department of Internal Medicine and UNM Comprehensive Cancer Center, UNM School of Medicine, Albuquerque, NM 87102, United States
| | - Leonard Spranger
- Institute of Bioinformatics, Freie Universität Berlin, Berlin, 14195, Germany
| | - Guy Karlebach
- The Jackson Laboratory for Genomic Medicine, CT 06032, United States
| | - J Harry Caufield
- Division of Environmental Genomics and Systems Biology, Lawrence Berkeley National Laboratory, Berkeley, CA 94710, United States
| | - Leigh Carmody
- The Jackson Laboratory for Genomic Medicine, CT 06032, United States
| | - Ben Coleman
- The Jackson Laboratory for Genomic Medicine, CT 06032, United States
- Institute for Systems Genomics, University of Connecticut, Farmington, CT 06032, United States
| | - Tudor I Oprea
- Department of Internal Medicine and UNM Comprehensive Cancer Center, UNM School of Medicine, Albuquerque, NM 87102, United States
| | - Justin Reese
- Division of Environmental Genomics and Systems Biology, Lawrence Berkeley National Laboratory, Berkeley, CA 94710, United States
| | - Giorgio Valentini
- AnacletoLab, Dipartimento di Informatica, Università degli Studi di Milano, Milano 20133, Italy
- ELLIS—European Laboratory for Learning and Intelligent Systems
| | - Peter N Robinson
- The Jackson Laboratory for Genomic Medicine, CT 06032, United States
- Institute for Systems Genomics, University of Connecticut, Farmington, CT 06032, United States
- ELLIS—European Laboratory for Learning and Intelligent Systems
- Berlin Institute of Health, Charité – Universitätsmedizin Berlin, Berlin, 10117, Germany
| |
Collapse
|
5
|
Menand N, Seshadhri C. Link prediction using low-dimensional node embeddings: The measurement problem. Proc Natl Acad Sci U S A 2024; 121:e2312527121. [PMID: 38363864 PMCID: PMC10895345 DOI: 10.1073/pnas.2312527121] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/21/2023] [Accepted: 01/09/2024] [Indexed: 02/18/2024] Open
Abstract
Graph representation learning is a fundamental technique for machine learning (ML) on complex networks. Given an input network, these methods represent the vertices by low-dimensional real-valued vectors. These vectors can be used for a multitude of downstream ML tasks. We study one of the most important such task, link prediction. Much of the recent literature on graph representation learning has shown remarkable success in link prediction. On closer investigation, we observe that the performance is measured by the AUC (area under the curve), which suffers biases. Since the ground truth in link prediction is sparse, we design a vertex-centric measure of performance, called the VCMPR@k plots. Under this measure, we show that link predictors using graph representations show poor scores. Despite having extremely high AUC scores, the predictors miss much of the ground truth. We identify a mathematical connection between this performance, the sparsity of the ground truth, and the low-dimensional geometry of the node embeddings. Under a formal theoretical framework, we prove that low-dimensional vectors cannot capture sparse ground truth using dot product similarities (the standard practice in the literature). Our results call into question existing results on link prediction and pose a significant scientific challenge for graph representation learning. The VCMPR plots identify specific scientific challenges for link prediction using low-dimensional node embeddings.
Collapse
Affiliation(s)
- Nicolas Menand
- Department of Computer and Information Science, University of Pennsylvania, Philadelphia, PA 19104
| | - C Seshadhri
- Department of Computer Science, University of California, Santa Cruz, CA 95064
| |
Collapse
|
6
|
Putman TE, Schaper K, Matentzoglu N, Rubinetti V, Alquaddoomi F, Cox C, Caufield JH, Elsarboukh G, Gehrke S, Hegde H, Reese J, Braun I, Bruskiewich R, Cappelletti L, Carbon S, Caron A, Chan L, Chute C, Cortes K, De Souza V, Fontana T, Harris N, Hartley E, Hurwitz E, Jacobsen JB, Krishnamurthy M, Laraway B, McLaughlin J, McMurry J, Moxon ST, Mullen K, O’Neil S, Shefchek K, Stefancsik R, Toro S, Vasilevsky N, Walls R, Whetzel P, Osumi-Sutherland D, Smedley D, Robinson P, Mungall C, Haendel M, Munoz-Torres M. The Monarch Initiative in 2024: an analytic platform integrating phenotypes, genes and diseases across species. Nucleic Acids Res 2024; 52:D938-D949. [PMID: 38000386 PMCID: PMC10767791 DOI: 10.1093/nar/gkad1082] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/18/2023] [Revised: 10/21/2023] [Accepted: 11/02/2023] [Indexed: 11/26/2023] Open
Abstract
Bridging the gap between genetic variations, environmental determinants, and phenotypic outcomes is critical for supporting clinical diagnosis and understanding mechanisms of diseases. It requires integrating open data at a global scale. The Monarch Initiative advances these goals by developing open ontologies, semantic data models, and knowledge graphs for translational research. The Monarch App is an integrated platform combining data about genes, phenotypes, and diseases across species. Monarch's APIs enable access to carefully curated datasets and advanced analysis tools that support the understanding and diagnosis of disease for diverse applications such as variant prioritization, deep phenotyping, and patient profile-matching. We have migrated our system into a scalable, cloud-based infrastructure; simplified Monarch's data ingestion and knowledge graph integration systems; enhanced data mapping and integration standards; and developed a new user interface with novel search and graph navigation features. Furthermore, we advanced Monarch's analytic tools by developing a customized plugin for OpenAI's ChatGPT to increase the reliability of its responses about phenotypic data, allowing us to interrogate the knowledge in the Monarch graph using state-of-the-art Large Language Models. The resources of the Monarch Initiative can be found at monarchinitiative.org and its corresponding code repository at github.com/monarch-initiative/monarch-app.
Collapse
Affiliation(s)
- Tim E Putman
- Department of Biomedical Informatics, University of Colorado Anschutz Medical Campus, Aurora, CO 80045, USA
| | - Kevin Schaper
- Department of Biomedical Informatics, University of Colorado Anschutz Medical Campus, Aurora, CO 80045, USA
| | | | - Vincent P Rubinetti
- Department of Biomedical Informatics, University of Colorado Anschutz Medical Campus, Aurora, CO 80045, USA
| | - Faisal S Alquaddoomi
- Department of Biomedical Informatics, University of Colorado Anschutz Medical Campus, Aurora, CO 80045, USA
| | - Corey Cox
- Department of Biomedical Informatics, University of Colorado Anschutz Medical Campus, Aurora, CO 80045, USA
| | - J Harry Caufield
- Environmental Genomics and Systems Biology, Lawrence Berkeley National Laboratory, Berkeley, CA 94720, USA
| | - Glass Elsarboukh
- Department of Biomedical Informatics, University of Colorado Anschutz Medical Campus, Aurora, CO 80045, USA
| | - Sarah Gehrke
- Department of Biomedical Informatics, University of Colorado Anschutz Medical Campus, Aurora, CO 80045, USA
| | - Harshad Hegde
- Environmental Genomics and Systems Biology, Lawrence Berkeley National Laboratory, Berkeley, CA 94720, USA
| | - Justin T Reese
- Environmental Genomics and Systems Biology, Lawrence Berkeley National Laboratory, Berkeley, CA 94720, USA
| | - Ian Braun
- Data Collaboration Center, Critical Path Institute, Tucson, AZ 85718, USA
| | | | | | - Seth Carbon
- Environmental Genomics and Systems Biology, Lawrence Berkeley National Laboratory, Berkeley, CA 94720, USA
| | - Anita R Caron
- European Bioinformatics Institute (EMBL-EBI), Hinxton CB10 1SD, UK
| | - Lauren E Chan
- College of Public Health and Human Sciences, Oregon State University, Corvallis, OR 97331, USA
| | - Christopher G Chute
- Schools of Medicine, Public Health, and Nursing, Johns Hopkins University, Baltimore, MD 21205, USA
| | - Katherina G Cortes
- Department of Biomedical Informatics, University of Colorado Anschutz Medical Campus, Aurora, CO 80045, USA
| | | | - Tommaso Fontana
- Dipartimento di Informatica, Università degli Studi di Milano Statale, Milano, Italy
| | - Nomi L Harris
- Environmental Genomics and Systems Biology, Lawrence Berkeley National Laboratory, Berkeley, CA 94720, USA
| | - Emily L Hartley
- Data Collaboration Center, Critical Path Institute, Tucson, AZ 85718, USA
| | - Eric Hurwitz
- Department of Biomedical Informatics, University of Colorado Anschutz Medical Campus, Aurora, CO 80045, USA
| | - Julius O B Jacobsen
- William Harvey Research Institute, Queen Mary University of London, London EC1M 6BQ, UK
| | - Madan Krishnamurthy
- Department of Biomedical Informatics, University of Colorado Anschutz Medical Campus, Aurora, CO 80045, USA
| | - Bryan J Laraway
- Department of Biomedical Informatics, University of Colorado Anschutz Medical Campus, Aurora, CO 80045, USA
| | | | - Julie A McMurry
- Department of Biomedical Informatics, University of Colorado Anschutz Medical Campus, Aurora, CO 80045, USA
| | - Sierra A T Moxon
- Environmental Genomics and Systems Biology, Lawrence Berkeley National Laboratory, Berkeley, CA 94720, USA
| | - Kathleen R Mullen
- Department of Biomedical Informatics, University of Colorado Anschutz Medical Campus, Aurora, CO 80045, USA
| | - Shawn T O’Neil
- Department of Biomedical Informatics, University of Colorado Anschutz Medical Campus, Aurora, CO 80045, USA
| | - Kent A Shefchek
- Department of Biomedical Informatics, University of Colorado Anschutz Medical Campus, Aurora, CO 80045, USA
| | - Ray Stefancsik
- European Bioinformatics Institute (EMBL-EBI), Hinxton CB10 1SD, UK
| | - Sabrina Toro
- Department of Biomedical Informatics, University of Colorado Anschutz Medical Campus, Aurora, CO 80045, USA
| | | | - Ramona L Walls
- Data Collaboration Center, Critical Path Institute, Tucson, AZ 85718, USA
| | - Patricia L Whetzel
- Department of Biomedical Informatics, University of Colorado Anschutz Medical Campus, Aurora, CO 80045, USA
| | | | - Damian Smedley
- William Harvey Research Institute, Queen Mary University of London, London EC1M 6BQ, UK
| | - Peter N Robinson
- The Jackson Laboratory for Genomic Medicine, Farmington, CT 6032, USA
| | - Christopher J Mungall
- Environmental Genomics and Systems Biology, Lawrence Berkeley National Laboratory, Berkeley, CA 94720, USA
| | - Melissa A Haendel
- Department of Biomedical Informatics, University of Colorado Anschutz Medical Campus, Aurora, CO 80045, USA
| | - Monica C Munoz-Torres
- Department of Biomedical Informatics, University of Colorado Anschutz Medical Campus, Aurora, CO 80045, USA
| |
Collapse
|
7
|
Cover runners-up of 2023. NATURE COMPUTATIONAL SCIENCE 2024; 4:1. [PMID: 38287197 DOI: 10.1038/s43588-024-00592-w] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 01/31/2024]
|
8
|
Chan LE, Casiraghi E, Putman T, Reese J, Harmon QE, Schaper K, Hedge H, Valentini G, Schmitt C, Motsinger-Reif A, Hall JE, Mungall CJ, Robinson PN, Haendel MA. Predicting nutrition and environmental factors associated with female reproductive disorders using a knowledge graph and random forests. MEDRXIV : THE PREPRINT SERVER FOR HEALTH SCIENCES 2023:2023.07.14.23292679. [PMID: 37502882 PMCID: PMC10371183 DOI: 10.1101/2023.07.14.23292679] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 07/29/2023]
Abstract
Objective Female reproductive disorders (FRDs) are common health conditions that may present with significant symptoms. Diet and environment are potential areas for FRD interventions. We utilized a knowledge graph (KG) method to predict factors associated with common FRDs (e.g., endometriosis, ovarian cyst, and uterine fibroids). Materials and Methods We harmonized survey data from the Personalized Environment and Genes Study on internal and external environmental exposures and health conditions with biomedical ontology content. We merged the harmonized data and ontologies with supplemental nutrient and agricultural chemical data to create a KG. We analyzed the KG by embedding edges and applying a random forest for edge prediction to identify variables potentially associated with FRDs. We also conducted logistic regression analysis for comparison. Results Across 9765 PEGS respondents, the KG analysis resulted in 8535 significant predicted links between FRDs and chemicals, phenotypes, and diseases. Amongst these links, 32 were exact matches when compared with the logistic regression results, including comorbidities, medications, foods, and occupational exposures. Discussion Mechanistic underpinnings of predicted links documented in the literature may support some of our findings. Our KG methods are useful for predicting possible associations in large, survey-based datasets with added information on directionality and magnitude of effect from logistic regression. These results should not be construed as causal, but can support hypothesis generation. Conclusion This investigation enabled the generation of hypotheses on a variety of potential links between FRDs and exposures. Future investigations should prospectively evaluate the variables hypothesized to impact FRDs.
Collapse
Affiliation(s)
- Lauren E Chan
- Oregon State University, College of Public Health and Human Sciences, Corvallis, OR, USA
| | - Elena Casiraghi
- AnacletoLab, Dipartimento di Informatica, Università degli Studi di Milano, Italy
- Environmental Genomics and Systems Biology Division, Lawrence Berkeley National Laboratory, Berkeley, CA, USA
| | - Tim Putman
- University of Colorado Anschutz Medical Campus, Aurora, CO, USA
| | - Justin Reese
- Environmental Genomics and Systems Biology Division, Lawrence Berkeley National Laboratory, Berkeley, CA, USA
| | - Quaker E Harmon
- National Institute of Environmental Health Sciences, Epidemiology Branch, Durham, NC, USA
| | - Kevin Schaper
- University of Colorado Anschutz Medical Campus, Aurora, CO, USA
| | - Harshad Hedge
- Environmental Genomics and Systems Biology Division, Lawrence Berkeley National Laboratory, Berkeley, CA, USA
| | - Giorgio Valentini
- AnacletoLab, Dipartimento di Informatica, Università degli Studi di Milano, Italy
| | - Charles Schmitt
- National Institute of Environmental Health Sciences, Office of Data Science, Durham, NC, USA
| | - Alison Motsinger-Reif
- National Institute of Environmental Health Sciences, Biostatistics & Computational Biology Branch, Durham, NC, USA
| | - Janet E Hall
- National Institute of Environmental Health Sciences, Clinical Research Branch, Durham, NC, USA
| | - Christopher J Mungall
- Environmental Genomics and Systems Biology Division, Lawrence Berkeley National Laboratory, Berkeley, CA, USA
| | - Peter N Robinson
- The Jackson Laboratory for Genomic Medicine, 10 Discovery Drive, Farmington, CT, USA
| | | |
Collapse
|