{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/130182"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/130182","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Applying generative adversarial networks to generate artificial genotype data in livestock","abstract":"Submission published under a 24 month embargo labeled 'Closed Access', the embargo will last until 2027-08-01","abstract_html":"Submission published under a 24 month embargo labeled 'Closed Access', the embargo will last until 2027-08-01","abstract_has_math":false,"creators":["Caballero Vargas, Edgar Giesus"],"institution":"University of Illinois Urbana-Champaign","degree_name":"M.S.","degree_level":"Thesis","degree_discipline":"Bioinformatics","degree_department":null,"school":null,"contributors":["Bresolin, Tiago","Wheeler, Matthew B","Roca, Alfred L."],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2025,"date_issued":"2025-07-21","date_published":"2025-07-21","updated_at":"2026-07-22T22:25:06Z","subjects":["Generative Artificial Intelligence Models","Synthetic Genotypes","Snp"],"languages":["en","eng"],"rights":["Copyright 2025 Edgar Caballero Vargas"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/2142/130182","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Bresolin, Tiago","Wheeler, Matthew B","Roca, Alfred L."]},{"key":"dc:creator","label":"Author","values":["Caballero Vargas, Edgar Giesus"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2025-07-21","2025-08"]},{"key":"dc:type","label":"Dc Type","values":["text"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Bioinformatics"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["M.S."]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["University of Illinois Urbana-Champaign"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Generative Artificial Intelligence Models","Synthetic Genotypes","Snp"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["en","eng"]},{"key":"dc:rights","label":"Dc Rights","values":["Copyright 2025 Edgar Caballero Vargas"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://hdl.handle.net/2142/130182"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Submission published under a 24 month embargo labeled 'Closed Access', the embargo will last until 2027-08-01","The student, Edgar Caballero Vargas, accepted the attached license on 2025-07-14 at 14:56.","The student, Edgar Caballero Vargas, submitted this Thesis for approval on 2025-07-14 at 15:14.","This Thesis was approved for publication on 2025-07-21 at 09:29.","DSpace SAF Submission Ingestion Package generated from Vireo submission #22555 on 2025-10-25 at 15:53:54","Genomics studies in livestock remain limited due to financial, ethical, or privacy considerations that restrict collaboration and data accessibility. To address these challenges, generative artificial intelligence models, such as Generative Adversarial Network (GAN), are being applied to generate biologically plausible synthetic data without compromising these standards. In this study, we trained a Principal Component (PC) Wasserstein GAN (PC-WGAN) with a gradient penalty to synthesize Single Nucleotide Polymorphism (SNP) in the principal component space. We used a simulated genotype dataset from 4,800 individuals and 37,540 SNP from chromosome 1, and retained 796 PC, which explained 90% of the total variance. These PC scores were used to generate synthetic PC scores and inverse transformed to SNP data. The validity of synthetic SNP data was assessed using both quantitative and visual approaches. Quantitatively, the Pearson correlation between the linkage disequilibrium (LD) values and minor allele frequency (MAF) distributions of the real and synthetic SNP datasets was calculated for comparison. Visually, the PC plots, LD decay curves, and MAF histograms were inspected to compare the distributions and structural patterns of the generated and real data. At 150 training epochs, the model effectively captured the major features of the real population, producing synthetic genotypes that overlapped with real genotypes in PC space and preserved long-range LD patterns and MAF distributions. While synthetic genotypes cannot replace real genomic data, our findings demonstrate that PC-WGAN produces biologically plausible artificial genotypes, offering a promising approach for future work in data augmentation, model benchmarking, and privacy-preserving livestock genomic research."]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Applying generative adversarial networks to generate artificial genotype data in livestock"]}]}],"canonical_facts":{"dc:contributor":["Bresolin, Tiago","Wheeler, Matthew B","Roca, Alfred L."],"dc:creator":["Caballero Vargas, Edgar Giesus"],"dc:date":["2025-07-21","2025-08"],"dc:description":["Submission published under a 24 month embargo labeled 'Closed Access', the embargo will last until 2027-08-01","The student, Edgar Caballero Vargas, accepted the attached license on 2025-07-14 at 14:56.","The student, Edgar Caballero Vargas, submitted this Thesis for approval on 2025-07-14 at 15:14.","This Thesis was approved for publication on 2025-07-21 at 09:29.","DSpace SAF Submission Ingestion Package generated from Vireo submission #22555 on 2025-10-25 at 15:53:54","Genomics studies in livestock remain limited due to financial, ethical, or privacy considerations that restrict collaboration and data accessibility. To address these challenges, generative artificial intelligence models, such as Generative Adversarial Network (GAN), are being applied to generate biologically plausible synthetic data without compromising these standards. In this study, we trained a Principal Component (PC) Wasserstein GAN (PC-WGAN) with a gradient penalty to synthesize Single Nucleotide Polymorphism (SNP) in the principal component space. We used a simulated genotype dataset from 4,800 individuals and 37,540 SNP from chromosome 1, and retained 796 PC, which explained 90% of the total variance. These PC scores were used to generate synthetic PC scores and inverse transformed to SNP data. The validity of synthetic SNP data was assessed using both quantitative and visual approaches. Quantitatively, the Pearson correlation between the linkage disequilibrium (LD) values and minor allele frequency (MAF) distributions of the real and synthetic SNP datasets was calculated for comparison. Visually, the PC plots, LD decay curves, and MAF histograms were inspected to compare the distributions and structural patterns of the generated and real data. At 150 training epochs, the model effectively captured the major features of the real population, producing synthetic genotypes that overlapped with real genotypes in PC space and preserved long-range LD patterns and MAF distributions. While synthetic genotypes cannot replace real genomic data, our findings demonstrate that PC-WGAN produces biologically plausible artificial genotypes, offering a promising approach for future work in data augmentation, model benchmarking, and privacy-preserving livestock genomic research."],"dc:format":["application/pdf"],"dc:identifier":["https://hdl.handle.net/2142/130182"],"dc:language":["en","eng"],"dc:rights":["Copyright 2025 Edgar Caballero Vargas"],"dc:subject":["Generative Artificial Intelligence Models","Synthetic Genotypes","Snp"],"dc:title":["Applying generative adversarial networks to generate artificial genotype data in livestock"],"dc:type":["text"],"thesis:degree_discipline":["Bioinformatics"],"thesis:degree_level":["Thesis"],"thesis:degree_name":["M.S."],"thesis:institution_name":["University of Illinois Urbana-Champaign"]},"updated_at":"2026-07-22T22:25:06Z"}