Applying gradient tree boosting to QTL mapping with Shapley additive explanations
デジタルデータあり（科学技術振興機構）
すぐに読む
J-STAGE
全国の図書館の所蔵
国立国会図書館サーチが連携している各図書館等から取得した所蔵情報を表示します。
所蔵館、利用可否等の詳細・最新状況は情報提供元の各館のサイト・データベースで直接ご確認ください。所蔵館から取寄せることが可能かなど、資料の利用方法は、ご自身が利用されるお近くの図書館へご相談ください。詳細は ヘルプ をご覧ください。
その他
J-STAGE
デジタルCiNii Research
検索サービスデジタル遷移先のサイトで、CiNii Researchが連携している機関・データベースの所蔵状況を確認できます。
書誌情報
この資料の詳細や典拠（同じ主題の資料を指すキーワード、著者名）等を確認できます。
- 資料種別
- 記事
- 著者・編者
- Tomohiro IshibashiAkio Onogi
- タイトル（掲載誌）
- Breeding science
- 巻号年月日等（掲載誌）
- 75(5):2025.12
- 掲載巻
- 75
- 掲載号
- 5
- 掲載ページ
- 378-391
- 掲載年月日（W3CDTF）
- 2025-12
- ISSN（掲載誌）
- 1344-7610
- ISSN-L（掲載誌）
- 1344-7610
- 出版事項（掲載誌）
- Kyoto : Japanese Society of Breeding
- 出版地（国名コード）
- JP
- 本文の言語コード
- eng
- NDLC
- 対象利用者
- 一般
- 所蔵機関
- 国立国会図書館
- 請求記号
- Z54-J372
- 連携機関・データベース
- 国立国会図書館 : 国立国会図書館雑誌記事索引
- 書誌ID（NDLBibID）
- 034474597
- 整理区分コード
- 632
- 要約等
- <p>Mapping quantitative trait loci (QTLs) is one of the major goals of quantitative genetics; however, identifying the interactions between QTLs (i.e., epistasis) remains challenging. Recently developed machine learning methods, such as deep learning and gradient boosting, are transforming the real world. These methods could advance QTL mapping methodologies because of their high capability for capturing complex relationships among features. One problem with applying such complex models to QTL mapping is the evaluation of feature importance. In this study, XGBoost, a popular gradient tree boosting algorithm, was applied for QTL mapping in biparental populations with Shapley additive explanations (SHAPs). SHAP is a local (i.e., instance-wise) importance index with the desired properties as feature importance indices. The SHAP-assisted XGBoost (SHAP-XGB) was compared with conventional methods, including composite interval mapping (CIM), multiple interval mapping (MIM), inclusive CIM (ICIM), and BayesC, using simulations and rice heading date data. SHAP-XGB performed comparably to CIM, MIM, ICIM, and BayesC in mapping main QTL effects and was superior to MIM, ICIM, and BayesC in mapping QTL interaction effects. As SHAP can evaluate local importance, interactions between markers can be visualized by plotting SHAP interaction values for each instance (plant/line). These results illustrated the strength of SHAP-XGB in detecting and interpreting epistatic QTLs and suggest the possibility that SHAP-XGB complements conventional methods.</p>
- DOI
- 10.1270/jsbbs.24083
- オンライン閲覧公開範囲
- インターネット公開
- 連携機関・データベース
- 科学技術振興機構 : J-STAGE
- 要約等
- <p>Mapping quantitative trait loci (QTLs) is one of the major goals of quantitative genetics; however, identifying the interactions between QTLs (i.e., epistasis) remains challenging. Recently developed machine learning methods, such as deep learning and gradient boosting, are transforming the real world. These methods could advance QTL mapping methodologies because of their high capability for capturing complex relationships among features. One problem with applying such complex models to QTL mapping is the evaluation of feature importance. In this study, XGBoost, a popular gradient tree boosting algorithm, was applied for QTL mapping in biparental populations with Shapley additive explanations (SHAPs). SHAP is a local (i.e., instance-wise) importance index with the desired properties as feature importance indices. The SHAP-assisted XGBoost (SHAP-XGB) was compared with conventional methods, including composite interval mapping (CIM), multiple interval mapping (MIM), inclusive CIM (ICIM), and BayesC, using simulations and rice heading date data. SHAP-XGB performed comparably to CIM, MIM, ICIM, and BayesC in mapping main QTL effects and was superior to MIM, ICIM, and BayesC in mapping QTL interaction effects. As SHAP can evaluate local importance, interactions between markers can be visualized by plotting SHAP interaction values for each instance (plant/line). These results illustrated the strength of SHAP-XGB in detecting and interpreting epistatic QTLs and suggest the possibility that SHAP-XGB complements conventional methods.</p>
- DOI
- 10.1270/jsbbs.24083
- 関連情報（URI）
- 参照
- pROC: an open-source package for R and S+ to analyze and compare ROC curvesA penalized maximum likelihood method for estimating epistatic effects of QTLA Bayesian model for detection of high-order interactions among genetic variants in genome-wide association studiesMapping Epistatic Quantitative Trait Loci With One-Dimensional Genome SearchesR/qtl: QTL mapping in experimental crossesDetecting epistasis with the marginal epistasis test in genetic mapping studies of quantitative traitsGene–gene interaction detection with deep learningA new method for exploring gene–gene and gene–environment interactions in GWAS with tree ensemble methods and SHAP valuesToward integration of genomic selection with crop modelling: the development of an integrated approach to predicting rice heading datesXGBoostExtension of the bayesian alphabet for genomic selectionEstimation of Quantitative Trait Locus Effects with Epistasis by Variational Bayes AlgorithmsGenetic control of flowering time in rice: integration of Mendelian genetics and genomicsCharacterization and detection of epistatic interactions of 3 QTLs, Hd1, Hd2, and Hd3, controlling heading date in rice using nearly isogenic linesMapping epistatic quantitative trait lociAn R package VIGoR for joint estimation of multiple linear learners with variational Bayesian inferenceMolecular basis of heading date control in riceExplaining individual predictions when features are dependent: More accurate approximations to Shapley valuesAxiomatic characterizations of probabilistic and cardinal-probabilistic interaction indicesNatural Variation in OsPRR37 Regulates Heading Date and Contributes to Rice Cultivation at a Wide Range of LatitudesA Modified Algorithm for the Improvement of Composite Interval MappingSure Independence Screening for Ultrahigh Dimensional Feature SpaceGenetic Interactions Among Ghd7, Ghd8, OsPRR37 and Hd1 Contribute to Large Variation in Heading Date in Rice"Why Should I Trust You?"Inclusive composite interval mapping (ICIM) for digenic epistasis of quantitative traits in biparental populationsHigh resolution of quantitative traits into multiple loci via interval mapping.Mapping mendelian factors underlying quantitative traits using RFLP linkage maps.Precision mapping of quantitative trait loci.The Role of Casein Kinase II in Flowering Time Regulation Has Diversified during EvolutionIdentification of quantitative trait loci controlling heading date in rice using a high-density linkage map<i>Hd6</i> , a rice quantitative trait locus involved in photoperiod sensitivity, encodes the α subunit of protein kinase CK2QTL IciMapping: Integrated software for genetic linkage map construction and quantitative trait locus mapping in biparental populationsMultiple Interval Mapping for Quantitative Trait Loci<i>DTH8</i> Suppresses Flowering in Rice, Influencing Plant Height and Yield Potential Simultaneously17. A Value for n-Person Games
- 連携機関・データベース
- 国立情報学研究所 : CiNii Research
- 提供元機関・データベース
- Japan Link Center雑誌記事索引データベースCrossref
- 書誌ID（NDLBibID）
- 034474597