000			03509nab|a22004817a|4500
001			66336
003			MX-TxCIM
005			20240919021005.0
008			20236s2023||||mx |||p|op||||00||0|eng|d
022			_a1367-4803
022			_a1460-2059
024	8		_ahttps://doi.org/10.1093/bioinformatics/btad336
040			_aMX-TxCIM
041			_aeng
100	1		_aTogninalli, M. _931117
245	1	0	_aMulti-modal deep learning improves grain yield prediction in wheat breeding by fusing genomics and phenomics
260			_bOxford University Press, _c2023. _aOxford (United Kingdom) :
500			_aPeer review
500			_aOpen Access
520			_aMotivation: Developing new crop varieties with superior performance is highly important to ensure robust and sustainable global food security. The speed of variety development is limited by long field cycles and advanced generation selections in plant breeding programs. While methods to predict yield from genotype or phenotype data have been proposed, improved performance and integrated models are needed. Results: We propose a machine learning model that leverages both genotype and phenotype measurements by fusing genetic variants with multiple data sources collected by unmanned aerial systems. We use a deep multiple instance learning framework with an attention mechanism that sheds light on the importance given to each input during prediction, enhancing interpretability. Our model reaches 0.754 6 0.024 Pearson correlation coefficient when predicting yield in similar environmental conditions; a 34.8% improvement over the genotype-only linear baseline (0.559 6 0.050). We further predict yield on new lines in an unseen environment using only genotypes, obtaining a prediction accuracy of 0.386 6 0.010, a 13.5% improvement over the linear baseline. Our multi-modal deep learning architecture efficiently accounts for plant health and environment, distilling the genetic contribution and providing excellent predictions. Yield prediction algorithms leveraging phenotypic observations during training therefore promise to improve breeding programs, ultimately speeding up delivery of improved varieties.
546			_aText in English
650		7	_2AGROVOC _911157 _aLearning
650		7	_2AGROVOC _91138 _aGrain
650		7	_2AGROVOC _91313 _aYields
650		7	_2AGROVOC _91310 _aWheat
650		7	_2AGROVOC _91029 _aBreeding
650		7	_2AGROVOC _91118 _aFood security
700	0		_aXu Wang _99093
700	1		_aKucera, T. _931118
700	1		_aShrestha, S. _98259
700	1		_aJULIANA P. _8001710082 _92690 _gFormerly ​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​Global Wheat Program
700	1		_aMondal, S. _8INT3211 _9904 _gFormerly Global Wheat Program
700	1		_aPinto Espinosa, F. _8I1707012 _gFormerly Global Wheat Program _94431
700	1		_aVelu, G. _8INT2983 _9880 _gGlobal Wheat Program
700	1		_aCrespo-Herrera, L.A. _8I1706538 _92608 _gGlobal Wheat Program
700	1		_aHuerta-Espino, J. _gGlobal Wheat Program _8CHUE01 _9397
700	1		_aSingh, R.P. _8INT0610 _9825 _gGlobal Wheat Program
700	1		_aBorgwardt, K. _931119
700	1		_aPoland, J.A. _92092
773	0		_tBioinformatics _gv. 39, no. 6, art. btad336 _dOxford (United Kingdom) : Oxford University Press, 2023 _x1367-4803 _wG76219
856	4		_yOpen Access through DSpace _uhttps://hdl.handle.net/10883/22634
942			_cJA _n0 _2ddc
999			_c66336 _d66328