LOCAL Regression Algorithm Improves near Infrared Spectroscopy Predictions When the Target Constituent Evolves in Breeding Populations

Abstract

The CGIAR Harvest Plus Challenge Program began in the mid-2000s to support the genetic improvement of nutritional quality in various crops, including the carotenoids content of cassava roots. Successful conventional breeding requires a large number of segregating progenies. However, only a few samples can be quantified by high performance liquid chromatography each day for total carotenoids (TCC) and b-carotene (TBC) contents, limiting the gains from breeding. This study describes the usefulness of near infrared (NIR) spectroscopy and the efficiency of a large database coupled to a LOCAL regression algorithm to reach accurate TCC/TBC predictions on fresh cassava roots. The cassava database (6026 samples) was built over six years. TCC values ranged from 0.11 μg g -1 to 29.0 μg g -1 , whereas TBC ranged from negligible values up to 20.1 μg g -1 . All values were measured and expressed on a fresh weight basis. Between 2009 and 2014 increases in TCC and TBC were 86% and 122%, respectively. A comparison of calibrations using partial least squares (PLS) regression and LOCAL regression was done. The standard error of prediction were 1.82 μg g -1 for TCC and 1.28 μg g -1 for TBC using PLS model and 1.38 μg g -1 and 1.02 μg g -1 , respectively, using LOCAL regression. The specificity of the data, with increasing content of the constituent of interest year after year, clearly showed the limitation of the classical partial least squares regression approach. The LOCAL regression algorithm takes advantage of large databases; this study highlighted the efficiency of this concept. NIR spectroscopy coupled to LOCAL regression led to efficient models for breeding programmes aiming at increasing carotenoids content in fresh cassava roots. NIR spectroscopy can also be used to predict other important constituents such as dry matter content and cyanogenic glucosides.

Carotenoids in Cassava Roots

“…The availability of irrigation at CIAT reduced the difference in dry and wet season, but only partially. As the problem of a lengthy harvesting season became evident, CIAT began the development of the protocol for predicting pVAC and DMC based on NIRS, as described above [82,84]. The possibility of selecting for high pVAC based on reliable NIRS predictions was a major breakthrough.…”

“…Spectra were corrected for light scattering using the standard normal variate and de-trend (SNVD) correction. Then, the second derivative of the Log(1/R) spectrum, calculated on five data points and smoothed using Savitzky-Golay polynomial smoothing on five data points, was used in combination with LOCAL regressions to develop prediction models [84].…”

Progress update: Crop development of biofortified staple food crops under HarvestPlus

“…However, they tend to overestimate carotenoid content when compared to HPLC due to other compounds also detected [21,22]. Near-infrared spectrometry (NIRS) has proven a costand time-efficient method for high-throughput screening for carotenoid content in sweet potato [23], banana [24,25], and cassava as well as for other important breeding traits such as dry matter content (DMC) and cyanogenic potential [26,27,28]. New portable devices such as iCheck and portable NIRS are being evaluated and show promise for use in the field when transport of fresh cassava roots to the nearest laboratory is a challenge [29].…”

Local partial least squares based on global PLS scores

“…Data used in this study for assessing the proposed local method come from a breeding program (Harvest Plus Challenge Program) on cassava plants monitored by the International Center for Tropical Agriculture in Colombia . One objective of the program was to study and improve the nutritive quality of the cassava roots (see Davrieux et al for details).…”

“…The present study focused on the total β-carotene content (TBC). Due to breeding improvements, the mean content of TBC increased slowly from 2009 to 2012, but a significant increase appeared in 2013, by which time the mean was 3 points higher than in 2009, 26 as shown in Table 1. Because of an increasing TBC content year after year, Davrieux et al showed the limitation of the usual global PLSR approach and got better predictions using a local PLSR.…”