Lesnoff, M. | bioRxiv Science

bioRxiv2023

Averaging a local-PLSR models to predict chemical compositions and nutritive values of forages from spectral near infrared data

Partial least squares regression (PLSR) is a reference method in chemometrics. In agronomy, it is used for instance to predict components of chemical composition (response variables y) of vegetal materials from spectral near infrared (NIR) data X collected from spectrometers. The principle of PLSR is to reduce the dimension of the spectral data X by computing vectors that are then used as latent variables (LVs) in a multiple linear model. A difficulty is to determine the relevant dimensionality (number of LVs) of the model for the given available data. This step can also become time consuming when many different datasets have to be processed and/or the datasets are frequently updated. An alternative to determinate the relevant PLSR dimensionality is the ensemble learning method "PLSR averaging". In the past, this method has been demonstrated to be efficient for complex biological materials such as mixed forages, and facilitates to automatize predictions (e.g. in user-friendly web interface platforms). This article presents the extension of the PLSR averaging to a k-nearest neighbors locally weighted PLSR pipeline (kNN-LWPLSR). The kNN-LWPLSR pipeline has the advantage to account for non-linearity between X and y existing for instance in heterogeneous data (e.g. mixing of vegetal species, collection from different geographical areas, etc.). In the article, kNN-LWPLSR averaging is applied to an extensive NIR database built to predict the chemical composition of European and tropical forages and feed. The main finding of the study was the overall superiority of the averaging compared to the usual kNN-LWPLSR. Averaging may therefore be recommended in local PLSR pipelines to predict NIR forage and feed data.

bioinformatics↗

bioRxiv2021

The genetic history of Mayotte and Madagascar cattle breeds mirrors the complex pattern of human exchanges in Western Indian Ocean

Despite their central economic and cultural role, the origin of cattle populations living in Indian Ocean islands still remains poorly documented. Here, we unravel the demographic and adaptive histories of the extant Zebus from the Mayotte and Madagascar islands using high-density SNP genotyping data. We found that these populations are very closely related and both display a predominant indicine ancestry. They diverged in the 16th century at the arrival of European people who transformed the trade network in the area. Their common ancestral cattle population originates from an admixture between an admixed African zebu population and an Indian zebu that occurred around the 12th century at the time of the earliest contacts between human African populations of the Swahili corridor and Austronesian people from Southeast Asia in Comoros and Madagascar. A steep increase of the estimated population sizes from the beginning of the 16th to the 17th century coincides with the expansion of the cattle trade. By carrying out genome scans for recent selection in the two cattle populations from Mayotte and Madagascar, we identified sets of candidate genes involved in biological functions (cancer, skin structure and UV-protection, nervous system and behavior, organ development, metabolism and immune response) broadly representative of the physiological adaptation to tropical conditions. Overall, the origin of the cattle populations from Western Indian Ocean islands mirrors the complex history of human migrations and trade in this area.

evolutionary biology↗