Biology subjects

Montserrat, D. M.

Publications and source records attributed to Montserrat, D. M..

3 recordsLinked to original sources

bioRxiv2023

Machine Learning Strategies for Improved Phenotype Prediction in Underrepresented Populations

Precision medicine models often perform better for populations of European ancestry due to the over-representation of this group in the genomic datasets and large-scale biobanks from which the models are constructed. As a result, prediction models may misrepresent or provide less accurate treatment recommendations for underrepresented populations, contributing to health disparities. This study introduces an adaptable machine learning toolkit that integrates multiple existing methodologies and novel techniques to enhance the prediction accuracy for underrepresented populations in genomic datasets. By leveraging machine learning techniques, including gradient boosting and automated methods, coupled with novel population-conditional re-sampling techniques, our method significantly improves the phenotypic prediction from single nucleotide polymorphism (SNP) data for diverse populations. We evaluate our approach using the UK Biobank, which is composed primarily of British individuals with European ancestry, and a minority representation of groups with Asian and African ancestry. Performance metrics demonstrate substantial improvements in phenotype prediction for underrepresented groups, achieving prediction accuracy comparable to that of the majority group. This approach represents a significant step towards improving prediction accuracy amidst current dataset diversity challenges. By integrating a tailored pipeline, our approach fosters more equitable validity and utility of statistical genetics methods, paving the way for more inclusive models and outcomes.

bioinformatics↗

bioRxiv2021

Neural ADMIXTURE: rapid population clustering with autoencoders

Characterizing the genetic substructure of large cohorts has become increasingly important as genetic association and prediction studies are extended to massive, increasingly diverse, biobanks. ADMIXTURE and STRUCTURE are widely used unsupervised clustering algorithms for characterizing such ancestral genetic structure. These methods decompose individual genomes into fractional cluster assignments with each cluster representing a vector of DNA marker frequencies. The assignments, and clusters, provide an interpretable representation for geneticists to describe population substructure at the sample level. However, with the rapidly increasing size of population biobanks and the growing numbers of variants genotyped (or sequenced) per sample, such traditional methods become computationally intractable. Furthermore, multiple runs with different hyperparameters are required to properly depict the population clustering using these traditional methods, increasing the computational burden. This can lead to days of compute. In this work we present Neural ADMIXTURE, a neural network autoencoder that follows the same modeling assumptions as ADMIXTURE, providing similar (or better) clustering, while reducing the compute time by orders of magnitude. Indeed, the equivalent of one month of continuous compute can be reduced to hours. In addition, Neural ADMIXTURE can include multiple outputs, providing the equivalent results as running the original ADMIXTURE algorithm many times with different numbers of clusters. Our models can also be stored, allowing later cluster assignment to be performed with a linear computational time. The software implementation of Neural ADMIXTURE can be found at https://github.com/ai-sandbox/neural-admixture.

genomics↗

bioRxiv2020

XGMix: Local-Ancestry Inference With Stacked XGBoost

AO_SCPLOWBSTRACTC_SCPLOWGenomic medicine promises increased resolution for accurate diagnosis, for personalized treatment, and for identification of population-wide health burdens at rapidly decreasing cost (with a genotype now cheaper than an MRI and dropping). The benefits of this emerging form of affordable, data-driven medicine will accrue predominantly to those populations whose genetic associations have been mapped, so it is of increasing concern that over 80% of such genome-wide association studies (GWAS) have been conducted solely within individuals of European ancestry [1]. The severe under-representation of the majority of the worlds populations in genetic association studies stems in part from an addressable algorithmic weakness: lack of simple, accurate, and easily trained methods for identifying and annotating ancestry along the genome (local ancestry). Here we present such a method (XGMix) based on gradient boosted trees, which, while being accurate, is also simple to use, and fast to train, taking minutes on consumer-level laptops.

genomics↗