Investigators have recently introduced powerful methods for population genetic inference that rely on supervised machine learning from simulated data. Despite their performance advantages, these methods can fail when the simulated training data does not adequately resemble data from the real world. Here, we show that this "simulation mis-specification" problem can be framed as a "domain adaptation" problem, where a model learned from one data distribution is applied to a dataset drawn from a different distribution. By applying an established domain-adaptation technique based on a gradient reversal layer (GRL), originally introduced for image classification, we show that the effects of simulation mis-specification can be substantially mitigated. We focus our analysis on two state-of-the-art deep-learning population genetic methods-SIA, which infers positive selection from features of the ancestral recombination graph (ARG), and ReLERNN, which infers recombination rates from genotype matrices. In the case of SIA, the domain adaptive framework also compensates for ARG inference error. Using the domain-adaptive SIA (dadaSIA) model, we estimate improved selection coefficients at selected loci in the 1000 Genomes CEU population. We anticipate that domain adaptation will prove to be widely applicable in the growing use of supervised machine learning in population genetics.
Download full-text PDF |
Source |
---|---|
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC10655966 | PMC |
http://dx.doi.org/10.1371/journal.pgen.1011032 | DOI Listing |
J Am Acad Orthop Surg
January 2025
From the Holland Bone and Joint Program, Sunnybrook Research Institute, Sunnybrook Health Sciences Centre, Toronto, Ontario, Canada (Boyer, Burns, Razmjou, Renteria, Sheth, Richards, and Whyne), the Division of Orthopaedic Surgery, University of Toronto, Toronto, Ontario, Canada (Burns, Sheth, Richards, and Whyne), the Institute of Biomedical Engineering, University of Toronto, Toronto, Ontario, Canada (Boyer, Burns, and Whyne), the Department of Physical Therapy, University of Toronto, Toronto, Ontario, Canada (Razmjou), and the Sunnybrook Orthopaedic Upper Limb (SOUL), Sunnybrook Health Science Centre, Toronto, Ontario, Canada (Sheth, Richards, and Whyne).
Introduction: Exercise-based physiotherapy is an established treatment of rotator cuff injury. Objective assessment of at-home exercise is critical to understand its relationship with clinical outcomes. This study uses the Smart Physiotherapy Activity Recognition System to measure at-home physiotherapy participation in patients with rotator cuff injury based on inertial sensor data captured from smart watches.
View Article and Find Full Text PDFCancer Med
February 2025
Department of Radiation Oncology (MAASTRO) GROW School for Oncology and Reproduction, Maastricht University Medical Centre+, Maastricht, the Netherlands.
Background: Lung cancer (LC) is the top cause of cancer deaths globally, prompting many countries to adopt LC screening programs. While screening typically relies on age and smoking intensity, more efficient risk models exist. We devised a Bayesian network (BN) for LC detection, testing its resilience with varying degrees of missing data and comparing it to a prior machine learning (ML) model.
View Article and Find Full Text PDFResusc Plus
January 2025
Department of Pediatrics, University of Virginia School of Medicine, Box 800386, Charlottesville, VA 22908, USA.
Background: More than 90% of in-hospital cardiac arrests involving children occur in an intensive care unit (ICU) with less than half surviving to discharge. We sought to assess the association of the display of risk scores of cardiovascular and respiratory instability with the incidence of cardiac arrest in a pediatric ICU.
Methods: Employing supervised machine learning, we previously developed predictive models of cardiovascular and respiratory instability, incorporating real-time physiologic and laboratory data, to display risk scores for potentially catastrophic clinical events in the subsequent 12 h.
Sci Rep
January 2025
Department of Cardiology, The First Affiliated Hospital of Chongqing Medical University, Chongqing, 400016, China.
To explore in depth the characteristics of the risk factors for diabetes and prediabetes pathogenesis and progression in special regions. We investigated medical data from 160 thousand cases in the newly developing urban area of a large modern city from 2015 to 2021. After excluding the population with incomplete data, a total of 47,608 people who underwent physical examinations and blood tests were included in this study.
View Article and Find Full Text PDFEnter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!