Skip to content

Machine Learning

Definition
AI-generated

Machine learning is a set of methods that fit predictive or generative models from data by optimizing an objective (loss or likelihood), rather than encoding all rules by hand; it spans supervised, unsupervised, self-supervised, and reinforcement learning, implemented with algorithms from linear models to deep neural networks.

Topics
LLM and Agents
Related
Area Under the ROC Curve (AUC) Causal Machine Learning for Single-Cell Genomics Deep Learning

Why it matters in GWAS

Machine learning is used for polygenic scores, phenotype imputation, variant and splice prediction, single-cell annotation, and mining literature or EHR text. Genetic studies require careful validation (cross-cohort, cross-ancestry, family-based checks) because flexible models can absorb population structure, relatedness, or batch effects that inflate apparent performance.

Example usage

"We framed PRS construction as a supervised machine-learning problem with L2-regularized linear models and nested cross-validation."

Area Under the ROC Curve (AUC) Causal Machine Learning for Single-Cell Genomics Deep Learning Foundation Model Large Language Model (LLM) Neural Network Polygenic Risk Score (PRS) Reinforcement Learning (RL) Supervised Learning Transfer Learning Unsupervised Learning
Related-term network

Click any node to open that term page.

Node order. The current term is first. Next come every page linked from Related terms, in the same top-to-bottom order as that list. Then new terms appear in two-hop layers: for each of those direct neighbors (in that same order), their related terms are appended if not already listed. A third pass does the same for two-hop nodes. The walk stops when a fixed maximum number of nodes is reached.

References

  • Jordan MI, Mitchell TM. (2015). Machine learning: Trends, perspectives, and prospects. Science.
← Luhya in Webuye, Kenya (LWK) MAGMA →

Last updated (UTC · Git history)