Skip to content

Convolutional Neural Network (CNN)

Definition
AI-generated

A convolutional neural network (CNN) applies learned local filters across spatial or sequential inputs (images, 1D sequence windows, or multi-channel tensors), pooling or striding to build hierarchical features; weight sharing makes CNNs data-efficient for grid-like or local-motif structure.

Topics
LLM and Agents
Synonyms
ConvNet
Related
Deep Learning Neural Network Splice Site Prediction

Why it matters in GWAS

CNNs score regulatory DNA, predict splice sites and motif effects from sequence, and analyze spatial omics (e.g. imaging endophenotypes or spatial transcriptomics tiles). When SNP or haplotype windows feed a CNN, LD and population structure can dominate unless explicitly controlled in training and evaluation.

Example usage

"We compared a CNN sequence model against position weight matrices for classifying pathogenic noncoding variants near GWAS lead SNPs."

Deep Learning Neural Network Splice Site Prediction Transformer
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

  • LeCun Y, et al. (1998). Gradient-based learning applied to document recognition. Proc IEEE.
← Controls-Only HWE Coortholog →

Last updated (UTC · Git history)