Graph-Based Gene Embedding
1Department of Ophthalmology, Harvard Medical School, Boston, MA, 02114, USA. hcousins@mgb.org.
Abstract:
Gene embeddings, concise numerical descriptions of complex genetic relationships, are powerful tools for predicting unknown functions of genes and drugs. The application of graph-specific representation learning algorithms on large biological network databases allows for the efficient computation of highly expressive gene embeddings. This chapter provides an explanation of the end-to-end calculation of such embeddings, with a focus on the most widely used and generally applicable datasets and algorithms.
Related Concept Videos
Ogive Graph
Multiple Bar Graph
Each bar or column in the multiple bar graph represents a data value. These graphs are used primarily in interrelating two or more sets of data. The categories of different kinds of data are listed along the horizontal or x-axis, whereas...
Vector Algebra: Graphical Method
We use the laws of geometry to construct resultant vectors, followed by trigonometry to find vector magnitudes and directions. For a geometric construction of the sum of two vectors in a plane, we follow the parallelogram rule. Suppose two vectors are at arbitrary positions. Translate either one of...
Graphical Representation of Inequalities
Gene Flow
Graphs of Two-Variable Functions

