Clustering Coefficient, Jaccard Index and Shortest path length. HiCoEx calculates topological properties incl. HiCoEx, a novel machine learning framework based on graph neural network HiCoEx is able to automatically capture important patterns for the prediction of co-expression from chromosomal contacts between genes, and visualize the gene-gene interactions for mechanistic exploration. □ HiCoEx: Prediction of Gene Co-expression from Chromatin Contacts with Graph Attention Network HYFA is genotype-agnostic, supports a variable number of collected tissues, and imposes strong inductive biases to leverage the shared regulatory architecture. HYFA imputes tissue-specific GE via a specialised graph neural network operating on a hypergraph of metagenes. Through transfer learning on a paired single-nucleus RNA-seq dataset (GTEx-v9), HYFA resolves cell-type signatures from bulk GE. HYFA (Hypergraph Factorisation), a parameter-efficient graph representation learning approach for joint multi-tissue and cell-type GE imputation. □ HYFA: Hypergraph factorisation for multi-tissue gene expression imputation A stack of Geoformer layers then iteratively updates these embeddings to improve their geometric consistency. It learns single- and pairwise-residue embeddings. OmegaFold combines a large pretrained language model for sequence modeling and a geometry-inspired transformer. OmegaFold enables accurate predictions on orphan proteins that do not belong to any functionally characterized protein family and antibodies that tend to have noisy MSAs due to fast evolution. □ OmegaFold: High-resolution de novo structure prediction from primary sequence
0 Comments
Leave a Reply. |