Related papers: Rapidly evolving in humans topologically associati…
The connection between chromatin nuclear organization and gene activity is vividly illustrated by the observation that transcriptional coregulation of certain genes appears to be directly influenced by their spatial proximity. This fact…
Self-supervised topological deep learning (TDL) represents a nascent but underexplored area with significant potential for modeling higher-order interactions in simplicial complexes and cellular complexes to derive representations of…
Gene regulation is a complex process involving the role of several genomic elements which work in concert to drive spatio-temporal expression. The experimental characterization of gene regulatory elements is a very complex and…
Conventional Sequential Recommender Systems (SRS) typically assign unique hash IDs (HID) to construct item embeddings, which mainly capture collaborative signals from historical user-item interactions. However, such embeddings are…
Comorbidity carries significant implications for disease understanding and management. The genetic causes for comorbidity often trace back to mutations occurred either in the same gene associated with two diseases or in different genes…
Biophysicists are modeling conformations of interphase chromosomes, often basing the strengths of interactions between segments distant on the genetic map on contact frequencies determined experimentally. Here, instead, we develop a…
In recent years, graph neural networks (GNNs) have emerged as a potent tool for learning on graph-structured data and won fruitful successes in varied fields. The majority of GNNs follow the message-passing paradigm, where representations…
Recurrence and metastasis have been regarded as two of the greatest obstacles for curing cancer. Cancer stem cell (CSC) have been found. They contribute to cancer development with the distinct feature of recurrence and resistance to the…
Genomic datasets generated with massively parallel sequencing methods have the potential to propel systematics in new and exciting directions, but selecting appropriate markers and methods is not straightforward. We applied two approaches…
The maintenance of the pluripotent state in human embryonic stem cells (hESCs) is critical for further application in regenerative medicine, drug testing and studies of fundamental biology. Currently, the selection of the best quality cells…
Intermediate layers of large language models (LLMs) best predict human brain responses to language, one of the most robust findings in computational neurolinguistics, yet why remains mechanistically unexplained. We address this gap by…
Due to its powerful capability of self-supervised representation learning and clustering, contrastive attributed graph clustering (CAGC) has achieved great success, which mainly depends on effective data augmentation and contrastive…
Recent chromosome conformation capture experiments have led to the discovery of dense, contiguous, megabase-sized topological domains that are similar across cell types and conserved across species. These domains are strongly correlated…
Background: Single-cell foundation models such as Geneformer and scGPT encode rich biological information, but whether this includes causal regulatory logic rather than statistical co-expression remains unclear. Sparse autoencoders (SAEs)…
Chromosomal rearrangements, particularly those mediated by transposable elements (TEs), can drive adaptive evolution by creating chimeric genes, inducing de novo gene formation, or altering gene expression. Here, we investigate…
Graph representation learning (GRL) has emerged as an effective technique for modeling graph-structured data. When modeling heterogeneity and dynamics in real-world complex networks, GRL methods designed for complex heterogeneous temporal…
The principles underlying the architectural landscape of chromatin beyond the nucleosome level in living cells remains largely unknown despite its potential to play a role in mammalian gene regulation. We investigated the 3-dimensional…
The human genome contains repetitive DNA at different level of sequence length, number and dispersion. Highly repetitive DNA is particularly rich in homo-- and di--nucleotide repeats, while middle repetitive DNA is rich of families of…
From patients and physicians perspectives, the clinical definition of a tumor malignant phenotype could be restricted to the early diagnosis of sub-types of malignancies with the increased risk of existing therapy failure and high…
Exchange type chromosome aberrations (ETCAs) are rearrangements of the genome that occur when chromosomes break and the resulting fragments rejoin with other fragments from other chromosomes. ETCAs are commonly observed in cancer cells and…