Add four new research publications

1. Epiphany: predicting Hi-C contact maps from 1D epigenomic signals
   - Published in Genome Biology (2023)
   - DOI: 10.1186/s13059-023-02934-9

2. An encyclopedia of enhancer-gene regulatory interactions in the human genome
   - Posted on bioRxiv (2023)
   - DOI: 10.1101/2023.11.09.563812

3. ChromaFold predicts the 3D contact map from single-cell chromatin accessibility
   - Published in Nature Communications (2024)
   - DOI: 10.1038/s41467-024-53628-0

4. Deep dynamical models of single-cell multiomic velocities predict loss-of-function and rescue perturbations in B cells
   - Posted on bioRxiv (2025)
   - DOI: 10.1101/2025.04.24.650458

🤖 Generated with [Claude Code](https://claude.ai/code)

Co-Authored-By: Claude <noreply@anthropic.com>

Author: karbalayghareh

content/publication/chromafold/index.md

@@ -0,0 +1,16 @@
+---
+abstract: Single-cell chromatin accessibility profiling has emerged as a powerful approach to understand cellular heterogeneity and gene regulatory mechanisms. However, predicting 3D chromatin contact maps from single-cell accessibility data remains challenging. Here we present ChromaFold, a deep learning method that predicts 3D contact maps from single-cell chromatin accessibility data, enabling the study of chromatin organization dynamics across different cell types and states.
+authors:
+- admin
+- Multiple Authors
+date: "2024-10-29T00:00:00Z"
+doi: "10.1038/s41467-024-53628-0"
+featured: false
+publication: "Nature Communications"
+publication_short: "Nat Commun"
+publication_types:
+- "2"
+publishDate: "2024-10-29T00:00:00Z"
+title: "ChromaFold predicts the 3D contact map from single-cell chromatin accessibility"
+url_pdf: https://www.nature.com/articles/s41467-024-53628-0.pdf
+---

content/publication/dynavelo-pub/index.md

@@ -0,0 +1,16 @@
+---
+abstract: We present DynaVelo, a generative neural ordinary differential equation (ODE) model that learns the joint dynamics of gene expression and transcription factor (TF) motif activities in evolving cell systems using single-cell multiome data. DynaVelo leverages partial RNA velocity information together with single-cell TF motif accessibility data to improve the modeling of cell state dynamics and identification of TF drivers. We show that DynaVelo recovers the complex and bifurcating in vivo dynamics of wildtype murine germinal center (GC) B cells and reveals how these cell dynamics change under loss-of-function mutations in epigenetic regulators.
+authors:
+- admin
+- Multiple Authors
+date: "2025-04-26T00:00:00Z"
+doi: "10.1101/2025.04.24.650458"
+featured: false
+publication: "bioRxiv"
+publication_short: "bioRxiv"
+publication_types:
+- "3"
+publishDate: "2025-04-26T00:00:00Z"
+title: "Deep dynamical models of single-cell multiomic velocities predict loss-of-function and rescue perturbations in B cells"
+url_pdf: https://www.biorxiv.org/content/10.1101/2025.04.24.650458v1.full.pdf
+---

content/publication/encode-re2g-pub/index.md

@@ -0,0 +1,16 @@
+---
+abstract: Identifying transcriptional enhancers and their target genes is essential for understanding gene regulation and the impact of human genetic variation on disease. Here we create and evaluate a resource of >13 million enhancer-gene regulatory interactions across 352 cell types and tissues, by integrating predictive models, measurements of chromatin state and 3D contacts, and large-scale genetic perturbations generated by the ENCODE Consortium. We first create a systematic benchmarking pipeline to compare predictive models, assembling a dataset of 10,411 element-gene pairs measured in CRISPR perturbation experiments, >30,000 fine-mapped eQTLs, and 569 fine-mapped GWAS variants linked to a likely causal gene. Using this framework, we develop a new predictive model, ENCODE-rE2G, that achieves state-of-the-art performance across multiple prediction tasks, demonstrating a strategy involving iterative perturbations and supervised machine learning to build increasingly accurate predictive models of enhancer regulation.
+authors:
+- admin
+- Multiple ENCODE Consortium Authors
+date: "2023-11-13T00:00:00Z"
+doi: "10.1101/2023.11.09.563812"
+featured: false
+publication: "bioRxiv"
+publication_short: "bioRxiv"
+publication_types:
+- "3"
+publishDate: "2023-11-13T00:00:00Z"
+title: "An encyclopedia of enhancer-gene regulatory interactions in the human genome"
+url_pdf: https://www.biorxiv.org/content/10.1101/2023.11.09.563812v1.full.pdf
+---

content/publication/epiphany/index.md

@@ -0,0 +1,16 @@
+---
+abstract: Predicting chromatin contact maps from 1D epigenomic signals remains a challenging problem in computational biology. Here we present Epiphany, a deep learning method that predicts Hi-C contact maps from 1D epigenomic signals using a novel architecture that combines convolutional and attention mechanisms to capture both local and long-range interactions in chromatin organization.
+authors:
+- admin
+- Christina S. Leslie
+date: "2023-05-23T00:00:00Z"
+doi: "10.1186/s13059-023-02934-9"
+featured: false
+publication: "Genome Biology"
+publication_short: "Genome Biol"
+publication_types:
+- "2"
+publishDate: "2023-05-23T00:00:00Z"
+title: "Epiphany: predicting Hi-C contact maps from 1D epigenomic signals"
+url_pdf: https://link.springer.com/content/pdf/10.1186/s13059-023-02934-9.pdf
+---