scFAN: Predicting transcription factor binding in single cells through deep learning

What is being modeled?
Genome-wide binding profiles of transcription factors
Description & purpose of resource

scFAN is a deep learning model that predicts the probability of a TF binding at a given genomic region, with inputs of ATAC-seq, DNA sequence, and DNA mapability data from that region.

Spatial scales
cellular
tissue
organ
Temporal scales
1 - 103 s
hours
days
This resource is currently
mature and useful in ongoing research
Has this resource been validated?
Yes
Key publications (e.g. describing or using resource)

Fu, Laiyi, Lihua Zhang, Emmanuel Dollinger, Qinke Peng, Qing Nie, and Xiaohui Xie. "Predicting transcription factor binding in single cells through deep learning." Science Advances 6, no. 51 (2020): eaba9031.

Collaborators
Xiaohui Xie (PI)
Qing Nie (PI)
PI contact information
xhx@uci.edu; qnie@uci.edu
Table sorting checkbox
Off

Request for Information (RFI): Inviting Comments and Suggestions to Advance and Strengthen Racial Equity, Diversity, and Inclusion in the Biomedical Research Workforce and Advance Health Disparities and Health Equity Research

This Notice is a Request for Information (RFI) inviting feedback on the approaches NIH can take to advance racial equity, diversity, and inclusion within all facets of the biomedical research workforce, and expand research to eliminate or lessen health disparities and inequities.

Review of this entire RFI notice is encouraged to ensure a comprehensive response is prepared and to have a full understanding of how your response will be utilized.

16th Annual Multicell Virtual-Tissue Modeling Online Summer School and Hackathon

We are pleased to announce the 16th Annual Multicell Virtual-Tissue Modeling Online Summer School and Hackathon -- 2021. Mechanistic modeling is an integral part of contemporary bioscience, used for hypothesis generation and testing, experiment design and interpretation and the design of therapeutic interventions. The CompuCell3D modeling environment allows researchers with modest programming experience to rapidly build and execute complex Virtual Tissue simulations of development, homeostasis, toxicity and disease in tissues, organs and organisms, covering sub-cellular, multi-cell and continuum tissue scales.

National Science Foundation - FY22/23 Emerging Frontiers in Research Innovation Solicitation 21-615

The National Science Foundation recently released a new topic as part of its Emerging Frontiers in Research and Innovation (EFRI) Program, titled, Brain-inspired Dynamics for Engineering Energy-Efficient Circuits and Artificial Intelligence (BRAID). This topic will support interdisciplinary research to create a new engineering science of brain-inspired engineered learning systems. Neuroscience research is in a period of explosive growth, producing new understanding of biological learning processes and their efficiency that remains largely untapped. This revolution in our understanding of the brain has revealed, for example, the critical interplay of temporal dynamics across time scales from milliseconds to lifetimes and neural structures across spatial scales from nanometers to entire brains. BRAID seeks to exploit emerging advances in neuroscience for the design of engineered learning systems that would exhibit the flexibility, robustness, and efficiency of biological intelligence, exemplified respectively by the continual and causal learning needed for adaptive autonomy, the abstraction and generalization needed to learn from few examples and to identify relevant strategies from previously learned concepts and contexts, and the energy efficiency needed to extend the benefits of learning and autonomy throughout the built environment. Each proposal submitted in response to the BRAID topic of the EFRI solicitation must address at least two out of the three threads (shown below): • Thread 1: Theoretical Neuroscience • Thread 2: Brain-informed Hardware Design • Thread 3: Algorithmic Learning for Resilient Adaptive Technologies While responses to all three threads are encouraged, response to Thread 1 is mandatory. The full solicitation (21-615) can be found here: https://beta.nsf.gov/funding/opportunities/emerging-frontiers-research-…. The EFRI program webinar slides and recording can be found here: https://www.nsf.gov/events/event_summ.jsp?cntn_id=303513&org=NSF. Each award can be up to 2M over grant lifetime (including both direct and indirect costs). The period of performance can be up to 4 years in duration. For the Fiscal Year 22 competition, Letter of Intent will be due on November 10, 2021. Preliminary Proposal will be due on December 16, 2021. Full Proposal will be due on March 10, 2022. For the Fiscal Year 23 competition, Letter of Intent will be due on September 12, 2022. Preliminary Proposal will be due on October 13, 2022. Full Proposal will be due on February 7, 2023. Investigators are encouraged to send a one-page summary comprising intellectual merit and broader impacts to braid@nsf.gov. Sincerely, Grace Grace M. Hwang, Ph.D. Program Director Disability and Rehabilitation Engineering (DARE) Program Chemical, Bioengineering, Environmental, and Transport Systems Division (CBET) Rehab@NSF: https://nsf.gov/eng/rehab.jsp Brain-inspired Dynamics for Engineering Energy-Efficient Circuits and Artificial Intelligence (BRAID) Neural and Cognitive Systems (NCS) National Robotics Initiative 3.0 (NRI) Understanding the Rules of Life: Emergent Networks (URoL:EN) Directorate for Engineering (ENG) National Science Foundation (NSF) 2415 Eisenhower Ave, Alexandria, VA 22314 ghwang@nsf.gov

Bridge2AI -- New NIH Funding Program

The NIH announces the Bridge to Artificial Intelligence program to propel biomedical research forward by setting the stage for widespread adoption of artificial intelligence (AI) that tackles complex biomedical challenges beyond human intuition. A key step in this process is generating new “flagship” data sets and best practices for machine learning analysis.