scAI: an unsupervised approach for the integrative analysis of parallel single-cell transcriptomic and epigenomic profiles

Investigators
Qing Nie
Contact info (email)
qnie@uci.edu
1. Define context(s)
reveal new biological insights
Current Conformance Level / Target Conformance Level
Extensive
Primary goal of the model/tool/database

scAI is an unsupervised approach that integrates parallel single-cell transcriptomic and epigenomic profiles, which enables the dissection of cellular heterogeneity within both transcriptomic and epigenomic layers and the understanding of transcriptional regulatory mechanisms.

Biological domain of the model
scRNA-seq and scATAC-seq data for various tissues
Structure(s) of interest in the model
cellular heterogeneity within both transcriptomic and epigenomic layers
Spatial scales included in the model
cellular to tissue
Time scales included in the model
seconds to hours
2. Data for building and validating the model
Data for building the model Published? Private? How is credibility checked? Current Conformance Level / Target Conformance Level
in vitro (primary cells cell, lines, etc.)
ex vivo (excised tissues)
in vivo pre-clinical (lower-level organism or small animal)
in vivo pre-clinical (large animal) Yes No The model was built in an unsupervised way on unbiased single-cell RNA sequencing data. Extensive
Human subjects/clinical
Other: ________________________
Data for validating the model Published? Private? How is credibility checked? Current Conformance Level / Target Conformance Level
in vitro (primary cells cell, lines, etc.)
ex vivo (excised tissues)
in vivo pre-clinical (lower-level organism or small animal)
in vivo pre-clinical (large animal) Yes No By 1) comparing the identified cell clusters to the known heterogenity in epigenomic profiles and 2) comparing the inferred differentiation trajectory to known developmental processes. Adequate
Human subjects/clinical
Other: ________________________ Yes No By comparing to simulated data. Adequate
3. Validate within context(s)
Who does it? When does it happen? How is it done? Current Conformance Level / Target Conformance Level
Verification Postdocs/Investigators Throughout the project By 1) making sure the convergence and correctness of algorithm and 2) checking the expected heterogeneity level in transcriptomics and epigenomics. Extensive
Validation Postdocs/Investigators As the unsupervised model was established 1) The inferred differentiation trajectory was compared to known knowledge and simulated data. 2) The identified key transcription factors was confirmed by TF databases. 3) The cell clustering from the integrated data agrees well with knowledge. Extensive
Uncertainty quantification
Sensitivity analysis Postdocs/investigators As the unsupervised model was established 1) Parallel runs with different random initializations gave similar results. 2) Altering the key parameters delivered robust observations. Adequate
Other:__________
Additional Comments
4. Limitations
Disclaimer statement (explain key limitations) Who needs to know about this disclaimer? How is this disclaimer shared with that audience? Current Conformance Level / Target Conformance Level
The technical noise in single-cell data might cause inaccuracy. Scientific community who intends to apply this method to raw single-cell data. Adequate
5. Version control
Current Conformance Level / Target Conformance Level
Extensive
Naming Conventions? Repository? Code Review?
individual modeler Yes Yes peers
within the lab Yes Yes peers
collaborators Yes Yes via regular meetings
6. Documentation
Current Conformance Level / Target Conformance Level
Code commented? Adequate
Scope and intended use described? Extensive
User’s guide? Extensive
Developer’s guide? Partial
7. Dissemination
Current Conformance Level / Target Conformance Level
Extensive
Target Audience(s): “Inner circle” Scientific community Public
Simulations
Models
Software package: https://github.com/sqjin/scAI package: https://github.com/sqjin/scAI
Results Shared folders Paper and tutorials
Implications of results
8. Independent reviews
Current Conformance Level / Target Conformance Level
To be done
Reviewer(s) name & affiliation:
When was review performed?
How was review performed and outcomes of the review?
9. Test competing implementations
Current Conformance Level / Target Conformance Level
Adequate
Yes or No (briefly summarize)
Were competing implementations tested? Yes. The method has been compared to several other commonly used methods on benchmark datasets.
Did this lead to model refinement or improvement? Yes.
10. Conform to standards
Current Conformance Level / Target Conformance Level
Adequate
Yes or No (briefly summarize)
Are there operating procedures, guidelines, or standards for this type of multiscale modeling? Yes. There are several standard procedures for preprocessing single-cell data.
How do your modeling efforts conform? Common data preprocessing procedures are followed.