pySCENIC is a lightning-fast python implementation of the SCENIC pipeline (Single-Cell rEgulatory Network Inference and Clustering) which enables biologists to infer transcription factors, gene regulatory networks and cell types from single-cell RNA-seq data.
I am currently learning how to use pySCENIC, and ran the given tutorial.
Right before the last step of the pySCENIC pipeline of creating the AUC matrix, it is suggested to build the regulons using the df2regulons function.
The output of this step is a long list of regulons, and for each regulon there are various parameters, including the transcription factor name, the gene2weight dictionary and more. For example, one of the regulons from the tutorial:
One of the parameters is a "score" for each regulon, in bold above.
What is this score? It is different than the AUC score calculated in the next step, so I am having trouble understanding what this score represents/how it is calculated...
Hello,
I am currently learning how to use pySCENIC, and ran the given tutorial. Right before the last step of the pySCENIC pipeline of creating the AUC matrix, it is suggested to build the regulons using the df2regulons function. The output of this step is a long list of regulons, and for each regulon there are various parameters, including the transcription factor name, the gene2weight dictionary and more. For example, one of the regulons from the tutorial:
name='6720489N17Rik', gene2weight=frozendict.frozendict({'Arhgef5': np.float64(1.0642277382469154), 'Dleu7': np.float64(1.171468799210279), 'Ltbp1': np.float64(1.3452080123862935), 'Slitrk6': np.float64(4.7638839176164405), 'BC023829': np.float64(3.057212543536579), 'Neb': np.float64(1.3027495474599102), 'Col8a1': np.float64(0.5131416679291328), 'Cep63': np.float64(0.6548412938225057), 'Nts': np.float64(1.1252382619078989), 'Kcp': np.float64(0.6260326748658571), 'Ryr1': np.float64(2.1651465131676484), 'Acer3': np.float64(3.718374867914573), 'Cep350': np.float64(1.9253248160252), 'Kdm2b': np.float64(0.6503335330805443), 'Wdr91': np.float64(0.7887676834397574), 'Slc43a3': np.float64(0.7715775632734195), 'Myof': np.float64(0.7719908731938169), 'Nphs1': np.float64(2.4437719970932585), 'Sgpp1': np.float64(1.0407409615981351)}), gene2occurrence=frozendict.frozendict({}), transcription_factor='6720489N17Rik', context=frozenset({'activating', 'transfac_pro__M06006.png'}), score=1.1904771156122713, nes=0.0, orthologous_identity=0.0, similarity_qvalue=0.0, annotation=''
One of the parameters is a "score" for each regulon, in bold above. What is this score? It is different than the AUC score calculated in the next step, so I am having trouble understanding what this score represents/how it is calculated...
Thank you in advance!