GuangyuWangLab2021 / cellDancer

Predict RNA velocity through deep learning
https://guangyuwanglab2021.github.io/cellDancer_website/
BSD 3-Clause "New" or "Revised" License
60 stars 11 forks source link

how can we know which gene to use? #8

Closed chen-peng-1874 closed 1 year ago

chen-peng-1874 commented 1 year ago

Dear GuangyuWanglab members,

I tried cellDancer, and it seems that the results are different with different gene lists. As we can see in your representative case studies 1 and 2, you used a known gene list, to be specific, you used "gene_list=['Psd3', 'Dcx', 'Syt11', 'Ntrk2', 'Gnao1', 'Gria1', 'Dctn3', 'Map1b', 'Camk2a', 'Gpm6b', 'Sez6l', 'Evl', 'Astn1', 'Ank2', 'Klf7', 'Tbc1d16', 'Atp1a3', 'Stxbp6', 'Scn2a1', 'Lhx9', 'Slc4a4', 'Ppfia2', 'Kcnip1', 'Ptpro', 'Diaph3', 'Slc1a3', 'Cadm1', 'Mef2c', 'Sptbn1', 'Ncald'] " for the hippocampus branch development study. So where are these genes come from? Do we need to search for the branching gene first?

And if I don't use gene list, that means I am actually calculating all the gene velocities, the results are inconsistence with that in vivo.

Thanks!

Abclisy commented 1 year ago

Hi, we manually searched the branching genes and combined them with the reported branching gene list. If you want to study branching genes, you may also manually search for branching genes.

For your second question, could you provide more detail? Thank you!

chen-peng-1874 commented 1 year ago

Thank you! I will search for branching genes. The second question is indeed the same as the first one. I just used all the genes, instead of the branching genes for generating velocity.