01 - NGS collection [human]

import pandas as pd

1 Kagawa et al., 2022 [GSE177616]

KAGAWA_URL='https://ftp.ncbi.nlm.nih.gov/geo/series/GSE177nnn/GSE177616/matrix/GSE177616_series_matrix.txt.gz'
kagawa_metadata = pd.read_table(KAGAWA_URL, skiprows=16, nrows=1, index_col = 0).T

kagawa_gsm = pd.DataFrame({'GSM': kagawa_metadata.index.values[0].split(' ')})

kagawa_gsm

	GSM
0	GSM5375527
1	GSM5375528
2	GSM5375529
3	GSM5375530
4	GSM5375531
...	...
2711	GSM5378537
2712	GSM5378538
2713	GSM5378539
2714	GSM5378540
2715

2716 rows × 1 columns

kagawa_gsm.to_csv("../pipeline/fetchngs/human_GSE177616.txt", index=None,header=None)

sh ~/Brickman/helper-scripts/nf-core_tower.sh \
    Kagawa_2022 \
    nextflow run nf-core/fetchngs \
    -r 1.10.0 \
    --input /projects/dan1/data/Brickman/projects/proks-salehin-et-al-2023/pipeline/fetchngs/human_GSE177616.txt

nf-core_tower.sh Meistermann_2021 nextflow run brickmanlab/scrnaseq \
    -r feature/smartseq \
    -c /projects/dan1/data/Brickman/projects/proks-salehin-et-al-2023/pipeline/smartseq.human.config \
    --input /scratch/Brickman/pipelines/Meistermann_2021/results/samplesheet/samplesheet.csv