task_ist_preprocessing/src/methods_transcript_assignment/segger/config.vsh.yaml at f24330f037001d26906deb0479beb0b3e4b43775 · openproblems-bio/task_ist_preprocessing · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
__merge__: /src/api/comp_method_transcript_assignment.yaml

name: segger
label: "Segger Transcript Assignment"
summary: "Assign transcripts to cells using the Segger method"
description: "Segger is a tool for cell segmentation in single-molecule spatial omics datasets that leverages graph neural networks (GNNs) and heterogeneous graphs."
links:
  documentation: "https://elihei2.github.io/segger_dev/"
  repository: "https://github.com/EliHei2/segger_dev"
references:
  doi: "10.1101/2025.03.14.643160"

arguments:
  - name: --transcripts_key
    type: string
    description: The key of the transcripts within the points of the spatial data
    default: transcripts
  - name: --coordinate_system
    type: string
    description: The key of the pixel space coordinate system within the spatial data
    default: global

#  - name: --force_2d
#    type: string
#    required: false
#    description: "Ignores z-column in the data if it is provided"
#    direction: input
#    default: "false"
#
#  - name: --min_molecules_per_cell
#    type: integer
#    required: false
#    description: "Minimal number of molecules per cell"
#    direction: input
#    default: 50
#
#  - name: --scale
#    type: double
#    required: false
#    description: |
#      "Scale parameter, which suggest approximate cell radius for the algorithm. Must be in the same units as
#      x and y molecule coordinates. Negative values mean it must be estimated from `min_molecules_per_cell`."
#    direction: input
#    default: -1.0
#
#  - name: --scale_std
#    type: string
#    required: false
#    description: "Standard deviation of scale across cells relative to `scale`"
#    direction: input
#    default: "25%"
#
#  - name: --n_clusters
#    type: integer
#    required: false
#    description: "Number of molecule clusters, i.e. major cell types."
#    direction: input
#    default: 4
#
#  - name: --prior_segmentation_confidence
#    type: double
#    required: false
#    description: "Confidence of the prior segmentation"
#    direction: input
#    default: 0.8

resources:
  - type: python_script
    path: script.py

engines:
#  - type: docker
#    image: openproblems/base_python:1
#    __merge__:
#      - /src/base/setup_spatialdata_partial.yaml
#    setup:
#      - type: python
#        pypi: [torch, pytorch-lightning, lightning]
#      - type: docker
#        run:
#          - git clone https://github.com/EliHei2/segger_dev.git
#          - cd segger_dev && pip install .[cuda12]
engines:
  - type: docker
    image: danielunyi42/segger_dev:cuda121
    setup:
      - type: apt
        packages: procps
      - type: python
        github:
          - openproblems-bio/core#subdirectory=packages/python/openproblems
      - type: python
        packages:
          - spatialdata
  - type: native

runners:
  - type: executable
  - type: nextflow
    directives:
      label: [ midtime, midcpu, midmem, gpu ]