Skip to content

Note

Click here to download the full example code

H01 Dataset#

In this notebook, you can learn how to work with the H01 dataset using NAVis.

The H01 dataset contains 57,000 cells and 150 million synapses from a cubic millimeter of the human temporal cortex, which is proofread using the CAVE ecoystem.

With this interface, you can access both a snapshot of the proofread dataset and the latest dataset using caveclient:

pip install caveclient -U

Authentication

If this is your first time using CAVEclient to access the H01 dataset, you might have to get and set your authentication token:

  1. Go to: https://https//global.brain-wire-test.org/auth/api/v1/create_token to create a new token.
  2. Log in with your Google credentials and copy the token shown afterward.
  3. Save it to your computer with: 
    from caveclient import CAVEclient
client = CAVEclient(server_address="https://global.brain-wire-test.org", datastack_name='h01_c3_flat', auth_token="PASTE_YOUR_TOKEN_HERE")
client.auth.save_token(token="PASTE_YOUR_TOKEN_HERE")

Note that the H01 dataset uses a server address that is different from the default CAVEClient server. Also be aware that creating a new token by finishing step 2 will invalidate the previous token!

import navis
from navis.interfaces import h01

# Initialize the client
client = h01.get_cave_client()

Query Tables#

client.materialize.get_versions()

Out:

[549, 527, 541, 543, 546, 548]

client.materialize.get_tables()

Out:

['cells', 'nucleus', 'synapses', 'proofreading_status_test', 'synapses_using_sample_voxel_coords']

Query Materialized Synapse Table#

Query the first few rows in the table

client.materialize.synapse_query(limit=10)

Out:

201 - "Limited query to 10 rows
id created superceded_id valid size pre_pt_supervoxel_id pre_pt_root_id post_pt_supervoxel_id post_pt_root_id pre_pt_position post_pt_position ctr_pt_position
0 40971523 2024-04-12 00:14:40.110821+00:00 NaN t NaN 134364238863925557 864691128621846602 134293870119747633 864691131861340864 [453256, 225950, 1879] [453086, 226004, 1838] [453312, 225966, 1883]
1 40971525 2024-04-12 00:14:40.110821+00:00 NaN t NaN 122744257927708975 864691132202350435 123448011605934094 864691132349699414 [369038, 157894, 4777] [373770, 158410, 12] [368610, 158562, 4703]
2 40971526 2024-04-12 00:14:40.110821+00:00 NaN t NaN 106917542483722336 864691132270145118 106776805062476142 864691132270173278 [253634, 204356, 1947] [252889, 204590, 2104] [253668, 204394, 1970]
3 40971531 2024-04-12 00:14:40.110821+00:00 NaN t NaN 123171415779180930 864691132169548413 123238142525309068 864691132434786616 [371948, 194706, 231] [372276, 167562, 393] [373837, 195793, 656]
4 40971532 2024-04-12 00:14:40.110821+00:00 NaN t NaN 112057964830916834 864691132186081100 123873454087733399 864691132406664067 [291270, 230762, 692] [376984, 182427, 422] [291536, 230572, 743]
5 40971533 2024-04-12 00:14:40.110821+00:00 NaN t NaN 123247282417042025 864691131368353049 123106476209209491 864691132146145331 [372432, 235870, 836] [371386, 235338, 800] [372404, 235926, 878]
6 40971543 2024-04-12 00:14:40.110821+00:00 NaN t NaN 111615894450340136 864691131150038069 110277925298765887 864691132256098281 [288132, 82436, 4516] [278270, 75460, 2688] [288126, 82449, 4534]
7 40971544 2024-04-12 00:14:40.110821+00:00 NaN t NaN 97420786213584924 864691132283064473 98476316705161844 864691132291684761 [184568, 226882, 2954] [192388, 226910, 1720] [186353, 228578, 2425]
8 40971558 2024-04-12 00:14:40.110821+00:00 NaN t NaN 106124452210671785 864691130242818215 106686508676678327 864691132254753632 [247898, 62853, 4234] [251917, 56124, 4088] [247909, 62819, 4232]
9 40971570 2024-04-12 00:14:40.110821+00:00 NaN t NaN 120781010190205127 864691131982166038 123383897072337185 864691132339647570 [354624, 210728, 2843] [373366, 204850, 1449] [354762, 211287, 2855]

Query specific pre- and/or postsynaptic IDs

syn = client.materialize.synapse_query(
    post_ids=[864691131861340864],
    # pre_ids=[ADD YOUR ROOT ID],
)
syn.head()
id created superceded_id valid size pre_pt_supervoxel_id pre_pt_root_id post_pt_supervoxel_id post_pt_root_id pre_pt_position post_pt_position ctr_pt_position
0 40882209 2024-04-12 00:14:37.031216+00:00 NaN t NaN 134364238863925573 864691128621846858 134293870119747633 864691131861340864 [453528, 225898, 1883] [453086, 226004, 1838] [453539, 225957, 1897]
1 40899780 2024-04-12 00:14:37.548445+00:00 NaN t NaN 134434607608102964 864691130486857485 134293870119747633 864691131861340864 [453872, 225934, 1847] [453086, 226004, 1838] [453854, 226063, 1851]
2 40924493 2024-04-12 00:14:38.495865+00:00 NaN t NaN 134223432656093315 864691132015686175 134293870119747633 864691131861340864 [452262, 225346, 1846] [453086, 226004, 1838] [453124, 225933, 1852]
3 40935748 2024-04-12 00:14:38.723502+00:00 NaN t NaN 134434676327579728 864691131840536421 134293870119747633 864691131861340864 [453838, 226378, 1849] [453086, 226004, 1838] [453786, 226050, 1873]
4 40954321 2024-04-12 00:14:39.566756+00:00 NaN t NaN 134293732747903463 864691132191805487 134293870119747633 864691131861340864 [453008, 224834, 1980] [453086, 226004, 1838] [453459, 225953, 1891] 
print(len(syn))

Out:

8

Live Synapse Queries#

import datetime as dt

# Check if root ID is the most recent root ID
root_id = 864691131861340864
now = dt.datetime.now(dt.timezone.utc)
is_latest = client.chunkedgraph.is_latest_roots([root_id], timestamp=now)
latest_id = client.chunkedgraph.get_latest_roots(root_id, timestamp=now)
print(is_latest, latest_id)

Out:

/opt/hostedtoolcache/Python/3.10.15/x64/lib/python3.10/site-packages/networkx/readwrite/json_graph/node_link.py:287: FutureWarning:


The default value will be changed to `edges="edges" in NetworkX 3.6.

To make this warning go away, explicitly set the edges kwarg, e.g.:

  nx.node_link_graph(data, edges="links") to preserve current behavior, or
  nx.node_link_graph(data, edges="edges") for forward compatibility.

[ True] [864691131861340864]

synapse_table = client.info.get_datastack_info()["synapse_table"]
df = client.materialize.query_table(
    synapse_table,
    timestamp=dt.datetime.now(dt.timezone.utc),
    filter_equal_dict={"post_pt_root_id": latest_id[0]},
)
df.head()
id created superceded_id valid size pre_pt_supervoxel_id pre_pt_root_id post_pt_supervoxel_id post_pt_root_id pre_pt_position post_pt_position ctr_pt_position
0 40882209 2024-04-12 00:14:37.031216+00:00 NaN t NaN 134364238863925573 864691128621846858 134293870119747633 864691131861340864 [453528, 225898, 1883] [453086, 226004, 1838] [453539, 225957, 1897]
1 40899780 2024-04-12 00:14:37.548445+00:00 NaN t NaN 134434607608102964 864691130486857485 134293870119747633 864691131861340864 [453872, 225934, 1847] [453086, 226004, 1838] [453854, 226063, 1851]
2 40924493 2024-04-12 00:14:38.495865+00:00 NaN t NaN 134223432656093315 864691132015686175 134293870119747633 864691131861340864 [452262, 225346, 1846] [453086, 226004, 1838] [453124, 225933, 1852]
3 40935748 2024-04-12 00:14:38.723502+00:00 NaN t NaN 134434676327579728 864691131840536421 134293870119747633 864691131861340864 [453838, 226378, 1849] [453086, 226004, 1838] [453786, 226050, 1873]
4 40954321 2024-04-12 00:14:39.566756+00:00 NaN t NaN 134293732747903463 864691132191805487 134293870119747633 864691131861340864 [453008, 224834, 1980] [453086, 226004, 1838] [453459, 225953, 1891]

Query Cells Table#

ct = client.materialize.query_table(table="cells")
ct.head()
id created superceded_id valid classification_system cell_type pt_supervoxel_id pt_root_id pt_position
0 1 2023-06-15 19:27:23.586264+00:00 NaN t 0, 0, 0 UNKNOWN0 0 0 [0, 0, 0]
1 2 2023-06-15 19:27:23.587056+00:00 NaN t 0, 0, 0 UNKNOWN0 0 0 [0, 0, 0]
2 3 2023-06-15 19:27:23.587786+00:00 NaN t 0, 0, 0 UNKNOWN0 0 0 [0, 0, 0]
3 4 2023-06-15 19:27:23.588481+00:00 NaN t 0, 0, 0 UNKNOWN0 0 0 [0, 0, 0]
4 5 2023-06-15 19:27:23.589166+00:00 NaN t 0, 0, 0 UNKNOWN0 0 0 [0, 0, 0] 
ct.cell_type.unique()

Out:

array(['UNKNOWN0', 'PYRAMIDAL', 'UNCLASSIFIEDNEURON', 'UNKNOWN2', 'OLIGO',
       'ASTROCYTE', 'MG_OPC', 'INTERNEURON', 'BLOODVESSELCELL',
       'UNKNOWN1', 'C-SHAPEDCELL_AKA_MG_OPC'], dtype=object)

Filter by cell type#

# Get the first 50 interneurons
interneuron_ids = ct[ct.cell_type == "INTERNEURON"].pt_root_id.values[:50]

# Remove 0 IDs
interneuron_ids = interneuron_ids[interneuron_ids != 0]

# What's left?
interneuron_ids

Out:

array([864691132341213351, 864691132343125732, 864691132440298746,
       864691132301485893, 864691132254968355, 864691132509654349,
       864691132254843391])

Fetch Neuron Meshes#

interneurons = h01.fetch_neurons(interneuron_ids, lod=2, with_synapses=False)
interneurons_ds = navis.simplify_mesh(interneurons, F=1 / 3)
interneurons_ds
<class 'navis.core.neuronlist.NeuronList'> containing 7 neurons (44.1MiB)
type name id units n_vertices n_faces
0 navis.MeshNeuron None 864691132301485893 1 nanometer 65943 130220
1 navis.MeshNeuron None 864691132341213351 1 nanometer 123979 239637
... ... ... ... ... ... ...
5 navis.MeshNeuron None 864691132254968355 1 nanometer 140941 277315
6 navis.MeshNeuron None 864691132254843391 1 nanometer 159764 313186 
# Plot
import seaborn as sns

colors = {n.id: sns.color_palette("Reds", 7)[i] for i, n in enumerate(interneurons_ds)}
navis.plot3d([interneurons_ds], color=colors)