Issue with model.initialize_archetypes()

[iamsalil]

I have an AnnData object (adata) from which I am trying to create a SEACells model. The AnnData object has 593 rows corresponding to 593 cells.
I'm running into an error at this line of code which I pulled from one of the tutorial notebooks:
`

    # SEACells parameter setup
    n_SEACells = 1 + int(len(adata)/75)
    build_kernel_on = "XPCA"
    n_waypoint_eigs = 10 # Number of eigenvalues to consider when initializing metacells
    
    # Build SEACells model
    model = SEACells.core.SEACells(adata,
              build_kernel_on=build_kernel_on,
              n_SEACells=n_SEACells,
              use_gpu=True,
              n_waypoint_eigs=n_waypoint_eigs,
              convergence_epsilon = 1e-5)
    model.construct_kernel_matrix()
    M = model.kernel_matrix

    # Initialize archetypes
    model.initialize_archetypes()`

The error I'm getting is an IndexError seemed to be caused by Palantir:

Traceback (most recent call last):
File "1_make_metacells.py", line 176, in main
model.initialize_archetypes()
File "/users/salil512/miniconda3/envs/seacells/lib/python3.8/site-packages/SEACells/gpu.py", line 162, in initialize_archetypes
waypoint_ix = self._get_waypoint_centers(k)
File "/users/salil512/miniconda3/envs/seacells/lib/python3.8/site-packages/SEACells/gpu.py", line 286, in _get_waypoint_centers
waypoint_init = palantir.core._max_min_sampling(data=dc_components, num_waypoints=k)
File "/users/salil512/miniconda3/envs/seacells/lib/python3.8/site-packages/palantir/core.py", line 145, in _max_min_sampling
dists[:, 0] = abs(vec - data[ind].values[iter_set])
IndexError: index 0 is out of bounds for axis 1 with size 0

I have the latest version of SEACells and my palantir version is 1.1

Some help debugging this would be appreciated. Thanks.

[iamsalil]

I determined the cause of the issue. n_waypoint_eigs must be <= n_SEACells + 1. If this does not hold true, then at line 132 of palantir/core.py, no_iterations is set to 0 and the error is thrown (In that function, data.shape[1] = n_waypoint_eigs-1 and num_waypoints = n_SEACells).

In this case, I had 8 SEACells and had set n_waypoint_eigs to 10, following the default number in the example notebooks.

Could you please advise in general about how n_SEACells and n_waypoint_eigs should be set? In a tutorial notebook it says that it should be the number of cells / 75. However, I feel like I read somewhere else (I can't seem to find the source for where I read it) that the number of SEACells should be equal to the number of cells / 100. Also, I didn't really find any direction about best practices for how to set the value of n_waypoint_eigs. What's best practices for this? Does it scale on the size of the dataset?

[zqun1]

I have the same problem when my n_SEACells is 7 (I do not have enough cells) while keeping n_waypoint_eigs=10. Any updates?

[OMIC-coding]

---

AttributeError Traceback (most recent call last)
Cell In[9], line 2
1 # Initialize archetypes---------------------------------------------------------------------------
AttributeError Traceback (most recent call last)
Cell In[9], line 2
1 # Initialize archetypes
----> 2 model.initialize_archetypes()

File ~/miniconda3/envs/seacells/lib/python3.8/site-packages/SEACells/core.py:129, in SEACells.initialize_archetypes(self)
126 else:
127 from_greedy = self.k
--> 129 greedy_ix = self._get_greedy_centers(n_mcs=from_greedy + 10)
130 if self.verbose:
131 print(f'Selecting {from_greedy} cells from greedy initialization.')

File ~/miniconda3/envs/seacells/lib/python3.8/site-packages/SEACells/core.py:245, in SEACells._get_greedy_centers(self, n_mcs)
236 """Initialize SEACells using fast greedy adaptive CSSP
237
238 From https://arxiv.org/pdf/1312.6838.pdf
(...)
241 :return: B - (array) n_datapoints x n_SEACells matrix with initial SEACell definitions
242 """
244 K = self.K
--> 245 n = K.shape[0]
247 if n_mcs is None:
248 k = self.k

AttributeError: 'NoneType' object has no attribute 'shape'
----> 2 model.initialize_archetypes()

File ~/miniconda3/envs/seacells/lib/python3.8/site-packages/SEACells/core.py:129, in SEACells.initialize_archetypes(self)
126 else:
127 from_greedy = self.k
--> 129 greedy_ix = self._get_greedy_centers(n_mcs=from_greedy + 10)
130 if self.verbose:
131 print(f'Selecting {from_greedy} cells from greedy initialization.')

File ~/miniconda3/envs/seacells/lib/python3.8/site-packages/SEACells/core.py:245, in SEACells._get_greedy_centers(self, n_mcs)
236 """Initialize SEACells using fast greedy adaptive CSSP
237
238 From https://arxiv.org/pdf/1312.6838.pdf
(...)
241 :return: B - (array) n_datapoints x n_SEACells matrix with initial SEACell definitions
242 """
244 K = self.K
--> 245 n = K.shape[0]
247 if n_mcs is None:
248 k = self.k

AttributeError: 'NoneType' object has no attribute 'shape'

[OMIC-coding]

Could you help me solve this bug? I am stuck in this step for a long time.