1-Photon 2-Photon Ratio Data

cleo/ephys/lfp.py

@@ -612,7 +612,7 @@ def connect_to_neuron_group(self, neuron_group: NeuronGroup, **kwparams):
         self._init_wslfp_calc(neuron_group, **kwparams)
 
         buf_len_ampa, buf_len_gaba = self._get_buf_lens_for_wslfp(
-            self._wslfps[neuron_group]
+            self._wslfps[neuron_group], **kwparams
         )
         self._t_ampa_bufs[neuron_group] = deque(maxlen=buf_len_ampa)
         self._I_ampa_bufs[neuron_group] = deque(maxlen=buf_len_ampa)
@@ -633,8 +633,8 @@ def _get_buf_lens_for_wslfp(self, wslfp_calc, **kwparams):
             try:
                 sample_period = self.probe.sim.io_processor.sample_period
             except AttributeError:  # probably means sim doesn't have io_processor
-                raise Exception(
-                    "RSWLFPSignalFromPSCs needs to know the sampling period."
+                raise RuntimeError(
+                    "RWSLFPSignalFromPSCs needs to know the sampling period."
                     " Either set the simulator's IO processor before injecting"
                     f" {self.probe.name} or "
                     f" specify it on injection: .inject({self.probe.name}"

cleo/ephys/spiking.py

@@ -245,6 +245,12 @@ def connect_to_neuron_group(self, neuron_group: NeuronGroup, **kwparams):
         # spike sorters don't sort by multi-channel recall; we only do this
         # for computational efficiency, to not get super distant neurons
 
+        # needed even if no neurons are recorded
+        if not self._prev_t:
+            self._prev_t = self.probe.sim.network.t
+        if self._mu_eap is None:
+            self._mu_eap = np.zeros((0, self.n_channels))
+
         n2keep = np.sum(where_to_keep)
         if n2keep == 0:
             warnings.warn(
@@ -271,14 +277,8 @@ def connect_to_neuron_group(self, neuron_group: NeuronGroup, **kwparams):
         assert len(self.i_ng_by_i_probe) == i_probe_start
         self.i_ng_by_i_probe.extend(list(zip([neuron_group] * n2keep, i2keep)))
 
-        if not self._prev_t:
-            self._prev_t = self.probe.sim.network.t
-
         # store neuron-channel mean and stdev of EAPs to use in subclasses
-        if self._mu_eap is None:
-            self._mu_eap = snr[where_to_keep]
-        else:
-            self._mu_eap = np.concatenate((self._mu_eap, snr[where_to_keep]), axis=0)
+        self._mu_eap = np.concatenate((self._mu_eap, snr[where_to_keep]), axis=0)
 
         return snr[where_to_keep].max(axis=1), new_i_probe
 
@@ -642,7 +642,11 @@ def sorted_units_snr(self) -> Float[np.ndarray, "{self.n_sorted}"]:
         return self._mu_eap[self._i_probe_by_i_sorted]
 
     def connect_to_neuron_group(self, neuron_group, **kwparams):
-        snr, i_probe = super().connect_to_neuron_group(neuron_group, **kwparams)
+        connect_result = super().connect_to_neuron_group(neuron_group, **kwparams)
+        if connect_result is None:
+            # No neurons with high-enough multi-channel recall to record
+            return
+        snr, i_probe = connect_result
         n_recorded_ng = len(snr)
         # filter by SNR (measured on peak channel)
         above_cutoff = snr >= self.snr_cutoff

cleo/opto/__init__.py

@@ -7,6 +7,16 @@
     enphr3_3s,
     gtacr2_4s,
     vfchrimson_4s,
+    reachr_4s,
+    chrimsonr_4s,
+    cschrimson_4s,
+    breaches_4s,
+    chrmine_4s,
+    cheta_4s,
+    chronos_4s,
+    cheriff_4s,
+    nphr_3s,
+    jaws_3s,
 )
 from cleo.opto.opsins import (
     BansalFourStateOpsin,