Finding neurons with multiple somata

Gregory Jefferis

2020-06-08

Source: vignettes/articles/multiple_somata.Rmd

Intro

Occasionally CATMAID users add the soma tag multiple times in error. We can find such neurons and generate CATMAID URLs to inspect them.

Setup

First load main packages

library(elmr)
cl=try(catmaid_login())
catmaid_available=inherits(cl, "catmaid_connection")
library(knitr)
# only run if catmaid available
# and cache so only run once per day
opts_chunk$set(eval=inherits(cl, "catmaid_connection"),cache.extra=Sys.Date())
library(dplyr)
rgl::setupKnitr()

Finding neurons with multiple somata

First let’s fetch information about all the labels (aka tags) applied to nodes in the current project.

label_stats=catmaid_get_label_stats()

Now let’s restrict to cases where there are multiple soma tags per skeleton

# select soma labels
soma_labels = label_stats %>%
  filter(labelName == 'soma') %>%
  group_by(skeletonID)

# select skeleton ids for neurons with multiple cell bodies
multiple_soma = soma_labels %>%
  count(skeletonID) %>%
  filter(n > 1) %>%
  arrange(desc(n))
  multiple_soma_info = soma_labels %>%
  filter(skeletonID %in% multiple_soma$skeletonID)

multiple_soma_info = soma_labels %>%
  filter(skeletonID%in% multiple_soma$skeletonID)

XYZ position of the nodes we picked

# wrapper for tree node details
node_details <- function(tnid) {
  res=catmaid_get_treenodes_detail(tnid)
  ul=catmaid_get_user_list()
  res$login=ul$login[match(res$user_id, ul$id)]
  # we expect these to be capitalised elsewhere
  cn=colnames(res)
  cn[cn%in%c("x","y","z")]=toupper(cn[cn%in%c("x","y","z")])
  colnames(res) <- cn
  res[c("X","Y","Z","radius","login")]
}

# note that we need to transpose the results of vnode_xyz to get X,Y,Z columns
multiple_soma_info <- cbind(as.data.frame(multiple_soma_info),
                            node_details(multiple_soma_info$treenodeID))

Now let’s calculate the distance from the neuropil surface

multiple_soma_info$d=pointsinside(xyzmatrix(multiple_soma_info),
                                  FAFB.surf, rval = 'distance')
multiple_soma_info %>%
  arrange(skeletonID, d) %>%
  group_by(skeletonID) %>%
  mutate(rank=row_number()) -> multiple_soma_info
kable(multiple_soma_info)
labelID labelName skeletonID treenodeID X Y Z radius login d rank
2773 soma 1298891 7525237 395632.7 95574.06 177520 2855 batesa -9679.5078 1
2773 soma 1298891 59494856 404913.9 96547.42 161000 51 serratosal 5889.5156 2
2773 soma 2015619 56565186 322684.0 154162.50 201600 1985 serratosal -13418.5234 1
2773 soma 2015619 18010667 371781.5 128202.72 176640 -1 batesa 14364.6289 2
2773 soma 3658067 12345094 618823.6 218756.61 60680 2440 alghailanis 2672.3125 1
2773 soma 3658067 30290984 413013.0 240218.00 145680 -1 polskyj 13872.9307 2
2773 soma 3721315 12460766 434532.3 254146.14 84880 3918 calles -1958.2344 1
2773 soma 3721315 12459557 433765.5 253732.36 84320 -1 dacksa -1411.6875 2
2773 soma 3726283 35469519 322771.5 155343.50 181680 2093 tenshawe -4883.0469 1
2773 soma 3726283 35469478 323028.0 155599.00 181200 -1 tenshawe -4637.3281 2
2773 soma 3788293 19104385 370375.0 152519.00 215520 1904 batesa -7053.4844 1
2773 soma 3788293 19104384 370363.0 152491.00 215400 1889 batesa -6953.6719 2
2773 soma 4705224 61576868 333411.7 155215.83 196000 1791 serratosal -2653.0000 1
2773 soma 4705224 21007576 381708.0 129635.00 171280 -1 robertsr 17971.9297 2
2773 soma 6645033 6781342 617127.0 261972.00 67160 3076 calles 226.7500 1
2773 soma 6645033 41219199 495504.6 264349.25 62520 -1 coatesk 11138.5625 2
2773 soma 6645033 43899462 484171.5 264798.03 77240 -1 dacksa 19888.3066 3
2773 soma 7145440 61582172 334965.7 152653.12 194360 2081 serratosal 352.7344 1
2773 soma 7145440 23455383 358511.0 139952.00 190680 -1 batesa 10689.1250 2
2773 soma 7937976 57573136 320074.8 162848.39 185360 1702 serratosal -8637.9688 1
2773 soma 7937976 13380406 377685.2 210574.42 176800 -1 batesa 4119.2852 2
2773 soma 8758601 49116764 440101.5 203967.33 56360 2454 helmickl 988.2656 1
2773 soma 8758601 52299679 476734.8 214770.89 39800 -1 helmickl 11180.4805 2
2773 soma 9623317 32110234 428951.1 298439.03 209400 1781 eichlerk -8578.3359 1
2773 soma 9623317 59058312 497413.8 339922.00 164720 42 eichlerk 19744.7188 2
2773 soma 10108062 33531079 419915.0 224525.00 51080 -1 coatesk -3335.2869 1
2773 soma 10108062 40684585 513639.0 219860.00 46640 -1 sweetn 700.5312 2
2773 soma 10110812 44656714 657952.0 265904.00 156680 -1 marquism -6115.3125 1
2773 soma 10110812 44656784 667914.0 256180.00 145520 -1 marquism 3447.3750 2
2773 soma 10234277 34371718 493445.3 360456.34 122800 2392 eichlerk -4578.6562 1
2773 soma 10234277 36336623 493429.4 360356.44 122560 2197 jefferis -4492.1562 2
2773 soma 10479161 35374843 192769.0 213598.00 202960 1960 obrusnikt -29056.5000 1
2773 soma 10479161 35376150 327465.0 208878.00 219720 -1 obrusnikt 13896.2900 2
2773 soma 12173355 44728863 649485.0 226483.00 181440 -1 marquism -4930.6875 1
2773 soma 12173355 44728872 648709.0 227851.00 181120 -1 marquism -3965.1250 2
2773 soma 12526415 1112769 486046.6 126634.30 162360 1926 adamjohn -2019.5625 1
2773 soma 12526415 49202602 486127.0 127527.00 162600 3513 gibbp -1784.5625 2
2773 soma 12526731 4375796 600107.4 164816.88 209640 1787 alis -19557.8125 1
2773 soma 12526731 49752844 600100.0 164768.00 209640 2471 gibbp -19553.0625 2
2773 soma 12529405 51019292 432457.0 146688.00 62800 1948 lia -2623.7188 1
2773 soma 12529405 51021568 462561.0 275852.00 192680 -1 lia 17362.4688 2
2773 soma 13082053 52561173 632767.4 284886.38 29440 2426 toj -13823.5625 1
2773 soma 13082053 52561151 632533.3 284312.50 30280 -1 toj -13011.1875 2
2773 soma 14019704 44310666 411763.0 163520.42 79080 2336 tenshawe 979.3810 1
2773 soma 14019704 44310655 411511.6 163639.28 79320 -1 tenshawe 983.9166 2
2773 soma 14462790 56638440 392006.1 167674.31 87520 1750 ludwigh 681.3281 1
2773 soma 14462790 57473239 372964.3 161629.42 106960 -1 ludwigh 4346.0938 2
2773 soma 14933802 59013131 293730.8 147386.66 207680 2541 kinde -8970.6250 1
2773 soma 14933802 56163931 272602.0 161879.00 235200 -1 sancerg -7160.1328 2
2773 soma 14997019 59362821 440576.4 190338.95 55000 3113 kandimallap -4747.6250 1
2773 soma 14997019 59844352 440777.4 183727.28 93760 -1 kandimallap 10568.4600 2

This lets us see that in some cases there are two soma tags outside the neuropil (negative d) and close together - these are probably duplicates - whereas in other cases it is likely that points were added in error. We can also plot the points colouring them by their rank order (most external first).

# make a colour palette with as many entries as the maximum number of soma 
# tags in a neuron
pal=rainbow(max(multiple_soma_info$rank))
multiple_soma_info %>%
  with(expr = spheres3d(X,Y,Z, col=pal[rank], rad=2000))
plot3d(FAFB)
par3d(zoom=.6)

Now we can use this information to construct an url for each node.

multiple_soma_info %>%
  rowwise() %>%
  mutate(url = open_fafb(
    cbind(X, Y, Z),
    active_skeleton_id = skeletonID,
    active_node_id = treenodeID,
    open = FALSE
  )) -> multiple_soma_info

It might be useful to know who ‘owns’ each neuron. I think the simplest way to assign this is by the user who has traced most nodes for each skeleton (since there may be different users responsible for each soma).

get_top_user <- function(x, ...) {
  ul=catmaid_get_user_list(...)
  # save time by checking unique skids only
  ddx=unique(x)
  gtu_one <- function(x, ...) {
    t <- try({
      res=catmaid_get_contributor_stats(x, ...)
      w=which.max(res$node_contributors$n)
      ul$login[match(res$node_contributors$id[w], ul$id)]
    })
    if(inherits(t, 'try-error')) NA_character_ else t
  }
  topus <- sapply(ddx, gtu_one)
  topus[match(x, ddx)]
}

Google sheet

Let’s make a google sheet with all those urls that we can then review manually:

library(googlesheets)
# helper function to upload via temp file
# since writing cells via API is very slow
gs_upload_tf <- function(x, ...) {
  tf=tempfile(fileext = '.tsv')
  on.exit(unlink(tf))
  write.table(x, file=tf, sep="\t", row.names = FALSE)
  gs_upload(tf, ...)
}

multiple_soma_info %>%
  arrange(skeletonID, d) %>%
  group_by(skeletonID) %>%
  mutate(user=get_top_user(skeletonID)) %>%
  gs_upload_tf(sheet_title = 'multi_soma_neurons')

As an alternative we can divide that up with one worksheet per user.

library(googlesheets)
gs <- googlesheets::gs_new("multi_soma_neurons_by_user")
gs_add_sheet <- function(x, gs, ...) {
  gs_ws_new(row_extent = nrow(x)+1, col_extent = ncol(x), ss = gs, ..., input=x, col_names=T)
}
multiple_soma_info %>%
  arrange(skeletonID, d) %>%
  mutate(user=factor(get_top_user(skeletonID))) -> msi2

for(u in levels(msi2$user)) {
  gs_add_sheet(subset(msi2, user==u), gs, ws_title=u)
  cat(".")
}