2.1.1 The connection

suppressPackageStartupMessages({
library(TxRegInfra)
library(mongolite)
library(Gviz)
library(EnsDb.Hsapiens.v75)
library(BiocParallel)
register(SerialParam())
})
con1 = mongo(url=URL_txregInAWS(), db="txregnet")
con1

## <Mongo collection> 'test' 
##  $aggregate(pipeline = "{}", options = "{\"allowDiskUse\":true}", handler = NULL, pagesize = 1000, iterate = FALSE) 
##  $count(query = "{}") 
##  $disconnect(gc = TRUE) 
##  $distinct(key, query = "{}") 
##  $drop() 
##  $export(con = stdout(), bson = FALSE, query = "{}", fields = "{}", sort = "{\"_id\":1}") 
##  $find(query = "{}", fields = "{\"_id\":0}", sort = "{}", skip = 0, limit = 0, handler = NULL, pagesize = 1000) 
##  $import(con, bson = FALSE) 
##  $index(add = NULL, remove = NULL) 
##  $info() 
##  $insert(data, pagesize = 1000, stop_on_error = TRUE, ...) 
##  $iterate(query = "{}", fields = "{\"_id\":0}", sort = "{}", skip = 0, limit = 0) 
##  $mapreduce(map, reduce, query = "{}", sort = "{}", limit = 0, out = NULL, scope = NULL) 
##  $remove(query, just_one = FALSE) 
##  $rename(name, db = NULL) 
##  $replace(query, update = "{}", upsert = FALSE) 
##  $run(command = "{\"ping\": 1}", simplify = TRUE) 
##  $update(query, update = "{\"$set\":{}}", filters = NULL, upsert = FALSE, multiple = FALSE)

We will write methods that work with the ‘fields’ of this object.

There is not much explicit reflectance in the mongolite API. The following is improvised and may be fragile:

parent.env(con1)$orig

## $name
## [1] "test"
## 
## $db
## [1] "txregnet"
## 
## $url
## [1] "mongodb+srv://user:user123@cluster1-ag7nd.mongodb.net/test"
## 
## $options
## List of 6
##  $ pem_file              : NULL
##  $ ca_file               : NULL
##  $ ca_dir                : NULL
##  $ crl_file              : NULL
##  $ allow_invalid_hostname: logi FALSE
##  $ weak_cert_validation  : logi FALSE

2.1.2 Queries and aggregation

If the mongo utility is available as a system command, we can get a list of collections in the database as follows.

if (verifyHasMongoCmd()) {
  head(c1 <- txregCollections(url=URL_txregInAWS(), db="txregnet"))
  }

Otherwise, as long as mongolite is installed, as long as we know the collection names of interest, we can use them as noted throughout this vignette.

We can get a record from a given collection:

mongo(url=URL_txregInAWS(), db="txregnet", 
   collection="Adipose_Subcutaneous_allpairs_v7_eQTL")$find(limit=1)

##             gene_id       variant_id tss_distance ma_samples ma_count
## 1 ENSG00000233750.3 1_743420_G_A_b37       612395         28       30
##         maf pval_nominal    slope slope_se    qvalue chr snp_pos A1 A2 build
## 1 0.0391645  0.000143004 0.559146 0.145246 0.0130483   1  743420  G  A   b37

Queries can be composed using JSON. We have a tool to generate queries that employ the mongodb aggregation method. Here we demonstrate this by computing, for each chromosome, the count and minimum values of the footprint statistic on CD14 cells.

m1 = mongo(url = URL_txregInAWS(), db = "txregnet",  collection="CD14_DS17215_hg19_FP")
newagg = makeAggregator( by="chr", vbl="stat", op="$min", opname="min")

The JSON layout of this aggregating query is

[
  {
    "$group": {
      "_id": ["$chr"],
      "count": {
        "$sum": [1]
      },
      "min": {
        "$min": ["$stat"]
      }
    }
  }
] 

Invocation returns a data frame:

head(m1$aggregate(newagg))

##     _id count        min
## 1  chrY   827 0.01907390
## 2 chr18 15868 0.06107950
## 3 chr10 40267 0.00601357
## 4  chr4 32947 0.02776440
## 5  chr6 54728 0.00565057
## 6 chr17 47987 0.01242310