Updated some documentation

ccdmb · Aug 27, 2024 · b3e4700 · b3e4700
1 parent f9052c8
commit b3e4700
Show file tree

Hide file tree

Showing 6 changed files with 39 additions and 39 deletions.
diff --git a/docs/faq.md b/docs/faq.md
@@ -79,6 +79,28 @@ _nf_script_9f2a833e: 9: unable to resolve class download_pfam_dat
 Please update Nextflow to a more recent version (>21) to resolve this issue.
 
 
+### On a network file system receive an error `open: can't stat file`.
+
+This is usually caused by a delay in how network file systems sync between many clients.
+If something is writing or reading files very quickly a program can have problems retrieving a file.
+If the server hasn't finished uploading and placing the file, then it can tell your program that the file doesn't exist.
+In SignalP3 this can potentially even cause segfaults (see: https://github.com/ccdmb/predector/issues/92#issuecomment-2034991440).
+
+A solution to this is to use a local filesystem to do the actual work.
+On an HPC you'll usually have some space in `/tmp` to do some work, and you can tell nextflow to stage files there with the following config.
+
+```
+process {
+  scratch = '/tmp'
+}
+```
+
+If you save this to a file, say "my_scratch.config", you can then supply that as an extra argument to nextflow.
+E.g. `nextflow run -c my_scratch.config -profile test,docker ccdmb/predector`
+
+Thanks to @ibebio for pointing us towards this problem.
+
+
 ### Running/setting up conda environment: `loadable library and perl binaries are mismatched (got handshake key 0xdb80080, needed 0xde00080)`
 
 This will usually happen if the operating system you're running on has some perl libraries in the search path for a different version of perl.

diff --git a/docs/install.md b/docs/install.md
@@ -68,11 +68,11 @@ Where you have a choice between versions for different operating systems, you sh
 - [SignalP](https://services.healthtech.dtu.dk/services/SignalP-3.0/9-Downloads.php#) version 3.0
 - [SignalP](https://services.healthtech.dtu.dk/services/SignalP-4.1/9-Downloads.php#) version 4.1g
 - [SignalP](https://services.healthtech.dtu.dk/services/SignalP-5.0/9-Downloads.php#) version 5.0b
-- [SignalP](https://services.healthtech.dtu.dk/services/SignalP-6.0/9-Downloads.php#) version 6.0g "fast" **\*currently optional**
+- [SignalP](https://services.healthtech.dtu.dk/services/SignalP-6.0/9-Downloads.php#) version 6.0h "fast" **\*currently optional**
 - [TargetP](https://services.healthtech.dtu.dk/services/TargetP-2.0/9-Downloads.php#) version 2.0
 - [DeepLoc](https://services.healthtech.dtu.dk/services/DeepLoc-1.0/9-Downloads.php#) version 1.0
 - [TMHMM](https://services.healthtech.dtu.dk/services/TMHMM-2.0/9-Downloads.php#) version 2.0c
-- [Phobius](http://software.sbc.su.se/cgi-bin/request.cgi?project=phobius) version 1.01
+- [Phobius](https://software.sbc.su.se/phobius.html) version 1.01
 
 Note that DTU (SignalP etc) don't keep older patches and minor versions available.
 If the specified version isn't available to download, another version with the same major number _should_ be fine.
@@ -102,11 +102,11 @@ curl -s "https://raw.githubusercontent.com/ccdmb/predector/1.2.7/install.sh" \
     -3 signalp-3.0.Linux.tar.Z \
     -4 signalp-4.1g.Linux.tar.gz \
     -5 signalp-5.0b.Linux.tar.gz \
-    -6 signalp-6.0g.fast.tar.gz \
+    -6 signalp-6.0h.fast.tar.gz \
     -t targetp-2.0.Linux.tar.gz \
     -d deeploc-1.0.All.tar.gz \
     -m tmhmm-2.0c.Linux.tar.gz \
-    -p phobius101_linux.tar.gz
+    -p phobius101_linux.tgz
 ```
 
 This will create the conda environment (named `predector`), or the docker (tagged `predector/predector:1.2.7`) or singularity (file `./predector.sif`) containers.
@@ -219,10 +219,10 @@ Modify the source tar archive filenames in the commands if necessary.
 signalp3-register signalp-3.0.Linux.tar.Z \
 && signalp4-register signalp-4.1g.Linux.tar.gz \
 && signalp5-register signalp-5.0b.Linux.tar.gz \
-&& signalp6-register signalp-6.0g.fast.tar.gz \
+&& signalp6-register signalp-6.0h.fast.tar.gz \
 && targetp2-register targetp-2.0.Linux.tar.gz \
 && deeploc-register deeploc-1.0.All.tar.gz \
-&& phobius-register phobius101_linux.tar.gz \
+&& phobius-register phobius101_linux.tgz \
 && tmhmm2-register tmhmm-2.0c.Linux.tar.gz
 ```
 
@@ -243,9 +243,9 @@ curl -s https://raw.githubusercontent.com/ccdmb/predector/1.2.7/Dockerfile \
   --build-arg SIGNALP3=signalp-3.0.Linux.tar.Z \
   --build-arg SIGNALP4=signalp-4.1g.Linux.tar.gz \
   --build-arg SIGNALP5=signalp-5.0b.Linux.tar.gz \
-  --build-arg SIGNALP6=signalp-6.0g.fast.tar.gz \
+  --build-arg SIGNALP6=signalp-6.0h.fast.tar.gz \
   --build-arg TARGETP2=targetp-2.0.Linux.tar.gz \
-  --build-arg PHOBIUS=phobius101_linux.tar.gz \
+  --build-arg PHOBIUS=phobius101_linux.tgz \
   --build-arg TMHMM=tmhmm-2.0c.Linux.tar.gz \
   --build-arg DEEPLOC=deeploc-1.0.All.tar.gz \
   -t predector/predector:1.2.7 \
@@ -272,9 +272,9 @@ Modify the source tar archive filenames if necessary.
 export SIGNALP3=signalp-3.0.Linux.tar.Z
 export SIGNALP4=signalp-4.1g.Linux.tar.gz
 export SIGNALP5=signalp-5.0b.Linux.tar.gz
-export SIGNALP6=signalp-6.0g.fast.tar.gz
+export SIGNALP6=signalp-6.0h.fast.tar.gz
 export TARGETP2=targetp-2.0.Linux.tar.gz
-export PHOBIUS=phobius101_linux.tar.gz
+export PHOBIUS=phobius101_linux.tgz
 export TMHMM=tmhmm-2.0c.Linux.tar.gz
 export DEEPLOC=deeploc-1.0.All.tar.gz
 

diff --git a/docs/output.md b/docs/output.md
@@ -60,9 +60,6 @@ There are a lot of columns, though generally you'll only be interested in a few
 | `has_phibase_effector_match` | Boolean [0, 1] | Indicates whether the protein had a significant hit to one of the phibase phenotypes: Effector, Hypervirulence, or loss of pathogenicity |
 | `has_phibase_virulence_match` | Boolean [0, 1] | Indicating whether the protein had a significant hit with the phenotype "reduced virulence" |
 | `has_phibase_lethal_match` | Boolean [0, 1] | Indicating whether the protein had a significant hit with the phenotype "lethal" |
-| `pfam_ids` | List | A comma separated list of all Pfam HMM ids matched | You can find details on Pfam match entries at http://pfam.xfam.org (use the "Jump to" search boxes with this ID). Matches are sorted by evalue, so the first hit is the best.|
-| `pfam_names` | List | A comma separated list of all Pfam HMM names matched | Matches are sorted by evalue, so the first hit is the best. |
-| `has_pfam_virulence_match` | Boolean [0, 1] | Indicating whether the protein had a significant hit to one of the selected Pfam HMMs associated with virulence function | A list of virulence associated Pfam entries is here: https://github.com/ccdmb/predector/blob/master/data/pfam_targets.txt |
 | `dbcan_matches` | List | A comma separated list of all dbCAN matches | You can find details on CAZYme families at http://www.cazy.org/. For more on dbCAN specifically see here https://bcb.unl.edu/dbCAN2/. Matches are sorted by evalue, so the first hit is the best. |
 | `has_dbcan_virulence_match` | Boolean [0, 1] | Indicating whether the protein had a significant hit to one of the dbCAN domains associated with virulence function | A list of virulence associated dbCAN entries is here: https://github.com/ccdmb/predector/blob/master/data/dbcan_targets.txt |
 | `effectorp1` | Float | The raw EffectorP v1 prediction pseudo-probability | Values above 0.5 are considered to be effector predictions |

diff --git a/docs/running.md b/docs/running.md
@@ -76,14 +76,6 @@ Important parameters are:
 --phibase <path>
   Path to the PHI-base fasta dataset.
 
---pfam_hmm <path>
-  Path to already downloaded gzipped pfam HMM database
-  default: download the hmms
-
---pfam_dat <path>
-  Path to already downloaded gzipped pfam DAT database
-  default: download the DAT file
-
 --dbcan <path>
   Path to already downloaded gzipped dbCAN HMM database
   default: download the hmms
@@ -133,12 +125,6 @@ Important parameters are:
   for documenting what was run.
   THIS OPTION WILL BE REMOVED IN A FUTURE RELEASE.
 
---no_pfam
-  Don't download and/or run Pfam and Pfamscan. Downloading Pfam is quite slow,
-  even though it isn't particularly big. Sometimes the servers are down too.
-  You might also run your proteomes through something like interproscan, in which
-  case you might not need these results. This means you can keep going without it.
-
 --no_dbcan
   Don't download and/or run searches against the dbCAN CAZyme dataset.
   If you're doing this analysis elsewhere, the dbCAN2 servers are down,
@@ -220,7 +206,7 @@ Those starting with two hyphens `--` are Predector defined parameters.
 In the pipeline ranking output tables we also provide a manual (i.e. not machine learning) ranking score for both effectors `manual_effector_score` and secretion `manual_secretion_score`.
 This was provided so that you could customise the ranking if the ML ranker isn't what you want.
 
-> NOTE: If you decide not to run specific analyses (e.g. signalp6 or Pfam), this may affect comparability between different runs of the pipeline.
+> NOTE: If you decide not to run specific analyses (e.g. signalp6), this may affect comparability between different runs of the pipeline.
 
 These scores are computed by a relatively simple linear function weighting features in the ranking table.
 You can customise the weights applied to the features from the command line.
@@ -239,7 +225,6 @@ It is composed of four other columns like this:
 has_effector_match = has_phibase_effector_match
                   or (effector_matches != '.')
                   or has_dbcan_virulence_match
-                  or has_pfam_virulence_match
 ```
 
 
@@ -383,7 +368,6 @@ In the config files, you can select these tasks by label.
 | software | `deepredeff`     |                                                                                                                      |
 | software | `emboss`         |                                                                                                                      |
 | software | `hmmer3`         |                                                                                                                      |
-| software | `pfamscan`       |                                                                                                                      |
 | software | `mmseqs`         |                                                                                                                      |
 
 
@@ -416,9 +400,9 @@ If you get an error about missing git tags when running either of the first two
 I suggest keeping copies of the proprietary dependencies handy in a folder or archive, and just building and removing the container/environment as you need it.
 
 
-### Providing pre-downloaded Pfam, PHI-base, and dbCAN datasets.
+### Providing pre-downloaded PHI-base, and dbCAN datasets.
 
-Sometimes the Pfam or dbCAN servers can be a bit slow for downloads, and are occasionally unavailable which will cause the pipeline to fail.
+Sometimes the dbCAN servers can be a bit slow for downloads, and are occasionally unavailable which will cause the pipeline to fail.
 You may want to keep the downloaded databases to reuse them (or pre-download them).
 
 If you've already run the pipeline once, they'll be in the `results` folder (unless you specified `--outdir`) so you can do:
@@ -429,17 +413,14 @@ nextflow run \
   -profile test \
   -resume ccdmb/predector \
   --phibase phi-base_current.fas \
-  --pfam_hmm downloads/Pfam-A.hmm.gz \
-  --pfam_dat downloads/Pfam-A.hmm.dat.gz \
   --dbcan downloads/dbCAN.txt \
   --effectordb downloads/effectordb.hmm.gz
 ```
 
 This will skip the download step at the beginning and just use those files, which saves a few minutes.
 
 You can also download the files from:
-- http://ftp.ebi.ac.uk/pub/databases/Pfam/current_release/ `Pfam-A.hmm.gz` and `Pfam-A.hmm.dat.gz`
-- https://bcb.unl.edu/dbCAN2/download/ `dbCAN-HMMdb-V10.txt`
+- https://bcb.unl.edu/dbCAN2/download/ `dbCAN-HMMdb-V13.txt`
 - http://www.phi-base.org/downloadLink.htm OR https://github.com/PHI-base/data/tree/master/releases (only need the `.fas` fasta file).
 - https://doi.org/10.6084/m9.figshare.16973665 `effectordb.hmm.gz`
 

diff --git a/environment.yml b/environment.yml
@@ -18,7 +18,7 @@ dependencies:
   - predector::effectorp2=2.0
   - predector::effectorp3=3.0=py_2
   - predector::localizer=1.0.4
-  - predector::phobius=1.01=4
+  - predector::phobius=1.01=5
   - predector::predectorutils=0.9.1
   - predector::signalp3=3.0b=3
   - predector::signalp4=4.1g=3

diff --git a/nextflow.config b/nextflow.config
@@ -65,8 +65,8 @@ params {
     private_phibase_version = "v4-17"
     // The PHI-base team often rename files. Best to get a release from a commit rather than master.
     private_phibase_url = "https://github.com/PHI-base/data/blob/38c9034d754482986f2f9f73b3b46d5bb7da1615/releases/phi-base_v4-17_2024-05-01.fas"
-    private_dbcan_version = "V12"
-    private_dbcan_url = "https://bcb.unl.edu/dbCAN2/download/dbCAN-HMMdb-V12.txt"
+    private_dbcan_version = "V13"
+    private_dbcan_url = "https://bcb.unl.edu/dbCAN2/download/dbCAN-HMMdb-V13.txt"
     private_effectordb_url = "https://figshare.com/ndownloader/files/31397770"
     private_effectordb_version = "1"
 }