d94b7ab22f12dfc6b2168b0af5c7a71d1195a7bf hiram Wed Jan 29 15:38:56 2025 -0800 new repeat masker installed no redmine diff --git src/hg/makeDb/doc/repeatMasker.txt src/hg/makeDb/doc/repeatMasker.txt new file mode 100644 index 00000000000..3217021d50e --- /dev/null +++ src/hg/makeDb/doc/repeatMasker.txt @@ -0,0 +1,647 @@ +############################################################################ +New version installed 2025-11-29 +############################################################################ + +cd /hive/data/outside/RepeatMasker + +wget --timestamping \ + https://www.repeatmasker.org/RepeatMasker/RepeatMasker-4.1.7-p1.tar.gz + +# -rw-rw-r-- 1 45757841 Jan 9 08:56 RepeatMasker-4.1.7-p1.tar.gz + +tar xvzf RepeatMasker-4.1.7-p1.tar.gz + +### unpacks into /hive/data/outside/RepeatMasker/RepeatMasker-4.1.7-p1 + +### copy over cross_match binary from previous RM: + +cp -p \ +/hive/data/staging/data/RepeatMasker221107/cross_match \ + /hive/data/outside/RepeatMasker/RepeatMasker-4.1.7-p1 + +### Verify it will function on the new hgwdev: + +ldd ./cross_match + linux-vdso.so.1 (0x00007ffd49b6b000) + libm.so.6 => /lib64/libm.so.6 (0x00007f938e903000) + libc.so.6 => /lib64/libc.so.6 (0x00007f938e600000) + /lib64/ld-linux-x86-64.so.2 (0x00007f938e9ee000) + +####### I don't think this Dfam.hmm file is necessary +### download Dfam library, took a long time, +wget --timestamping \ +https://www.dfam.org/releases/Dfam_3.8/families/Dfam.hmm.gz +real 448m55.460s + +### took an hour to gunzip: time gunzip Dfam.hmm.gz +real 55m47.295s +user 50m42.646s +sys 4m9.112s + + +result here: +-rw-rw-r-- 1 92142601810 Nov 15 2023 Dfam.hmm.gz + +moved to RepeatMasker-4.1.7-p1/Library/ and gunzip +to get Dfam.hmm: + +-rw-rw-r-- 1 818448373587 Nov 15 2023 Dfam.hmm + +du -hsc Libraries/Dfam.hmm +763G Libraries/Dfam.hmm + +### pick the partitioned dfam library files +# check for latest dfam library in: +https://www.dfam.org/releases/Dfam_3.8/families/FamDB/ + +### Downloading partition 9: +https://www.dfam.org/releases/Dfam_3.8/families/FamDB/dfam38-1_full.8.h5.gz + +# and the other 8 partitions: + +for I in `seq 0 7` +do +printf "wget --timestamping https://www.dfam.org/releases/Dfam_3.8/families/FamDB/dfam38-1_full.${I}.h5.gz) > wget.${I}.log 2>&1\n" 1>&2 +time (wget --timestamping https://www.dfam.org/releases/Dfam_3.8/families/FamDB/dfam38-1_full.${I}.h5.gz) > wget.${I}.log 2>&1 +done + +Unpacked all those into Libraries/famdb/ + +ls -ogrt Libraries/famdb +total 1621230144 +-rw-rw-r-- 1 127407996360 Nov 12 18:06 dfam38-1_full.8.h5 +-rw-rw-r-- 1 63916952120 Nov 12 18:06 dfam38-1_full.7.h5 +-rw-rw-r-- 1 69738994608 Nov 12 18:06 dfam38-1_full.6.h5 +-rw-rw-r-- 1 72138843520 Nov 12 18:06 dfam38-1_full.5.h5 +-rw-rw-r-- 1 88179255072 Nov 12 18:06 dfam38-1_full.4.h5 +-rw-rw-r-- 1 91034940616 Nov 12 18:06 dfam38-1_full.3.h5 +-rw-rw-r-- 1 119488176888 Nov 12 18:06 dfam38-1_full.2.h5 +-rw-rw-r-- 1 126569122792 Nov 12 18:06 dfam38-1_full.1.h5 +-rw-rw-r-- 1 71595401776 Nov 12 18:06 dfam38-1_full.0.h5 + +#### +https://www.repeatmasker.org/rmblast/ + +downloaded rmblast binaries built by RepeatMasker: + +wget --timestamping https://www.repeatmasker.org/rmblast/rmblast-2.14.1+-x64-linux.tar.gz + +Unpacked into /hive/data/outside/rmblast-2.14.1 + +tar xvzf rmblast-2.14.1+-x64-linux.tar.gz + +Verify all the binaries will function with the dynamic libraries +on the new hgwdev machine + +cd /hive/data/outside/rmblast-2.14.1/bin + +for F in *; do echo "#### $F ####"; ldd ./${F} 2>&1; done > ../ldd.all +sed -e 's/^ //;' ldd.all | cut -d' ' -f1 | sort | uniq -c + 24 #### + 21 /lib64/ld-linux-x86-64.so.2 + 21 libc.so.6 + 21 libgcc_s.so.1 + 19 libgomp.so.1 + 21 libm.so.6 + 13 libz.so.1 + 11 libzstd.so.1 + 21 linux-vdso.so.1 + 3 not + +The 'not' is 'not a dynamic executable': + +#### get_species_taxids.sh #### + not a dynamic executable +#### legacy_blast.pl #### + not a dynamic executable +#### update_blastdb.pl #### + not a dynamic executable + +#### Picked up new version of hmmer +cd /hive/data/outside + wget --timestamping http://eddylab.org/software/hmmer/hmmer.tar.gz +-rw-rw-r-- 1 19669667 Nov 4 04:37 hmmer.tar.gz + +tar xvzf hmmer.tar.gz +Unpacks into: +drwxr-xr-x 10 4096 Aug 15 2023 hmmer-3.4 + +mv hmmer.tar.gz hmmer-3.4 +[hiram@hgwdev /hive/data/outside/hmmer-3.4] mkdir ../hmmer +./configure --prefix=/hive/data/outside/hmmer + +HMMER configuration: + compiler: gcc -O3 -pthread + host: x86_64-pc-linux-gnu + linker: + libraries: -lpthread + DP implementation: sse + +Now do 'make' to build HMMER, and optionally: + 'make check' to run self tests, + 'make install' to install programs and man pages, + '(cd easel; make install)' to install Easel tools. + +time (make) > mout.log 2>&1 + +time (make install) > mout.install.log 2>&1 + +[hiram@hgwdev /hive/data/outside/hmmer-3.4] ls -ogrt ../hmmer/bin +total 30464 +-rwxr-xr-x 1 454192 Jan 29 15:19 alimask +-rwxr-xr-x 1 802704 Jan 29 15:19 hmmalign +-rwxr-xr-x 1 926904 Jan 29 15:19 hmmbuild +-rwxr-xr-x 1 508000 Jan 29 15:19 hmmconvert +-rwxr-xr-x 1 803176 Jan 29 15:19 hmmemit +-rwxr-xr-x 1 516904 Jan 29 15:19 hmmfetch +-rwxr-xr-x 1 508128 Jan 29 15:19 hmmlogo +-rwxr-xr-x 1 1180104 Jan 29 15:19 hmmpgmd +-rwxr-xr-x 1 1188584 Jan 29 15:19 hmmpgmd_shard +-rwxr-xr-x 1 520520 Jan 29 15:19 hmmpress +-rwxr-xr-x 1 965448 Jan 29 15:19 hmmscan +-rwxr-xr-x 1 965768 Jan 29 15:19 hmmsearch +-rwxr-xr-x 1 549984 Jan 29 15:19 hmmsim +-rwxr-xr-x 1 503432 Jan 29 15:19 hmmstat +-rwxr-xr-x 1 1148768 Jan 29 15:19 jackhmmer +-rwxr-xr-x 1 1096904 Jan 29 15:19 phmmer +-rwxr-xr-x 1 1156968 Jan 29 15:19 nhmmer +-rwxr-xr-x 1 966008 Jan 29 15:19 nhmmscan +-rwxr-xr-x 1 511520 Jan 29 15:19 makehmmerdb + + +### running configure: it starts up saying: + +RepeatMasker Configuration Program + +Checking for libraries... + + - Found a FamDB root partition + +<PRESS ENTER TO CONTINUE> + +Add a Search Engine: + 1. Crossmatch: [ Configured, Default ] + 2. RMBlast: [ Un-configured ] + 3. HMMER3.1 & DFAM: [ Un-configured ] + 4. ABBlast: [ Un-configured ] + + 5. Done + +Enter Selection: + +For #1 it requires the path to the directory where cross_match exists + +The path Phil Green's cross_match program ( phrap program suite ). +CROSSMATCH_DIR [/hive/data/outside/RepeatMasker/RepeatMasker-4.1.7-p1]: + +Do you want Crossmatch to be your default +search engine for Repeatmasker? (Y/N) [ Y ]: + +For #2: +The path to the installation of the RMBLAST sequence alignment program. +RMBLAST_DIR: /hive/data/outside/rmblast-2.14.1/bin + +For #3: +The path to the HMMER profile HMM search software. +HMMER_DIR: /hive/data/outside/hmmer/bin + +Do you want HMMER3.1 & DFAM to be your default +search engine for Repeatmasker? (Y/N) [ Y ]: N + +Add a Search Engine: + 1. Crossmatch: [ Configured, Default ] + 2. RMBlast: [ Configured ] + 3. HMMER3.1 & DFAM: [ Configured ] + 4. ABBlast: [ Un-configured ] + + 5. Done + +Enter Selection: 5 +Building RMBlast frozen libraries.. +The program is installed with a the following repeat libraries: + +FamDB Directory : /hive/data/outside/RepeatMasker/RepeatMasker-4.1.7-p1/Libraries/famdb +FamDB Generator : famdb.py v1.0 +FamDB Format Version: 1.0 +FamDB Creation Date : 2023-11-15 11:30:15.311827 + +Database: Dfam +Version : 3.8 +Date : 2023-11-14 + +Dfam - A database of transposable element (TE) sequence alignments and HMMs. + +9 Partitions Present +Total consensus sequences present: 3574116 +Total HMMs present : 3574078 + +... and a lot of printout about the libraries + +### test the installation: + +cd /dev/shm + +/hive/data/outside/RepeatMasker/RepeatMasker-4.1.7-p1/RepeatMasker \ + -engine crossmatch -s -species "Homo sapiens" /dev/null + +RepeatMasker version 4.1.7-p1 +Search Engine: Crossmatch [ 1.090518 ] + +Using Master RepeatMasker Database: /hive/data/outside/RepeatMasker/RepeatMasker-4.1.7-p1/Libraries/famdb + Title : Dfam + Version : 3.8 + Date : 2023-11-14 + Families : 3,574,116 + +Species/Taxa Search: + Homo sapiens [NCBI Taxonomy ID: 9606] + Lineage: root;cellular organisms;Eukaryota;Opisthokonta;Metazoa; + Eumetazoa;Bilateria;Deuterostomia;Chordata; + Craniata <chordates>;Vertebrata <vertebrates>; + Gnathostomata <vertebrates>;Teleostomi;Euteleostomi; + Sarcopterygii;Dipnotetrapodomorpha;Tetrapoda;Amniota; + Mammalia;Theria <mammals>;Eutheria;Boreoeutheria; + Euarchontoglires;Primates;Haplorrhini;Simiiformes +Including only curated families: + 1380 families in ancestor taxa; 52 lineage-specific families + +Building general libraries in: /hive/data/outside/RepeatMasker/RepeatMasker-4.1.7-p1/Libraries/CONS-Dfam_3.8/general +Building species libraries in: /hive/data/outside/RepeatMasker/RepeatMasker-4.1.7-p1/Libraries/CONS-Dfam_3.8/Homo_sapiens +File /dev/null appears to be empty. + +### also tested: + +/hive/data/outside/RepeatMasker/RepeatMasker-4.1.7-p1/RepeatMasker \ + -engine hmmer -pa 4 -s -species "Homo sapiens" /dev/null + +/hive/data/outside/RepeatMasker/RepeatMasker-4.1.7-p1/RepeatMasker \ + -engine rmblast -pa 1 -s -species "Homo sapiens" /dev/null + +############################################################################ +New version installed 2022-12-07 +############################################################################ + +mkdir /hive/data/staging/data/RepeatMasker221107 +cd /hive/data/staging/data/RepeatMasker221107 + +wget --timestamping \ +http://www.repeatmasker.org/RepeatMasker/RepeatMasker-4.1.4.tar.gz + +That unpacks to make a directory: ./RepeatMasker/ +move it up into this directory: +mv RepeatMasker RepeatMasker.d +cd RepeatMasker.d +mv * .. +mv ./github .. +cd .. +rmdir RepeatMasker.d + +Obtain full Dfam.h5 to replace minimal library in this distribution: +cd /hive/data/staging/data/RepeatMasker221107/Libraries +wget --timestamping \ + https://www.dfam.org/releases/Dfam_3.6/families/Dfam.h5.gz +# that takes 30 to 40 minutes + +Much larger than the default one here: + +-rw-rw-r-- 1 26381535800 Jul 21 01:02 Dfam.h5.gz +-rw-r--r-- 1 5474183168 Jul 20 13:53 Dfam.h5 + +mv Dfam.h5 Dfam.h5.orig +gunzip DFam.hg5.gz + +-rw-rw-r-- 1 171010916736 Jul 21 01:02 Dfam.h5 + +# copy cross_match from previous install +cd /hive/data/staging/data/RepeatMasker210401 +cp -p cross_match ../RepeatMasker221107/ + +When all external software is installed, + try running the configure script, it now requires + the python3 install from /cluster/software/bin + +export PATH=/cluster/software/bin:$PATH +now configure will run: + ./configure + +Answering the questions: +The full path including the name for the TRF program. +TRF_PRGM: /cluster/bin/x86_64/trf.4.09 + +Add a Search Engine: + 1. Crossmatch: [ Un-configured ] + 2. RMBlast: [ Un-configured ] + 3. HMMER3.1 & DFAM: [ Un-configured ] + 4. ABBlast: [ Un-configured ] + + 5. Done + + +The path Phil Green's cross_match program ( phrap program suite ). +CROSSMATCH_DIR: /hive/data/staging/data/RepeatMasker221107 + + + you want Crossmatch to be your default +search engine for Repeatmasker? (Y/N) [ Y ]: + +Add a Search Engine: + 1. Crossmatch: [ Configured, Default ] + 2. RMBlast: [ Un-configured ] + 3. HMMER3.1 & DFAM: [ Un-configured ] + 4. ABBlast: [ Un-configured ] + + 5. Done + +The path to the installation of the RMBLAST sequence alignment program. +RMBLAST_DIR: /hive/data/outside/rmblast-2.11.0/bin + +Do you want RMBlast to be your default +search engine for Repeatmasker? (Y/N) [ Y ]: N + +The path to the HMMER profile HMM search software. +HMMER_DIR: /hive/data/outside/hmmer-3.3.2/src + +Do you want HMMER3.1 & DFAM to be your default +search engine for Repeatmasker? (Y/N) [ Y ]: N + +Leaving ABBlast unconfigured + +Add a Search Engine: + 1. Crossmatch: [ Configured, Default ] + 2. RMBlast: [ Configured ] + 3. HMMER3.1 & DFAM: [ Configured ] + 4. ABBlast: [ Un-configured ] + + 5. Done + +Enter Selection: 5 +Building FASTA version of RepeatMasker.lib .... + +This takes a long time since it is processing this +file into fasta: +-rw-rw-r-- 1 171010916736 Jul 21 01:02 Dfam.h5 +That is 160 Gb +After about an hour, finished: + +............................................ +Building RMBlast frozen libraries.. +The program is installed with a the following repeat libraries: +File: /hive/data/staging/data/RepeatMasker221107/Libraries/Dfam.h5 +Database: Dfam +Version: 3.6 +Date: 2022-04-12 + +Dfam - A database of transposable element (TE) sequence alignments and HMMs. + +Total consensus sequences: 733031 +Total HMMs: 732993 + + +Further documentation on the program may be found here: + /hive/data/staging/data/RepeatMasker221107/repeatmasker.help + +############################################################################ +Thu Dec 8 09:07:57 PST 2022 + +Configure new install of RepeatModeler: + +cd /hive/data/outside/RepeatModeler-2.0.4 +perl configure +# answering questions for that: +The path to the installation of RepeatMasker (RM 4.1.4 or higher) +REPEATMASKER_DIR: /hive/data/staging/data/RepeatMasker221107 + +The path to the installation of the RECON de-novo repeatfinding program. +RECON_DIR: /hive/data/outside/RECON-1.08/bin + +The path to the installation of the RepeatScout ( 1.0.6 or higher ) de-novo repeatfinding program. +RSCOUT_DIR: /hive/data/outside/RepeatScout-1.0.6 + +The full path to TRF program. TRF must be named "trf". ( 4.0.9 or higher ) +TRF_DIR [/cluster/bin/x86_64]: /cluster/bin/x86_64 + +[hiram@hgwdev /cluster/bin/x86_64] ls -l trf* +-rwxr-xr-x 1 hiram protein 111112 Mar 4 2016 trf +-rwxr-xr-x 1 hiram protein 111112 Mar 4 2016 trf.4.09 +-rwxrwxr-x 1 hiram genecats 111670 Nov 26 2012 trf.407b +-rwxrwxr-x 1 build genecats 5516672 Nov 21 10:14 trfBig + +The path to the installation of the CD-Hit sequence clustering package. +CDHIT_DIR: /hive/data/outside/cdhit-master + +The path to the installation directory of the UCSC TwoBit Tools (twoBitToFa, faToTwoBit, twoBitInfo etc). +UCSCTOOLS_DIR [/cluster/bin/x86_64]: + +The path to the installation of the RMBLAST (2.13.0 or higher) +RMBLAST_DIR: /hive/data/outside/rmblast-2.13.0/bin + +LTR Structural Identication Pipeline [optional] + +In addition to RECON/RepeatScout this version of RepeatModeler +has the option of running an additional analysis to identify +structural features of LTR sequences. + +Do you wish to configure RepeatModeler for this type +of analysis [y] or n?: y + +The path to the installation of the GenomeTools package. +GENOMETOOLS_DIR: /hive/data/outside/genometools-1.6.2/bin + +The path to the installation of the LTR_Retriever (v2.9.0 and higher) structural LTR analysis package. +LTR_RETRIEVER_DIR: /hive/data/outside/LTR_retriever-2.9.0 + +The path to the installation of the MAFFT multiple alignment program.', +MAFFT_DIR: /hive/data/outside/mafft-7.505-with-extensions/bin + +The path to the installation of the Ninja phylogenetic analysis package. +NINJA_DIR: /hive/data/outside/NINJA-0.95-cluster_only/NINJA + -- Setting perl interpreter and version... + +Congratulations! RepeatModeler is now ready to use. +[hiram@hgwdev /hive/data/outside/RepeatModeler-2.0.4] + +############################################################################ + +To find new versions of RepeatMasker software: + + http://www.repeatmasker.org/RMDownload.html + +Example version 01 Feb 2017, you want a new directory here:: + + mkdir /hive/data/staging/data/RepeatMasker170201 + cd /hive/data/staging/data/RepeatMasker170201 + + wget --timestamping http://www.repeatmasker.org/RepeatMasker-open-4-0-7.tar.gz + tar -xvzf RepeatMasker-open-4-0-7.tar.gz + +Creates the directory ./RepeatMasker/ +Probably could some a tar argument to override that and make it be . + + mv RepeatMasker RepeatMasker.download + cd RepeatMasker.download + mv * .. + cd + rmdir RepeatMasker.download + +Pick up the full libraries from www.girinst.org +Requires an account and a login there. It asks for user name/password +when you click on the download link: + http://www.girinst.org/server/RepBase/protected/repeatmaskerlibraries/RepBaseRepeatMaskerEdition-20170127.tar.gz +from this menu page: + http://www.girinst.org/server/RepBase/index.php + +-rw-rw-rw- 1 51207503 Mar 16 22:01 RepBaseRepeatMaskerEdition-20170127.tar.gz + +It unpacks into ./Libraies: + + tar xvzf RepBaseRepeatMaskerEdition-20170127.tar.gz +Libraries/README +Libraries/RMRBSeqs.embl + +-rw-r--r-- 1 3721 Jan 28 2017 README +-rw-r--r-- 1 166648733 Jan 28 2017 RMRBSeqs.embl + +Find Dfam file: Dfam.hmm.gz +at: http://www.dfam.org/web_download/Release/Dfam_2.0/ + +wget --timestamping 'http://www.dfam.org/web_download/Release/Dfam_2.0/Dfam.hmm.gz' + +-rw-rw-r-- 1 239726414 Sep 22 2015 Dfam.hmm.gz + +In this case, it is identical to what is already in RepeatMasker: + +md5sum */Dfam.hmm* +c8dbc5c353a60c97e5c9870483314ab9 Libraries/Dfam.hmm +zcat Dfam.hmm.gz | md5sum +c8dbc5c353a60c97e5c9870483314ab9 - + +Copy cross_match binary from previous version: + +cp -p ../RepeatMasker151029/cross_match . + +And the hmmer/ binaries: + +rsync -a -P ../RepeatMasker151029/hmmer/ ./hmmer/ + +Answering questions during the ./configure: + +path to cross_match: /scratch/data/RepeatMasker170201 +path to hmmer: /scratch/data/RepeatMasker170201/hmmer +rmblast dir: /hive/data/outside/rmblastn-2.2.28/bin +default search engine crossmatch +trf program: /cluster/bin/x86_64/trf.4.09 + +Must work in the path desired for the path on the ku nodes: + +cd /scratch/data/RepeatMasker170201 +./configure + +**PERL PROGRAM** + + This is the full path to the Perl interpreter. + e.g. /usr/local/bin/perl or enter "env" if you prefer to use + the "/usr/bin/env perl" mechanism to locate perl. + +Enter path [ /usr/bin/perl ]: env + + This is the path to the directory where + the RepeatMasker program has been installed. + +Enter path [ /hive/data/staging/data/RepeatMasker170201 ]: /scratch/data/RepeatMasker170201 + +Rebuilding RepeatMaskerLib.embl library + - Read in 216 sequences from /scratch/data/RepeatMasker170201/Libraries/DfamConsensus.embl + - Read in 44968 sequences from /scratch/data/RepeatMasker170201/Libraries/RMRBSeqs.embl + - Read in 44968 annotations from /scratch/data/RepeatMasker170201/Libraries/RMRBMeta.embl + Saving RepeatMaskerLib.embl library... +RepeatMaskerLib.embl: 45184 total sequences. + -- Building FASTA database... + + This is the full path to the TRF program. + This is now used by RepeatMasker to mask simple repeats. + +Enter path [ /cluster/bin/x86_64/trf ]: /cluster/bin/x86_64/trf.4.09 + +Add a Search Engine: + 1. CrossMatch: [ Un-configured ] + 2. RMBlast - NCBI Blast with RepeatMasker extensions: [ Un-configured ] + 3. WUBlast/ABBlast (required by DupMasker): [ Un-configured ] + 4. HMMER3.1 & DFAM: [ Un-configured ] + + 5. Done + + +Enter Selection: 1 + + This is the path to the location where + the cross_match program has been installed. + +Enter path [ ]: /scratch/data/RepeatMasker170201 + +Do you want CrossMatch to be your default +search engine for Repeatmasker? (Y/N) [ Y ]: + + +And again: + +Add a Search Engine: + 1. CrossMatch: [ Configured, Default ] + 2. RMBlast - NCBI Blast with RepeatMasker extensions: [ Un-configured ] + 3. WUBlast/ABBlast (required by DupMasker): [ Un-configured ] + 4. HMMER3.1 & DFAM: [ Un-configured ] + + 5. Done + + +Enter Selection: 2 + + This is the path to the location where + the rmblastn and makeblastdb programs can be found. + +Enter path [ ]: /hive/data/outside/rmblastn-2.2.28/bin + +Building RMBlast frozen libraries.. + + +Do you want RMBlast to be your default +search engine for Repeatmasker? (Y/N) [ Y ]: N + +And again: + +Add a Search Engine: + 1. CrossMatch: [ Configured, Default ] + 2. RMBlast - NCBI Blast with RepeatMasker extensions: [ Configured ] + 3. WUBlast/ABBlast (required by DupMasker): [ Un-configured ] + 4. HMMER3.1 & DFAM: [ Un-configured ] + + 5. Done + + +Enter Selection: 4 + + This is the path to the location where + the nhmmer program can be found. + +Enter path [ ]: /scratch/data/RepeatMasker170201/hmmer + +ERROR: Could not identify version of the nhmmer program. + Most likely this is older than 3.1. Please + ensure you have at least 3.1 installed and then + rerun configure. + Data returned from nhmmer exec: +# nhmmscan :: search DNA sequence(s) against a DNA profile database +# HMMER hmmer3.1-snap20121016 (October 2012); http://hmmer.org/ +# Copyright (C) 2011 Howard Hughes Medical Institute. +# Freely distributed under the GNU General Public License (GPLv3). +# - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - +Usage: nhmmscan [-options] <hmmdb> <seqfile> + + +HMMER not configured! +<PRESS ENTER TO CONTINUE> + + +And that is finished. Despite that error about hmmer, it is correct, +edit the RepeatMaskerConfig.pm file and set: + + $HMMER_DIR = "/scratch/data/RepeatMasker170201/hmmer"