https://bioinformaticsonline.com/snippets?offset=280 https://bioinformaticsonline.com/snippets/view/39687/install-blast-locally Tue, 09 Jul 2019 15:58:10 -0500 https://bioinformaticsonline.com/snippets/view/39687/install-blast-locally Download page https://blast.ncbi.nlm.nih.gov/Blast.cgi?CMD=Web&PAGE_TYPE=BlastDocs&DOC_TYPE=Download Ubuntu / Debian sudo apt-get install ncbi-blast+ CentOS # download latest BLAST version wget ftp://ftp.ncbi.nlm.nih.gov/blast/executables/blast+/LATEST/ncbi-blast-2.8.1+-x64-linux.tar.gz # decompress tar -zxvf ncbi-blast-2.8.1+-x64-linux.tar.gz # add BLAST location to system PATH export PATH=$HOME/tools/BLAST/ncbi-blast-2.8.1+/bin:$PATH]]> Abhimanyu Singh https://bioinformaticsonline.com/snippets/view/39456/split-array-in-perl Sat, 01 Jun 2019 04:23:02 -0500 https://bioinformaticsonline.com/snippets/view/39456/split-array-in-perl my @tests = ( ["FOO", "BAR"], ["CRATE", "TRACE"], ["CRATE", "CRATE"], ["TRACE", "CRATE"], ["CREATE", "TRACT"], ["DWAYNE", "DUANE"], ); for my $word_pair (@tests) { #Nice way to split the values my ($w1, $w2) = @$word_pair; my $simw = simw $w1, $w2; say "distance between $w1 and $w2 is: ", 1 - $simw; }]]> BioJoker https://bioinformaticsonline.com/snippets/view/39310/one-liner-for-reads-mapping Sun, 28 Apr 2019 12:37:57 -0500 https://bioinformaticsonline.com/snippets/view/39310/one-liner-for-reads-mapping bwa aln -t 8 targetGenome.fa reads.fastq | bwa samse targetGenome.fa - reads.fastq\ | samtools view -bt targetGenome.fa - | samtools sort - reads.bwa.targetGenome samtools index reads.bwa.targetGenome.bam]]> Rahul Nayak https://bioinformaticsonline.com/snippets/view/39023/perl-script-to-count-occurrence-of-a-character Wed, 20 Feb 2019 20:03:55 -0600 https://bioinformaticsonline.com/snippets/view/39023/perl-script-to-count-occurrence-of-a-character #!/usr/bin/env perl # -*- coding: utf-8 -*- #!/usr/bin/perl use strict; use warnings; my %count_of; while ( <> ) { my @val = split "\t", $_; #my ( $word) = m/(\w+)/; $count_of{$val[13]}++; } foreach my $word ( sort { $count_of{$a} <=> $count_of{$b} } keys %count_of ) { print "$word\t$count_of{$word}\n"; }]]> Jit https://bioinformaticsonline.com/snippets/view/38544/backward-elimination-with-python Fri, 28 Dec 2018 07:16:48 -0600 https://bioinformaticsonline.com/snippets/view/38544/backward-elimination-with-python #Backward Elimination with p-values only: import statsmodels.formula.api as sm def backwardElimination(x, sl): numVars = len(x[0]) for i in range(0, numVars): regressor_OLS = sm.OLS(y, x).fit() maxVar = max(regressor_OLS.pvalues).astype(float) if maxVar > sl: for j in range(0, numVars - i): if (regressor_OLS.pvalues[j].astype(float) == maxVar): x = np.delete(x, j, 1) regressor_OLS.summary() return x SL = 0.05 X_opt = X[:, [0, 1, 2, 3, 4, 5]] X_Modeled = backwardElimination(X_opt, SL) #Backward Elimination with p-values and Adjusted R Squared: import statsmodels.formula.api as sm def backwardElimination(x, SL): numVars = len(x[0]) temp = np.zeros((50,6)).astype(int) for i in range(0, numVars): regressor_OLS = sm.OLS(y, x).fit() maxVar = max(regressor_OLS.pvalues).astype(float) adjR_before = regressor_OLS.rsquared_adj.astype(float) if maxVar > SL: for j in range(0, numVars - i): if (regressor_OLS.pvalues[j].astype(float) == maxVar): temp[:,j] = x[:, j] x = np.delete(x, j, 1) tmp_regressor = sm.OLS(y, x).fit() adjR_after = tmp_regressor.rsquared_adj.astype(float) if (adjR_before >= adjR_after): x_rollback = np.hstack((x, temp[:,[0,j]])) x_rollback = np.delete(x_rollback, j, 1) print (regressor_OLS.summary()) return x_rollback else: continue regressor_OLS.summary() return x SL = 0.05 X_opt = X[:, [0, 1, 2, 3, 4, 5]] X_Modeled = backwardElimination(X_opt, SL)]]> BioStar https://bioinformaticsonline.com/snippets/view/38533/split-the-multifasta-in-separate-files Tue, 25 Dec 2018 19:03:27 -0600 https://bioinformaticsonline.com/snippets/view/38533/split-the-multifasta-in-separate-files cat Avaga_allPalindrome.fa | awk '{ if (substr($0, 1, 1)==">") {filename=(substr($0,2) ".fa")} print $0 > filename }']]> Jit https://bioinformaticsonline.com/snippets/view/38428/perl-script-to-split-fasta-sequence-and-create-overlaps Tue, 11 Dec 2018 10:41:14 -0600 https://bioinformaticsonline.com/snippets/view/38428/perl-script-to-split-fasta-sequence-and-create-overlaps #!/usr/bin/perl use strict; use warnings; my $len = 5000; my $over = 200; my $seq_id=$ARGV[0]; my $seqFile = $ARGV[1]; my $seq; open(my $fh, "<", "$seqFile") or die "Can't open < $seqFile: $!"; while (<$fh>) { chomp; if (m/^>/) { $seq_id = $_; } else { $seq .= $_; } } for (my $i = 1; $i <= length $seq; $i += ($len - $over)) { my $s = substr ($seq, $i - 1, $len); print "$seq_id.($i-", $i + (length $s) - 1, ")\n$s\n"; }]]> BioJoker https://bioinformaticsonline.com/snippets/view/38423/finding-kmers-from-fasta-sequence-file Tue, 11 Dec 2018 09:33:24 -0600 https://bioinformaticsonline.com/snippets/view/38423/finding-kmers-from-fasta-sequence-file Save it in sample.fa >test TAATGCCATGGGATGTT jellyfish count -m 3 -s 100000 sample.fa -o sample.jf jellyfish dump -c sample.jf It return TGT 1 GAT 1 GGG 1 GGA 1 CAT 1 TGC 1 TAA 1 GCC 1 CCA 1 GTT 1 TGG 1 ATG 3 AAT 1]]> Jit https://bioinformaticsonline.com/snippets/view/38358/sync-github-repo Sat, 01 Dec 2018 14:55:59 -0600 https://bioinformaticsonline.com/snippets/view/38358/sync-github-repo http://stackoverflow.com/questions/6373277/git-sync-local-repo-with-remote-one This makes your local repo exactly like your remote repo. Remember to replace origin and master with the remote and branch that you want to synchronize with. git fetch origin git reset --hard origin/master git clean -f -d]]> BioJoker https://bioinformaticsonline.com/snippets/view/38290/setting-up-falconunzip-conda-environments-for-genome-assembly Fri, 23 Nov 2018 12:01:02 -0600 https://bioinformaticsonline.com/snippets/view/38290/setting-up-falconunzip-conda-environments-for-genome-assembly ➜ Analysis_Results conda create -n denovo_asm Solving environment: done ## Package Plan ## environment location: /home/urbe/anaconda3/envs/denovo_asm Proceed ([y]/n)? y Preparing transaction: done Verifying transaction: done Executing transaction: done # # To activate this environment, use # # $ conda activate denovo_asm # # To deactivate an active environment, use # # $ conda deactivate ➜ Analysis_Results source activate denovo_asm (denovo_asm) ➜ Analysis_Results conda install pb-assembly Solving environment: done ## Package Plan ## environment location: /home/urbe/anaconda3/envs/denovo_asm added / updated specs: - pb-assembly The following packages will be downloaded: package | build ---------------------------|----------------- python-2.7.15 | h33da82c_5 13.6 MB conda-forge pysam-0.14.1 | py27hae42fb6_1 7.2 MB bioconda pb-dazzler-0.0.0 | h470a237_0 755 KB bioconda cryptography-vectors-2.3.1 | py27_1000 30.5 MB conda-forge requests-2.20.1 | py27_1000 83 KB conda-forge setuptools-40.6.2 | py27_0 622 KB conda-forge avro-python2-1.8.2 | py_1 30 KB bioconda python-sortedcontainers-2.0.5| py_0 25 KB bioconda genomicconsensus-2.3.2 | py27_3 97 KB bioconda python-consensuscore2-3.1.0| py27_2 848 KB bioconda enum34-1.1.6 | py27_1001 56 KB conda-forge chardet-3.0.4 | py27_1003 180 KB conda-forge pyopenssl-18.0.0 | py27_1000 78 KB conda-forge linecache2-1.0.0 | py_1 13 KB conda-forge urllib3-1.23 | py27_1001 150 KB conda-forge pycparser-2.19 | py_0 87 KB conda-forge python-consensuscore-1.1.1 | py27h02d93b8_2 1.4 MB bioconda pytz-2018.7 | py_0 226 KB conda-forge cryptography-2.3.1 | py27hdffb7b8_0 964 KB conda-forge python-edlib-1.2.3.post1 | py27h470a237_0 135 KB bioconda pbcore-1.6.5 | py27_0 9.7 MB bioconda pysocks-1.6.8 | py27_1002 22 KB conda-forge cython-0.29 | py27hfc679d8_0 4.3 MB conda-forge future-0.17.0 | py27_1000 708 KB conda-forge ipaddress-1.0.22 | py_1 18 KB conda-forge pb-assembly-0.0.2 | py27_0 4 KB bioconda six-1.11.0 | py27_1001 20 KB conda-forge h5py-2.8.0 | py27h7eb728f_3 1.1 MB conda-forge asn1crypto-0.24.0 | py27_1003 154 KB conda-forge cffi-1.11.5 | py27h5e8e0c9_1 388 KB conda-forge pb-falcon-0.2.4 | py27ha92aebf_0 716 KB bioconda python-msgpack-0.5.6 | py27h470a237_0 282 KB bioconda unittest2-1.1.0 | py_0 68 KB conda-forge minimap2-2.14 | ha92aebf_0 2.0 MB bioconda mkl-2018.0.3 | 1 198.7 MB python-intervaltree-2.1.0 | py_0 22 KB bioconda pbcommand-1.1.1 | py27_2 193 KB bioconda nim-falcon-0.0.0 | 0 271 KB bioconda iso8601-0.1.12 | py_1 9 KB conda-forge pbalign-0.3.1 | py27_1 76 KB bioconda mummer4-4.0.0beta2 | pl526hfc679d8_3 1.3 MB bioconda mkl_random-1.0.2 | py27_0 1.0 MB conda-forge wheel-0.32.3 | py27_0 34 KB conda-forge intel-openmp-2019.1 | 144 885 KB traceback2-1.4.0 | py27_0 28 KB conda-forge idna-2.7 | py27_1002 131 KB conda-forge sqlite-3.25.3 | hb1c47c0_0 1.6 MB conda-forge ------------------------------------------------------------ Total: 280.6 MB The following NEW packages will be INSTALLED: asn1crypto: 0.24.0-py27_1003 conda-forge avro-python2: 1.8.2-py_1 bioconda bcftools: 1.9-h4da6232_0 bioconda bedtools: 2.27.1-he941832_2 bioconda blas: 1.0-mkl blasr: 5.3.2-hac9d22c_3 bioconda blasr_libcpp: 5.3.1-hac9d22c_2 bioconda bwa: 0.7.17-ha92aebf_3 bioconda bzip2: 1.0.6-h470a237_2 conda-forge ca-certificates: 2018.10.15-ha4d7672_0 conda-forge certifi: 2018.10.15-py27_1000 conda-forge cffi: 1.11.5-py27h5e8e0c9_1 conda-forge chardet: 3.0.4-py27_1003 conda-forge cryptography: 2.3.1-py27hdffb7b8_0 conda-forge cryptography-vectors: 2.3.1-py27_1000 conda-forge curl: 7.62.0-h74213dd_0 conda-forge cython: 0.29-py27hfc679d8_0 conda-forge decorator: 4.3.0-py_0 conda-forge enum34: 1.1.6-py27_1001 conda-forge future: 0.17.0-py27_1000 conda-forge genomicconsensus: 2.3.2-py27_3 bioconda h5py: 2.8.0-py27h7eb728f_3 conda-forge hdf5: 1.10.2-hc401514_2 conda-forge htslib: 1.7-0 bioconda idna: 2.7-py27_1002 conda-forge intel-openmp: 2019.1-144 ipaddress: 1.0.22-py_1 conda-forge iso8601: 0.1.12-py_1 conda-forge krb5: 1.16.2-hbb41f41_0 conda-forge libcurl: 7.62.0-hbdb9355_0 conda-forge libdeflate: 1.0-h470a237_0 bioconda libedit: 3.1.20170329-haf1bffa_1 conda-forge libffi: 3.2.1-hfc679d8_5 conda-forge libgcc: 7.2.0-h69d50b8_2 conda-forge libgcc-ng: 7.2.0-hdf63c60_3 conda-forge libgfortran: 3.0.0-1 conda-forge libgfortran-ng: 7.2.0-hdf63c60_3 conda-forge libssh2: 1.8.0-h5b517e9_3 conda-forge libstdcxx-ng: 7.2.0-hdf63c60_3 conda-forge linecache2: 1.0.0-py_1 conda-forge minimap2: 2.14-ha92aebf_0 bioconda mkl: 2018.0.3-1 mkl_fft: 1.0.6-py27_0 conda-forge mkl_random: 1.0.2-py27_0 conda-forge mummer4: 4.0.0beta2-pl526hfc679d8_3 bioconda ncurses: 6.1-hfc679d8_1 conda-forge networkx: 2.2-py_1 conda-forge nim-falcon: 0.0.0-0 bioconda numpy: 1.15.0-py27h1b885b7_0 numpy-base: 1.15.0-py27h3dfced4_0 openssl: 1.0.2p-h470a237_1 conda-forge pb-assembly: 0.0.2-py27_0 bioconda pb-dazzler: 0.0.0-h470a237_0 bioconda pb-falcon: 0.2.4-py27ha92aebf_0 bioconda pbalign: 0.3.1-py27_1 bioconda pbbam: 0.18.0-h1310cd9_1 bioconda pbcommand: 1.1.1-py27_2 bioconda pbcore: 1.6.5-py27_0 bioconda perl: 5.26.2-h470a237_0 conda-forge pip: 18.1-py27_1000 conda-forge pycparser: 2.19-py_0 conda-forge pyopenssl: 18.0.0-py27_1000 conda-forge pysam: 0.14.1-py27hae42fb6_1 bioconda pysocks: 1.6.8-py27_1002 conda-forge python: 2.7.15-h33da82c_5 conda-forge python-consensuscore: 1.1.1-py27h02d93b8_2 bioconda python-consensuscore2: 3.1.0-py27_2 bioconda python-edlib: 1.2.3.post1-py27h470a237_0 bioconda python-intervaltree: 2.1.0-py_0 bioconda python-msgpack: 0.5.6-py27h470a237_0 bioconda python-sortedcontainers: 2.0.5-py_0 bioconda pytz: 2018.7-py_0 conda-forge readline: 7.0-haf1bffa_1 conda-forge requests: 2.20.1-py27_1000 conda-forge samtools: 1.9-h8ee4bcc_1 bioconda setuptools: 40.6.2-py27_0 conda-forge six: 1.11.0-py27_1001 conda-forge sqlite: 3.25.3-hb1c47c0_0 conda-forge tk: 8.6.9-ha92aebf_0 conda-forge traceback2: 1.4.0-py27_0 conda-forge unittest2: 1.1.0-py_0 conda-forge urllib3: 1.23-py27_1001 conda-forge wheel: 0.32.3-py27_0 conda-forge xz: 5.2.4-h470a237_1 conda-forge zlib: 1.2.11-h470a237_3 conda-forge Proceed ([y]/n)? y Downloading and Extracting Packages python-2.7.15 | 13.6 MB | ##################################### | 100% pysam-0.14.1 | 7.2 MB | ##################################### | 100% pb-dazzler-0.0.0 | 755 KB | ##################################### | 100% cryptography-vectors | 30.5 MB | ##################################### | 100% requests-2.20.1 | 83 KB | ##################################### | 100% setuptools-40.6.2 | 622 KB | ##################################### | 100% avro-python2-1.8.2 | 30 KB | ##################################### | 100% python-sortedcontain | 25 KB | ##################################### | 100% genomicconsensus-2.3 | 97 KB | ##################################### | 100% python-consensuscore | 848 KB | ##################################### | 100% enum34-1.1.6 | 56 KB | ##################################### | 100% chardet-3.0.4 | 180 KB | ##################################### | 100% pyopenssl-18.0.0 | 78 KB | ##################################### | 100% linecache2-1.0.0 | 13 KB | ##################################### | 100% urllib3-1.23 | 150 KB | ##################################### | 100% pycparser-2.19 | 87 KB | ##################################### | 100% python-consensuscore | 1.4 MB | ##################################### | 100% pytz-2018.7 | 226 KB | ##################################### | 100% cryptography-2.3.1 | 964 KB | ##################################### | 100% python-edlib-1.2.3.p | 135 KB | ##################################### | 100% pbcore-1.6.5 | 9.7 MB | ##################################### | 100% pysocks-1.6.8 | 22 KB | ##################################### | 100% cython-0.29 | 4.3 MB | ##################################### | 100% future-0.17.0 | 708 KB | ##################################### | 100% ipaddress-1.0.22 | 18 KB | ##################################### | 100% pb-assembly-0.0.2 | 4 KB | ##################################### | 100% six-1.11.0 | 20 KB | ##################################### | 100% h5py-2.8.0 | 1.1 MB | ##################################### | 100% asn1crypto-0.24.0 | 154 KB | ##################################### | 100% cffi-1.11.5 | 388 KB | ##################################### | 100% pb-falcon-0.2.4 | 716 KB | ##################################### | 100% python-msgpack-0.5.6 | 282 KB | ##################################### | 100% unittest2-1.1.0 | 68 KB | ##################################### | 100% minimap2-2.14 | 2.0 MB | ##################################### | 100% mkl-2018.0.3 | 198.7 MB | ##################################### | 100% python-intervaltree- | 22 KB | ##################################### | 100% pbcommand-1.1.1 | 193 KB | ##################################### | 100% nim-falcon-0.0.0 | 271 KB | ##################################### | 100% iso8601-0.1.12 | 9 KB | ##################################### | 100% pbalign-0.3.1 | 76 KB | ##################################### | 100% mummer4-4.0.0beta2 | 1.3 MB | ##################################### | 100% mkl_random-1.0.2 | 1.0 MB | ##################################### | 100% wheel-0.32.3 | 34 KB | ##################################### | 100% intel-openmp-2019.1 | 885 KB | ##################################### | 100% traceback2-1.4.0 | 28 KB | ##################################### | 100% idna-2.7 | 131 KB | ##################################### | 100% sqlite-3.25.3 | 1.6 MB | ##################################### | 100% Preparing transaction: done Verifying transaction: done Executing transaction: | ############################################################################## # # # PacBio(R) tools distributed via Bioconda are: pre-release versions, not # # necessarily ISO compliant, intended for Research Use Only and not for use # # in diagnostic procedures, intended only for command-line users, and # # possibly newer than the currently available SMRT(R) Analysis builds. While # # efforts have been made to ensure that releases on Bioconda live up to the # # quality that PacBio strives for, we make no warranty regarding any # # Bioconda release. # # # # As PacBio tools distributed via Bioconda are not covered by any service # # level agreement or the like, please *do not* contact a PacBio Field # # Applications Scientist or PacBio Customer Service for assistance with any # # Bioconda release. We instead provide an issue tracker for you to report # # issues to us at: # # # # https://github.com/PacificBiosciences/pbbioconda # # # # We make no warranty that any such issue will be addressed, # # to any extent or within any time frame. # # # # BSD 3-Clause Clear License # # # # Please see https://github.com/PacificBiosciences/pbbioconda for # # information on License, Copyright and Disclaimer # # # ############################################################################## / ############################################################################## # # # PacBio(R) tools distributed via Bioconda are: pre-release versions, not # # necessarily ISO compliant, intended for Research Use Only and not for use # # in diagnostic procedures, intended only for command-line users, and # # possibly newer than the currently available SMRT(R) Analysis builds. While # # efforts have been made to ensure that releases on Bioconda live up to the # # quality that PacBio strives for, we make no warranty regarding any # # Bioconda release. # # # # As PacBio tools distributed via Bioconda are not covered by any service # # level agreement or the like, please *do not* contact a PacBio Field # # Applications Scientist or PacBio Customer Service for assistance with any # # Bioconda release. We instead provide an issue tracker for you to report # # issues to us at: # # # # https://github.com/PacificBiosciences/pbbioconda # # # # We make no warranty that any such issue will be addressed, # # to any extent or within any time frame. # # # # BSD 3-Clause Clear License # # # # Please see https://github.com/PacificBiosciences/pbbioconda for # # information on License, Copyright and Disclaimer # # # ############################################################################## ############################################################################## # # # PacBio(R) tools distributed via Bioconda are: pre-release versions, not # # necessarily ISO compliant, intended for Research Use Only and not for use # # in diagnostic procedures, intended only for command-line users, and # # possibly newer than the currently available SMRT(R) Analysis builds. While # # efforts have been made to ensure that releases on Bioconda live up to the # # quality that PacBio strives for, we make no warranty regarding any # # Bioconda release. # # # # As PacBio tools distributed via Bioconda are not covered by any service # # level agreement or the like, please *do not* contact a PacBio Field # # Applications Scientist or PacBio Customer Service for assistance with any # # Bioconda release. We instead provide an issue tracker for you to report # # issues to us at: # # # # https://github.com/PacificBiosciences/pbbioconda # # # # We make no warranty that any such issue will be addressed, # # to any extent or within any time frame. # # # # BSD 3-Clause Clear License # # # # Please see https://github.com/PacificBiosciences/pbbioconda for # # information on License, Copyright and Disclaimer # # # ############################################################################## ############################################################################## # # # PacBio(R) tools distributed via Bioconda are: pre-release versions, not # # necessarily ISO compliant, intended for Research Use Only and not for use # # in diagnostic procedures, intended only for command-line users, and # # possibly newer than the currently available SMRT(R) Analysis builds. While # # efforts have been made to ensure that releases on Bioconda live up to the # # quality that PacBio strives for, we make no warranty regarding any # # Bioconda release. # # # # As PacBio tools distributed via Bioconda are not covered by any service # # level agreement or the like, please *do not* contact a PacBio Field # # Applications Scientist or PacBio Customer Service for assistance with any # # Bioconda release. We instead provide an issue tracker for you to report # # issues to us at: # # # # https://github.com/PacificBiosciences/pbbioconda # # # # We make no warranty that any such issue will be addressed, # # to any extent or within any time frame. # # # # BSD 3-Clause Clear License # # # # Please see https://github.com/PacificBiosciences/pbbioconda for # # information on License, Copyright and Disclaimer # # # ############################################################################## ############################################################################## # # # PacBio(R) tools distributed via Bioconda are: pre-release versions, not # # necessarily ISO compliant, intended for Research Use Only and not for use # # in diagnostic procedures, intended only for command-line users, and # # possibly newer than the currently available SMRT(R) Analysis builds. While # # efforts have been made to ensure that releases on Bioconda live up to the # # quality that PacBio strives for, we make no warranty regarding any # # Bioconda release. # # # # As PacBio tools distributed via Bioconda are not covered by any service # # level agreement or the like, please *do not* contact a PacBio Field # # Applications Scientist or PacBio Customer Service for assistance with any # # Bioconda release. We instead provide an issue tracker for you to report # # issues to us at: # # # # https://github.com/PacificBiosciences/pbbioconda # # # # We make no warranty that any such issue will be addressed, # # to any extent or within any time frame. # # # # BSD 3-Clause Clear License # # # # Please see https://github.com/PacificBiosciences/pbbioconda for # # information on License, Copyright and Disclaimer # # # ############################################################################## done (denovo_asm) ➜ Analysis_Results]]> Jit