Mercurial > repos > jay > pdaug_ml_models
changeset 6:8697dc4a7f45 draft
"planemo upload for repository https://github.com/jaidevjoshi83/pdaug commit e8c8198105af7eab636fb2405e5ff335539ca14b"
author | jay |
---|---|
date | Sun, 31 Jan 2021 02:43:58 +0000 |
parents | d5a209484c17 |
children | c8cb2baa4e6f |
files | PDAUG_AA_Property_Based_Peptide_Generation/PDAUG_AA_Property_Based_Peptide_Generation.py PDAUG_ML_Models/PDAUG_ML_Models.xml |
diffstat | 2 files changed, 38 insertions(+), 6 deletions(-) [+] |
line wrap: on
line diff
--- a/PDAUG_AA_Property_Based_Peptide_Generation/PDAUG_AA_Property_Based_Peptide_Generation.py Thu Jan 28 04:26:52 2021 +0000 +++ b/PDAUG_AA_Property_Based_Peptide_Generation/PDAUG_AA_Property_Based_Peptide_Generation.py Sun Jan 31 02:43:58 2021 +0000 @@ -129,6 +129,21 @@ OutFasta.write(">sequence_"+str(i)+'\n') OutFasta.write(O+'\n') + +def MixedLibrary_seq(seqnum, centrosymmetric, centroasymmetric, helix, kinked, oblique, rand, randAMP, randAMPnoCM, OutFasta): + + lib = MixedLibrary(int(seqnum), int(centrosymmetric), int(centroasymmetric), int(helix), int(kinked), int(oblique), int(rand), int(randAMP), int(randAMPnoCM)) + lib.generate_sequences() + OutFasta = open(OutFasta, 'w') + + OutPep = lib.sequences + + for i,O in enumerate(OutPep): + OutFasta.write(">sequence_"+str(i)+'\n') + OutFasta.write(O+'\n') + + + if __name__=='__main__': parser = argparse.ArgumentParser(description='Deployment tool') @@ -192,6 +207,19 @@ Arc.add_argument("-y","--hyd_gra", default='False', help="Method to mutate the generated sequences to have a hydrophobic gradient by substituting the last third of the sequence amino acids to hydrophobic.") Arc.add_argument("-O", "--OutFasta", required=True, default=None, help="Output Fasta") + Mix = subparsers.add_parser('MixedLibrary') + Mix.add_argument("-s","--seq_num", required=True, default=None, help="number of sequences to be generated") + Mix.add_argument("-c","--centrosymmetric", required=False, default=1, help="ratio of symmetric centrosymmetric sequences in the library") + Mix.add_argument("-ca","--centroasymmetric", required=False, default=1, help="ratio of asymmetric centrosymmetric sequences in the library") + Mix.add_argument("-hl","--helix", required=False, default=1, help="ratio of asymmetric centrosymmetric sequences in the library") + Mix.add_argument("-k","--kinked", required=False, default=1, help="ratio of asymmetric centrosymmetric sequences in the library") + Mix.add_argument("-o", "--oblique", required=False, default=1, help=" ratio of oblique oriented amphipathic helical sequences in the library") + Mix.add_argument("-r", "--rand", required=False, default=1, help="ratio of random sequneces in the library") + Mix.add_argument("-ra", "--randAMP", required=False, default=1, help="ratio of random sequences with APD2 amino acid distribution in the library") + Mix.add_argument("-rp", "--randAMPnoCM", required=False, default=1, help="ratio of random sequences with APD2 amino acid distribution without Cys and Met in the library") + Mix.add_argument("-O", "--OutFasta", required=True, default=None, help="Output Fasta") + + args = parser.parse_args() if sys.argv[1] == 'Random': @@ -212,5 +240,9 @@ AMPngrams_seq(args.seq_num, args.n_min, args.n_max, args.OutFasta) elif sys.argv[1] == 'AmphipathicArc': AmphipathicArc_seq(int(args.seq_num), int(args.lenmin_s), int(args.lenmax_s), int(args.arcsize), args.hyd_gra, args.OutFasta) + elif sys.argv[1] == 'MixedLibrary': + MixedLibrary_seq(args.seq_num, args.centrosymmetric, args.centroasymmetric, args.helix, args.kinked, args.oblique, args.rand, args.randAMP, args.randAMPnoCM, args.OutFasta) else: - print("You entered Wrong Values: ") \ No newline at end of file + print("You entered Wrong Values: ") + +
--- a/PDAUG_ML_Models/PDAUG_ML_Models.xml Thu Jan 28 04:26:52 2021 +0000 +++ b/PDAUG_ML_Models/PDAUG_ML_Models.xml Sun Jan 31 02:43:58 2021 +0000 @@ -585,10 +585,10 @@ <conditional name='TestMethods'> <param name="SelTestMethods" type="select" label="Choose the Test method" argument="--TestMethod" help="Data testing method"> - <option value="Internal">Internal</option> - <option value="TestSplit">TestSplit</option> - <option value="External">External</option> - <option value="Predict">Predict</option> + <option value="Internal">Internal Test</option> + <option value="TestSplit">Train Test Split</option> + <option value="External">External Test Data</option> + <option value="Predict">Predict Unknown</option> </param> <when value="Internal"> <param name="nFolds" type="integer" label="Cross validation" value="5" min="5" max="10" argument="--nfold" help="Cross validation"/> @@ -720,7 +720,7 @@ * **Training File** Tabulalr files with labeled peptide descriptor data. * **Select Machine Learning algorithms** Select algorithm. * **Select Advanced Parameters** Select the advance parameter details of each of the parameters that can be found on sklearn website. - * **Select the test method** (predict or internal test) + * **Select the test method** (Internal Test, Train Test Split, External Test Data, and Predict Unknown) * **Cross Validation** Up to 10 fold cross-validation. * **Method to Scale the data** MinMaxScaler and standard scaler.