Method and apparatus for identification of biomolecules

Abstract

The present disclosure presents methods, systems, and devices for dentifying new molecules directly from biological sequence information, with at least one of a desired bioactivity profile, functional attribute, biochemical reactivity, biological impact, pharmacological characteristic or therapeutic effect. The present disclosure further includes analyzing, at the processor, data features of biological sequence information and other data sources, including a feature-definition set by processing, using one or more bioinformatic techniques, computational algorithms, or methods of statistical machine learning, data sources relating to biological or chemical molecules, including biomolecules, including but not limited to peptides, having desired physical or chemical characteristics, bioactivities, functional attributes, biological impacts, pharmacologic properties or therapeutic effects.

What is claimed is: 
     
         1 . A method of identifying, on an electronic device including a processor and memory, new molecules directly from biological sequence information, with at least one of a desired bioactivity profile, functional attribute, biochemical reactivity, biological impact, pharmacological characteristic or therapeutic effect, the method comprising
 analyzing, at the processor, data features of biological sequence information and other data sources, including a feature-definition set by processing, using one or more bioinformatic techniques, computational algorithms, or methods of statistical machine learning, data sources relating to biological or chemical molecules, including biomolecules, including but not limited to peptides, having desired physical or chemical characteristics, bioactivities, functional attributes, biological impacts, pharmacologic properties or therapeutic effects.   
     
     
         2 . The method of  claim 1 , further comprising deriving, at the processor, a set of data features, including but not limited to biological sequence features, using methods of statistical machine learning, computational biology or bioinformatics, that distinguish biological sequences encoding to peptides or other biomolecules, or the peptides or other biomolecules with the desired bioactivity profile from biological sequences encoding to peptides or other biomolecules that lack the desired bioactivity profile. 
     
     
         3 . The method of  claim 1 , further comprising deriving, at the processor, a set of data features, using methods of statistical machine learning, computational biology or bioinformatics, that distinguish, define or are shared by sets of biological sequences encoding to peptides or other biomolecules with the desired bioactivity profile. 
     
     
         4 . The method of  claim 3 , further comprising searching, at the processor, a feature-detection set for biological sequence features that are the same as or similar to the sequence features distinguishing, defining or shared by sequences encoding, regulating or relating to peptides or other biomolecules with the desired bioactivity profile. 
     
     
         5 . The method of  claim 4 , further comprising compiling, at the processor, a list of the shared feature sequences discovered in the feature-detection genome set encoding, regulating or relating to novel peptides or other biomolecules predicted to have the desired bioactivity profile. 
     
     
         6 . The method of  claim 5 , further comprising producing, at the biomolecule synthesis system, the predicted biomolecules discovered in the feature-detection set using standard procedures of molecular synthesis. 
     
     
         7 . The method of  claim 6 , further comprising testing, at the bioassay evaluation device, the predicted biomolecules using an appropriate bioassay designed to assess the actual bioactivity profile of the produced biomolecules. 
     
     
         8 . The method of  claim 7 , further comprising compiling, at the processor, a list of the predicted biomolecules that exhibit the validated biomolecules and a list of biomolecules that lack the rejected biomolecules. 
     
     
         9 . The method of  claim 8 , further comprising refining, at the processor, the shared feature sequences that are associated with the validated biomolecules, but are not associated with the rejected biomolecules by performing one or more additional iterations of the following steps:
 encoding, using one or more bioinformatic techniques, computational algorithms, or methods of statistical machine learning, to biological or biochemical molecules, including but limited to peptides, having desired physical or chemical characteristics, bioactivities, functional attributes, biological impacts, pharmacologic properties or therapeutic effects, and   deriving a set of biological data features, using methods of statistical machine learning, that distinguish, define or are shared by peptides or other biomolecules, or sets of biological sequences encoding to peptides or other biomolecules, with the desired bioactivity profile.   
     
     
         10 . The method of  claim 9 , further comprising compiling, at the processor, a revised shared feature sequence data. 
     
     
         11 . The method of  claim 10 , further comprising searching, at the processor, the biological sequence information of the feature detection set, or a new feature detection set which includes some additional biological sequence information from one or more organisms using the revised shared feature sequence data. 
     
     
         12 . The method of  claim 11 , further comprising compiling, at the processor, a new or improved predicted biomolecule list with associated sequence features. 
     
     
         13 . The method of  claim 12 , further comprising one or more iterations of one or more of the following steps: the production of the predicted biomolecules by producing, at the biomolecule synthesis system, the predicted biomolecules discovered in the feature-detection set using standard procedures of molecular synthesis; the testing of the new or improved predicted biomolecules by testing, at the bioassay evaluation device, the predicted biomolecules using an appropriate bioassay designed to assess the actual bioactivity profile of the produced biomolecules; the compilation of a new or revised list of validated and rejected biomolecules, as compiling, at the processor, a list of the predicted biomolecules that exhibit the validated biomolecules and a list of biomolecules that lack the rejected biomolecules; refining, at the processor, the shared feature sequences that are associated with the validated biomolecules, but are not associated with the rejected biomolecules by performing one or more additional iterations of the following steps:
 encoding, using one or more bioinformatic techniques, computational algorithms, or methods of statistical machine learning, to biological or biochemical molecules, including but limited to peptides, having desired physical or chemical characteristics, bioactivities, functional attributes, biological impacts, pharmacologic properties or therapeutic effects, and   deriving a set of biological data features, using methods of statistical machine learning, that distinguish, define or are shared by peptides or other biomolecules, or sets of biological sequences encoding to peptides or other biomolecules, with the desired bioactivity profile; and compiling, at the processor, a revised shared feature sequence data.   
     
     
         14 . The method of  claim 2 , wherein the methods of statistical machine learning, computational biology or bioinformatics comprise at least one of an association rule learning, principal component analysis, latent class analysis, latent class prediction by Bayesian inference, support vector machines, semi-supervised learning, reinforcement learning, directed acyclic graphical models, distance-metric and similarity learning, artificial neural networks and hierarchical feature detection and representation. 
     
     
         15 . The method of  claim 3 , wherein the methods of statistical machine learning, computational biology or bioinformatics comprise at least one of an association rule learning, principal component analysis, latent class analysis, latent class prediction by Bayesian inference, support vector machines, semi-supervised learning, reinforcement learning, directed acyclic graphical models, distance-metric and similarity learning, artificial neural networks or hierarchical feature detection and representation. 
     
     
         16 . The method of  claim 9 , wherein the methods of statistical machine learning, computational biology or bioinformatics comprise at least one of an association rule learning, principal component analysis, latent class analysis, latent class prediction by Bayesian inference, support vector machines, semi-supervised learning, reinforcement learning, directed acyclic graphical models, distance-metric and similarity learning, artificial neural networks or hierarchical feature detection and representation. 
     
     
         17 . The method of  claim 6 , wherein the procedures of molecular synthesis include at least one of in-vitro chemical synthesis, recombinant viral, bacterial, fungal, insect, protist, cell-culture, fosmid, cosmid or plasmid cloning and expression vectors, plants biomolecule cloning, expression and synthesis systems, synthetic biological organisms for biomolecule production, extraction or harvest of biomolecules from the organisms in which they are naturally present, or other natural or engineered expression and production systems for biomolecules. 
     
     
         18 . The method of  claim 1 , wherein the other data sources comprises at least one of chemical structure data, number of hydrogen bond donors or acceptors, molecular weight, number of rotational bonds, pH data, pKa data, pharmacokinetic data, pharmacodynamic data, hydrophobicity, lipophilicity, membrane permeability, diffusion coefficient, physiological transport dynamics, cellular localization data, absorption data, number of side chains, structural motif data, number of disulfide bonds, number or spatial arrangement of intramolecular bonds, secondary or tertiary structure, three dimensional shape or conformation, protein-protein interaction structure or potential, potential polymerization or interaction potential, P-450 enzyme interaction data, metabolic data, excretion or clearance data, liver toxicity data, Ames test data, drug persistence data, mammalian LD50 data, inter-molecular conjugation data, molecular cyclization data, biomolecular helix, sheet, strand, loop or turn data, electro-chemical data, ionization potential, water solvation data, oral bioavailability data, polar surface area data, drug safety data, drug efficacy data, small molecule analog data, kinase, G-protein, cellular receptor, secretory or signaling molecule, hormone, antibody or antigen or other moiety or species analog, agonist, antagonist or mimetic data, gene expression data, protein expression data, or drug target epitope data. 
     
     
         19 . An electronic device configured to identify new molecules directly from biological sequence information, with at least one of a desired bioactivity profile, functional attribute, biochemical reactivity, biological impact, pharmacological characteristic or therapeutic effect, the electronic device comprising:
 a processor;   a memory communicatively coupled to the processor, the memory configured to store instructions to cause the processor to   analyze data features of biological sequence information and other data sources, including a feature-definition set by processing, using one or more bioinformatic techniques, computational algorithms, or methods of statistical machine learning, data sources relating to biological or chemical molecules, including biomolecules, including but not limited to peptides, having desired physical or chemical characteristics, bioactivities, functional attributes, biological impacts, pharmacologic properties or therapeutic effects.