Reinforcement learningReinforcement learning (RL) is an area of machine learning concerned with how intelligent agents ought to take actions in an environment in order to maximize the notion of cumulative reward. Reinforcement learning is one of three basic machine learning paradigms, alongside supervised learning and unsupervised learning. Reinforcement learning differs from supervised learning in not needing labelled input/output pairs to be presented, and in not needing sub-optimal actions to be explicitly corrected.
Protein primary structureProtein primary structure is the linear sequence of amino acids in a peptide or protein. By convention, the primary structure of a protein is reported starting from the amino-terminal (N) end to the carboxyl-terminal (C) end. Protein biosynthesis is most commonly performed by ribosomes in cells. Peptides can also be synthesized in the laboratory. Protein primary structures can be directly sequenced, or inferred from DNA sequencess.
Deep reinforcement learningDeep reinforcement learning (deep RL) is a subfield of machine learning that combines reinforcement learning (RL) and deep learning. RL considers the problem of a computational agent learning to make decisions by trial and error. Deep RL incorporates deep learning into the solution, allowing agents to make decisions from unstructured input data without manual engineering of the state space. Deep RL algorithms are able to take in very large inputs (e.g.
Post-translational modificationPost-translational modification (PTM) is the covalent process of changing proteins following protein biosynthesis. PTMs may involve enzymes or occur spontaneously. Proteins are created by ribosomes translating mRNA into polypeptide chains, which may then change to form the mature protein product. PTMs are important components in cell signalling, as for example when prohormones are converted to hormones. Post-translational modifications can occur on the amino acid side chains or at the protein's C- or N- termini.
Peptide bondIn organic chemistry, a peptide bond is an amide type of covalent chemical bond linking two consecutive alpha-amino acids from C1 (carbon number one) of one alpha-amino acid and N2 (nitrogen number two) of another, along a peptide or protein chain. It can also be called a eupeptide bond to distinguish it from an isopeptide bond, which is another type of amide bond between two amino acids. When two amino acids form a dipeptide through a peptide bond, it is a type of condensation reaction.
Feature learningIn machine learning, feature learning or representation learning is a set of techniques that allows a system to automatically discover the representations needed for feature detection or classification from raw data. This replaces manual feature engineering and allows a machine to both learn the features and use them to perform a specific task. Feature learning is motivated by the fact that machine learning tasks such as classification often require input that is mathematically and computationally convenient to process.
Peptide synthesisIn organic chemistry, peptide synthesis is the production of peptides, compounds where multiple amino acids are linked via amide bonds, also known as peptide bonds. Peptides are chemically synthesized by the condensation reaction of the carboxyl group of one amino acid to the amino group of another. Protecting group strategies are usually necessary to prevent undesirable side reactions with the various amino acid side chains. Chemical peptide synthesis most commonly starts at the carboxyl end of the peptide (C-terminus), and proceeds toward the amino-terminus (N-terminus).
Nucleic acid sequenceA nucleic acid sequence is a succession of bases within the nucleotides forming alleles within a DNA (using GACT) or RNA (GACU) molecule. This succession is denoted by a series of a set of five different letters that indicate the order of the nucleotides. By convention, sequences are usually presented from the 5' end to the 3' end. For DNA, with its double helix, there are two possible directions for the notated sequence; of these two, the sense strand is used.
ChemoproteomicsChemoproteomics (also known as chemical proteomics) entails a broad array of techniques used to identify and interrogate protein-small molecule interactions. Chemoproteomics complements phenotypic drug discovery, a paradigm that aims to discover lead compounds on the basis of alleviating a disease phenotype, as opposed to target-based drug discovery (reverse pharmacology), in which lead compounds are designed to interact with predetermined disease-driving biological targets.
Sequence analysisIn bioinformatics, sequence analysis is the process of subjecting a DNA, RNA or peptide sequence to any of a wide range of analytical methods to understand its features, function, structure, or evolution. Methodologies used include sequence alignment, searches against biological databases, and others. Since the development of methods of high-throughput production of gene and protein sequences, the rate of addition of new sequences to the databases increased very rapidly.
