Unsupervised learningUnsupervised learning, is paradigm in machine learning where, in contrast to supervised learning and semi-supervised learning, algorithms learn patterns exclusively from unlabeled data. Neural network tasks are often categorized as discriminative (recognition) or generative (imagination). Often but not always, discriminative tasks use supervised methods and generative tasks use unsupervised (see Venn diagram); however, the separation is very hazy. For example, object recognition favors supervised learning but unsupervised learning can also cluster objects into groups.
G proteinG proteins, also known as guanine nucleotide-binding proteins, are a family of proteins that act as molecular switches inside cells, and are involved in transmitting signals from a variety of stimuli outside a cell to its interior. Their activity is regulated by factors that control their ability to bind to and hydrolyze guanosine triphosphate (GTP) to guanosine diphosphate (GDP). When they are bound to GTP, they are 'on', and, when they are bound to GDP, they are 'off'. G proteins belong to the larger group of enzymes called GTPases.
Respiratory syncytial virusRespiratory syncytial virus (RSV), also called human respiratory syncytial virus (hRSV) and human orthopneumovirus, is a common, contagious virus that causes infections of the respiratory tract. It is a negative-sense, single-stranded RNA virus. Its name is derived from the large cells known as syncytia that form when infected cells fuse. RSV is a common cause of respiratory hospitalization in infants, and reinfection remains common in later life: it is a notable pathogen in all age groups.
AntigenIn immunology, an antigen (Ag) is a molecule, moiety, foreign particulate matter, or an allergen, such as pollen, that can bind to a specific antibody or T-cell receptor. The presence of antigens in the body may trigger an immune response. Antigens can be proteins, peptides (amino acid chains), polysaccharides (chains of simple sugars), lipids, or nucleic acids. Antigens exist on normal cells, cancer cells, parasites, viruses, fungi, and bacteria. Antigens are recognized by antigen receptors, including antibodies and T-cell receptors.
Active siteIn biology and biochemistry, the active site is the region of an enzyme where substrate molecules bind and undergo a chemical reaction. The active site consists of amino acid residues that form temporary bonds with the substrate, the binding site, and residues that catalyse a reaction of that substrate, the catalytic site. Although the active site occupies only ~10–20% of the volume of an enzyme, it is the most important part as it directly catalyzes the chemical reaction.
Adaptive immune systemThe adaptive immune system, also known as the acquired immune system, or specific immune system is a subsystem of the immune system that is composed of specialized, systemic cells and processes that eliminate pathogens or prevent their growth. The acquired immune system is one of the two main immunity strategies found in vertebrates (the other being the innate immune system). Like the innate system, the adaptive immune system includes both humoral immunity components and cell-mediated immunity components and destroys invading pathogens.
Deep belief networkIn machine learning, a deep belief network (DBN) is a generative graphical model, or alternatively a class of deep neural network, composed of multiple layers of latent variables ("hidden units"), with connections between the layers but not between units within each layer. When trained on a set of examples without supervision, a DBN can learn to probabilistically reconstruct its inputs. The layers then act as feature detectors. After this learning step, a DBN can be further trained with supervision to perform classification.
Blood proteinBlood-proteins, also termed plasma proteins, are proteins present in blood plasma. They serve many different functions, including transport of lipids, hormones, vitamins and minerals in activity and functioning of the immune system. Other blood proteins act as enzymes, complement components, protease inhibitors or kinin precursors. Contrary to popular belief, haemoglobin is not a blood protein, as it is carried within red blood cells, rather than in the blood serum.
Polyclonal B cell responsePolyclonal B cell response is a natural mode of immune response exhibited by the adaptive immune system of mammals. It ensures that a single antigen is recognized and attacked through its overlapping parts, called epitopes, by multiple clones of B cell. In the course of normal immune response, parts of pathogens (e.g. bacteria) are recognized by the immune system as foreign (non-self), and eliminated or effectively neutralized to reduce their potential damage. Such a recognizable substance is called an antigen.
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.
Peripheral membrane proteinPeripheral membrane proteins, or extrinsic membrane proteins, are membrane proteins that adhere only temporarily to the biological membrane with which they are associated. These proteins attach to integral membrane proteins, or penetrate the peripheral regions of the lipid bilayer. The regulatory protein subunits of many ion channels and transmembrane receptors, for example, may be defined as peripheral membrane proteins.
Generative modelIn statistical classification, two main approaches are called the generative approach and the discriminative approach. These compute classifiers by different approaches, differing in the degree of statistical modelling. Terminology is inconsistent, but three major types can be distinguished, following : A generative model is a statistical model of the joint probability distribution on given observable variable X and target variable Y; A discriminative model is a model of the conditional probability of the target Y, given an observation x; and Classifiers computed without using a probability model are also referred to loosely as "discriminative".
