The fetal circulation contains several embryo-specific proteins normally present in the serum of adult individuals in very small concentrations . Pedersen (1) described the first protein of this group in calf serum (fetuin) and since then several embryo-specific serum proteins have been demonstrated in a number of mammalian species (2, 3) . Alpha-fetoprotein(AFP),' an embryo-specific protein synthesized by the liver, is the first alphaprotein to appear in mammalian sera during ontogenetic development and is the dominant serum protein in early embryonic life at a time when albumin and transferrin are present in trace amounts (4, 5) . The physiological level of AFP in the fetus reaches milligram amounts (4 mg/ml in human) during early-mid gestation and then drops linearly as birth approaches and shortly thereafter falls to normal background adult levels which are on the order of 0 .001% of the maximal fetal levels . It has been suggested that the appearance of AFP is due to the absence of a repressor which normally appears toward the end of embryonic life (6) . This protein has been considered a tumor-associated embryonic antigen since Abelev and co-workers (7) originally observed the reappearance of high concentrations of AFP in the serum of patients with primary liver cancer . Elevated AFP levels have subsequently been shown to occur in other malignant (especially teratocarcinomas) as well as nonmalignant conditions, particularly those associated with liver regeneration (8) . However, the relative specificity of markedly elevated AFP levels for primary liver cancer has been emphasized (9) .The function of AFP in the fetus is unknown, nor is it known why there is a re-expression of the protein in certain pathological conditions during postnatal life . One intriguing possibility is that AFP has immunoregulatory properties which are important for the exemption of the histoincompatible embryo from immunological attack by the maternal immune system . Furthermore, the demonstration of immunosuppressive activity by AFP in relation to its occurrence in certain malignant conditions would be consistent with the association known to exist between various forms of immune deficiency and neoplastic disease .

Interaction sites on protein surfaces mediate virtually all biological activities, and their identification holds promise for disease treatment and drug design. Novel algorithmic approaches for the prediction of these sites have been produced at a rapid rate, and the field has seen significant advancement over the past decade. However, the most current methods have not yet been reviewed in a systematic and comprehensive fashion. Herein, we describe the intricacies of the biological theory, datasets, and features required for modern protein-protein interaction site (PPIS) prediction, and present an integrative analysis of the state-of-the-art algorithms and their performance. First, the major sources of data used by predictors are reviewed, including training sets, evaluation sets, and methods for their procurement. Then, the features employed and their importance in the biological characterization of PPISs are explored. This is followed by a discussion of the methodologies adopted in contemporary prediction programs, as well as their relative performance on the datasets most recently used for evaluation. In addition, the potential utility that PPIS identification holds for rational drug design, hotspot prediction, and computational molecular docking is described. Finally, an analysis of the most promising areas for future development of the field is presented.

Evidence from various systems suggests that thymus-derived lymphocytes can affect the quality of antibody responses by recognizing various portions of the immunoglobulin receptor of bone-marrow-derived thymus-independent lymphocytes. A model for this process is proposed involving two antigen-specific mature T helper cells, one of which also is specific for immunoglobulin determinants. These two cells act synergistically. Evidence from adoptive secondary antibody responses demonstrates that both cells are antigen-specific T cells and that the immunoglobulin-recognizing T helper cell is absent from experimentally agammaglobulinemic mice. This cell is termed an "immunoglobulin-dependent T cell" because its activation requires the presence of immunoglobulin.

BackgroundTransient protein-protein interactions (PPIs), which underly most biological processes, are a prime target for therapeutic development. Immense progress has been made towards computational prediction of PPIs using methods such as protein docking and sequence analysis. However, docking generally requires high resolution structures of both of the binding partners and sequence analysis requires that a significant number of recurrent patterns exist for the identification of a potential binding site. Researchers have turned to machine learning to overcome some of the other methods’ restrictions by generalising interface sites with sets of descriptive features. Best practices for dataset generation, features, and learning algorithms have not yet been identified or agreed upon, and an analysis of the overall efficacy of machine learning based PPI predictors is due, in order to highlight potential areas for improvement.ResultsThe presence of unknown interaction sites as a result of limited knowledge about protein interactions in the testing set dramatically reduces prediction accuracy. Greater accuracy in labelling the data by enforcing higher interface site rates per domain resulted in an average 44% improvement across multiple machine learning algorithms. A set of 10 biologically unrelated proteins that were consistently predicted on with high accuracy emerged through our analysis. We identify seven features with the most predictive power over multiple datasets and machine learning algorithms. Through our analysis, we created a new predictor, RAD-T, that outperforms existing non-structurally specializing machine learning protein interface predictors, with an average 59% increase in MCC score on a dataset with a high number of interactions.ConclusionCurrent methods of evaluating machine-learning based PPI predictors tend to undervalue their performance, which may be artificially decreased by the presence of un-identified interaction sites. Changes to predictors’ training sets will be integral to the future progress of interface prediction by machine learning methods. We reveal the need for a larger test set of well studied proteins or domain-specific scoring algorithms to compensate for poor interaction site identification on proteins in general.

No abstract