What is AI? Applications of artificial intelligence to dermatology.

In the past, the skills required to make an accurate dermatological diagnosis have required exposure to thousands of patients over many years. However, in recent years, artificial intelligence (AI) has made enormous advances, particularly in the area of image classification. This has led computer scientists to apply these techniques to develop algorithms that are able to recognize skin lesions, particularly melanoma. Since 2017, there have been numerous studies assessing the accuracy of algorithms, with some reporting that the accuracy matches or surpasses that of a dermatologist. While the principles underlying these methods are relatively straightforward, it can be challenging for the practising dermatologist to make sense of a plethora of unfamiliar terms in this domain. Here we explain the concepts of AI, machine learning, neural networks and deep learning, and explore the principles of how these tasks are accomplished. We critically evaluate the studies that have assessed the efficacy of these methods and discuss limitations and potential ethical issues. The burden of skin cancer is growing within the Western world, with major implications for both population skin health and the provision of dermatology services. AI has the potential to assist in the diagnosis of skin lesions and may have particular value at the interface between primary and secondary care. The emerging technology represents an exciting opportunity for dermatologists, who are the individuals best informed to explore the utility of this powerful novel diagnostic tool, and facilitate its safe and ethical implementation within healthcare systems.

Protein family and fold occurrence in genomes: power-law behaviour and evolutionary model.

Global surveys of genomes measure the usage of essential molecular parts, defined here as protein families, superfamilies or folds, in different organisms. Based on surveys of the first 20 completely sequenced genomes, we observe that the occurrence of these parts follows a power-law distribution. That is, the number of distinct parts (F) with a given genomic occurrence (V) decays as F=aV(-b), with a few parts occurring many times and most occurring infrequently. For a given organism, the distributions of families, superfamilies and folds are nearly identical, and this is reflected in the size of the decay exponent b. Moreover, the exponent varies between different organisms, with those of smaller genomes displaying a steeper decay (i.e. larger b). Clearly, the power law indicates a preference to duplicate genes that encode for molecular parts which are already common. Here, we present a minimal, but biologically meaningful model that accurately describes the observed power law. Although the model performs equally well for all three protein classes, we focus on the occurrence of folds in preference to families and superfamilies. This is because folds are comparatively insensitive to the effects of point mutations that can cause a family member to diverge beyond detectable similarity. In the model, genomes evolve through two basic operations: (i) duplication of existing genes; (ii) net flow of new genes. The flow term is closely related to the exponent b and can accommodate considerable gene loss; however, we demonstrate that the observed data is reproduced best with a net inflow, i.e. with more gene gain than loss. Moreover, we show that prokaryotes have much higher rates of gene acquisition than eukaryotes, probably reflecting lateral transfer. A further natural outcome from our model is an estimation of the fold composition of the initial genome, which potentially relates to the common ancestor for modern organisms. Supplementary material pertaining to this work is available from www.partslist.org/powerlaw.

What is bioinformatics? A proposed definition and overview of the field.

BACKGROUND: The recent flood of data from genome sequences and functional genomics has given rise to new field, bioinformatics, which combines elements of biology and computer science. OBJECTIVES: Here we propose a definition for this new field and review some of the research that is being pursued, particularly in relation to transcriptional regulatory systems. METHODS: Our definition is as follows: Bioinformatics is conceptualizing biology in terms of macromolecules (in the sense of physical-chemistry) and then applying "informatics" techniques (derived from disciplines such as applied maths, computer science, and statistics) to understand and organize the information associated with these molecules, on a large-scale. RESULTS AND CONCLUSIONS: Analyses in bioinformatics predominantly focus on three types of large datasets available in molecular biology: macromolecular structures, genome sequences, and the results of functional genomics experiments (e.g. expression data). Additional information includes the text of scientific papers and "relationship data" from metabolic pathways, taxonomy trees, and protein-protein interaction networks. Bioinformatics employs a wide range of computational techniques including sequence and structural alignment, database design and data mining, macromolecular geometry, phylogenetic tree construction, prediction of protein structure and function, gene finding, and expression data clustering. The emphasis is on approaches integrating a variety of computational methods and heterogeneous data sources. Finally, bioinformatics is a practical discipline. We survey some representative applications, such as finding homologues, designing drugs, and performing large-scale censuses. Additional information pertinent to the review is available over the web at http://bioinfo.mbb.yale.edu/what-is-it.

Interrelating different types of genomic data, from proteome to secretome: 'oming in on function.

With the completion of genome sequences, the current challenge for biology is to determine the functions of all gene products and to understand how they contribute in making an organism viable. For the first time, biological systems can be viewed as being finite, with a limited set of molecular parts. However, the full range of biological processes controlled by these parts is extremely complex. Thus, a key approach in genomic research is to divide the cellular contents into distinct sub-populations, which are often given an "-omic" term. For example, the proteome is the full complement of proteins encoded by the genome, and the secretome is the part of it secreted from the cell. Carrying this further, we suggest the term "translatome" to describe the members of the proteome weighted by their abundance, and the "functome" to describe all the functions carried out by these. Once the individual sub-populations are defined and analyzed, we can then try to reconstruct the full organism by interrelating them, eventually allowing for a full and dynamic view of the cell. All this is, of course, made possible because of the increasing amount of large-scale data resulting from functional genomics experiments. However, there are still many difficulties resulting from the noisiness and complexity of the information. To some degree, these can be overcome through averaging with broad proteomic categories such as those implicit in functional and structural classifications. For illustration, we discuss one example in detail, interrelating transcript and cellular protein populations (transcriptome and translatome). Further information is available at http://bioinfo.mbb.yale.edu/what-is-it.

Amino acid-base interactions: a three-dimensional analysis of protein-DNA interactions at an atomic level.

To assess whether there are universal rules that govern amino acid-base recognition, we investigate hydrogen bonds, van der Waals contacts and water-mediated bonds in 129 protein-DNA complex structures. DNA-backbone interactions are the most numerous, providing stability rather than specificity. For base interactions, there are significant base-amino acid type correlations, which can be rationalised by considering the stereochemistry of protein side chains and the base edges exposed in the DNA structure. Nearly two-thirds of the direct read-out of DNA sequences involves complex networks of hydrogen bonds, which enhance specificity. Two-thirds of all protein-DNA interactions comprise van der Waals contacts, compared to about one-sixth each of hydrogen and water-mediated bonds. This highlights the central importance of these contacts for complex formation, which have previously been relegated to a secondary role. Although common, water-mediated bonds are usually non-specific, acting as space-fillers at the protein-DNA interface. In conclusion, the majority of amino acid-base interactions observed follow general principles that apply across all protein-DNA complexes, although there are individual exceptions. Therefore, we distinguish between interactions whose specificities are 'universal' and 'context-dependent'. An interactive Web-based atlas of side chain-base contacts provides access to the collected data, including analyses and visualisation of the three-dimensional geometry of the interactions.

Protein-RNA interactions: a structural analysis.

A detailed computational analysis of 32 protein-RNA complexes is presented. A number of physical and chemical properties of the intermolecular interfaces are calculated and compared with those observed in protein-double-stranded DNA and protein-single-stranded DNA complexes. The interface properties of the protein-RNA complexes reveal the diverse nature of the binding sites. van der Waals contacts played a more prevalent role than hydrogen bond contacts, and preferential binding to guanine and uracil was observed. The positively charged residue, arginine, and the single aromatic residues, phenylalanine and tyrosine, all played key roles in the RNA binding sites. A comparison between protein-RNA and protein-DNA complexes showed that whilst base and backbone contacts (both hydrogen bonding and van der Waals) were observed with equal frequency in the protein-RNA complexes, backbone contacts were more dominant in the protein-DNA complexes. Although similar modes of secondary structure interactions have been observed in RNA and DNA binding proteins, the current analysis emphasises the differences that exist between the two types of nucleic acid binding protein at the atomic contact level.

An overview of the structures of protein-DNA complexes.

On the basis of a structural analysis of 240 protein-DNA complexes contained in the Protein Data Bank (PDB), we have classified the DNA-binding proteins involved into eight different structural/functional groups, which are further classified into 54 structural families. Here we present this classification and review the functions, structures and binding interactions of these protein-DNA complexes.

New tools and resources for analysing protein structures and their interactions.

The determination of protein structures has furthered our understanding of how various proteins perform their functions. With the large number of structures currently available in the PDB, it is necessary to be able to easily study these proteins in detail. Here new software tools are presented which aim to facilitate this analysis; these include the PDBsum WWW site which provides a summary description of all PDB entries, the programs TOPS and NUCPLOT to plot schematic diagrams representing protein topology and DNA-binding interactions, SAS a WWW-based sequence-analysis tool incorporating structural data, and WWW servers for the analysis of protein-protein interfaces and analyses of over 300 haem-binding proteins.

NUCPLOT: a program to generate schematic diagrams of protein-nucleic acid interactions.

Proteins that bind to DNA are found in all areas of genetic activity within the cell. To help understand how these proteins perform their various functions, it is useful to analyse which residues are involved in binding to the DNA and how they interact with the bases and sugar-phosphate backbone of nucleic acids. Here we describe a program called NUCPLOT which can automatically identify these interactions from the 3D atomic coordinates of the complex from a PDB file and generate a plot that shows all the interactions in a schematic manner. The program produces a PostScript output file representing hydrogen, van der Waals and covalent bonds between the protein and the DNA. The resulting diagram is both clear and simple and allows immediate identification of important interactions within the structure. It also facilitates comparison of binding found in different structures. NUCPLOT is a completely automatic program, which can be used for any protein-DNA complex and will also work for certain protein-RNA structures.

Protein clefts in molecular recognition and function.

One of the primary factors determining how proteins interact with other molecules is the size of clefts in the protein's surface. In enzymes, for example, the active site is often characterized by a particularly large and deep cleft, while interactions between the molecules of a protein dimer tend to involve approximately planar surfaces. Here we present an analysis of how cleft volumes in proteins relate to their molecular interactions and functions. Three separate datasets are used, representing enzyme-ligand binding, protein-protein dimerization and antibody-antigen complexes. We find that, in single-chain enzymes, the ligand is bound in the largest cleft in over 83% of the proteins. Usually the largest cleft is considerably larger than the others, suggesting that size is a functional requirement. Thus, in many cases, the likely active sites of an enzyme can be identified using purely geometrical criteria alone. In other cases, where there is no predominantly large cleft, chemical interactions are required for pinpointing the correct location. In antibody-antigen interactions the antibody usually presents a large cleft for antigen binding. In contrast, protein-protein interactions in homodimers are characterized by approximately planar interfaces with several clefts involved. However, the largest cleft in each subunit still tends to be involved.