Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “Protein language model”

Search indexed PubMed citations on genomics, clinical trials, systematic reviews and public health. Explore titles, authors and supplied subject terms, then open the PubMed record.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 91 records · Page 5Linked to original sources
PubMed2006

ROKU: a novel method for identification of tissue-specific genes.

BACKGROUND: One of the important goals of microarray research is the identification of genes whose expression is considerably higher or lower in some tissues than in others. We would like to have ways of identifying such tissue-specific genes. RESULTS: We describe a method, ROKU, which selects tissue-specific patterns from gene expression data for many tissues and thousands of genes. ROKU ranks genes according to their overall tissue specificity using Shannon entropy and detects tissues specific to each gene if any exist using an outlier detection method. We evaluated the capacity for the detection of various specific expression patterns using synthetic and real data. We observed that ROKU was superior to a conventional entropy-based method in its ability to rank genes according to overall tissue specificity and to detect genes whose expression pattern are specific only to objective tissues. CONCLUSION: ROKU is useful for the detection of various tissue-specific expression patterns. The framework is also directly applicable to the selection of diagnostic markers for molecular classification of multiple classes.

Algorithms↗
PubMed1998

A prototype molecular interactive collaborative environment (MICE).

Illustrations of macromolecular structure in the scientific literature contain a high level of semantic content through which the authors convey, among other features, the biological function of that macromolecule. We refer to these illustrations as molecular scenes. Such scenes, if available electronically, are not readily accessible for further interactive interrogation. The basic PDB format does not retain features of the scene; formats like PostScript retain the scene but are not interactive; and the many formats used by individual graphics programs, while capable of reproducing the scene, are neither interchangeable nor can they be stored in a database and queried for features of the scene. MICE defines a Molecular Scene Description Language (MSDL) which allows scenes to be stored in a relational database (a molecular scene gallery) and queried. Scenes retrieved from the gallery are rendered in Virtual Reality Modeling Language (VRML) and currently displayed in WebView, a VRML browser modified to support the Virtual Reality Behavior System (VRBS) protocol. VRBS provides communication between multiple client browsers, each capable of manipulating the scene. This level of collaboration works well over standard Internet connections and holds promise for collaborative research at a distance and distance learning. Further, via VRBS, the VRML world can be used as a visual cue to trigger an application such as a remote MEME search. MICE is very much work in progress. Current work seeks to replace WebView with Netscape, Cosmoplayer, a standard VRML plug-in, and a Java-based console. The console consists of a generic kernel suitable for multiple collaborative applications and additional application-specific controls. Further details of the MICE project are available at http:/(/)mice.sdsc.edu.

Computational Biology↗
PubMed2003

A probabilistic model for identifying protein names and their name boundaries.

This paper proposes a method for identifying protein names in biomedical texts with an emphasis on detecting protein name boundaries. We use a probabilistic model which exploits several surface clues characterizing protein names and incorporates word classes for generalization. In contrast to previously proposed methods, our approach does not rely on natural language processing tools such as part-of-speech taggers and syntactic parsers, so as to reduce processing overhead and the potential number of probabilistic parameters to be estimated. A notion of certainty is also proposed to improve precision for identification. We implemented a protein name identification system based on our proposed method, and evaluated the system on real-world biomedical texts in conjunction with the previous work. The results showed that overall our system performs comparably to the state-of-the-art protein name identification system and that higher performance is achieved for compound names. In addition, it is demonstrated that our system can further improve precision by restricting the system output to those names with high certainties.

Artificial Intelligence↗
PubMed2005

Evolutionary sequence analysis of complete eukaryote genomes.

BACKGROUND: Gene duplication and gene loss during the evolution of eukaryotes have hindered attempts to estimate phylogenies and divergence times of species. Although current methods that identify clusters of orthologous genes in complete genomes have helped to investigate gene function and gene content, they have not been optimized for evolutionary sequence analyses requiring strict orthology and complete gene matrices. Here we adopt a relatively simple and fast genome comparison approach designed to assemble orthologs for evolutionary analysis. Our approach identifies single-copy genes representing only species divergences (panorthologs) in order to minimize potential errors caused by gene duplication. We apply this approach to complete sets of proteins from published eukaryote genomes specifically for phylogeny and time estimation. RESULTS: Despite the conservative criterion used, 753 panorthologs (proteins) were identified for evolutionary analysis with four genomes, resulting in a single alignment of 287,000 amino acids. With this data set, we estimate that the divergence between deuterostomes and arthropods took place in the Precambrian, approximately 400 million years before the first appearance of animals in the fossil record. Additional analyses were performed with seven, 12, and 15 eukaryote genomes resulting in similar divergence time estimates and phylogenies. CONCLUSION: Our results with available eukaryote genomes agree with previous results using conventional methods of sequence data assembly from genomes. They show that large sequence data sets can be generated relatively quickly and efficiently for evolutionary analyses of complete genomes.

Animals↗
PubMed2026

A trainable language model with potential to modulate translation rates in non-model organisms by generating upstream untranslated region sequence libraries.

Tuning protein expression in non-model organisms is often constrained by the lack of validated genetic parts and predictive design tools. Translational tuning through the modulation of upstream untranslated regions (5'-UTRs) offers a potentially organism-agnostic route, but existing methods typically rely on mechanistic assumptions, prior knowledge that may not be available in non-model contexts, or the screening of sequence libraries. Here, we present a simple generative approach for creating synthetic 5'-UTR libraries based solely on the genomic sequence statistics of any desired organism. The method uses a sliding-window n-gram language model applied to native 5'-UTR sequences to produce novel sequences that preserve organism-specific base distributions and motifs without hard-coding specific motifs or mechanistic rules into inflexible statistical templates. We have applied this approach to the model bacterium Escherichia coli and the non-model probiotic Limosilactobacillus reuteri. Libraries of approximately 1,000 sequences were generated for each organism, from which about 100 unique sequences were experimentally tested for translation of a fluorescent reporter protein. In both organisms, the synthetic libraries yielded a broad range of translation levels from this relatively small number of tested variants. Sequences derived from an organism's own genomic statistics provided a more uniformly distributed range of translation rates in that organism than sequences derived from the other species. Correlations of individual sequence performance across the two species were weak, and thermodynamic predictions of ribosome binding strength showed very little predictive power, especially in the non-model L. reuteri. The results demonstrate that simple statistical language model approaches applied to genomic data can generate functional translational regulatory sequence libraries without detailed mechanistic knowledge or explicit reference to consensus motifs. The approach requires minimal computational resources, avoids reproducing native sequences, and can be readily applied to any organism with a sequenced genome. This strategy may lower technical barriers to expression tuning in non-model organisms.

5' Untranslated Regions↗
PubMed2004

Wnt pathway curation using automated natural language processing: combining statistical methods with partial and full parse for knowledge extraction.

MOTIVATION: Wnt signaling is a very active area of research with highly relevant publications appearing at a rate of more than one per day. Building and maintaining databases describing signal transduction networks is a time-consuming and demanding task that requires careful literature analysis and extensive domain-specific knowledge. For instance, more than 50 factors involved in Wnt signal transduction have been identified as of late 2003. In this work we describe a natural language processing (NLP) system that is able to identify references to biological interaction networks in free text and automatically assembles a protein association and interaction map. RESULTS: A 'gold standard' set of names and assertions was derived by manual scanning of the Wnt genes website (http://www.stanford.edu/~rnusse/wntwindow.html) including 53 interactions involved in Wnt signaling. This system was used to analyze a corpus of peer-reviewed articles related to Wnt signaling including 3369 Pubmed and 1230 full text papers. Names for key Wnt-pathway associated proteins and biological entities are identified using a chi-squared analysis of noun phrases over-represented in the Wnt literature as compared to the general signal transduction literature. Interestingly, we identified several instances where generic terms were used on the website when more specific terms occur in the literature, and one typographic error on the Wnt canonical pathway. Using the named entity list and performing an exhaustive assertion extraction of the corpus, 34 of the 53 interactions in the 'gold standard' Wnt signaling set were successfully identified (64% recall). In addition, the automated extraction found several interactions involving key Wnt-related molecules which were missing or different from those in the canonical diagram, and these were confirmed by manual review of the text. These results suggest that a combination of NLP techniques for information extraction can form a useful first-pass tool for assisting human annotation and maintenance of signal pathway databases. AVAILABILITY: The pipeline software components are freely available on request to the authors. CONTACT: dstates@umich.edu SUPPLEMENTARY INFORMATION: http://stateslab.bioinformatics.med.umich.edu/software.html.

Animals↗
PubMed2003

Initial large-scale exploration of protein-protein interactions in human brain.

Study of protein interaction networks is crucial to post-genomic systems biology. Aided by high-throughput screening technologies, biologists are rapidly accumulating protein-protein interaction data. Using a random yeast two-hybrid (R2H) process, we have performed large-scale yeast two-hybrid searches with approximately fifty thousand random human brain cDNA bait fragments against a human brain cDNA prey fragment library. From these searches, we have identified 13,656 unique protein-protein interaction pairs involving 4,473 distinct known human loci. In this paper, we have performed our initial characterization of the protein interaction network in human brain tissue. We have classified and characterized all identified interactions based on Gene Ontology (GO) annotation of interacting loci. We have also described the "scale-free" topological structure of the network.

Brain↗
PubMed2004

Use of morphological analysis in protein name recognition.

Protein name recognition aims to detect each and every protein names appearing in a PubMed abstract. The task is not simple, as the graphic word boundary (space separator) assumed in conventional preprocessing does not necessarily coincide with the protein name boundary. Such boundary disagreement caused by tokenization ambiguity has usually been ignored in conventional preprocessing of general English. In this paper, we argue that boundary disagreement poses serious limitations in biomedical English text processing, not to mention protein name recognition. Our key idea for dealing with the boundary disagreement is to apply techniques used in Japanese morphological analysis where there are no word boundaries. Having evaluated the proposed method with GENIA corpus 3.02, we obtain F-measure of 69.01 on a strict criterion and 79.32 on a relaxed criterion. The result is comparable to other published work in protein name recognition, without resorting to manually prepared ad hoc feature engineering. Further, compared to the conventional preprocessing, the use of morphological analysis as preprocessing improves the performance of protein name recognition and reduces the execution time.

Abstracting and Indexing↗
PubMed2006

Finding regions of significance in SELDI measurements for identifying protein biomarkers.

MOTIVATION: There is a well-recognized potential of protein expression profiling using the surface-enhanced laser desorption and ionization technology for discovering biomarkers that can be applied in clinical diagnosis, prognosis and therapy prediction. The pre-processing of the raw data, however, is still problematic. METHODS: We focus on the peak detection step, where the standard method is marked by poor specificity. Currently, scientists need to inspect individual spectra visually and laboriously in order to verify that spectral peaks identified by the standard method are real. Motivated by this multi-spectral process, we investigate an analytical approach-called RS for 'regions of significance'-that reduces the data to a single spectrum of F-statistics capturing significant variability between spectra. To account for multiple testing, we use a false discovery rate criterion for identifying potentially interesting proteins. RESULTS: We show that RS has better operating characteristics than several existing methods and demonstrate routine applications on a number of large datasets.

Algorithms↗
PubMed2003

Amino acid code of protein secondary structure.

The calculation of protein three-dimensional structure from the amino acid sequence is a fundamental problem to be solved. This paper presents principles of the code theory of protein secondary structure, and their consequence--the amino acid code of protein secondary structure. The doublet code model of protein secondary structure, developed earlier by the author (Shestopalov, 1990), is part of this theory. The theory basis are: 1) the name secondary structure is assigned to the conformation, stabilized only by the nearest (intraresidual) and middle-range (at a distance no more than that between residues i and i + 5) interactions; 2) the secondary structure consists of regular (alpha-helical and beta-structural) and irregular (coil) segments; 3) the alpha-helices, beta-strands and coil segments are encoded, respectively, by residue pairs (i, i + 4), (i, i + 2), (i, i = 1), according to the numbers of residues per period, 3.6, 2, 1; 4) all such pairs in the amino acid sequence are codons for elementary structural elements, or structurons; 5) the codons are divided into 21 types depending on their strength, i.e. their encoding capability; 6) overlappings of structurons of one and the same structure generate the longer segments of this structure; 7) overlapping of structurons of different structures is forbidden, and therefore selection of codons is required, the codon selection is hierarchic; 8) the code theory of protein secondary structure generates six variants of the amino acid code of protein secondary structure. There are two possible kinds of model construction based on the theory: the physical one using physical properties of amino acid residues, and the statistical one using results of statistical analysis of a great body of structural data. Some evident consequences of the theory are: a) the theory can be used for calculating the secondary structure from the amino acid sequence as a partial solution of the problem of calculation of protein three-dimensional structure from the amino acid sequence, and the calculated secondary structure and codon strength distribution can be used for simulating the next step of protein folding; b) one can propose that the same secondary structures can be folded into different tertiary structures and, vice versa, different secondary structures can be folded into the same tertiary structures, provided codon distributions are considered also; c) codons can be considered as first elements of protein three-dimensional structure language.

Amino Acid Sequence↗
PubMed1997

A new approach to protein fold recognition based on Delaunay tessellation of protein structure.

We propose new algorithms for sequence-structure compatibility (fold recognition) searches in multi-dimensional sequence-structure space. Individual amino acid residues in protein structures are represented by their C alpha atoms; thus each protein is described as a collection of points in three-dimensional space. Delaunay tessellation of a protein generates an aggregate of space-filling, irregular tetrahedra, or Delaunay simplices. Statistical analysis of quadruplet residue compositions of all Delaunay simplices in a representative dataset of protein structures leads to a novel four body contact residue potential expressed as log likelihood factor q. The q factors are calculated for native 20 letter amino acid alphabet and several reduced alphabets. Two sequence-structure compatibility functions are computed as (i) the sum of q factors for all Delaunay simplices in a given protein, or (ii) 3D-1D Delaunay tessellation profiles where the individual residue profile value is calculated as the sum of q factors for all simplices that share this vertex residue. Both threading functions have been implemented in structure-recognizes-sequence and sequence-recognizes-structure protocols for protein fold recognition. We find that both profile and total score based threading functions can distinguish both the native fold from incorrect folds for a sequence, and the native sequence from non-native sequences for a fold.

Amino Acid Sequence↗
PubMed2001

Genomics, complexity and drug discovery: insights from Boolean network models of cellular regulation.

The completion of the first draft of the human genome sequence has revived the old notion that there is no one-to-one mapping between genotype and phenotype. It is now becoming clear that to elucidate the fundamental principles that govern how genomic information translates into organismal complexity, we must overcome the current habit of ad hoc explanations and instead embrace novel, formal concepts that will involve computer modelling. Most modelling approaches aim at recreating a living system via computer simulation, by including as much details as possible. In contrast, the Boolean network model reviewed here represents an abstraction and a coarse-graining, such that it can serve as a simple, efficient tool for the extraction of the very basic design principles of molecular regulatory networks, without having to deal with all the biochemical details. We demonstrate here that such a discrete network model can help to examine how genome-wide molecular interactions generate the coherent, rule-like behaviour of a cell - the first level of integration in the multi-scale complexity of the living organism. Hereby the various cell fates, such as differentiation, proliferation and apoptosis, are treated as attractor states of the network. This modelling language allows us to integrate qualitative gene and protein interaction data to explain a series of hitherto non-intuitive cell behaviours. As the human genome project starts to reveal the limits of the current simplistic 'one gene - one function - one target' paradigm, the development of conceptual tools to increase our understanding of how the intricate interplay of genes gives rise to a global 'biological observable' will open a new perspective for post-genomic drug target discovery.

Animals↗
PubMed2006

Applying hybrid reasoning to mine for associative features in biological data.

We develop the means to mine for associative features in biological data. The hybrid reasoning schema for deterministic machine learning and its implementation via logic programming is presented. The methodology of mining for correlation between features is illustrated by the prediction tasks for protein secondary structure and phylogenetic profiles. The suggested methodology leads to a clearer approach to hierarchical classification of proteins and a novel way to represent evolutionary relationships. Comparative analysis of Jasmine and other statistical and deterministic systems (including Explanation-Based Learning and Inductive Logic Programming) are outlined. Advantages of using deterministic versus statistical data mining approaches for high-level exploration of correlation structure are analyzed.

Algorithms↗
PubMed2005

Application of latent semantic analysis to protein remote homology detection.

MOTIVATION: Remote homology detection between protein sequences is a central problem in computational biology. The discriminative method such as the support vector machine (SVM) is one of the most effective methods. Many of the SVM-based methods focus on finding useful representations of protein sequence, using either explicit feature vector representations or kernel functions. Such representations may suffer from the peaking phenomenon in many machine-learning methods because the features are usually very large and noise data may be introduced. Based on these observations, this research focuses on feature extraction and efficient representation of protein vectors for SVM protein classification. RESULTS: In this study, a latent semantic analysis (LSA) model, which is an efficient feature extraction technique from natural language processing, has been introduced in protein remote homology detection. Several basic building blocks of protein sequences have been investigated as the 'words' of 'protein sequence language', including N-grams, patterns and motifs. Each protein sequence is taken as a 'document' that is composed of bags-of-word. The word-document matrix is constructed first. The LSA is performed on the matrix to produce the latent semantic representation vectors of protein sequences, leading to noise-removal and smart description of protein sequences. The latent semantic representation vectors are then evaluated by SVM. The method is tested on the SCOP 1.53 database. The results show that the LSA model significantly improves the performance of remote homology detection in comparison with the basic formalisms. Furthermore, the performance of this method is comparable with that of the complex kernel methods such as SVM-LA and better than that of other sequence-based methods such as PSI-BLAST and SVM-pairwise.

Algorithms↗
PubMed1990

Excluded volume approximation to protein-solvent interaction. The solvent contact model.

Important properties of globular proteins, such as the stability of its folded state, depend sensitively on interactions with solvent molecules. Existing methods for estimating these interactions, such as the geometrical surface model, are either physically misleading or too time consuming to be applied routinely in energy calculations. As an alternative, we derive here a simple model for the interactions between protein atoms and solvent atoms in the first hydration layer, the solvent contact model, based on the conservation of the total number of atomic contacts, a consequence of the excluded-volume effect. The model has the conceptual advantage that protein-protein contacts and protein-solvent contacts are treated in the same language and the technical advantage that the solvent term becomes a particularly simple function of interatomic distances. The model allows rapid calculation of any physical property that depends only on the number and type of protein-solvent nearest-neighbor contacts. We propose use of the method in the calculation of protein solvation energies, conformational energy calculations, and molecular dynamics simulations.

Amino Acids↗
PubMed2006

Recent developments of the chemistry development kit (CDK) - an open-source java library for chemo- and bioinformatics.

The Chemistry Development Kit (CDK) provides methods for common tasks in molecular informatics, including 2D and 3D rendering of chemical structures, I/O routines, SMILES parsing and generation, ring searches, isomorphism checking, structure diagram generation, etc. Implemented in Java, it is used both for server-side computational services, possibly equipped with a web interface, as well as for applications and client-side applets. This article introduces the CDK's new QSAR capabilities and the recently introduced interface to statistical software.

Computational Biology↗
PubMed2006

Ruby-Helix: an implementation of helical image processing based on object-oriented scripting language.

Helical image analysis in combination with electron microscopy has been used to study three-dimensional structures of various biological filaments or tubes, such as microtubules, actin filaments, and bacterial flagella. A number of packages have been developed to carry out helical image analysis. Some biological specimens, however, have a symmetry break (seam) in their three-dimensional structure, even though their subunits are mostly arranged in a helical manner. We refer to these objects as "asymmetric helices". All the existing packages are designed for helically symmetric specimens, and do not allow analysis of asymmetric helical objects, such as microtubules with seams. Here, we describe Ruby-Helix, a new set of programs for the analysis of "helical" objects with or without a seam. Ruby-Helix is built on top of the Ruby programming language and is the first implementation of asymmetric helical reconstruction for practical image analysis. It also allows easier and semi-automated analysis, performing iterative unbending and accurate determination of the repeat length. As a result, Ruby-Helix enables us to analyze motor-microtubule complexes with higher throughput to higher resolution.

Algorithms↗
PubMed1996

Sequential and parallel molecular mechanics calculations.

This article describes a gradient algorithm for the computational optimization of model molecular structures, and discusses the various compromises inherent in the practical expression of the algorithm in a Fortran computer program (VULCAN) for both sequential and parallel computers. Details are given of some previously undiscussed properties of gradient algorithms; various acceleration techniques are compared; and some traps for the unwary are highlighted.

Algorithms↗