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 217 records · Page 12Linked to original sources
PubMed2001

Network dynamics and cell physiology.

Complex assemblies of interacting proteins carry out most of the interesting jobs in a cell, such as metabolism, DNA synthesis, movement and information processing. These physiological properties play out as a subtle molecular dance, choreographed by underlying regulatory networks. To understand this dance, a new breed of theoretical molecular biologists reproduces these networks in computers and in the mathematical language of dynamical systems.

CDC2 Protein Kinase↗
PubMed2006

PANTHER version 6: protein sequence and function evolution data with expanded representation of biological pathways.

PANTHER is a freely available, comprehensive software system for relating protein sequence evolution to the evolution of specific protein functions and biological roles. Since 2005, there have been three main improvements to PANTHER. First, the sequences used to create evolutionary trees are carefully selected to provide coverage of phylogenetic as well as functional information. Second, PANTHER is now a member of the InterPro Consortium, and the PANTHER hidden markov Models (HMMs) are distributed as part of InterProScan. Third, we have dramatically expanded the number of pathways associated with subfamilies in PANTHER. Pathways provide a detailed, structured representation of protein function in the context of biological reaction networks. PANTHER pathways were generated using the emerging Systems Biology Markup Language (SBML) standard using pathway network editing software called CellDesigner. The pathway collection currently contains approximately 1500 reactions in 130 pathways, curated by expert biologists with authorship attribution. The curation environment is designed to be easy to use, and the number of pathways is growing steadily. Because the reaction participants are linked to subfamilies and corresponding HMMs, reactions can be inferred across numerous different organisms. The HMMs can be downloaded by FTP, and tools for analyzing data in the context of pathways and function ontologies are available at http://www.pantherdb.org.

Animals↗
PubMed1998

3DinSight: an integrated relational database and search tool for the structure, function and properties of biomolecules.

MOTIVATION: Although a large amount of information on the structure, function and properties of biomolecules is becoming available, it is difficult to understand the relationship between them. Thus, we have attempted to create an integrated relational database, search and visualization tool, 3DinSight, to help researchers to gain insight into their relationship. RESULTS: We have gathered data on the structure, function and properties of biomolecules, and implemented them into a relational database system. The structural data contain several subset data such as protein homologues, protein-DNA complex, in order to enable searching within a specific class of data. The functional data include motif sequence and mutation data of proteins. Also, various amino acid properties are implemented as a relational table. The World Wide Web (WWW) interfaces enable users to carry out various kinds of searches among these data. The locations of motif sequences and mutations are automatically mapped on the structure, and visualized in three-dimensional (3D) space by interactive viewers, VRML (Virtual Reality Modeling Language) and RasMol. In the case of VRML, the mapped 3D objects are hyper-linked to the corresponding document data. Also, amino acid properties, linked with structure, functional and mutation sites, can be displayed as graph plots. AVAILABILITY: 3DinSight is freely accessible through the Internet (http://www.rtc.riken.go.jp/3DinSight.h tml). CONTACT: sarai@rtc.riken.go.jp

Computer Communication Networks↗
PubMed1986

Turn prediction in proteins using a pattern-matching approach.

We extend the use of amino acid sequence patterns [Cohen, F.E., Abarbanel, R. M., Kuntz, I. D., & Fletterick, R. J. (1983) Biochemistry 22, 4894-4904] to the identification of turns in globular proteins. The approach uses a conservative strategy, combined with a hierarchical search (strongest patterns first) and length-dependent masking, to achieve high accuracy (95%) on a test set of proteins of known structure. Applying the same procedure to homologous families gives a 90% success rate. Straightforward changes are suggested to improve the predictive power. The computer program, written in Lisp, provides a general pattern-recognition language well suited for a number of investigations of protein and nucleic acid sequences.

Amino Acid Sequence↗
PubMed2004

Enhancement to the RANKPEP resource for the prediction of peptide binding to MHC molecules using profiles.

We introduced previously an on-line resource, RANKPEP that uses position specific scoring matrices (PSSMs) or profiles for the prediction of peptide-MHC class I (MHCI) binding as a basis for CD8 T-cell epitope identification. Here, using PSSMs that are structurally consistent with the binding mode of MHC class II (MHCII) ligands, we have extended RANKPEP to prediction of peptide-MHCII binding and anticipation of CD4 T-cell epitopes. Currently, 88 and 50 different MHCI and MHCII molecules, respectively, can be targeted for peptide binding predictions in RANKPEP. Because appropriate processing of antigenic peptides must occur prior to major histocompatibility complex (MHC) binding, cleavage site prediction methods are important adjuncts for T-cell epitope discovery. Given that the C-terminus of most MHCI-restricted epitopes results from proteasomal cleavage, we have modeled the cleavage site from known MHCI-restricted epitopes using statistical language models. The RANKPEP server now determines whether the C-terminus of any predicted MHCI ligand may result from such proteasomal cleavage. Also implemented is a variability masking function. This feature focuses prediction on conserved rather than highly variable protein segments encoded by infectious genomes, thereby offering identification of invariant T-cell epitopes to thwart mutation as an immune evasion mechanism.

Algorithms↗
PubMed2025

Target and biomarker exploration portal for drug discovery.

MOTIVATION: The discovery of novel drug targets and precision biomarkers remains a major challenge in drug development, with traditional differential expression analysis often overlooking key regulatory proteins. Here, we present a novel, web-based bioinformatics tool, the Target and Biomarker Exploration Portal (TBEP), designed to accelerate the drug discovery process by integrating large-scale biomedical data with network analysis techniques. RESULTS: TBEP harnesses machine-learning approaches to mine and combine multimodal datasets, including human genetics, functional genomics, and protein-protein interaction networks, to decode causal disease mechanisms and uncover novel therapeutic targets and precision biomarkers for specific phenotypes. A unique feature of the tool is its ability to process large-scale data in real-time, facilitated by an efficient cloud-based architecture. Additionally, the tool incorporates an integrated large language model (LLM), which assists researchers in exploring and interpreting complex biological relationships within the generated networks and multi-omics data using natural language (English). By offering an intuitive, interactive interface, the LLM enhances the exploration of biological insights, making it easier for scientists to derive actionable conclusions. This powerful integration of network analysis, multi-omics data, and LLM provides a robust framework for accelerating the identification of novel drug targets. AVAILABILITY AND IMPLEMENTATION: The tool is publicly available at https://tbep.missouri.edu. The source code, documentation and installation instructions are available at GitHub repository: https://github.com/mizzoudbl/tbep.

Drug Discovery↗
PubMed2006

Depicting combinatorial complexity with the molecular interaction map notation.

To help us understand how bioregulatory networks operate, we need a standard notation for diagrams analogous to electronic circuit diagrams. Such diagrams must surmount the difficulties posed by complex patterns of protein modifications and multiprotein complexes. To meet that challenge, we have designed the molecular interaction map (MIM) notation (http://discover.nci.nih.gov/mim/). Here we show the advantages of the MIM notation for three important types of diagrams: (1) explicit diagrams that define specific pathway models for computer simulation; (2) heuristic maps that organize the available information about molecular interactions and encompass the possible processes or pathways; and (3) diagrams of combinatorially complex models. We focus on signaling from the epidermal growth factor receptor family (EGFR, ErbB), a network that reflects the major challenges of representing in a compact manner the combinatorial complexity of multimolecular complexes. By comparing MIMs with other diagrams of this network that have recently been published, we show the utility of the MIM notation. These comparisons may help cell and systems biologists adopt a graphical language that is unambiguous and generally understood.

Combinatorial Chemistry Techniques↗
PubMed2006

Continuous photobleaching in vesicles and living cells: a measure of diffusion and compartmentation.

We present a comprehensive and analytical treatment of continuous photobleaching in a compartment, under single photon excitation. In the very short time regime (t<0.1 ms), the diffusion does not play any role. After a transition (or short time regime), one enters in the long time regime (t>0.1-5 s), for which the diffusion and the photobleaching balance each other. In this long time regime, the diffusion is either fast (i.e., the photobleaching probability of a molecule diffusing through the laser beam is low) so that the photobleaching rate is independent of the diffusion constant and dependent only of the laser power, or the diffusion is slow (i.e., the photobleaching probability is high) and the photobleaching rate is mainly dependent on the diffusion constant. We illustrate our theory by using giant unilamellar vesicles ranging from approximately 10 to 100 microm in diameter, loaded with molecules of various diffusion constants (from 20 to 300 microm2/s) and various photobleaching cross sections, illuminated under laser powers between 3 and 100 microW. We also demonstrated that information about compartmentation can be obtained by this method in living cells expressing enhanced green fluorescent proteins or that were loaded with small FITC-dextrans. Our quantitative approach shows that molecules freely diffusing in a cellular compartment do experience a continuous photobleaching. We provide a generic theoretical framework that should be taken into account when studying, under confocal microscopy, molecular interactions, permeability, etc.

Biophysics↗
PubMedDate not supplied

Presentation of the SIGMA software: Software of Imagery and Graphics for Molecular Architecture.

Sigma (Software of Imagery and Graphics for Molecular Architecture) is a software package designed for visualization and exploration of three-dimensional (3D) molecular electron microscopy data. It comprises a text and two graphic modes. In the text mode, a language allows the writing of scripts for repetitive tasks. The two graphic modes are based on the multiwindow environment with a mouse as pointer. The first graphic mode is dedicated to vectorial objects and the second to pixel/voxel objects. The data imported by SIGMA have various origins such as 3D reconstruction volumes, Protein Data Bank data, or geometrical objects like spheres, cubes, or cylinders. These 3D objects are interactively rotated, translated, and rendered with SIGMA. This software, written in C language, runs on Silicon Graphics workstations using the X-Window plus Motif environment. The specific 3D routines are based on the Silicon Graphics GL library.

Animals↗
PubMed2000

Knowledge, skills, and behavior improvements on peer educators and low-income Hispanic participants after a stage of change-based bilingual nutrition education program.

A nutrition education program, entitled La Cocina Saludable, was designed according to the Stage of Change Model and implemented in ten southern Colorado counties. The objectives were to improve the nutrition related knowledge, skills, and behaviors that lead to healthy lifestyles in a low-income Hispanic population. The content of the program included nutrition information designed to help mothers of preschool children provide for their children's nutritional needs. Previous studies suggest that low-income Hispanics often demonstrate low intakes of vitamins A and C, calcium, iron, and protein, and high rates of diabetes, obesity, and infections. Additionally, this population presents many obstacles for nutrition educators including limited resources, child care, transportation, time, language, culture, literacy, health beliefs, and, in some cases, the transient nature of the population. The program attempted to overcome these barriers by incorporating a flexible program format carried out by abuela (Hispanic grandmother) educators using the processes described in the Stage of Change Model. The program was evaluated using a knowledge, skills and behavior pre-test, post-test, and six-month follow-up survey on both the abuela educators as well as the actual class participants. Results of the peer education training sessions suggest that this type of training program can be effective in increasing the knowledge, skills, and behavior of peer educators as well as reduce need for retraining for educators who continuously teach classes. Additionally, the results suggest that this type of program can be effective in changing selected nutrition related knowledge, skills, and behaviors leading to healthy lifestyles for low-income Hispanic mothers of preschool children.

Adult↗
PubMed2026

CLASPP: A unified model for predicting post-translational modifications.

Post-Translational Modifications (PTMs) are a fundamental mechanism for regulating cellular pathways and increasing the functional diversity of the proteome. Accurately predicting the PTM types that are likely to occur at a given site in the primary sequence is a key challenge in functional proteomics. Existing PTM prediction models predominantly focus on either single PTM types or employ ensemble methods that combine multiple models to predict different PTM types. This fragmentation is largely driven by the vast imbalance in data availability across PTM types, making it difficult to predict multiple PTM types with a single model. To address this limitation, we present the Contrastively Learned Attention-based Stratified PTM Predictor (CLASPP), a unified PTM prediction model. CLASPP addresses imbalance challenges by leveraging unsupervised clustering-based undersampling and a novel contrastive learning framework tailored to PTM data. Additionally, our hierarchical data organization and curation are shown to improve CLASPP's performance by balancing the representation of individual PTM types and provides a standardized dataset to train and validate future model designs. Drawing inspiration from advancements in image and natural language processing, the CLASPP model employs a multi-stage training strategy and a high-quality, curated training dataset to improve PTM prediction performance. To uncover what is learned during the contrastive learning stage, the CLASPP model is shown to distinguish known protein kinase substrate specificity profiles as a form of explainability. Finally, we evaluate the application of CLASPP in predicting PTMs in different model organisms and experimentally validated ubiquitination sites in the understudied DCLK3 kinase. Overall, CLASPP represents a unified model for PTM prediction that addresses key bottlenecks in data imbalance and offers new strategies for biological data curation, thereby improving PTM-type prediction performance across diverse organisms.

Protein Processing, Post-Translational↗
PubMed2004

Pathway databases.

Network representations of biological pathways offer a functional view of molecular biology that is different from and complementary to sequence, expression, and structure databases. There is currently available a wide range of digital collections of pathway data, differing in organisms included, functional area covered (e.g., metabolism vs. signaling), detail of modeling, and support for dynamic pathway construction. While it is currently impossible for these databases to communicate with each other, there are several efforts at standardizing a data exchange language for pathway data. Databases that represent pathway data at the level of individual interactions make it possible to combine data from different predefined pathways and to query by network connectivity. Computable representations of pathways provide a basis for various analyses, including detection of broad network patterns, comparison with mRNA or protein abundance, and simulation.

Computational Biology↗
PubMed2003

Prediction of polypeptide fragments exposed to the solvent.

A method is presented to predict those polypeptide segments within a globular protein that are more likely to be exposed to the solvent. The protein amino acidic sequence is the only information needed by this new algorithm. It uses a consensus hydrophobicity scale, derived from 28 known scales, and it is based on the comparison between the average hydrophobicity of a polypeptide fragment and the average hydrophobicity expected for a segment containing the same number of residues. The latter values are pre-computed from a non-redundant set of single chain protein structural domains. The comparison between the two average values results in a t value that readily provides the prediction with a statistical significance. A jack-knife validation analysis indicates that the protein segment predicted to be the most solvent exposed is actually solvent exposed and amongst the fragments that are most exposed. The source of a stand-alone program, written in C language, that allows the prediction of the most likely solvent exposed segment in a globular protein is available from the author.

Algorithms↗
PubMed2004

CEBS object model for systems biology data, SysBio-OM.

MOTIVATION: To promote a systems biology approach to understanding the biological effects of environmental stressors, the Chemical Effects in Biological Systems (CEBS) knowledge base is being developed to house data from multiple complex data streams in a systems friendly manner that will accommodate extensive querying from users. Unified data representation via a single object model will greatly aid in integrating data storage and management, and facilitate reuse of software to analyze and display data resulting from diverse differential expression or differential profile technologies. Data streams include, but are not limited to, gene expression analysis (transcriptomics), protein expression and protein-protein interaction analysis (proteomics) and changes in low molecular weight metabolite levels (metabolomics). RESULTS: To enable the integration of microarray gene expression, proteomics and metabolomics data in the CEBS system, we designed an object model, Systems Biology Object Model (SysBio-OM). The model is comprehensive and leverages other open source efforts, namely the MicroArray Gene Expression Object Model (MAGE-OM) and the Proteomics Experiment Data Repository (PEDRo) object model. SysBio-OM is designed by extending MAGE-OM to represent protein expression data elements (including those from PEDRo), protein-protein interaction and metabolomics data. SysBio-OM promotes the standardization of data representation and data quality by facilitating the capture of the minimum annotation required for an experiment. Such standardization refines the accuracy of data mining and interpretation. The open source SysBio-OM model, which can be implemented on varied computing platforms is presented here. AVAILABILITY: A universal modeling language depiction of the entire SysBio-OM is available at http://cebs.niehs.nih.gov/SysBioOM/. The Rational Rose object model package is distributed under an open source license that permits unrestricted academic and commercial use and is available at http://cebs.niehs.nih.gov/cebsdownloads. The database and interface are being built to implement the model and will be available for public use at http://cebs.niehs.nih.gov.

Database Management Systems↗
PubMed2004

An efficient algorithm for detecting frequent subgraphs in biological networks.

MOTIVATION: With rapidly increasing amount of network and interaction data in molecular biology, the problem of effectively analyzing this data is an important one. Graph theoretic formalisms, commonly used for these analysis tasks, often lead to computationally hard problems due to their relation with subgraph isomorphism. RESULTS: This paper presents an innovative new algorithm for detecting frequently occurring patterns and modules in biological networks. Using an innovative graph simplification technique, which is ideally suited to biological networks, our algorithm renders these problems computationally tractable. Indeed, we show experimentally that our algorithm can extract frequently occurring patterns in metabolic pathways extracted from the KEGG database within seconds. The proposed model and algorithm are applicable to a variety of biological networks either directly or with minor modifications. AVAILABILITY: Implementation of the proposed algorithms in the C programming language is available as open source at http://www.cs.purdue.edu/homes/koyuturk/pathway/

Algorithms↗
PubMed1994

[Study of physiological functions of human ceruloplasmin. The effect of ceruloplasmin on immunocytes in a normal state and in pathology].

The immunomodulating effect of ceruloplasmin (CP) on the major components of the immunocompetent system of the organism--the natural resistance system and the specific immune response--has been established. CP can exert various influences on the level of expression of specific markers of T- and B-lymphocytes (as determined by various modifications of the rosette-forming test), on the phagocytic activity of neutrophils and monocytes as well as on the activity of "respiratory burst" enzymes. CP modulation was found to depend predominantly on the initial level of the immunological parameters to be determined, i. e., on the extent of immune inflammation in human patients. Thus, it was found that CP not only plays the roles of an antioxidant and a copper-transporting protein, but is also capable to interact with immunocytes, altering their biological activities. The observed immunotropicity of CP, its ability to directly interact with immunocytes and to model the immune function at the cell level provides evidence for the existence of a universal molecular language of information exchange between the macroorganism cells of various nature and origin.

Adolescent↗
PubMed2004

MolTalk--a programming library for protein structures and structure analysis.

BACKGROUND: Two of the mostly unsolved but increasingly urgent problems for modern biologists are a) to quickly and easily analyse protein structures and b) to comprehensively mine the wealth of information, which is distributed along with the 3D co-ordinates by the Protein Data Bank (PDB). Tools which address this issue need to be highly flexible and powerful but at the same time must be freely available and easy to learn. RESULTS: We present MolTalk, an elaborate programming language, which consists of the programming library libmoltalk implemented in Objective-C and the Smalltalk-based interpreter MolTalk. MolTalk combines the advantages of an easy to learn and programmable procedural scripting with the flexibility and power of a full programming language. An overview of currently available applications of MolTalk is given and with PDBChainSaw one such application is described in more detail. PDBChainSaw is a MolTalk-based parser and information extraction utility of PDB files. Weekly updates of the PDB are synchronised with PDBChainSaw and are available for free download from the MolTalk project page http://www.moltalk.org following the link to PDBChainSaw. For each chain in a protein structure, PDBChainSaw extracts the sequence from its co-ordinates and provides additional information from the PDB-file header section, such as scientific organism, compound name, and EC code. CONCLUSION: MolTalk provides a rich set of methods to analyse and even modify experimentally determined or modelled protein structures. These methods vary in complexity and are thus suitable for beginners and advanced programmers alike. We envision MolTalk to be most valuable in the following applications:1) To analyse protein structures repetitively in large-scale, i.e. to benchmark protein structure prediction methods or to evaluate structural models. The quality of the resulting 3D-models can be assessed by e.g. calculating a Ramachandran-Sasisekharan plot.2) To quickly retrieve information for (a limited number of) macro-molecular structures, i.e. H-bonds, salt bridges, contacts between amino acids and ligands or at the interface between two chains.3) To programme more complex structural bioinformatics software and to implement demanding algorithms through its portability to Objective-C, e.g. iMolTalk.4) To be used as a front end to databases, e.g. PDBChainSaw.

Artificial Intelligence↗
PubMed1997

A model for the mechanism of polymerase translocation.

A general mechanism for polymerase translocation is elaborated. The central feature of this mechanism is that a rapid translocational equilibrium is established after each cycle of nucleoside monophosphate incorporation such that the polymerase distributes itself by diffusional sliding between all accessible positions on the template with relative occupancy determined by relative free energy. While alternative models for translocation have not been fully developed, much of the language currently used to describe this step suggests an active mechanism coupled to conformational transitions in the polymerase. For example, a recent study of force generation by Escherichia coli RNA polymerase during transcription suggests that it is a mechanoenzyme analogous to kinesin of myosin motor proteins. While the proposed mechanism does not rule out conformational transitions during polymerase translocation, it suggests that they may be unnecessary and that translocation can be explained in terms of the affinity of the active site for nucleoside triphosphate and the relative free energies of the polymerase bound at different positions on the template. This mechanism makes specific predictions which are borne out experimentally with polymerases as distinct as E. coli DNAP I, phage T7 RNAP, and E. coli RNAP.

Bacteriophage T7↗