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 181 records · Page 10Linked to original sources
PubMed2003

Importing statistical measures into Artemis enhances gene identification in the Leishmania genome project.

BACKGROUND: Seattle Biomedical Research Institute (SBRI) as part of the Leishmania Genome Network (LGN) is sequencing chromosomes of the trypanosomatid protozoan species Leishmania major. At SBRI, chromosomal sequence is annotated using a combination of trained and untrained non-consensus gene-prediction algorithms with ARTEMIS, an annotation platform with rich and user-friendly interfaces. RESULTS: Here we describe a methodology used to import results from three different protein-coding gene-prediction algorithms (GLIMMER, TESTCODE and GENESCAN) into the ARTEMIS sequence viewer and annotation tool. Comparison of these methods, along with the CODONUSAGE algorithm built into ARTEMIS, shows the importance of combining methods to more accurately annotate the L. major genomic sequence. CONCLUSION: An improvised and powerful tool for gene prediction has been developed by importing data from widely-used algorithms into an existing annotation platform. This approach is especially fruitful in the Leishmania genome project where there is large proportion of novel genes requiring manual annotation.

Algorithms↗
PubMed1999

Visualisation and integration of G protein-coupled receptor related information help the modelling: description and applications of the Viseur program.

G Protein-Coupled Receptors (GPCRs) constitute a superfamily of receptors that forms an important therapeutic target. The number of known GPCR sequences and related information increases rapidly. For these reasons, we are developing the Viseur program to integrate the available information related to GPCRs. The Viseur program allows one to interactively visualise and/or modify the sequences, transmembrane areas, alignments, models and results of mutagenesis experiments in an integrated environment. This integration increases the ease of modelling GPCRs: visualisation and manipulation improvements enable easier databank interrogation and interpretation. Unique program features include: (i) automatic construction of 'Snake-like' diagrams or hyperlinked GPCR molecular models to HTML or VRML and (ii) automatic access to a mutagenesis data server through the Internet. The novel algorithms or methods involved are presented, followed by the overall complementary features of the program. Finally, we present two applications of the program: (i) an automatic construction of GPCR snake-like diagrams for the GPCRDB WWW server, and (ii) a preparation of the modelling of the 5HT receptor subtypes. The interest of the direct access to mutagenesis results through an alignment and a molecular model are discussed. The Viseur program, which runs on SGI workstations, is freely available and can be used for preparing the modelling of integral membrane proteins or as an alignment editor tool.

Algorithms↗
PubMed2026

HyLnc: a hybrid deep learning and feature-based approach for long non-coding RNA prediction.

Long non-coding RNAs (lncRNAs) play important roles in gene regulation, development and disease, yet accurate identification of lncRNAs from transcriptomic data remains a major computational challenge. Existing methods often rely either on handcrafted sequence features or deep learning approaches, each with their inherent limitations in capturing the full complexity of RNA sequences. In this study, we proposed HyLnc, a computational framework that integrates transformer-based contextual embeddings with biologically meaningful sequence features for improved lncRNA prediction. A custom BERT-based model was first pre-trained on a large corpus of metazoan RNA sequences using a masked language modelling strategy to learn contextual nucleotide dependencies. The model was subsequently fine-tuned on curated datasets of lncRNAs and protein-coding transcripts and 256-dimensional deep sequence embeddings were extracted. Parallelly, 348 handcrafted features, including ORF characteristics, untranslated region (UTR) properties, nucleotide composition and Fickett scores, were computed. A multi-stage feature selection strategy was applied to identify the most informative features, resulting in optimized hybrid feature sets. Multiple machine learning classifiers were evaluated, with the RF model achieving the best performance. The proposed framework attained an accuracy of 91.30%, F1-score of 91.23% and MCC of 82.60 on an independent validation dataset, outperforming several existing lncRNA prediction tools. Thus, HyLnc demonstrates that integrating deep contextual representations with biologically interpretable features enhances lncRNA prediction. This approach provides a robust and scalable solution for large-scale transcriptome annotation and can be extended to other sequence-based prediction.

RNA, Long Noncoding↗
PubMed2002

Finding relevant references to genes and proteins in Medline using a Bayesian approach.

MOTIVATION: Mining the biomedical literature for references to genes and proteins always involves a tradeoff between high precision with false negatives, and high recall with false positives. Having a reliable method for assessing the relevance of literature mining results is crucial to finding ways to balance precision and recall, and for subsequently building automated systems to analyze these results. We hypothesize that abstracts and titles that discuss the same gene or protein use similar words. To validate this hypothesis, we built a dictionary- and rule-based system to mine Medline for references to genes and proteins, and used a Bayesian metric for scoring the relevance of each reference assignment. RESULTS: We analyzed the entire set of Medline records from 1966 to late 2001, and scored each gene and protein reference using a Bayesian estimated probability (EP) based on word frequency in a training set of 137837 known assignments from 30594 articles to 36197 gene and protein symbols. Two test sets of 148 and 150 randomly chosen assignments, respectively, were hand-validated and categorized as either good or bad. The distributions of EP values, when plotted on a log-scale histogram, are shown to markedly differ between good and bad assignments. Using EP values, recall was 100% at 61% precision (EP=2 x 10(-5)), 63% at 88% precision (EP=0.008), and 10% at 100% precision (EP=0.1). These results show that Medline entries discussing the same gene or protein have similar word usage, and that our method of assessing this similarity using EP values is valid, and enables an EP cutoff value to be determined that accurately and reproducibly balances precision and recall, allowing automated analysis of literature mining results. .

Abstracting and Indexing↗
PubMed2005

Unbiased descriptor and parameter selection confirms the potential of proteochemometric modelling.

BACKGROUND: Proteochemometrics is a new methodology that allows prediction of protein function directly from real interaction measurement data without the need of 3D structure information. Several reported proteochemometric models of ligand-receptor interactions have already yielded significant insights into various forms of bio-molecular interactions. The proteochemometric models are multivariate regression models that predict binding affinity for a particular combination of features of the ligand and protein. Although proteochemometric models have already offered interesting results in various studies, no detailed statistical evaluation of their average predictive power has been performed. In particular, variable subset selection performed to date has always relied on using all available examples, a situation also encountered in microarray gene expression data analysis. RESULTS: A methodology for an unbiased evaluation of the predictive power of proteochemometric models was implemented and results from applying it to two of the largest proteochemometric data sets yet reported are presented. A double cross-validation loop procedure is used to estimate the expected performance of a given design method. The unbiased performance estimates (P2) obtained for the data sets that we consider confirm that properly designed single proteochemometric models have useful predictive power, but that a standard design based on cross validation may yield models with quite limited performance. The results also show that different commercial software packages employed for the design of proteochemometric models may yield very different and therefore misleading performance estimates. In addition, the differences in the models obtained in the double CV loop indicate that detailed chemical interpretation of a single proteochemometric model is uncertain when data sets are small. CONCLUSION: The double CV loop employed offer unbiased performance estimates about a given proteochemometric modelling procedure, making it possible to identify cases where the proteochemometric design does not result in useful predictive models. Chemical interpretations of single proteochemometric models are uncertain and should instead be based on all the models selected in the double CV loop employed here.

Algorithms↗
PubMed2004

Identification of related gene/protein names based on an HMM of name variations.

Gene and protein names follow few, if any, true naming conventions and are subject to great variation in different occurrences of the same name. This gives rise to two important problems in natural language processing. First, can one locate the names of genes or proteins in free text, and second, can one determine when two names denote the same gene or protein? The first of these problems is a special case of the problem of named entity recognition, while the second is a special case of the problem of automatic term recognition (ATR). We study the second problem, that of gene or protein name variation. Here we describe a system which, given a query gene or protein name, identifies related gene or protein names in a large list. The system is based on a dynamic programming algorithm for sequence alignment in which the mutation matrix is allowed to vary under the control of a fully trainable hidden Markov model.

Algorithms↗
PubMed1992

Grammatical model of the regulation of gene expression.

Based on a formal proof that justifies the search for generative grammars in the study of gene regulation, a linguistic formalization of an exhaustive data base of Escherichia coli sigma 70 promoters and their regulatory binding sites has been initiated. The grammar presented here generates all the arrays of the collection plus those that are predicted as consistent with the principles of regulation of sigma 70 promoters. "Systems of regulation," sets of regulatory sites that collaborate in a mechanism of regulation, are represented by means of syntactic categories. A small set of phrase structure rules restricted by an X-bar principle and by a hierarchical, c-command relation generates a representation of arrays of sites of regulation where the selection of the protein(s) identifying the system(s) of regulation occurs. Based on the features of the proteins, optional duplicated proximal and remote sites are generated by means of transformational rules. Consistency with the data, the predictions that the grammar generates, and important similarities and differences with some aspects of the generative theory of natural language are discussed.

Gene Expression Regulation, Bacterial↗
PubMed2004

Pathway logic modeling of protein functional domains in signal transduction.

Protein functional domains (PFDs) are consensus sequences within signaling molecules that recognize and assemble other signaling components into complexes. Here we describe the application of an approach called Pathway Logic to the symbolic modeling signal transduction networks at the level of PFDs. These models are developed using Maude, a symbolic language founded on rewriting logic. Models can be queried (analyzed) using the execution, search and model-checking tools of Maude. We show how signal transduction processes can be modeled using Maude at very different levels of abstraction involving either an overall state of a protein or its PFDs and their interactions. The key insight for the latter is our algebraic representation of binding interactions as a graph.

Computational Biology↗
PubMed2006

Evaluation of techniques for increasing recall in a dictionary approach to gene and protein name identification.

Gene and protein name identification in text requires a dictionary approach to relate synonyms to the same gene or protein, and to link names to external databases. However, existing dictionaries are incomplete. We investigate two complementary methods for automatic generation of a comprehensive dictionary: combination of information from existing gene and protein databases and rule-based generation of spelling variations. Both methods have been reported in literature before, but have hitherto not been combined and evaluated systematically. We combined gene and protein names from several existing databases of four different organisms. The combined dictionaries showed a substantial increase in recall on three different test sets, as compared to any single database. Application of 23 spelling variation rules to the combined dictionaries further increased recall. However, many rules appeared to have no effect and some appear to have a detrimental effect on precision.

Abstracting and Indexing↗
PubMed2005

Integration of the Gene Ontology into an object-oriented architecture.

BACKGROUND: To standardize gene product descriptions, a formal vocabulary defined as the Gene Ontology (GO) has been developed. GO terms have been categorized into biological processes, molecular functions, and cellular components. However, there is no single representation that integrates all the terms into one cohesive model. Furthermore, GO definitions have little information explaining the underlying architecture that forms these terms, such as the dynamic and static events occurring in a process. In contrast, object-oriented models have been developed to show dynamic and static events. A portion of the TGF-beta signaling pathway, which is involved in numerous cellular events including cancer, differentiation and development, was used to demonstrate the feasibility of integrating the Gene Ontology into an object-oriented model. RESULTS: Using object-oriented models we have captured the static and dynamic events that occur during a representative GO process, "transforming growth factor-beta (TGF-beta) receptor complex assembly" (GO:0007181). CONCLUSION: We demonstrate that the utility of GO terms can be enhanced by object-oriented technology, and that the GO terms can be integrated into an object-oriented model by serving as a basis for the generation of object functions and attributes.

Algorithms↗
PubMed2005

High-recall protein entity recognition using a dictionary.

SUMMARY: Protein name extraction is an important step in mining biological literature. We describe two new methods for this task: semiCRFs and dictionary HMMs. SemiCRFs are a recently-proposed extension to conditional random fields (CRFs) that enables more effective use of dictionary information as features. Dictionary HMMs are a technique in which a dictionary is converted to a large HMM that recognizes phrases from the dictionary, as well as variations of these phrases. Standard training methods for HMMs can be used to learn which variants should be recognized. We compared the performance of our new approaches with that of Maximum Entropy (MaxEnt) and normal CRFs on three datasets, and improvement was obtained for all four methods over the best published results for two of the datasets. CRFs and semiCRFs achieved the highest overall performance according to the widely-used F-measure, while the dictionary HMMs performed the best at finding entities that actually appear in the dictionary-the measure of most interest in our intended application. AVAILABILITY: Dictionary HMMs were implemented in Java. Algorithms are available through an information extraction package MINORTHIRD on http://minorthird.sourceforge.net

Algorithms↗
PubMed2005

SNPHunter: a bioinformatic software for single nucleotide polymorphism data acquisition and management.

BACKGROUND: Single nucleotide polymorphisms (SNPs) provide an important tool in pinpointing susceptibility genes for complex diseases and in unveiling human molecular evolution. Selection and retrieval of an optimal SNP set from publicly available databases have emerged as the foremost bottlenecks in designing large-scale linkage disequilibrium studies, particularly in case-control settings. RESULTS: We describe the architectural structure and implementations of a novel software program, SNPHunter, which allows for both ad hoc-mode and batch-mode SNP search, automatic SNP filtering, and retrieval of SNP data, including physical position, function class, flanking sequences at user-defined lengths, and heterozygosity from NCBI dbSNP. The SNP data extracted from dbSNP via SNPHunter can be exported and saved in plain text format for further down-stream analyses. As an illustration, we applied SNPHunter for selecting SNPs for 10 major candidate genes for type 2 diabetes, including CAPN10, FABP4, IL6, NOS3, PPARG, TNF, UCP2, CRP, ESR1, and AR. CONCLUSION: SNPHunter constitutes an efficient and user-friendly tool for SNP screening, selection, and acquisition. The executable and user's manual are available at http://www.hsph.harvard.edu/ppg/software.htm

Algorithms↗
PubMed2002

How to distinguish between the vacuum cleaner and flippase mechanisms of the lmrA multi-drug transporter in Lactococcus lactis.

A numerical model of the LmrA multi-drug transport system of Lactococcus lactis is used to explore the possibility of distinguishing experimentally between two putative transport mechanisms, i.e., the vacuum-cleaner and the flippase mechanisms. This comparative model also serves as an example of numerical simulation with the scripting language Python and its scientific add-on Scipy.

Bacterial Proteins↗
PubMed2025

Out-of-the-box bioinformatics capabilities of large language models (LLMs).

Large Language Models (LLMs), AI agents and co-scientists promise to accelerate scientific discovery across fields ranging from chemistry to biology. Bioinformatics- the analysis of DNA, RNA and protein sequences plays a crucial role in biological research and is especially amenable to AI-driven automation given its computational nature. Here, we assess the bioinformatics capabilities of three popular general-purpose LLMs on a set of tasks covering basic analytical questions that include code writing and multi-step reasoning in the domain. Utilizing questions from Rosalind, a bioinformatics educational platform, we compare the performance of the LLMs vs. humans on 104 questions undertaken by 110 to 68,760 individuals globally. GPT-3.5 provided correct answers for 59/104 (58%) questions, while Llama-3-70B and GPT-4o answered 49/104 (47%) correctly. GPT-3.5 was the best performing in most categories, followed by Llama-3-70B and then GPT-4o. 71% of the questions were correctly answered by at least one LLM. The best performing categories included DNA analysis, while the worst performing were sequence alignment/comparative genomics and genome assembly. Overall, LLMs performance mirrored that of humans with lower performance in tasks in which humans had low performance and vice versa. However, LLMs also failed in some instances where most humans were correct and, in a few cases, LLMs excelled where most humans failed. To the best of our knowledge, this presents the first assessment of general purpose LLMs on basic bioinformatics tasks in distinct areas relative to the performance of hundreds to thousands of humans. LLMs provide correct answers to several questions that require use of biological knowledge, reasoning, statistical analysis and computer code.

Journal Article↗
PubMed2005

[Study on the application for near-infrared spectroscopy quantitative analysis and selecting optimum wavelength by the MAXR regression procedure].

This paper introduces the principle and method with which the model about the quantitative analysis of Fourier transformation near infrared (NIR) spectroscopy by MAXR regression procedure can be established. In this way, the authors have selected the wave length information by Matlab language design programming in order to establish the quantitative analysis models with near infrared spectroscopy. Taking sixty-six wheat samples as experiment materials, quantitative analysis models to determine protein content are established with thirty-three samples. The relative coefficient are 0.977 1 and 0.976 5 respectively and the standard error are 0.335 and 0.340 between the predication result of the two models which include respectively two or three wave length information and Kjeldahl's value for the protein content of the another thirty-three wheat samples. When selecting the wave length information, the MAXR regression procedure can establish the optimum regression models which contain 1 or 2...or k wavelength information respectively. MAXR regression procedure is a useful method when selecting the optimum wavelength information because of its shorter computation time, and the method not only can carefully select the essential wavelength information to establish NIR spectroscopy quantitative analysis models of resisting multicollinearity information disturbance, but also to establish the work for selecting optimum wavelength information which can direct to design the special NIR analysis instrument for analyzing specific component in the special samples.

Algorithms↗
PubMed2005

ABNER: an open source tool for automatically tagging genes, proteins and other entity names in text.

ABNER (A Biomedical Named Entity Recognizer) is an open source software tool for molecular biology text mining. At its core is a machine learning system using conditional random fields with a variety of orthographic and contextual features. The latest version is 1.5, which has an intuitive graphical interface and includes two modules for tagging entities (e.g. protein and cell line) trained on standard corpora, for which performance is roughly state of the art. It also includes a Java application programming interface allowing users to incorporate ABNER into their own systems and train models on new corpora.

Algorithms↗
PubMed1996

Image library of biological macromolecules.

An Image Library of Biological Macromolecules is described, which contains image and text files related to structures of biological macromolecules. Currently, the Library has approximately 3000 image files of approximately 300 structures of biological macromolecules whose coordinates are available in the Protein Data Bank and in the Nucleic Acid Database. The entries include all RNA structures, approximately 70 DNA structures, 150 proteins and a few carbohydrates. The Library contains further images of amino acids, of standard and modified nucleotides and of nucleic acid model structures. Each entry consists of an annotation file with bibliographic and sequence information and possibly comments, of a color-coded distance plot and of structure images. Almost all of the images are available both in a mono and in a stereo representation. Standard procedures for generating these images were strictly avoided. Therefore, mixed rendering, coloring and labeling techniques were used extensively. Since May 1995 the Library has a growing division of images in the new Virtual Reality Modeling Language (VRML) format. The Image Library of Biological Macromolecules can be accessed via the World-Wide Web (http://www.imb-jena.de/IMAGE.html). There is a large number of structures determined by experimental and/or modeling techniques which are not intended to be included into the Protein Data Bank or Nucleic Acid Database for some reason. The Image Library could be a repository of these structures and of images of these and other structures of biological macromolecules including structures which are not known at atomic detail. Authors who are willing to make available images or coordinates to the scientific community via the Image Library of Biological Macromolecules are requested to contact the author.

Computer Communication Networks↗
PubMed2003

On the evolution of primitive genetic codes.

The primordial genetic code probably has been a drastically simplified ancestor of the canonical code that is used by contemporary cells. In order to understand how the present-day code came about we first need to explain how the language of the building plan can change without destroying the encoded information. In this work we introduce a minimal organism model that is based on biophysically reasonable descriptions of RNA and protein, namely secondary structure folding and knowledge based potentials. The evolution of a population of such organism under competition for a common resource is simulated explicitly at the level of individual replication events. Starting with very simple codes, and hence greatly reduced amino acid alphabets, we observe a diversification of the codes in most simulation runs. The driving force behind this effect is the possibility to produce fitter proteins when the repertoire of amino acids is enlarged.

Amino Acid Sequence↗