Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “Computational prediction”

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 19 recordsLinked to original sources
PubMed2026

Computational prediction of a multi-epitope Human Metapneumovirus vaccine candidate through integrated reverse vaccinology and pan-genomic approaches.

Human metapneumovirus (HMPV) is a primary cause of global respiratory infections yet no approved vaccine currently exists. This study computationally predicts a multi-epitope vaccine candidate using a diverse dataset of 65 HMPV sequences spanning five continents. Following the screening of lead proteins for antigenicity and virulence, fifteen highly conserved MHC-I, MHC-II and B-cell epitopes were prioritized. These were integrated with a putative L7/L12 adjuvant using optimized AAY, GPGPG, and KK linkers to design three constructs (HMPV_V1-V3). Structural validation identified HMPV-V2 as the lead candidate that exhibits a Z-score of-5.24 and 87.7% of residues in favored Ramachandran regions indicating excellent stereochemical quality and structural stability. In silico docking indicated a strong predicted binding affinity between HMPV-V2 and the TLR4 receptor (energy: -969.2). Immune simulations predicted a robust adaptive response characterized by high IgG1 titers, memory B-cell maturation, and a Th1-dominant cytokine profile. Furthermore, molecular dynamics simulations suggested exceptional structural integrity for HMPV-V2, maintaining a low RMSD of 8.213 and RMSF of 0.737 throughout the simulation. Optimized in silico cloning into the pET28a (+) vector indicated a high potential for protein expression in E. coli systems. While these findings provide a theoretically grounded blueprint for vaccine development, this study is entirely computational and lacks experimental validation. Further in vitro and in vivo testing is required to confirm the actual safety and immunogenicity of the proposed candidate.

Metapneumovirus↗
PubMed1978

Computer prediction of left ventricular complicance throughout diastole in normal patients.

This study deals with the development of a computer program to predict instantaneous left ventricular complicance, as defined by the tangent modulus E, throughout diastole. Diastole is divided into discrete time intervals according to the major events which occur: the start of isovolumic relaxation (aortic valve closure), mitral valve opening, the point of minimum left ventricular pressure, the junction of the rapid and slow filling phases, the start of atrial systole, and the peak of the 'a' wave. Each interval is separated into subintervals. Over each subinterval two mechanisms are assumed to operate: myocardial relaxation or contraction producing a pressure change without an accompanying volume change, followed by explansion of the left ventricle at constant pressure. Although these mechanisms occur simultaneously in the intact heart, they are treated sequentially in a multistage computer program that employs the finite element technique to determine the displacements within a thick-walled ellipsoidal shell. The smaller the time interval between successive stages, the closer is the approximation to the actual continous process of myocardial relaxation, contraction, and distension. Diastolic determinants revealed in this investigation are the mechanical properties of the myocardium, the state variables of pressure and volume, and the control variables of wall thickness and cavity size. In isovolumic relaxation, the myocardium relaxes and the ventricular wall thickens to reduce intracavitary pressure. The relaxation process continues and intraventricular pressure falls to a minimum (0-point) while ventricular volume increases after mitral valve opening. In the succeeding phases, excluding atrial systole, ventricular filling pursues, the properties of the myocardium change, there is an increase in tone (possibly due to myocardial contraction), the wall thins and intraventricular pressure rises. Computer prediction shows that at the start of diastole the tangent modulus is approximately 6 times the enddiastolic value, and is nearly 0 at the onset of the slow filling phase. Tangant modulus is a useful index by which to distinguish normal from abnormal patients provided the characteristics of E as a function of time are recognized and compared throughout diastole.

Compliance↗
PubMed2026

Multimodal alignment improves generalizability of genomic biomarker prediction in computational pathology.

Computational pathology models that use digitized histopathology whole-slide images have the potential to become a cost-effective and scalable alternative to molecular assays for the prediction of genomic biomarkers, a key task in precision oncology. However, as new genomic biomarkers are discovered or quantified, large, labeled datasets must be prospectively collected to train new models. To address this challenge, we developed multimodal alignment for biomarker learning and generalization (MARBLE), a multimodal contrastive pretraining strategy that integrates structured biomarker knowledge into representation learning of histopathology images. MARBLE aligns histopathology-derived representations with representations of genomic biomarkers generated by a large language model (LLM) and a protein language model (PLM). This biologically informed alignment enables data-efficient generalization to novel, out-of-distribution biomarkers. Using the MSK-IMPACT cohort of over 40,000 patients across multiple biomarker panel versions, we design experiments grounded in real-world data to demonstrate the value of our proposed approach.

CP: computational biology↗
PubMed1977

Computer-aided prediction of gangrenous and perforating appendicitis.

The clinical details of 100 patients with proved acute appendicitis were compared with those of 100 patients with perforating or gangrenous appendicitis. Twenty features were found to be significantly different between the two groups. This information was incorporated into a computer data base and used in the differential diagnosis of abdominal pain. A program written to predict the probability that gangrene or perforation was present in patients with appendicitis gave a diagnostic accuracy over 91%. A clinical scoring index, which accurately predicted the state of the appendix in 88% of patients, was constructed from the significant differences between the two groups. When clinical scoring or computer analysis predicts a high probability of perforation or gangrene in patients with appendicitis, surgery should be performed without delay.

Acute Disease↗
PubMed1976

A symptomatic discriminant to identify recurrent ulcer in patients with dysperpsia after gastric surgery.

A questionnaire has been completed by 99 patients referred for investigation of symptoms after gastric operations. The replies were analysed in an attempt to distinguish patients with a recurrent peptic ulcer from those with no recurrent ulcer. All cases were investigated by barium meal, endoscopy, and oral cholecystography. All recurrent ulcers were confirmed by reoperation and patients with gastric carcinoma, gallstones, or symptomatic hiatus hernia were excluded. The study was retrospective in 40 patients in whom the diagnosis was already confirmed when the questionnaire was analysed and prospective in 59 in whom the diagnosis was originally unknown. The replies were analysed with (a) a small computer using Bayes' theorem, (b) weighted tables, and (c) a discriminant analysis. The computer prediction of the prospective data was 85% accurate. The results of simpler methods were almost as good as the computer prediction, and questions related only to the severity of pain and vomiting accurately distinguished recurrent ulcer from other causes of dyspepsia in 81% of patients.

Diagnosis, Computer-Assisted↗
PubMed1979

[Use of a computer to predict the development of vertebrogenic lumbosacral radiculitis].

On the basis of a linear discriminant analysis, a special system of automatized prognosis and early diagnosis of vertebrogenic lumbosacral radiculitis was elaborated with the aid of a computer. The system permits to elucidate among the population examined a group of individuals with high risk of the disease. The information file for computer processing included data of the studies on 24 risk factors in 350 patients and 450 individuals in the control group. The prognostical value of different risk-factors is discussed. The results of the system trial in industrial conditions are given.

Diagnosis, Computer-Assisted↗
PubMed1975

Pattern recognitiion and structure-activity relationship studies. Computer-assisted prediction of antitumor activity in structurally diverse drugs in an experimental mouse brain tumor system.

This paper reports the application of pattern recognition and substructural analysis to the problem of predicting the antineoplastic activity of 24 test compounds in an experimental mouse brain tumor system based on 138 structurally diverse compounds tested in this tumor system. The molecules were represented by three types of substructural fragments, the augmented atom, the heteropath, and the ring fragments. Of the two pattern recognition methods used to predict the activity of the test compounds the nearest neighbor method predicted 83% correctly while the learning machine method predicted 92% correctly. The test structures and the important substructural fragments used in this study are given and the implications of these results are discussed.

Animals↗
PubMed1979

Prediction of beta-turns.

An automated computer prediction of the chain reversal regions of globular proteins is described herein using bend frequencies and beta-turn conformational parameters (Pt) determined from 408 beta-turns in 29 proteins calculated from x-ray atomic coordinates. The probability of bend occurrence at residue i is pt = fi X fi+1 X fi+2 X fi+3 with the average bend probability less than Pt greater than = 0.55 X 10(-4). Tetrapeptides with pt greater than 0.75 X 10(-4) ( approximately to 1.5 X less than pt greater than) as well as less than Pt greater than 1.00 and less than Pa greater than less than less than Pt greater than greater than less than P beta greater than are selected by the computer as probable bends. Adjacent probable bends (i.e., 11-14, 12-15, 13-16) are compared pairwise by the computer, and the tetrapeptide with the higher pt value is predicted as a beta-turn. The percentage of bend and nonbend residues predicted correctly for 29 proteins by this computer algorithm is %t+nt = 70%, whereas 78% of the beta-turns were localized correctly within +/- 2 residues. The average beta-turn content in the 29 proteins is 32%, with helical proteins having fewer bends (17%) than beta-sheet proteins (41%). Three proteins having iron-sulfur clusters were found with the highest percentages of beta-turns: Chromatium high potential iron protein (65%), ferredoxin (57%), and rubredoxin (65%). Finally, the bend frequencies at all 12 positions from 457 beta-turns in 29 proteins (Chou and Fasman, 1977) were used to test the effectiveness of predicting bends using 2, 4, 8, and 12 residues as well as different cut-off pt values. The computer analysis showed that 1.25 less than pt greater than to be the best cut-off yielding 70% accuracy in %t+nt for 4 residues and %t+nt = 73% for 12 residues in predicting the bend and nonbend regions of proteins.

Amino Acid Sequence↗
PubMed2026

AI-integrated digital breeding for crop improvement.

Crop breeding increasingly depends on the effective integration and interpretation of large, heterogeneous datasets spanning genomic, phenotypic, multi-omics, and environmental layers. Conventional breeding approaches are often insufficient to capture the complex relationships among these data or to support timely selection decisions. Digital breeding can help address this limitation by complementing field experimentation, mixed models, and genomic prediction with the integration of biological data and computational prediction throughout the breeding process. In particular, the rapid advancement of artificial intelligence (AI) has improved the analysis of high-dimensional datasets and broadened its application to trait prediction, selection, and breeding design. Here, we review recent developments in AI-enabled digital breeding, encompassing genomic, phenomic, and multi-omics data generation and analysis, predictive modeling, explainable and generative AI, and data-driven breeding decision support. We further discuss emerging AI applications, their current contributions to crop research and breeding, and the major considerations affecting their reliable and practical implementation. Collectively, this review provides a structured understanding of the roles of AI across the digital breeding process and offers guidance for future methodological development and practical application in crop improvement.

artificial intelligence↗
PubMed1977

Computer densitometry for angiographic assessment of arterial cholesterol content and gross pathology in human atherosclerosis.

Sequential change studies in human atherosclerosis are desirable in disease regression trials but are now limited by dependence on the occurrence of epidemiologic end-points. Prior radiographic studies have pertained to advanced obstructive atherosclerosis. This is a study of measures applied by computer-generated densitometry of angiograms to assess early to advanced nonobstructive atherosclerosis. Measures are based on pathologic and angiographic appearance of all stages of atherosclerosis and include image edge roughness, local width, and local contrast density changes. Femoral angiograms were made in 21 cadavers under simulated clinical conditions, with a pressurized radiopaque casting material. Full-size color photographs were made of 10 cm. segments of opened artery, with matching cast and arterial specimens analyzed for cholesterol content. Four graders, on two occasions, sequenced the photographs in increasing order of disease on the basis of the International Atherosclerosis Grading scheme. The correlation between the two sessions was 0.93. Thirteen computer indices correlated significantly with visual grade and cholesterol and were allowed to compete in a step-wise regression for best indices of prediction. Computer index correlation coefficient for visual grade prediction was 0.86, and for cholesterol content, 0.84. Computer densitometry measurement appears useful in the evaluation of all stages of atherosclerosis as recorded angiographically and obviates the necessity for exacting visual comparisons of large numbers of films.

Angiography↗
PubMed1978

Pharmacokinetics of antimalarials and proposals for dosage regimens.

Blood level data for the antimalarials amodiaquine, chloroguanide, chloroquine, pyrimethamine, quinine and sulphadoxine have been retrieved from the literature and pharmacokinetically analyzed. Minimum, average and maximum blood level concentrations at steady state in suppressive treatment and peak concentrations in therapeutic treatment were predicted and blood level-time curves simulated. Based on the computer-predicted data, changes in dosage regimens are proposed to reduce the fluctuations between maximum and minimum levels in suppressive treatment, and for obtaining maximum peak levels in therapeutic treatment already with the loading dose.

Antimalarials↗
PubMed2024

PredIL13: Stacking a variety of machine and deep learning methods with ESM-2 language model for identifying IL13-inducing peptides.

Interleukin (IL)-13 has emerged as one of the recently identified cytokine. Since IL-13 causes the severity of COVID-19 and alters crucial biological processes, it is urgent to explore novel molecules or peptides capable of including IL-13. Computational prediction has received attention as a complementary method to in-vivo and in-vitro experimental identification of IL-13 inducing peptides, because experimental identification is time-consuming, laborious, and expensive. A few computational tools have been presented, including the IL13Pred and iIL13Pred. To increase prediction capability, we have developed PredIL13, a cutting-edge ensemble learning method with the latest ESM-2 protein language model. This method stacked the probability scores outputted by 168 single-feature machine/deep learning models, and then trained a logistic regression-based meta-classifier with the stacked probability score vectors. The key technology was to implement ESM-2 and to select the optimal single-feature models according to their absolute weight coefficient for logistic regression (AWCLR), an indicator of the importance of each single-feature model. Especially, the sequential deletion of single-feature models based on the iterative AWCLR ranking (SDIWC) method constructed the meta-classifier consisting of the top 16 single-feature models, named PredIL13, while considering the model's accuracy. The PredIL13 greatly outperformed the-state-of-the-art predictors, thus is an invaluable tool for accelerating the detection of IL13-inducing peptide within the human genome.

Humans↗
PubMed1977

The evaluation of clinical predictions. A method and initial application.

Clinical predictions are never certain but are inherently probablisitc. The accuracy coefficient, a measure of probabilistic accuracy based on probability assigned to outcomes that occur, was used to assess the skill of clinical rheumatologists in predicting patient outcomes. Physicians' scores correlated well with degree of clinical experience. An approach to evaluation based on the measure provides a sensitive assessment of marginal benefit of technologies such as laboratory tests, diagnostic procedures or computer consultations. Most currently used methods of computer prediction were not as accurate as the best physicians tested. By allowing measurement of ability to individualize predictions to each patient's unique characteristics, the accuracy-coefficient approach has potential use in physician assessment.

Bayes Theorem↗
PubMed2025

TripLexicon: prediction and analysis of gene regulatory RNA-DNA interactions.

MOTIVATION: Non-coding RNA (ncRNA) plays a crucial role in gene regulation, including by forming sequence-specific RNA-DNA interactions at gene regulatory elements. One form of interaction takes place via the formation of RNA:DNA:DNA triple helices (triplexes). Accurate computational prediction of triplex formation from nucleotide sequences is an important tool in ncRNA research but remains somewhat inaccessible and complex. To address this, we created TripLexicon, a web-based interface for accessing and analyzing predicted gene regulatory RNA-DNA interactions in human and mouse. RESULTS: Predicted interactions can be accessed from RNA-, DNA-, and region-centric perspectives. For each RNA transcript, visualizations at genome and nucleotide resolution are available, providing insight into target genes and regions, as well as putative functional domains of the transcript. Predicted target genes can immediately be subjected to ontology and pathway enrichment analysis, providing rapid insight into potential functions mediated by the RNA-DNA interactions of the queried transcript. DNA and region queries are designed to identify potentially important ncRNA interactors at sites of interest. AVAILABILITY AND IMPLEMENTATION: TripLexicon is accessible at https://triplexicon.uni-frankfurt.de. This website is free and open to all users and there is no login requirement. All data and code is uploaded to Zenodo: https://zenodo.org/records/17143608 and the code for the webserver is available on Github: https://github.com/SchulzLab/TripLexicon.

Software↗