SEARCH · Search PubMed

Results for “machine learning prediction 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.

SourceResearch connectionFrom yearThrough year

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

At least 289 records · Page 16Linked to original sources

PubMed2006

ANGLE: a sequencing errors resistant program for predicting protein coding regions in unfinished cDNA.

In the process of making full-length cDNA, predicting protein coding regions helps both in the preliminary analysis of genes and in any succeeding process. However, unfinished cDNA contains artifacts including many sequencing errors, which hinder the correct evaluation of coding sequences. Especially, predictions of short sequences are difficult because they provide little information for evaluating coding potential. In this paper, we describe ANGLE, a new program for predicting coding sequences in low quality cDNA. To achieve error-tolerant prediction, ANGLE uses a machine-learning approach, which makes better expression of coding sequence maximizing the use of limited information from input sequences. Our method utilizes not only codon usage, but also protein structure information which is difficult to be used for stochastic model-based algorithms, and optimizes limited information from a short segment when deciding coding potential, with the result that predictive accuracy does not depend on the length of an input sequence. The performance of ANGLE is compared with ESTSCAN on four dataset each of them having a different error rate (one frame-shift error or one substitution error per 200-500 nucleotides) and on one dataset which has no error. ANGLE outperforms ESTSCAN by 9.26% in average Matthews's correlation coefficient on short sequence dataset (< 1000 bases). On long sequence dataset, ANGLE achieves comparable performance.

Algorithms↗

PubMed2026

Senescent fibroblasts drive CD8+ T cell dysfunction in colorectal cancer via CD36-mediated lipid transfer and peroxidation.

BACKGROUND: Functional exhaustion of tumor-infiltrating CD8+ T cells represents a hallmark of colorectal cancer (CRC) immunosuppression, though its mechanistic drivers remain elusive. Given the established correlation between CRC progression and stromal senescence characterized by pathological lipid accumulation and impaired immunity, we investigated whether and how senescent fibroblasts actively regulate CD8+ T cell dysfunction. METHODS: Single-cell RNA sequencing (scRNA-seq) analysis was conducted to unveil the diverse fibroblast populations and the significant lipid metabolism changes between senescent fibroblasts and non-senescent fibroblasts in human CRC specimens and adjacent normal mucosa. Machine-learning identified senescent fibroblasts with a distinct gene signature. Cell-cell communication analysis was used to evaluate the interactions between senescent fibroblasts and CD8+ T cells in colorectal cancer. Co-culture experiments were conducted among senescent fibroblasts, CD8+ T cells and patient-derived organoids of CRC (CRC-PDOs), with the results evaluated with high-content imaging and propidium iodide/Hoechst 33,342 staining. Flow cytometry, ELISA and lipid pulse-chase with BODIPY FL C16 were performed to detect the alterations of CD8+ T cell cytotoxic function and metabolic status. AOM/DSS-induced CRC mouse model was used to conduct in vivo validation to evaluate whether senolytics could suppress CRC progression. Patients from the Cancer Genome Atlas colorectal cancer cohort were stratified into CD36-high and CD36-low groups by median expression, and drug sensitivity for GDSC2 compounds was predicted computationally using the oncoPredict R package. RESULTS: ScRNA-seq demonstrated the specific cell population presence and divergence of senescent fibroblasts between neoplastic and histologically normal adjacent cell clusters in CRC. Random Forest was employed for cell senescence classification. Feature importance analysis identified five genes as key contributors to the model’s decision process. Cell-cell communication analysis revealed enhanced interactions between senescent fibroblasts and CD8+ T cells in CRC. Co-culture of senescent fibroblasts significantly impaired the cytotoxic functions of CD8+ T cells on CRC-PDOs, which was reflected by the declined proportions of granzyme B (GZMB) + and interferon gamma (IFNγ) + CD8+ T cells and enhanced viability of CRC-PDOs. Mechanistically, the co-culture with senescent fibroblasts promoted the lipid shuttling into CD8+ T cells to induce lipid peroxidation and downstream impairment of cytotoxicity. Furthermore, the inhibition of CD36, the specific scavenger receptor for lipid uptake of CD8+ T cells, effectively suppressed lipid transfer and peroxidation thereby preserving the effector functions of CD8+ T cells and ultimately promoting tumor apoptosis. Complementarily, in vivo senolytic treatment significantly suppressed CRC progression in AOM-DSS CRC mouse models. Top 12 therapeutic agents were identified significantly enhanced predicted efficacy in CD36-high tumors. CONCLUSIONS: Our study identified a substantial population of senescent fibroblasts in human CRC through single cell transcriptomics, machine-learning and clinical biopsies. These senescent fibroblasts impair CD8+ T cell-mediated killing of CRC-PDOs via CD36-dependent lipid transfer, suggesting senolytic targeting of stromal cells as a promising immunotherapeutic strategy for CRC.

Colorectal Neoplasms↗

PubMed2026

Machine Learning-Based Preoperative Predicting TERT Promoter Mutation and EGFR Gene Amplification Phenotype in IDH Wild-Type Glioblastoma Using Advanced MR Habitat Imaging.

BACKGROUND AND PURPOSE: The telomerase reverse transcriptase (TERT) gene promoter mutation is a crucial factor for identifying an isocitrate dehydrogenase (IDH) wild-type glioblastoma with poor prognosis, and the epidermal growth factor receptor (EGFR) amplification may be a potential prognostic factor. The purpose of this study was to investigate the value of the tumor habitats imaging model on advanced MRI in predicting TERT promoter mutation and EGFR gene amplification phenotype of IDH wild-type glioblastoma. MATERIALS AND METHODS: One hundred seventy-nine patients with pretreatment conventional MRI, DWI, and DSC-PWI were included. The data were divided into the training set (n=112), test set (n=29), and time-independent validation set (n=38). Based on the ADC and CBV map, the solid tumor area was split into several habitat subregions using the k-means clustering algorithm (hypovascular hypercellular area, hypervascular area, and hypovascular hypocellular area). In the training set, TERT promoter mutation and EGFR gene amplification phenotype prediction models were constructed using the random forest method. The reliability of prediction models was validated in the test and the time-independent validation sets. Receiver operating characteristic (ROC) curve analysis, calibration curve, and decision curve analysis (DCA) were used. RESULTS: The area under the curve (AUC) of the training, test, and validation sets of the TERT promoter prediction model was 0.877, 0.783, and 0.796, respectively. The accuracy of the TERT promoter prediction model was 82.1%, 75.9%, and 76.3%, respectively. The AUCs of the 3 sets for the EGFR gene amplification status prediction model were 0.877, 0.784, and 0.878, respectively. The accuracy of the EGFR gene amplification status prediction model was 79.5%, 75.9%, and 89.5%, respectively. Moreover, the prediction probability of these models was in good agreement with the actual result. CONCLUSIONS: The tumor habitat imaging model based on advanced MRI was useful for accurately predicting TERT promoter mutation and EGFR amplification status in IDH wild-type glioblastoma.

Humans↗

PubMed1996

New approaches in molecular structure prediction.

In the past years, much effort has been put on the development of new methodologies and algorithms for the prediction of protein secondary and tertiary structures from (sequence) data; this is reviewed in detail. New approaches for these predictions such as neural network methods, genetic algorithms, machine learning, and graph theoretical methods are discussed. Secondary structure prediction algorithms were improved mostly by considering families of related proteins; however, for the reliable tertiary structure modeling of proteins, knowledge-based techniques are still preferred. Methods and examples with more or less successful results are described. Also, programs and parameterizations for energy minimisations, molecular dynamics, and electrostatic interactions have been improved, especially with respect to their former limits of applicability. Other topics discussed in this review include the use of traditional and on-line databases, the docking problem and surface properties of biomolecules, packing of protein cores, de novo design and protein engineering, prediction of membrane protein structures, the verification and reliability of model structures, and progress made with currently available software and computer hardware. In summary, the prediction of the structure, function, and other properties of a protein is still possible only within limits, but these limits continue to be moved.

Chemical Phenomena↗

PubMed2024

Combination of computational techniques and RNAi reveal targets in Anopheles gambiae for malaria vector control.

Increasing reports of insecticide resistance continue to hamper the gains of vector control strategies in curbing malaria transmission. This makes identifying new insecticide targets or alternative vector control strategies necessary. CLassifier of Essentiality AcRoss EukaRyote (CLEARER), a leave-one-organism-out cross-validation machine learning classifier for essential genes, was used to predict essential genes in Anopheles gambiae and selected predicted genes experimentally validated. The CLEARER algorithm was trained on six model organisms: Caenorhabditis elegans, Drosophila melanogaster, Homo sapiens, Mus musculus, Saccharomyces cerevisiae and Schizosaccharomyces pombe, and employed to identify essential genes in An. gambiae. Of the 10,426 genes in An. gambiae, 1,946 genes (18.7%) were predicted to be Cellular Essential Genes (CEGs), 1716 (16.5%) to be Organism Essential Genes (OEGs), and 852 genes (8.2%) to be essential as both OEGs and CEGs. RNA interference (RNAi) was used to validate the top three highly expressed non-ribosomal predictions as probable vector control targets, by determining the effect of these genes on the survival of An. gambiae G3 mosquitoes. In addition, the effect of knockdown of arginase (AGAP008783) on Plasmodium berghei infection in mosquitoes was evaluated, an enzyme we computationally inferred earlier to be essential based on chokepoint analysis. Arginase and the top three genes, AGAP007406 (Elongation factor 1-alpha, Elf1), AGAP002076 (Heat shock 70kDa protein 1/8, HSP), AGAP009441 (Elongation factor 2, Elf2), had knockdown efficiencies of 91%, 75%, 63%, and 61%, respectively. While knockdown of HSP or Elf2 significantly reduced longevity of the mosquitoes (p<0.0001) compared to control groups, Elf1 or arginase knockdown had no effect on survival. However, arginase knockdown significantly reduced P. berghei oocytes counts in the midgut of mosquitoes when compared to LacZ-injected controls. The study reveals HSP and Elf2 as important contributors to mosquito survival and arginase as important for parasite development, hence placing them as possible targets for vector control.

Animals↗

PubMed2026

Machine learning-based clinical tool for identifying factors associated with symptomatic knee osteoarthritis: the Nagahama study.

BACKGROUND: A clinical tool that evaluates factors associated with symptomatic knee osteoarthritis (OA) based on modifiable factors is lacking. This study aimed to develop a machine learning-based clinical assessment tool using modifiable factors to identify factors associated with symptomatic knee OA and to determine its accuracy. METHODS: This study included 429 participants (81.8% women; age, 69.0 ± 5.3 years) from the Nagahama Study who were ≥60 years old and had radiographically confirmed knee OA. A Knee Society Knee Scoring System 2011 symptom score of <23 points defined symptomatic knee OA. Participants were randomly assigned to training (70%) and test (30%) datasets. A machine learning model was developed using Extreme Gradient Boosting with 27 variables, and the SHapley Additive exPlanation (SHAP) values were used to assess feature importance. The top 8 features were translated into a 100-point clinical scoring tool weighted by their SHAP contributions. The cutoff value indicating symptomatic knee OA in the clinical assessment tool was determined using receiver operating characteristic analysis, and model performance was evaluated in both datasets. RESULTS: The clinical assessment tool consisted of low back pain, OA severity, depressive tendencies, knee flexion/extension range of motion, knee extension and hip abduction strength, and lower limb muscle quality. The model showed moderate discriminative performance (AUC 0.771 and 0.773 in the training and test datasets, respectively), with a cutoff point of 47. CONCLUSION: The proposed clinical assessment tool may provide a structured framework for assessing modifiable factors associated with symptomatic knee OA, reflecting their contribution to current symptom status.

Humans↗

PubMed2025

Establishment of a prognostic model based on ER stress-related cell death genes and proposing a novel combination therapy in acute myeloid leukemia.

BACKGROUND: Acute myeloid leukemia (AML) is a highly heterogeneous malignancy, presenting significant challenges in accurately predicting patient prognosis. Dysregulation of endoplasmic reticulum (ER) stress and resistance to programmed cell death (PCD) are hallmarks of AML cells. However, the prognostic significance of the interplay between ER stress and cell death pathways in AML remains largely unexplored. METHODS: We analyzed RNA sequencing and clinical data from 887 AML patients across 4 cohorts to develop an ER stress-related cell death index (ERCDI) using 10 machine-learning algorithms with 117 unique combinations. Survival and time-dependent Receiver Operating Characteristic Curve (ROC) analyses were performed to assess the model's efficacy. Clinical characteristics, the tumor immune microenvironment, and drug sensitivity differences between the high- and low-risk groups were also analyzed. The CMap database was used to identify potential therapeutic drugs. In vitro and in vivo experiments, including CCK-8, colony formation, flow cytometry, Transwell assays, and xenograft mouse models, were conducted to evaluate the effects of the target genes and candidate drugs. RESULTS: The ERCDI demonstrated strong prognostic and predictive performance for prognosis in AML patients. Furthermore, the ERCDI effectively predicted immunotherapy and chemotherapy outcomes and was associated with the immune features of the different risk groups. DNA damage-inducible transcript 4 protein (DDIT4), a key gene associated with ERCDI, is related to poor prognosis in AML patients with high expression. Additionally, the knockdown of DDIT4 significantly inhibited AML cell proliferation, induced cell apoptosis, and promoted cell cycle arrest. Chaetocin was subsequently identified as a candidate compound for AML treatment. Subsequent experiments suggested that combining chaetocin and venetoclax is a potentially promising therapeutic strategy for AML. CONCLUSION: The ERCDI provides personalized risk assessment and treatment recommendations for individual AML patients. The combined use of chaetocin and venetoclax can potentially be repurposed for AML therapy.

Humans↗

PubMed2025

mamp-ml: A deep learning approach to epitope immunogenicity in plants.

Eukaryotes detect biomolecules through surface-localized receptors, key signaling components. A subset of receptors survey for pathogens, induce immunity, and restrict pathogen growth. Comparative genomics of both hosts and pathogens has unveiled vast sequence variation in receptors and potential ligands, creating an experimental bottleneck. We have developed mamp-ml, a machine learning framework for predicting plant receptor-ligand interactions. We leveraged existing functional data from over two decades of foundational research, together with the large protein language model ESM-2, to build a pipeline and model that predicts immunogenic outcomes using a combination of receptor-ligand features. Our model achieves 73% prediction accuracy on a held-out test set, even when an experimental structure is lacking. Our approach enables high-throughput screening of LRR receptor-ligand combinations and provides a computational framework for engineering plant immune systems.

Journal Article↗

PubMed2026

Integrative multi-omics and single-cell analysis identifies EGFR pathway activation and metabolic reprogramming as potential synthetic lethal vulnerabilities in resistance to the FGFR inhibitor AZD4547.

BACKGROUND: Although fibroblast growth factor receptor (FGFR) inhibitors (FGFRi) have demonstrated clinical promise, the inevitable emergence of acquired resistance remains a critical bottleneck, severely compromising their long-term clinical efficacy. The pan-cancer molecular landscape and heterogeneous mechanisms driving this resistance, ranging from genetic alterations to dynamic network rewiring, remain poorly understood. METHODS: We integrated large-scale pharmacogenomic profiling of the FGFR inhibitor AZD4547 from the GDSC2 and PRISM databases with single-cell RNA sequencing to dissect the multi-omics landscape of FGFRi resistance across 312 cell lines from 8 cancer types. This multi-omics framework was further extended by machine learning modeling and systematic synthetic lethality screening to uncover actionable therapeutic targets. In vitro viability assays and western blot analysis were subsequently conducted to experimentally evaluate the predicted FGFR-EGFR synthetic lethality. RESULTS: Our dual-database analysis unveiled a multi-dimensional atlas of FGFRi resistance. We identified cancer-specific genomic drivers, such as ELF4 amplification in glioblastoma, alongside key transcriptomic markers including UCP2 and FSCN1, highlighting a shift towards metabolic reprogramming and epithelial-mesenchymal transition (EMT). Single-cell analysis unveiled that resistance is linked to the heterogeneous enrichment of baseline subpopulations characterized by distinct metaprograms, including cell-cycle dysregulation. Furthermore, a random forest model built on a LASSO-derived transcriptomic signature was constructed, demonstrating promising predictive capability for AZD4547 sensitivity (mean test-set AUC = 0.73, 95% CI [0.63, 0.80]); the signature generalized well to erdafitinib but showed limited transferability to some other FGFR inhibitors (e.g. pemigatinib, BGJ398). Most notably, our synthetic lethal screening revealed a convergent reliance on compensatory RTK signaling (specifically EGFR pathway enrichment) and downstream MAPK/PI3K cascades in resistant phenotypes, providing converging computational evidence for EGFR pathway activation as an adaptive bypass mechanism. This predicted synthetic lethality was experimentally supported in two FGFR-dependent cell line models (RT112 and CCLP1), in which combined FGFR-EGFR inhibition produced marked synergistic antiproliferative effects. CONCLUSIONS: This study establishes a comprehensive multi-omics atlas of resistance to the FGFR inhibitor AZD4547, delineating convergent mechanisms of metabolic reprogramming and EGFR-mediated bypass signaling. Our findings characterize the resistance as a dynamic network rewiring and nominate rational combination strategies to overcome this therapeutic bottleneck. While FGFR-EGFR co-inhibition is experimentally supported, metabolic co-targeting remains a computationally derived, hypothesis-generating strategy.

Benzamides↗

PubMed2026

Decoding gene regulation in plant genomes with artificial intelligence.

One of the central goals of plant functional genomics is to uncover regulatory mechanisms that shape agriculturally important traits to inform crop improvement. Recent advances in machine learning (ML) and artificial intelligence (AI), especially Large Language Models (LLMs), have greatly transformed our ability to derive regulatory information from complex genomics data. This review starts with a brief introduction of recent advances in AI and ML. We then present a plant-focused synthesis of emerging applications of AI- and LLM tools to: (i) predict epigenomic features, regulatory DNA elements, and gene expressions; (ii) infer gene regulatory network; and (iii) estimate post-transcriptional regulation.

Artificial intelligence↗

PubMed2026

Serum Proteomic Profiling Implicates a Dysregulated Neurohormonal-Inflammatory Axis in Post-Fontan Sinus Tachycardia.

BACKGROUND: Postoperative sinus tachycardia is a poorly understood complication following the Fontan procedure. The molecular signaling cascades triggering acute tachycardia remain uncharacterized, limiting therapeutic innovation. Here, we present a retrospective study leveraging serum proteomics and machine learning to identify the molecular drivers of postoperative Fontan sinus tachycardia. METHODS: We integrated a clinically relevant ovine Fontan model with continuous telemetric heart rate monitoring and human patient data. Serum proteomics coupled with least absolute shrinkage and selection operator and Boruta machine learning algorithms were used to identify protein panels predictive of postoperative sinus tachycardia. Cross-species validation was performed by comparing proteomic signatures from sheep and pediatric patients undergoing Glenn or Fontan surgery. RESULTS: Ovine Fontan animals demonstrated significant heart rate elevation beginning on postoperative day 1, peaking at postoperative day 3 (159.4±11.7 bpm versus preoperative, 105.3±10.5 bpm; P=0.0002), before trending toward baseline by postoperative day 10. This pattern was mirrored in human patients with a more modest magnitude. Surgical controls did not exhibit tachycardia. The principal component most correlated with heart rate (principal component 1: r=0.78, P=2.2×10-4) was enriched for inflammatory and neural pathways. The Boruta algorithm identified an 11-protein panel with strong predictive power (area under the receiver operating characteristic curve, 0.963). Cross-species comparison demonstrated that angiotensinogen, angiotensin-converting enzyme, and pentraxin 3 were similarly dysregulated in both species postoperatively. CONCLUSIONS: This study provides molecular evidence implicating a dysregulated neurohormonal-inflammatory axis in acute postoperative Fontan sinus tachycardia and establishes a foundation for developing targeted diagnostics and therapeutics for this complication.

Animals↗

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↗

PubMed2006

More complete gene silencing by fewer siRNAs: transparent optimized design and biophysical signature.

Highly accurate knockdown functional analyses based on RNA interference (RNAi) require the possible most complete hydrolysis of the targeted mRNA while avoiding the degradation of untargeted genes (off-target effects). This in turn requires significant improvements to target selection for two reasons. First, the average silencing activity of randomly selected siRNAs is as low as 62%. Second, applying more than five different siRNAs may lead to saturation of the RNA-induced silencing complex (RISC) and to the degradation of untargeted genes. Therefore, selecting a small number of highly active siRNAs is critical for maximizing knockdown and minimizing off-target effects. To satisfy these needs, a publicly available and transparent machine learning tool is presented that ranks all possible siRNAs for each targeted gene. Support vector machines (SVMs) with polynomial kernels and constrained optimization models select and utilize the most predictive effective combinations from 572 sequence, thermodynamic, accessibility and self-hairpin features over 2200 published siRNAs. This tool reaches an accuracy of 92.3% in cross-validation experiments. We fully present the underlying biophysical signature that involves free energy, accessibility and dinucleotide characteristics. We show that while complete silencing is possible at certain structured target sites, accessibility information improves the prediction of the 90% active siRNA target sites. Fast siRNA activity predictions can be performed on our web server at http://optirna.unl.edu/.

Artificial Intelligence↗

PubMed2026

seq2ribo: Structure-aware integration of machine learning and simulation to predict ribosome location profiles from RNA sequences.

MOTIVATION: Ribosome dynamics are vital in the process of protein expression. Current methods rely on ribosome profiling (Ribo-seq), RNA-seq profiles, and full genomic context. This restricts their use in de novo sequence design, like messenger RNA (mRNA) vaccines. Simulation-only approaches like the Totally Asymmetric Simple Exclusion Process (TASEP) oversimplify translation by focusing solely on codon elongation times. RESULTS: We present seq2ribo, a hybrid simulation and machine learning framework that predicts ribosome A-site locations using only an mRNA sequence as input. Our method first employs a novel structure-aware TASEP (sTASEP), which models translation using a comprehensive set of fitted parameters that include codon wait times and structural features, such as local angles, base-pairing, and discrete positional buckets. The ribosome locations generated by sTASEP are then processed by a polisher model, which learns to refine the simulated ribosome distributions. seq2ribo provides high-fidelity predictions of ribosome locations across diverse cell types (iPSC, HEK293, LCL, and RPE-1), significantly outperforming baselines. seq2ribo is the first method to achieve meaningful positional correlation with observed ribosome profiles from sequence alone, reaching transcript-level Pearson correlations up to 0.920 and within-transcript shape correlations up to 0.186, where all baselines yield near-zero values on these metrics. seq2ribo also reduces elementwise error by up to 37.7% relative to the sequence-only Translatomer baseline. By adding a task-specific head, seq2ribo achieves Pearson correlations up to 0.732 with experimental translation efficiency (TE) across several cell lines, and up to 0.903 with measured protein expression. By operating from sequence alone, seq2ribo provides a new tool for synthetic biology, enabling the rational design and optimization of mRNA sequences without the need for expression-level data or genomic context.

Journal Article↗

PubMed2003

Combining the performance strengths of the logistic regression and neural network models: a medical outcomes approach.

The assessment of medical outcomes is important in the effort to contain costs, streamline patient management, and codify medical practices. As such, it is necessary to develop predictive models that will make accurate predictions of these outcomes. The neural network methodology has often been shown to perform as well, if not better, than the logistic regression methodology in terms of sample predictive performance. However, the logistic regression method is capable of providing an explanation regarding the relationship(s) between variables. This explanation is often crucial to understanding the clinical underpinnings of the disease process. Given the respective strengths of the methodologies in question, the combined use of a statistical (i.e., logistic regression) and machine learning (i.e., neural network) technology in the classification of medical outcomes is warranted under appropriate conditions. The study discusses these conditions and describes an approach for combining the strengths of the models.

Artificial Intelligence↗

PubMed2006

Analysis and prediction of helix shift errors in homology modeling.

High sequence identity between two proteins (e.g. > 60%) is a strong evidence for high structural similarity. However, internal shifts in one of the two proteins can sometimes give rise to unexpectedly high structural differences. This, in turn, causes unreliable structure predictions when two such proteins are used in homology modeling. Here, we perform a computational analysis of helix shifts and we show that their occurrence can be predicted with statistical learning methods. Our results indicate that helix shifts increase the RMS error by factor 2.6 compared to those protein pairs without a helix shift. Although helix shifts are rare (1.6% of helices and a commensurately higher number of proteins are affected), they therefore pose a significant problem for reliable structure prediction systems. In this paper, we prototype a new approach for model quality assessment and demonstrate that it can successfully warn against helix shifts. A support vector machine trained on a wide range of sequence and structure properties predicts the occurrence of helix shifts with a sensitivity of 74.2% and a specificity of 83.6%. On an equalized test dataset, this corresponds to an accuracy of 78.9%. Projected to the full dataset, it translates to an accuracy of 83.4%. Our analysis shows that helix shift detection is a valuable building block for highly reliable structure prediction systems. Furthermore, the statistical learning based approach to helix shift detection that we employ here is orthogonal to well-established model quality assessment methods (which use geometric constraint checking or mean force potentials). Therefore, a further increase of prediction accuracy is expected from the combination of these methods.

Computational Biology↗

PubMed2020

Exploration of predictive and prognostic alternative splicing signatures in lung adenocarcinoma using machine learning methods.

BACKGROUND: Alternative splicing (AS) plays critical roles in generating protein diversity and complexity. Dysregulation of AS underlies the initiation and progression of tumors. Machine learning approaches have emerged as efficient tools to identify promising biomarkers. It is meaningful to explore pivotal AS events (ASEs) to deepen understanding and improve prognostic assessments of lung adenocarcinoma (LUAD) via machine learning algorithms. METHOD: RNA sequencing data and AS data were extracted from The Cancer Genome Atlas (TCGA) database and TCGA SpliceSeq database. Using several machine learning methods, we identified 24 pairs of LUAD-related ASEs implicated in splicing switches and a random forest-based classifiers for identifying lymph node metastasis (LNM) consisting of 12 ASEs. Furthermore, we identified key prognosis-related ASEs and established a 16-ASE-based prognostic model to predict overall survival for LUAD patients using Cox regression model, random survival forest analysis, and forward selection model. Bioinformatics analyses were also applied to identify underlying mechanisms and associated upstream splicing factors (SFs). RESULTS: Each pair of ASEs was spliced from the same parent gene, and exhibited perfect inverse intrapair correlation (correlation coefficient = - 1). The 12-ASE-based classifier showed robust ability to evaluate LNM status of LUAD patients with the area under the receiver operating characteristic (ROC) curve (AUC) more than 0.7 in fivefold cross-validation. The prognostic model performed well at 1, 3, 5, and 10 years in both the training cohort and internal test cohort. Univariate and multivariate Cox regression indicated the prognostic model could be used as an independent prognostic factor for patients with LUAD. Further analysis revealed correlations between the prognostic model and American Joint Committee on Cancer stage, T stage, N stage, and living status. The splicing network constructed of survival-related SFs and ASEs depicts regulatory relationships between them. CONCLUSION: In summary, our study provides insight into LUAD researches and managements based on these AS biomarkers.

Adenocarcinoma of Lung↗

PubMed2026

GUANinE v1.1 reveals complementarity of supervised and genomic language models.

There has been much debate about the benefits of supervised versus unsupervised learning on genomes. Determining which is better in what contexts requires developing comprehensive benchmarks spanning functional and evolutionary tasks. Importantly, such benchmarks need large sample sizes to enable well-powered ranking of models. Having developed and applied such a benchmark here (GUANinE v1.1), we conclusively demonstrate each paradigm offers key advantages and outperforms on certain tasks. In accordance with training, supervised sequence-to-function models exhibit strong performance when annotating functional states characterized by chromatin accessibility or histone marks, while self-supervised language models outperform on evolutionary conservation. Our hundreds of new evaluations in this v1.1 expansion provide evidence for a tradeoff between input context size and model parameter count for a fixed compute budget, which we depict with new metrics such as kiloparameters/base pair. We also construct two new large-scale variant interpretation tasks in v1.1: cadd-snv measuring deleteriousness, and clinvar-snv measuring clinical pathogenicity. We find that conservation scores, and by extension, genomic language models, predict deleteriousness well, but successfully translating deleteriousness predictions to pathogenicity remains challenging. GUANinE v1.1 newly evaluates dozens of pretrained genomic models, and we conclude that moderate-context hybrid or post-trained language models may define the next era of machine learning in genomics.

Genomics↗