Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 15 of 15 for “"SpliceAI"”.
-
Evaluation of SpliceAI for Improved Genetic Variant Classification in Inherited Ophthalmic Disease Genes
ABSTRACT EVALUATION OF SPLICEAI FOR IMPROVED GENETIC VARIANT CLASSIFICATION IN INHERITED OPHTHALMIC DISEASE GENES By Melissa Jean Reeves, Ph.D. A dissertation submitted in partial fulfillment of the requirements for the degree of Doctor of Philosophy at Virginia Commonwealth University. Virginia …
-
Advancing Neural Network Prediction in Genomics Through Multi-View Learning, Multi-Species Learning, Input Representations, and Model Integration
… which predicts gene expression abundance, and SpliceAI (Jaganathan et al., 2019), which predicts splice site locations. In our multi-view learning experiments, we demonstrate that supplementing Xpresso inputs with SpliceAI predictions improves predictive performance, while supplementing them …
-
Integrative Deep-Learning and Transcriptome-Resolved Framework for Discovery of Cryptic Splicing Variants in Breast Cancer
… καρκίνο. Αν και μοντέλα βαθιάς μάθησης όπως το SpliceAI επιτρέπουν την πρόβλεψη μεταλλάξεων που επηρεάζουν την μετακίνηση με βάση την αλληλουχία DNA, η συστηματική επιβεβαίωση μέσω μεταγραφικών δεδομένων παραμένει περιορισμένη. Η παρούσα εργασία παρουσιάζει ένα ολοκληρωμένο υπολογιστικό πλαίσιο …
-
Systems biology of deregulated splicing in cancer. A pan-cancer analysis of dysfunctional splicing machinery and alternative splicing events.
… the DNA sequence, we used the deep-learning tool SpliceAI. To the extent of our knowledge, SpliceAI has not been previously used to analyze RNA-sequencing from cancerous samples - cell lines nor human tumour samples. In this project, we decided to test the deep learning algorithm in data from the …
-
Improving diagnosis of genetic disease through computational investigation of splicing
… semantic encoding of DNA data are explored. CI-SpliceAI, a new algorithm to predict aberrant splicing, is developed and made available to the wider scientific community. Methods of how to explain shallow and deep learning are applied in order to visualise feature contribution of otherwise …
-
Nachweis von kodierenden und nicht-kodierenden Sequenzvarianten in Patient:innen mit Muskelerkrankungen
… Mithilfe spezialisierter Werkzeuge wie SpliceAI wurden potenzielle Spleißeffekte und die funktionelle Bedeutung der Varianten bewertet. Die Kombination dieser Analysen ermöglichte eine detaillierte funktionelle Charakterisierung, die für die diagnostische Bewertung von Varianten von …
-
Optimising Genome Sequencing Data Reanalysis in Patients with Unsolved Primary Immunodeficiencies
… tools, including Diploid MoonTM, ClinSV and SpliceAI. We identified three new diagnoses with pathogenic/pathogenic variants, as per the American College of Medical Genetics/Association for Molecular Pathology (ACMG/AMP) criteria, and numerous variants of uncertain significance (VUS), …
-
Predicting transposable element exonization with deep learning and large sequence models
… model exon and splice site predictors, including SpliceAI, AlphaGenome, SegmentNT, SegmentEnformer, SegmentBorzoi, and STEP2h. Reporting performance per exon class, including constitutive, alternative, terminal, non-coding, and TE-derived exons, exposes a recall-driven drop on TE-derived exons …
-
Decoding the Language of Genomes: Bridging Sequences and Function through Deep Learning
… frameworks for splice‑site prediction: OpenSpliceAI is a PyTorch re‑implementation of SpliceAI that delivers faster inference and seamless retraining; Splam is a compact residual convolutional neural network that accurately predicts splice junctions from local sequence context. Finally, …
-
Toward improving rare disease diagnosis : the rate of predicted splice variants reported from genome-wide sequencing and the discovery of RNA-binding protein with multiple splicing as a novel candidate gene causing a congenital malformation syndrome
… an impact. Using two in silico predictor tools, SpliceAI and TraP, variants from a large pediatric sequencing cohort were reanalyzed. A previously unreported candidate splice variant, GRIN2B:NM_000834.5:c.1781-19T>A, was identified in 1 of 90 undiagnosed families, introducing a possible diagnosis …
-
Genotype-phenotype correlation in junctional epidermolysis bullosa
… analysis with the in-silico tools MMSplice and SpliceAI in order to predict resultant transcripts. A dedicated JEB deep phenotyping tool was developed which was used to systematically examine the clinical features of JEB individuals. Eighteen unique mutations in LAMB3, LAMA3, LAMC2 or COL17A1 …
-
ON BIOINFORMATIC METHODS FOR THE DETECTION OF ALTERNATIVELY SPLICED VARIANTS FOR CLINICAL DIAGNOSTICS
… and compares their outputs to predictions from SpliceAI. Chapter 3 examines clinical accessibility, comparing computational resource usage, control cohort design, and confounder correction strategies, and provides guidelines for parameter selection in diagnostic practice. Chapter 4 applies …
-
Investigation of transcript regulatory functions via integrated analysis of data generated by high-throughput sequencing methods
… tools such as microT-CNN for target prediction, SpliceAI for splicing impact estimation, and ORFfinder for coding sequence identification, the pipeline enables efficient annotation of variant effects in non-coding and coding regions. This framework facilitates reproducible, high-throughput …
-
Bioinformatics and cancer genomics approaches to advance precision medicine and elucidate tumor mutational landscapes
… them with the Variant Effect Predictor (VEP), SpliceAI, and Genotype-Tissue Expression (GTEx) junction counts and compared our results to other tools that integrate genomic and transcriptomic data. We identified novel splice-associated variants and previously unreported patterns of splicing …
-
Decoding the Genetic Basis of Inherited Retinal Dystrophies for Precision Medicine
… con las predicciones bioinformáticas de SpliceAI. La integración de los resultados clínicos, genéticos y funcionales permitió además la reclasificación clínica de algunos pacientes e identificar nuevas asociaciones genotipo-fenotipo, como FAM161A con distrofia de conos-bastones y GUCY2D …