Publications by authors named "I Hajirasouliha"
A Probabilistic Liquefaction Hazard Analysis: Case Studies from the Marmara Region.
Geotech Geol Eng (Dordr)
January 2025
Earthquake induced soil liquefaction poses a significant threat to buildings and infrastructure, as evidenced by numerous catastrophic seismic events. Existing approaches of regional liquefaction hazard assessment predominantly rely on deterministic analysis methods. This paper presents a novel Probabilistic Liquefaction Hazard Analysis (PLHA) framework based on Monte-Carlo (MC) simulations to mitigate future seismic risks associated with liquefaction.
View Article and Find Full Text PDFMotivation: Recent benchmarks of structural variant (SV) detection tools revealed that the majority of human genome structural variations (SVs), especially the medium-range (50-10,000 bp) SVs cannot be resolved with short-read sequencing, but long-read SV callers achieve great results on the same datasets. While improvements have been made, high-coverage long-read sequencing is associated with higher costs and input DNA requirements. To decrease the cost one can lower the sequence coverage, but the current long-read SV callers perform poorly with coverage below 10×.
View Article and Find Full Text PDFArticle Synopsis
- Assessing fertilized human embryos for in vitro fertilization is rapidly evolving through artificial intelligence, with a focus on improving prediction accuracy using time-lapse imaging.
- BELA, a new advanced model, predicts embryo ploidy status effectively without needing embryologists' input, utilizing multitask learning to enhance quality assessments.
- With a strong performance of 0.76 in distinguishing euploidy from aneuploidy embryos, BELA demonstrates potential for streamlining the embryo evaluation process, although it won't replace existing genetic testing methods.
Motivation: Recent advancements in long-read RNA sequencing have enabled the examination of full-length isoforms, previously uncaptured by short-read sequencing methods. An alternative powerful method for studying isoforms is through the use of barcoded short-read RNA reads, for which a barcode indicates whether two short-reads arise from the same molecule or not. Such techniques included the 10x Genomics linked-read based SParse Isoform Sequencing (SPIso-seq), as well as Loop-Seq, or Tell-Seq.
View Article and Find Full Text PDFArticle Synopsis
- Advances in AI and deep learning are transforming embryo quality assessment in IVF, focusing on optimizing time-lapse imaging for better predictions.
- The new model, BELA (Blastocyst Evaluation Learning Algorithm), outperforms previous methods by utilizing multitask learning to assess embryo quality without reliance on embryologists' subjective input.
- BELA achieves a 0.76 AUC for identifying euploidy vs. aneuploidy, streamlining the evaluation process and reducing the workload for embryologists, although it does not replace genetic testing for aneuploidy.