sgRNA design for DLT gene editing using CRISPR-Cas9 and in-silico mutation prediction in Rice cv. Hawara Bunar

The DWARF AND LOW TILLERRING (DLT) gene is a transcription factor for a gene involved in Brassinosteroid (BR) biosynthesis. Manipulating BR biosynthesis will affect the height and tiller number of rice. CRISPR-Cas9 is an accurate tool to edit a gene sequence. The accuracy of site editing of the CRISPR-Cas9-mediated target gene editing is determined by the 20 nucleotide sequences in the sgRNA and the binding site known as the Protospacer Adjacent Motif (PAM). The study aimed to design sgRNA and predict the DLT gene mutation sites in rice cv. Hawara Bunar. The exon 1 of the DLT gene was amplified using a primer pair designed from the reference gene. The PCR product was then sequenced, and the sequence was used to design sgRNA. The study has designed sgRNA located on the targeted sequence that corresponds to the Gras family protein domain of the exon1 DLT gene. The mutation sites were predicted to be at the domain site through the alignment of the nucleotide and amino acid sequences of the DLT gene and the reference gene. It is predicted that mutations in the target site that corresponds to the protein domain will change the protein structure and its function.

Benchmarking artificial intelligence methods for end-to-end computational pathology

Artificial intelligence (AI) can extract subtle visual information from digitized histopathology slides and yield scientific insight on genotype-phenotype interactions as well as clinically actionable recommendations. Classical weakly supervised pipelines use an end-to-end approach with residual neural networks (ResNets), modern convolutional neural networks such as EfficientNet, or non-convolutional architectures such as vision transformers (ViT). In addition, multiple-instance learning (MIL) and clustering-constrained attention MIL (CLAM) are being used for pathology image analysis. However, it is unclear how these different approaches perform relative to each other. Here, we implement and systematically compare all five methods in six clinically relevant end-to-end prediction tasks using data from N=4848 patients with rigorous external validation. We show that histological tumor subtyping of renal cell carcinoma is an easy task which approaches successfully solved with an area under the receiver operating curve (AUROC) of above 0.9 without any significant differences between approaches. In contrast, we report significant performance differences for mutation prediction in colorectal, gastric and bladder cancer. Weakly supervised ResNet- and ViT-based workflows significantly outperformed other methods, in particular MIL and CLAM for mutation prediction. As a reason for this higher performance we identify the ability of ResNet and ViT to assign high prediction scores to highly informative image regions with plausible histopathological image features. We make all source codes publicly available at https://github.com/KatherLab/HIA, allowing easy application of all methods on any end-to-end problem in computational pathology.

Comparable Performance of Deep Learning–Based to Manual-Based Tumor Segmentation in KRAS/NRAS/BRAF Mutation Prediction With MR-Based Radiomics in Rectal Cancer

Radiomic features extracted from segmented tumor regions have shown great power in gene mutation prediction, while deep learning–based (DL-based) segmentation helps to address the inherent limitations of manual segmentation. We therefore investigated whether deep learning–based segmentation is feasible in predicting KRAS/NRAS/BRAF mutations of rectal cancer using MR-based radiomics. In this study, we proposed DL-based segmentation models with 3D V-net architecture. One hundred and eight patients’ images (T2WI and DWI) were collected for training, and another 94 patients’ images were collected for validation. We evaluated the DL-based segmentation manner and compared it with the manual-based segmentation manner through comparing the gene prediction performance of six radiomics-based models on the test set. The performance of the DL-based segmentation was evaluated by Dice coefficients, which are 0.878 ± 0.214 and 0.955 ± 0.055 for T2WI and DWI, respectively. The performance of the radiomics-based model in gene prediction based on DL-segmented VOI was evaluated by AUCs (0.714 for T2WI, 0.816 for DWI, and 0.887 for T2WI+DWI), which were comparable to that of corresponding manual-based VOI (0.637 for T2WI, P=0.188; 0.872 for DWI, P=0.181; and 0.906 for T2WI+DWI, P=0.676). The results showed that 3D V-Net architecture could conduct reliable rectal cancer segmentation on T2WI and DWI images. All-relevant radiomics-based models presented similar performances in KRAS/NRAS/BRAF prediction between the two segmentation manners.

Novel Compound Missense and Intronic Splicing Mutation in ALDH18A1 Causes Autosomal Recessive Spastic Paraplegia

Background: Hereditary spastic paraplegia (HSP) caused by mutations in ALDH18A1 have been reported as spastic paraplegia 9 (SPG9), with autosomal dominant and autosomal recessive transmission (SPG9A and SPG9B). SPG9 is rare and has shown phenotypic and genotypic heterogeneity in previous reports.Methods: This study screened ALDH18A1 mutations in autosomal recessive HSP patients using combined whole exome sequencing and RNA splicing analysis. We conducted in silico investigations, co-segregation analysis, and ELISA-based analysis of P5CS (Δ1-pyrroline-5-carboxylate synthetase; encoded by ALDH18A1) concentration to validate the pathogenicity of the detected ALDH18A1 variants. All previously reported bi-allelic ALDH18A1 mutations and cases were reviewed to summarize the genetic and clinical features of ALDH18A1-related HSP.Results: A novel missense mutation c.880T>C, p.S294P and an intronic splicing mutation c.-28-13A>G were both detected in ALDH18A1 in an autosomal recessive family presenting with a complicated form HSP. ELISA assays revealed significantly decreased P5CS concentration in the proband's plasma compared with that in the healthy controls. Moreover, review of previously reported recessive cases showed that SPG9B patients in our cohort presented with milder symptoms, i.e., later age at onset and without cognitive impairment.Conclusion: The present study expands the genetic and clinical spectrum of SPG9B caused by ALDH18A1 mutation. Our work defines new genetic variants to facilitate future diagnoses, in addition to demonstrating the highly informative value of splicing mutation prediction in the characterization of disease-related intronic variants.