Explore the vast range of titles available.

In recent years, drug sensitivity prediction has garnered a great deal of attention due to the growing interest in precision medicine. Several computational methods have been developed for drug sensitivity prediction and the identification of related markers. However, most previous studies have ignored genetic interaction, although complex diseases (e.g., cancer) involve many genes intricately connected in a molecular network rather than the abnormality of a single gene. To effectively predict drug sensitivity and understand its mechanism, we propose a novel strategy for explainable drug sensitivity prediction based on sample-specific gene regulatory networks, designated Xprediction. Our strategy first estimates sample-specific gene regulatory networks that enable us to identify the molecular interplay underlying varying clinical characteristics of cell lines. We then, predict drug sensitivity based on the estimated sample-specific gene regulatory networks. The predictive models are based on machine learning approaches, i.e., random forest, kernel support vector machine, and deep neural network. Although the machine learning models provide remarkable results for prediction and classification, we cannot understand how the models reach their decisions. In other words, the methods suffer from the black box problem and thus, we cannot identify crucial molecular interactions that involve drug sensitivity-related mechanisms. To address this issue, we propose a method that describes the importance of each molecular interaction for the drug sensitivity prediction result. The proposed method enables us to identify crucial gene-gene interactions and thereby, interpret the prediction results based on the identified markers. To evaluate our strategy, we applied Xprediction to EGFR-TKIs prediction based on drug sensitivity specific gene regulatory networks and identified important molecular interactions for EGFR-TKIs prediction. Our strategy effectively performed drug sensitivity prediction compared with prediction based on the expression levels of genes. We also verified through literature, the EGFR-TKIs-related mechanisms of a majority of the identified markers. We expect our strategy to be a useful tool for predicting tasks and uncovering complex mechanisms related to pharmacological profiles, such as mechanisms of acquired drug resistance or sensitivity of cancer cells.

Cancer cells secrete large amounts of extracellular vesicles (EVs) originating from multivesicular bodies (MVBs). Mature MVBs fuse either with the plasma membrane for release as EVs, often referred as to exosomes or with lysosomes for degradation. However, the mechanisms regulating MVB fate remain unknown. Here, we investigated the regulators of MVB fate by analyzing the effects of signaling inhibitors on EV secretion from cancer cells engineered to secrete luciferase‐labeled EVs. Inhibition of the oncogenic MEK/ERK pathway suppressed EV release and activated lysosome formation. MEK/ERK‐mediated lysosomal inactivation impaired MVB degradation, resulting in increased EV secretion from cancer cells. Moreover, MEK/ERK inhibition prevented c‐MYC expression and induced the nuclear translocation of MiT/TFE transcription factors, thereby promoting the activation of lysosome‐related genes, including the gene encoding a subunit of vacuolar‐type H+‐ATPase, which is responsible for lysosomal acidification and function. Furthermore, c‐MYC upregulation was associated with lysosomal gene downregulation in MEK/ERK‐activated renal cancer cells/tissues. These findings suggest that the MEK/ERK/c‐MYC pathway controls MVB fate and promotes EV production in human cancers by inactivating lysosomal function. MEK/ERK‐mediated oncogenic signals promote EV secretion by lysosomal inactivation. MEK/ERK activation induces c‐MYC expression and suppresses nuclear localization of MiT/TFE transcription factors, leading to the downregulation of lysosome‐related genes critical for lysosome function.

In recent years, personalized gene regulatory networks have received significant attention, and interpretation of the multilayer networks has been a critical issue for a comprehensive understanding of gene regulatory systems. Although several statistical and machine learning approaches have been developed and applied to reveal sample-specific regulatory pathways, integrative understanding of the massive multilayer networks remains a challenge. To resolve this problem, we propose a novel artificial intelligence (AI) strategy for comprehensive gene regulatory network analysis. In our strategy, personalized gene networks corresponding specific clinical characteristic are constructed and the constructed network is considered as a second-order tensor. Then, an explainable AI method based on deep learning is applied to decompose the multilayer networks, thus we can reveal all-encompassing gene regulatory systems characterized by clinical features of patients. To evaluate the proposed methodology, we apply our method to the multilayer gene networks under varying conditions of an epithelial–mesenchymal transition (EMT) process. From the comprehensive analysis of multilayer networks, we identified novel markers, and the biological mechanisms of the identified genes and their reciprocal mechanisms are verified through the literature. Although any biological knowledge about the identified genes was not incorporated in our analysis, our data-driven approach based on AI approach provides biologically reliable results. Furthermore, the results provide crucial evidences to reveal biological mechanism related to various diseases, e.g., keratinocyte proliferation. The use of explainable AI method based on the tensor decomposition enables us to reveal global and novel mechanisms of gene regulatory system from the massive multiple networks, which cannot be demonstrated by existing methods. We expect that the proposed method provides a new insight into network biology and it will be a useful tool to integrative gene network analysis related complex architectures of diseases.

Tumor cells evade targeted drugs by rewiring their genetic and epigenetic networks. Here, we identified that inhibition of MAPK signaling rapidly induces an epithelial-to-mesenchymal transition program by promoting re-localization of an apical-basal polarity protein, Scribble, in oncogene-addicted lung cancer models. Mis-localization of Scribble suppressed Hippo-YAP signaling, leading to YAP nuclear translocation. Furthermore, we discovered that a RAS superfamily protein MRAS is a direct target of YAP. Treatment with KRAS G12C inhibitors induced MRAS expression, which formed a complex with SHOC2, precipitating feedback activation of MAPK signaling. Abrogation of YAP activation or MRAS induction enhanced the efficacy of KRAS G12C inhibitor treatment in vivo. These results highlight a role for protein localization in the induction of a non-genetic mechanism of resistance to targeted therapies in lung cancer. Furthermore, we demonstrate that induced MRAS expression is a key mechanism of adaptive resistance following KRAS G12C inhibitor treatment.

This study aimed to address the limitations of conventional methods for measuring skeletal muscle mass for sarcopenia diagnosis by introducing an artificial intelligence (AI) system for direct computed tomography (CT) analysis. The primary focus was on enhancing simplicity, reproducibility, and convenience, and assessing the accuracy and speed of AI compared with conventional methods. A cohort of 3096 cases undergoing CT imaging up to the third lumbar (L3) level between 2011 and 2021 were included. Random division into preprocessing and sarcopenia cohorts was performed, with further random splits into training and validation cohorts for BMI_AI and Body_AI creation. Sarcopenia_AI utilizes the Skeletal Muscle Index (SMI), which is calculated as (total skeletal muscle area at L3)/(height) 2 . The SMI was conventionally measured twice, with the first as the AI label reference and the second for comparison. Agreement and diagnostic change rates were calculated. Three groups were randomly assigned and 10 images before and after L3 were collected for each case. AI models for body region detection (Deeplabv3) and sarcopenia diagnosis (EfficientNetV2-XL) were trained on a supercomputer, and their abilities and speed per image were evaluated. The conventional method showed a low agreement rate (κ coefficient) of 0.478 for the test cohort and 0.236 for the validation cohort, with diagnostic changes in 43% of cases. Conversely, the AI consistently produced identical results after two measurements. The AI demonstrated robust body region detection ability (intersection over Union (IoU) = 0.93), accurately detecting only the body region in all images. The AI for sarcopenia diagnosis exhibited high accuracy, with a sensitivity of 82.3%, specificity of 98.1%, and a positive predictive value of 89.5%. In conclusion, the reproducibility of the conventional method for sarcopenia diagnosis was low. The developed sarcopenia diagnostic AI, with its high positive predictive value and convenient diagnostic capabilities, is a promising alternative for addressing the shortcomings of conventional approaches.

Background Nanopore sequencing is a rapidly developing third-generation sequencing technology, which can generate long nucleotide reads of molecules within a portable device in real-time. Through detecting the change of ion currency signals during a DNA/RNA fragment’s pass through a nanopore, genotypes are determined. Currently, the accuracy of nanopore basecalling has a higher error rate than the basecalling of short-read sequencing. Through utilizing deep neural networks, the-state-of-the art nanopore basecallers achieve basecalling accuracy in a range from 85% to 95%. Result In this work, we proposed a novel basecalling approach from a perspective of instance segmentation. Different from previous approaches of doing typical sequence labeling, we formulated the basecalling problem as a multi-label segmentation task. Meanwhile, we proposed a refined U-net model which we call UR-net that can model sequential dependencies for a one-dimensional segmentation task. The experiment results show that the proposed basecaller URnano achieves competitive results on the in-species data, compared to the recently proposed CTC-featured basecallers. Conclusion Our results show that formulating the basecalling problem as a one-dimensional segmentation task is a promising approach, which does basecalling and segmentation jointly.

Read-depths (RDs) are frequently used in identifying structural variants (SVs) from sequencing data. For existing RD-based SV callers, it is difficult for them to determine breakpoints in single-nucleotide resolution due to the noisiness of RD data and the bin-based calculation. In this paper, we propose to use the deep segmentation model UNet to learn base-wise RD patterns surrounding breakpoints of known SVs. We integrate model predictions with an RD-based SV caller to enhance breakpoints in single-nucleotide resolution. We show that UNet can be trained with a small amount of data and can be applied both in-sample and cross-sample. An enhancement pipeline named RDBKE significantly increases the number of SVs with more precise breakpoints on simulated and real data. The source code of RDBKE is freely available at https://github.com/yaozhong/deepIntraSV .

[This corrects the article DOI: 10.1371/journal.pone.0241508.].

Approximately 5%–10% of breast cancers are hereditary, caused by germline pathogenic variants (GPVs) in breast cancer predisposition genes. To date, most studies of the prevalence of GPVs and risk of breast cancer for each gene based on cases and noncancer controls have been conducted in Europe and the United States, and little information from Japanese populations is available. Furthermore, no studies considered confounding by established environmental factors and single‐nucleotide polymorphisms (SNPs) identified in genome‐wide association studies (GWAS) together in GPV evaluation. To evaluate the association between GPVs in nine established breast cancer predisposition genes including BRCA1/2 and breast cancer risk in Japanese women comprehensively, we conducted a case‐control study within the Hospital‐based Epidemiologic Research Program at Aichi Cancer Center (629 cases and 1153 controls). The associations between GPVs and the risk of breast cancer were assessed by odds ratios (OR) and 95% confidence intervals (CI) using logistic regression models adjusted for potential confounders. A total of 25 GPVs were detected among all cases (4.0%: 95% CI: 2.6–5.9), whereas four individuals carried GPVs in all controls (0.4%). The OR for breast cancer by all GPVs and by GPVs in BRCA1/2 was 12.2 (4.4–34.0, p = 1.74E‐06) and 16.0 (4.2–60.9, p = 5.03E‐0.5), respectively. A potential confounding with GPVs was observed for the GWAS‐identified SNPs, whereas not for established environmental risk factors. In conclusion, GPVs increase the risk of breast cancer in Japanese women regardless of environmental factors and GWAS‐identified SNPs. Future studies investigating interactions with environment and SNPs are warranted. To evaluate the association between germline pathogenic variants (GPVs) in nine established breast cancer predisposition genes including BRCA1/2 and breast cancer risk in Japanese women comprehensively, we conducted a case‐control study (629 cases and 1153 controls) adjusted for potential confounders. A potential confounding with GPVs was observed for the genome‐wide association studies (GWAS)‐identified SNPs, whereas not for established environmental risk factors. GPVs increase the risk of breast cancer in Japanese women regardless of environmental factors and GWAS‐identified SNPs.

PurposeLow-grade adenosquamous carcinoma (LGASC) is a rare type of metaplastic carcinoma of the breast (MBC) with an indolent clinical course. A few LGASC cases with high-grade transformation have been reported; however, the genetics underlying malignant progression of LGASC remain unclear.MethodsWe performed whole-genome sequencing analysis on five MBCs from four patients, including one case with matching primary LGASC and a lymph node metastatic tumor consisting of high-grade MBC with a predominant metaplastic squamous cell carcinoma component (MSC) that progressed from LGASC and three cases of independent de novo MSC.ResultsUnlike de novo MSC, LGASC and its associated MSC showed no TP53 mutation and tended to contain fewer structural variants than de novo MSC. Both LGASC and its associated MSC harbored the common GNAS c.C2530T:p.Arg844Cys mutation, which was more frequently detected in the cancer cell fraction of MSC. MSC associated with LGASC showed additional pathogenic deletions of multiple tumor-suppressor genes, such as KMT2D and BTG1. Copy number analysis revealed potential 18q loss of heterozygosity in both LGASC and associated MSC. The frequency of SMAD4::DCC fusion due to deletions increased with progression to MSC; however, chimeric proteins were not detected. SMAD4 protein expression was already decreased at the LGASC stage due to unknown mechanisms.ConclusionNot only LGASC but also its associated high-grade MBC may be genetically different from de novo high-grade MBC. Progression from LGASC to high-grade MBC may involve the concentration of driver mutations caused by clonal selection and inactivation of tumor-suppressor genes.