High UV damage and low repair, but not cytosine deamination, stimulate mutation hotspots at ETS binding sites in melanoma.

Noncoding mutation hotspots have been identified in melanoma and many of them occur at the binding sites of E26 transformation-specific (ETS) proteins; however, their formation mechanism and functional impacts are not fully understood. Here, we used UV (Ultraviolet) damage sequencing data and analyzed cyclobutane pyrimidine dimer (CPD) formation, DNA repair, and CPD deamination in human cells at single-nucleotide resolution. Our data show prominent CPD hotspots immediately after UV irradiation at ETS binding sites, particularly at sites with a conserved TTCCGG motif, which correlate with mutation hotspots identified in cutaneous melanoma. Additionally, CPDs are repaired slower at ETS binding sites than in flanking DNA. Cytosine deamination in CPDs to uracil is suggested as an important step for UV mutagenesis. However, we found that CPD deamination is significantly suppressed at ETS binding sites, particularly for the CPD hotspot on the 5' side of the ETS motif, arguing against a role for CPD deamination in promoting ETS-associated UV mutations. Finally, we analyzed a subset of frequently mutated promoters, including the ribosomal protein genes RPL13A and RPS20, and found that mutations in the ETS motif can significantly reduce the promoter activity. Thus, our data identify high UV damage and low repair, but not CPD deamination, as the main mechanism for ETS-associated mutations in melanoma and uncover important roles of often-overlooked mutation hotspots in perturbing gene transcription.

AlpaPICO: Extraction of PICO frames from clinical trial documents using LLMs.

In recent years, there has been a surge in the publication of clinical trial reports, making it challenging to conduct systematic reviews. Automatically extracting Population, Intervention, Comparator, and Outcome (PICO) from clinical trial studies can alleviate the traditionally time-consuming process of manually scrutinizing systematic reviews. Existing approaches of PICO frame extraction involves supervised approach that relies on the existence of manually annotated data points in the form of BIO label tagging. Recent approaches, such as In-Context Learning (ICL), which has been shown to be effective for a number of downstream NLP tasks, require the use of labeled examples. In this work, we adopt ICL strategy by employing the pretrained knowledge of Large Language Models (LLMs), gathered during the pretraining phase of an LLM, to automatically extract the PICO-related terminologies from clinical trial documents in unsupervised set up to bypass the availability of large number of annotated data instances. Additionally, to showcase the highest effectiveness of LLM in oracle scenario where large number of annotated samples are available, we adopt the instruction tuning strategy by employing Low Rank Adaptation (LORA) to conduct the training of gigantic model in low resource environment for the PICO frame extraction task. More specifically, both of the proposed frameworks utilize AlpaCare as base LLM which employs both few-shot in-context learning and instruction tuning techniques to extract PICO-related terms from the clinical trial reports. We applied these approaches to the widely used coarse-grained datasets such as EBM-NLP, EBM-COMET and fine-grained datasets such as EBM-NLPrev and EBM-NLPh. Our empirical results show that our proposed ICL-based framework produces comparable results on all the version of EBM-NLP datasets and the proposed instruction tuned version of our framework produces state-of-the-art results on all the different EBM-NLP datasets. Our project is available at https://github.com/shrimonmuke0202/AlpaPICO.git.

Generation of site-specifically labelled fluorescent human XPA to investigate DNA binding dynamics during nucleotide excision repair.

Nucleotide excision repair (NER) promotes genomic integrity by removing bulky DNA adducts introduced by external factors such as ultraviolet light. Defects in NER enzymes are associated with pathological conditions such as Xeroderma Pigmentosum, trichothiodystrophy, and Cockayne syndrome. A critical step in NER is the binding of the Xeroderma Pigmentosum group A protein (XPA) to the ss/ds DNA junction. To better capture the dynamics of XPA interactions with DNA during NER we have utilized the fluorescence enhancement through non-canonical amino acids (FEncAA) approach. 4-azido-L-phenylalanine (4AZP or pAzF) was incorporated at Arg-158 in human XPA and conjugated to Cy3 using strain-promoted azide-alkyne cycloaddition. The resulting fluorescent XPA protein (XPACy3) shows no loss in DNA binding activity and generates a robust change in fluorescence upon binding to DNA. Here we describe methods to generate XPACy3 and detail in vitro experimental conditions required to stably maintain the protein during biochemical and biophysical studies.

Wiskott Aldrich syndrome protein (WASp)-deficient Th1 cells promote R-loop-driven transcriptional insufficiency and transcription-coupled nucleotide excision repair factor (TC-NER)-driven genome-instability in the pathogenesis of T cell acute lymphoblastic leukemia.

BACKGROUND: T-ALL is an aggressive hematological tumor that develops as the result of a multi-step oncogenic process which causes expansion of hematopoietic progenitors that are primed for T cell development to undergo malignant transformation and growth. Even though first-line therapy has a significant response rate, 40% of adult patients and 20% of pediatric patients will relapse. Therefore, there is an unmet need for treatment for relapsed/refractory T-ALL to develop potential targeted therapies. METHODS: Pediatric T-ALL patient derived T cells were grown under either nonskewingTh0 or Th1-skewing conditions to further process for ChIP-qPCR, RDIP-qPCR and other RT-PCR assays. Endogenous WASp was knocked out using CRISPR-Cas9 and was confirmed using flow cytometry and western blotting. LC-MS/MS was performed to find out proteomic dataset of WASp-interactors generated from Th1-skewed, human primary Th-cells. DNA-damage was assessed by immunofluorescence confocal-imaging and single-cell gel electrophoresis (comet assay). Overexpression of RNaseH1 was also done to restore normal Th1-transcription in WASp-deficient Th1-skewed cells. RESULTS: We discovered that nuclear-WASp is required for suppressing R-loop production (RNA/DNA-hybrids) at Th1-network genes by ribonucleaseH2 (RNH2) and topoisomerase1. Nuclear-WASp is associated with the factors involved in preventing and dissolving R-loops in Th1 cells. In nuclear- WASp-reduced malignant Th1-cells, R-loops accumulate in vivo and are processed into DNA-breaks by transcription-coupled-nucleotide-excision repair (TC-NER). Several epigenetic modifications were also found to be involved at Th1 gene locus which are responsible for active/repressive marks of particular genes. By demonstrating WASp as a physiologic regulator of programmed versus unprogrammed R-loops, we suggest that the transcriptional role of WASp in vivo extends also to prevent transcription-linked DNA damage during malignancy and through modification of epigenetic dysregulations. CONCLUSION: Our findings present a provocative possibility of resetting R-loops as a therapeutic intervention to correct both immune deficiency and malignancy in T-cell acute lymphoblastic leukemia patients and a novel role of WASp in the epigenetic regulation of T helper cell differentiation in T-ALL patients, anticipating WASp's requirement for the suppression of T-ALL progression.

Artificial intelligence-powered pharmacovigilance: A review of machine and deep learning in clinical text-based adverse drug event detection for benchmark datasets.

OBJECTIVE: The primary objective of this review is to investigate the effectiveness of machine learning and deep learning methodologies in the context of extracting adverse drug events (ADEs) from clinical benchmark datasets. We conduct an in-depth analysis, aiming to compare the merits and drawbacks of both machine learning and deep learning techniques, particularly within the framework of named-entity recognition (NER) and relation classification (RC) tasks related to ADE extraction. Additionally, our focus extends to the examination of specific features and their impact on the overall performance of these methodologies. In a broader perspective, our research extends to ADE extraction from various sources, including biomedical literature, social media data, and drug labels, removing the limitation to exclusively machine learning or deep learning methods. METHODS: We conducted an extensive literature review on PubMed using the query "(((machine learning [Medical Subject Headings (MeSH) Terms]) OR (deep learning [MeSH Terms])) AND (adverse drug event [MeSH Terms])) AND (extraction)", and supplemented this with a snowballing approach to review 275 references sourced from retrieved articles. RESULTS: In our analysis, we included twelve articles for review. For the NER task, deep learning models outperformed machine learning models. In the RC task, gradient Boosting, multilayer perceptron and random forest models excelled. The Bidirectional Encoder Representations from Transformers (BERT) model consistently achieved the best performance in the end-to-end task. Future efforts in the end-to-end task should prioritize improving NER accuracy, especially for 'ADE' and 'Reason'. CONCLUSION: These findings hold significant implications for advancing the field of ADE extraction and pharmacovigilance, ultimately contributing to improved drug safety monitoring and healthcare outcomes.

Getting to Know Named Entity Recognition: Better Information Retrieval.

Named entity recognition (NER) is a powerful computer system that utilizes various computing strategies to extract information from raw text input, since the early 1990s. With rapid advancement in AI and computing, NER models have gained significant attention and been serving as foundational tools across numerus professional domains to organize unstructured data for research and practical applications. This is particularly evident in the medical and healthcare fields, where NER models are essential in efficiently extract critical information from complex documents that are challenging for manual review. Despite its successes, NER present limitations in fully comprehending natural language nuances. However, the development of more advanced and user-friendly models promises to improve work experiences of professional users significantly.

The Role of DNA Repair (XPC, XPD, XPF, and XPG) Gene Polymorphisms in the Development of Myeloproliferative Neoplasms.

Background and Objectives: Several polymorphisms have been described in various DNA repair genes. Nucleotide excision DNA repair (NER) detects defects of DNA molecules and corrects them to restore genome integrity. We hypothesized that the XPC, XPD, XPF, and XPG gene polymorphisms influence the appearance of myeloproliferative neoplasms (MPNs). Materials and Methods: We investigated the XPC 1496C>T (rs2228000, XPC Ala499Val), XPC 2920A>C (rs228001, XPC Lys939Gln), XPD 2251A>C (rs13181, XPD Lys751Gln), XPF-673C>T (rs3136038), XPF 11985A>G (rs254942), and XPG 3507G>C (rs17655, XPG Asp1104His) polymorphisms by polymerase chain reaction-restriction fragment length polymorphism analysis in 393 MPN patients [153 with polycythemia vera (PV), 201 with essential thrombocythemia (ET), and 39 with primary myelofibrosis (PMF)] and 323 healthy controls. Results: Overall, we found that variant genotypes of XPD 2251A>C were associated with an increased risk of MPN (OR = 1.54, 95% CI = 1.15-2.08, p = 0.004), while XPF-673C>T and XPF 11985A>G were associated with a decreased risk of developing MPN (OR = 0.56, 95% CI = 0.42-0.76, p < 0.001; and OR = 0.26, 95% CI = 0.19-0.37, p < 0.001, respectively). Conclusions: In light of our findings, XPD 2251A>C polymorphism was associated with the risk of developing MPN and XPF-673C>T and XPF 11985A>G single nucleotide polymorphisms (SNPs) may have a protective role for MPN, while XPC 1496C>T, XPC 2920A>C, and XPG 3507G>C polymorphisms do not represent risk factors in MPN development.

Methods for Assessment of Nucleotide Excision Repair Efficiency.

Nucleotide excision repair (NER) is responsible for removing a wide variety of bulky adducts from DNA, thus contributing to the maintenance of genome stability. The efficiency with which proteins of the NER system recognize and remove bulky adducts depends on many factors and is of great clinical and diagnostic significance. The review examines current concepts of the NER system molecular basis in eukaryotic cells and analyzes methods for the assessment of the NER-mediated DNA repair efficiency both in vitro and ex vivo.

Exploring Negated Entites for Named Entity Recognition in Italian Lung Cancer Clinical Reports.

This paper explores the potential of leveraging electronic health records (EHRs) for personalized health research through the application of artificial intelligence (AI) techniques, specifically Named Entity Recognition (NER). By extracting crucial patient information from clinical texts, including diagnoses, medications, symptoms, and lab tests, AI facilitates the rapid identification of relevant data, paving the way for future care paradigms. The study focuses on Non-small cell lung cancer (NSCLC) in Italian clinical notes, introducing a novel set of 29 clinical entities that include both presence or absence (negation) of relevant information associated with NSCLC. Using a state-of-the-art model pretrained on Italian biomedical texts, we achieve promising results (average F1-score of 80.8%), demonstrating the feasibility of employing AI for extracting biomedical information in the Italian language.

Development of Unified Terminological System Based on UMLS: Experience and Perspectives.

This article presents experience in construction the National Unified Terminological System (NUTS) with an ontological structure based on international Unified Medical Language System (UMLS). UMLS has been adapted and enriched with formulations from national directories, relationships, extracted from the texts of scientific articles and electronic health records, and weight coefficients.

Cisplatin-induced DNA crosslinks trigger neurotoxicity in C. elegans.

The anticancer drug cisplatin (CisPt) injures post-mitotic neuronal cells, leading to neuropathy. Furthermore, CisPt triggers cell death in replicating cells. Here, we aim to unravel the relevance of different types of CisPt-induced DNA lesions for evoking neurotoxicity. To this end, we comparatively analyzed wild-type and loss of function mutants of C. elegans lacking key players of specific DNA repair pathways. Deficiency in ercc-1, which is essential for nucleotide excision repair (NER) and interstrand crosslink (ICL) repair, revealed the most pronounced enhancement in CisPt-induced neurotoxicity with respect to the functionality of post-mitotic chemosensory AWA neurons, without inducing neuronal cell death. Potentiation of CisPt-triggered neurotoxicity in ercc-1 mutants was accompanied by complex alterations in both basal and CisPt-stimulated mRNA expression of genes involved in the regulation of neurotransmission, including cat-4, tph-1, mod-1, glr-1, unc-30 and eat-18. Moreover, xpf-1, csb-1, csb-1;xpc-1 and msh-6 mutants were significantly more sensitive to CisPt-induced neurotoxicity than the wild-type, whereas xpc-1, msh-2, brc-1 and dog-1 mutants did not distinguish from the wild-type. The majority of DNA repair mutants also revealed increased basal germline apoptosis, which was analyzed for control. Yet, only xpc-1, xpc-1;csb-1 and dog-1 mutants showed elevated apoptosis in the germline following CisPt treatment. To conclude, we provide evidence that neurotoxicity, including sensory neurotoxicity, is triggered by CisPt-induced DNA intra- and interstrand crosslinks that are subject of repair by NER and ICL repair. We hypothesize that especially ERCC1/XPF, CSB and MSH6-related DNA repair protects from chemotherapy-induced neuropathy in the context of CisPt-based anticancer therapy.

An important step towards the comprehensive sun protection: Blue-light exposure inhibits DNA repair in reconstituted human skin and a broadband sunscreen avoids this inhibition.

The field of sun protection is quickly changing and the research article by Douki et al., published in the current issue of Photochemistry and Photobiology, reported key experimental data that will certainly help the development of better sun care products. Mutagenic photoproducts (CPDs, cyclobutane pyrimidine dimers and 6-4PPs, pyrimidine-6-4-pyrimidone photoproducts) were formed in the reconstructed human epidermis (RHE) by UVB (312 nm) irradiation, and their concentrations were detected by HPLC-MS/MS as a function of time after the UVB treatment. RHE had been previously exposed or not (control) to blue light (427 nm). Both CPDs and 6-4PPs were shown to last longer in blue-light irradiated RHE, proving the inhibition of the DNA repair by blue light exposure. This is a highly relevant information because sunscreens allow people to enjoy longer periods under the sun and consequently, to endure very high doses of blue light. The work also reported results obtained with RHEs previously treated with a sunscreen formulation containing a broadband filter that offers blue-light protection. Interestingly, authors observed that the DNA repair was not significantly inhibited in RHE previously treated with the sunscreen offering broadband protection. Readers will find a scientifically sound proof of the importance of blue-light protection in sun care products.

Sequential post-translational modifications regulate damaged DNA-binding protein DDB2 function.

Nucleotide excision repair (NER) is a major DNA repair system and hereditary defects in this system cause critical genetic diseases (e.g., xeroderma pigmentosum, Cockayne syndrome, and trichothiodystrophy). Various proteins are involved in the eukaryotic NER system and undergo several post-translational modifications. Damaged DNA-binding protein 2 (DDB2) is a DNA damage recognition factor in the NER pathway. We previously demonstrated that DDB2 was SUMOylated in response to UV irradiation; however, its physiological roles remain unclear. We herein analyzed several mutants and showed that the N-terminal tail of DDB2 was the target for SUMOylation; however, this region did not contain a consensus SUMOylation sequence. We found a SUMO-interacting motif (SIM) in the N-terminal tail that facilitated SUMOylation. The ubiquitination of a SUMOylation-deficient DDB2 SIM mutant was decreased and its retention of chromatin was prolonged. The SIM mutant showed impaired NER, possibly due to a decline in the timely handover of the lesion site to XPC. These results suggest that the SUMOylation of DDB2 facilitates NER through enhancements in ubiquitination.

Skin cancer induction by the antimycotic drug voriconazole is caused by impaired DNA damage detection due to chromatin compaction.

Phototoxicity and skin cancer are severe adverse effects of the anti-fungal drug Voriconazole (VOR). These adverse effects resemble those seen in xeroderma pigmentosum (XP), caused by defective DNA nucleotide excision repair (NER), and we show that VOR decreases NER capacity. We show that VOR treatment does not perturb the expression of NER, or other DNA damage-related genes, but that VOR localizes to heterochromatin, in complexes containing histone acetyltransferase GCN5. Impairment of GCN5 binding to histone H3 reduced acetylation of H3, restricting damage-dependent chromatin unfolding, thereby reducing NER initiation. Restoration of H3 histone acetylation using histone deacetylase inhibitors (HDACi), rescued VOR-induced NER repression, thus offering a preventive therapeutic option. These findings underline the importance of DNA damage-dependent chromatin remodeling as an important prerequisite of functional DNA repair.

BioBBC: a multi-feature model that enhances the detection of biomedical entities.

The rapid increase in biomedical publications necessitates efficient systems to automatically handle Biomedical Named Entity Recognition (BioNER) tasks in unstructured text. However, accurately detecting biomedical entities is quite challenging due to the complexity of their names and the frequent use of abbreviations. In this paper, we propose BioBBC, a deep learning (DL) model that utilizes multi-feature embeddings and is constructed based on the BERT-BiLSTM-CRF to address the BioNER task. BioBBC consists of three main layers; an embedding layer, a Long Short-Term Memory (Bi-LSTM) layer, and a Conditional Random Fields (CRF) layer. BioBBC takes sentences from the biomedical domain as input and identifies the biomedical entities mentioned within the text. The embedding layer generates enriched contextual representation vectors of the input by learning the text through four types of embeddings: part-of-speech tags (POS tags) embedding, char-level embedding, BERT embedding, and data-specific embedding. The BiLSTM layer produces additional syntactic and semantic feature representations. Finally, the CRF layer identifies the best possible tag sequence for the input sentence. Our model is well-constructed and well-optimized for detecting different types of biomedical entities. Based on experimental results, our model outperformed state-of-the-art (SOTA) models with significant improvements based on six benchmark BioNER datasets.

Knowledge Base Prototype Creating with Using Interdisciplinary Metathesaurus.

This article presents our experience in development an ontological model can be used in clinical decision support systems (CDSS) creating. We have used the largest international biomedical terminological metathesaurus the Unified Medical Language System (UMLS) as the basis of our model. This metathesaurus has been adapted into Russian using an automated hybrid translation system with expert control. The product we have created was named as the National Unified Terminological System (NUTS). We have added more than 33 million scientific and clinical relationships between NUTS terms, extracted from the texts of scientific articles and electronic health records. We have also computed weights for each relationship, standardized their values and created symptom checker in preliminary diagnostics based on this. We expect, that the NUTS allow solving task of named entity recognition (NER) and increasing terms interoperability in different CDSS.

DNA lesions that block transcription induce the death of Trypanosoma cruzi via ATR activation, which is dependent on the presence of R-loops.

Trypanosoma cruzi is the etiological agent of Chagas disease and a peculiar eukaryote with unique biological characteristics. DNA damage can block RNA polymerase, activating transcription-coupled nucleotide excision repair (TC-NER), a DNA repair pathway specialized in lesions that compromise transcription. If transcriptional stress is unresolved, arrested RNA polymerase can activate programmed cell death. Nonetheless, how this parasite modulates these processes is unknown. Here, we demonstrate that T. cruzi cell death after UV irradiation, a genotoxic agent that generates lesions resolved by TC-NER, depends on active transcription and is signaled mainly by an apoptotic-like pathway. Pre-treated parasites with α-amanitin, a selective RNA polymerase II inhibitor, become resistant to such cell death. Similarly, the gamma pre-irradiated cells are more resistant to UV when the transcription processes are absent. The Cockayne Syndrome B protein (CSB) recognizes blocked RNA polymerase and can initiate TC-NER. Curiously, CSB overexpression increases parasites' cell death shortly after UV exposure. On the other hand, at the same time after irradiation, the single-knockout CSB cells show resistance to the same treatment. UV-induced fast death is signalized by the exposition of phosphatidylserine to the outer layer of the membrane, indicating a cell death mainly by an apoptotic-like pathway. Furthermore, such death is suppressed in WT parasites pre-treated with inhibitors of ataxia telangiectasia and Rad3-related (ATR), a key DDR kinase. Signaling for UV radiation death may be related to R-loops since the overexpression of genes associated with the resolution of these structures suppress it. Together, results suggest that transcription blockage triggered by UV radiation activates an ATR-dependent apoptosis-like mechanism in T. cruzi, with the participation of CSB protein in this process.

Mediator complex in transcription regulation and DNA repair: Relevance for human diseases.

The Mediator complex is an essential coregulator of RNA polymerase II transcription. More recent developments suggest Mediator functions as a link between transcription regulation, genome organisation and DNA repair mechanisms including nucleotide excision repair, base excision repair, and homologous recombination. Dysfunctions of these processes are frequently associated with human pathologies, and growing evidence shows Mediator involvement in cancers, neurological, metabolic and infectious diseases. The detailed deciphering of molecular mechanisms of Mediator functions, using interdisciplinary approaches in different biological models and considering all functions of this complex, will contribute to our understanding of relevant human diseases.

Named entity recognition and emotional viewpoint monitoring in online news using artificial intelligence.

Network news is an important way for netizens to get social information. Massive news information hinders netizens to get key information. Named entity recognition technology under artificial background can realize the classification of place, date and other information in text information. This article combines named entity recognition and deep learning technology. Specifically, the proposed method introduces an automatic annotation approach for Chinese entity triggers and a Named Entity Recognition (NER) model that can achieve high accuracy with a small number of training data sets. The method jointly trains sentence and trigger vectors through a trigger-matching network, utilizing the trigger vectors as attention queries for subsequent sequence annotation models. Furthermore, the proposed method employs entity labels to effectively recognize neologisms in web news, enabling the customization of the set of sensitive words and the number of words within the set to be detected, as well as extending the web news word sentiment lexicon for sentiment observation. Experimental results demonstrate that the proposed model outperforms the traditional BiLSTM-CRF model, achieving superior performance with only a 20% proportional training data set compared to the 40% proportional training data set required by the conventional model. Moreover, the loss function curve shows that my model exhibits better accuracy and faster convergence speed than the compared model. Finally, my model achieves an average accuracy rate of 97.88% in sentiment viewpoint detection.

ERCC4: a potential regulatory factor in inflammatory bowel disease and inflammation-associated colorectal cancer.

The pathogenesis of inflammatory bowel disease (IBD) remains unclear and is associated with an increased risk of developing colitis-associated cancer (CAC). Under sustained inflammatory stimulation in the intestines, loss of early DNA damage response genes can lead to tumor formation. Many proteins are involved in the pathways of DNA damage response and play critical roles in protecting genes from various potential damages that DNA may undergo. ERCC4 is a structure-specific endonuclease that participates in the nucleotide excision repair (NER) pathway. The catalytic site of ERCC4 determines the activity of NER and is an indispensable gene in the NER pathway. ERCC4 may be involved in the imbalanced process of DNA damage and repair in IBD-related inflammation and CAC. This article primarily reviews the function of ERCC4 in the DNA repair pathway and discusses its potential role in the processes of IBD-related inflammation and carcinogenesis. Finally, we explore how this knowledge may open novel avenues for the treatment of IBD and IBD-related cancer.