Integrating spatial and single-cell transcriptomics reveals tumor heterogeneity and intercellular networks in colorectal cancer.

Single cell RNA sequencing (scRNA-seq), a powerful tool for studying the tumor microenvironment (TME), does not preserve/provide spatial information on tissue morphology and cellular interactions. To understand the crosstalk between diverse cellular components in proximity in the TME, we performed scRNA-seq coupled with spatial transcriptomic (ST) assay to profile 41,700 cells from three colorectal cancer (CRC) tumor-normal-blood pairs. Standalone scRNA-seq analyses revealed eight major cell populations, including B cells, T cells, Monocytes, NK cells, Epithelial cells, Fibroblasts, Mast cells, Endothelial cells. After the identification of malignant cells from epithelial cells, we observed seven subtypes of malignant cells that reflect heterogeneous status in tumor, including tumor_CAV1, tumor_ATF3_JUN | FOS, tumor_ZEB2, tumor_VIM, tumor_WSB1, tumor_LXN, and tumor_PGM1. By transferring the cellular annotations obtained by scRNA-seq to ST spots, we annotated four regions in a cryosection from CRC patients, including tumor, stroma, immune infiltration, and colon epithelium regions. Furthermore, we observed intensive intercellular interactions between stroma and tumor regions which were extremely proximal in the cryosection. In particular, one pair of ligands and receptors (C5AR1 and RPS19) was inferred to play key roles in the crosstalk of stroma and tumor regions. For the tumor region, a typical feature of TMSB4X-high expression was identified, which could be a potential marker of CRC. The stroma region was found to be characterized by VIM-high expression, suggesting it fostered a stromal niche in the TME. Collectively, single cell and spatial analysis in our study reveal the tumor heterogeneity and molecular interactions in CRC TME, which provides insights into the mechanisms underlying CRC progression and may contribute to the development of anticancer therapies targeting on non-tumor components, such as the extracellular matrix (ECM) in CRC. The typical genes we identified may facilitate to new molecular subtypes of CRC.

A review of graph and complex network theory in water distribution networks: Mathematical foundation, application and prospects.

Graph theory (GT) and complex network theory play an increasingly important role in the design, operation, and management of water distribution networks (WDNs) and these tasks were originally often heavily dependent on hydraulic models. Facing the general reality of the lack of high-precision hydraulic models in water utilities, GT has become a promising surrogate or assistive technology. However, there is a lack of a systematic review of how and where the GT techniques are applied to the field of WDNs, along with an examination of potential directions that GT can contribute to addressing WDNs' challenges. This paper presents such a review and first summarizes the graph construction methods and topological properties of WDNs, which are mathematical foundations for the application of GT in WDNs. Then, main application areas, including state estimation, performance evaluation, partitioning, optimal design, optimal sensor placement, critical components identification, and interdependent networks analysis, are identified and reviewed. GT techniques can provide acceptable results and valuable insights while having a low computational burden compared with hydraulic models. Combining GT with hydraulic model significantly enhances the performance of analysis methods. Four research challenges, namely reasonable abstraction, data availability, tailored topological indicators, and integration with Graph Neural Networks (GNNs), have been identified as key areas for advancing the application and implementation of GT in WDNs. This paper would have a positive impact on promoting the use of GT for optimal design and sustainable management of WDNs.

circRNADisease v2.0: an updated resource for high-quality experimentally supported circRNA-disease associations.

circRNADisease v2.0 is an enhanced and reliable database that offers experimentally verified relationships between circular RNAs (circRNAs) and various diseases. It is accessible at http://cgga.org.cn/circRNADisease/ or http://cgga.org.cn:9091/circRNADisease/. The database currently includes 6998 circRNA-disease entries across multiple species, representing a remarkable 19.77-fold increase compared to the previous version. This expansion consists of a substantial rise in the number of circRNAs (from 330 to 4246), types of diseases (from 48 to 330) and covered species (from human only to 12 species). Furthermore, a new section has been introduced in the database, which collects information on circRNA-associated factors (genes, proteins and microRNAs), molecular mechanisms (molecular pathways), biological functions (proliferation, migration, invasion, etc.), tumor and/or cell line and/or patient-derived xenograft (PDX) details, and prognostic evidence in diseases. In addition, we identified 7 159 865 relationships between mutations and circRNAs among 30 TCGA cancer types. Due to notable enhancements and extensive data expansions, the circRNADisease 2.0 database has become an invaluable asset for both clinical practice and fundamental research. It enables researchers to develop a more comprehensive understanding of how circRNAs impact complex diseases.

Modeling Indirect Greenhouse Gas Emissions Sources from Urban Wastewater Treatment Plants: Integrating Machine Learning Models to Compensate for Sparse Parameters with Abundant Observations.

Electricity consumption and sludge yield (SY) are important indirect greenhouse gas (GHG) emission sources in wastewater treatment plants (WWTPs). Predicting these byproducts is crucial for tailoring technology-related policy decisions. However, it challenges balancing mass balance models and mechanistic models that respectively have limited intervariable nexus representation and excessive requirements on operational parameters. Herein, we propose integrating two machine learning models, namely, gradient boosting tree (GBT) and deep learning (DL), to precisely pointwise model electricity consumption intensity (ECI) and SY for WWTPs in China. Results indicate that GBT and DL are capable of mining massive data to compensate for the lack of available parameters, providing a comprehensive modeling focusing on operation conditions and designed parameters, respectively. The proposed model reveals that lower ECI and SY were associated with higher treated wastewater volumes, more lenient effluent standards, and newer equipment. Moreover, ECI and SY showed different patterns when influent biochemical oxygen demand is above or below 100 mg/L in the anaerobic-anoxic-oxic process. Therefore, managing ECI and SY requires quantifying the coupling relationships between biochemical reactions instead of isolating each variable. Furthermore, the proposed models demonstrate potential economic-related inequalities resulting from synergizing water pollution and GHG emissions management.

Metagenomic next-generation sequencing of bronchoalveolar lavage fluid assists in the diagnosis of pathogens associated with lower respiratory tract infections in children.

Worldwide, lower respiratory tract infections (LRTI) are an important cause of hospitalization in children. Due to the relative limitations of traditional pathogen detection methods, new detection methods are needed. The purpose of this study was to evaluate the value of metagenomic next-generation sequencing (mNGS) of bronchoalveolar lavage fluid (BALF) samples for diagnosing children with LRTI based on the interpretation of sequencing results. A total of 211 children with LRTI admitted to the First Affiliated Hospital of Guangzhou Medical University from May 2019 to December 2020 were enrolled. The diagnostic performance of mNGS versus traditional methods for detecting pathogens was compared. The positive rate for the BALF mNGS analysis reached 95.48% (95% confidence interval [CI] 92.39% to 98.57%), which was superior to the culture method (44.07%, 95% CI 36.68% to 51.45%). For the detection of specific pathogens, mNGS showed similar diagnostic performance to PCR and antigen detection, except for Streptococcus pneumoniae, for which mNGS performed better than antigen detection. S. pneumoniae, cytomegalovirus and Candida albicans were the most common bacterial, viral and fungal pathogens. Common infections in children with LRTI were bacterial, viral and mixed bacterial-viral infections. Immunocompromised children with LRTI were highly susceptible to mixed and fungal infections. The initial diagnosis was modified based on mNGS in 29.6% (37/125) of patients. Receiver operating characteristic (ROC) curve analysis was performed to predict the relationship between inflammation indicators and the type of pathogen infection. BALF mNGS improves the sensitivity of pathogen detection and provides guidance in clinical practice for diagnosing LRTI in children.

The Use of Antimicrobial Drug in Patients During the COVID-19 Pandemic: A Meta-Analysis.

Objective: To analyze the use of antimicrobial drugs in patients during the COVID-19 pandemic. Methods: We searched for literature about antimicrobial treatment in COVID-19 patients through the Cochrane Library, Embase, PubMed, the Chinese biomedical literature database, CNKI, the Chinese journal full-text database, Wanfang, and Vipu. The quality evaluation of the literature was performed by Jadad's quality score. Results: A total of three articles reported on ivermectin treatment in patients with COVID-19, and the Meta-analysis showed no clinical and statistical heterogeneity among the studies (I2 = 15%, P = .31), a fixed effect model was used to incorporate effect sizes. The clinical effect of the observed group was not different from the control group (P = .16). None of the three ivermectin articles with clinical effect as the effect indicator showed a significant difference (P > .05), suggesting no publication bias. A total of four publications reported the treatment with azithromycin in patients with COVID-19, and the Meta-analysis showed no clinical and statistical heterogeneity between the studies (I2 = 0%, P = .88), using a fixed-effect model to incorporate the effect sizes. The clinical effect of the observed group was not different from the control group (P = .57). None of the four azithromycin articles with a clinical effect as the effect index was statistically significant (P > .05), suggesting no publication bias. Conclusion: During the COVID-19 pandemic, the patient's use of antibiotics does not significantly improve clinical efficacy, so antibiotic use is recommended only for patients with complicated bacterial infections.

singleCellBase: a high-quality manually curated database of cell markers for single cell annotation across multiple species.

Annotating cells in the analysis of single-cell RNA-seq (scRNA-seq) data is one of the most challenging tasks that researchers are actively addressing. Manual cell annotation is generally considered the gold standard method, although it is labor intensive and independent of prior knowledge. At present, the relationship between high-quality, known marker genes and cell types is very limited, especially for a variety of species other than humans and mice. The singleCellBase is a manually curated resource of high-quality cell types and gene markers associations across multiple species. In details, it offers 9,158 entries spanning a total of 1,221 cell types and linking with 8,740 genes (cell markers), covering 464 diseases/status, and 165 types of tissues across 31 species. The singleCellBase provides a user-friendly interface to the scientific community to browse, search, download and submit records of marker genes and cell types. The resource providing ineluctable prior knowledge required by manual cell annotation, which is valuable to interpret scRNA-seq data and elucidate what cell type or cell state that a cell population represents.

Lyoniresinol attenuates cerebral ischemic stroke injury in MCAO rat based on oxidative stress suppression via regulation of Akt/GSK-3ß/Nrf2 signaling.

Stroke is one of the predominant causes of death and disability. Currently, besides thrombolytic therapy, neuroprotection is also generally recognized as a promising way for stroke treatment, which would be very important for the functional recovery of stroke patients. However, it's reported that all the current available neuroprotective drugs have failed in clinical investigations of stroke treatments so far. Lyoniresinol (LNO) is a natural lignan with powerful antioxidant and cytoprotective activities. In this study, OGD/R leaded HT22 cell damage models and Middle Cerebral Artery Occlusion (MCAO) rats were used to investigate the effect of LNO on cerebral ischemic stroke injury and related mechanisms. The cell experiments revealed LNO can suppress the oxygen glucose deprivation-reoxygenation (OGD/R) induced apoptosis of HT22 cells. Subsequently, LNO can improve nerve function deficit and brain injury in MCAO rats with a higher neurological function scores and less infarct size. And the further molecular mechanisms studies suggested LNO activated the PI3K/AKT/GSK-3ß/NRF2 signaling and improved the oxidative stress in cells to inhibit the OGD/R induced apoptosis in HT22 cells. Collectively, our findings would be useflu for the further drug development of LNO as new drug for stroke and its related diseases.

Data augmentation with norm-AE and selective pseudo-labelling for unsupervised domain adaptation.

We address the Unsupervised Domain Adaptation (UDA) problem in image classification from a new perspective. In contrast to most existing works which either align the data distributions or learn domain-invariant features, we directly learn a unified classifier for both the source and target domains in the high-dimensional homogeneous feature space without explicit domain alignment. To this end, we employ the effective Selective Pseudo-Labelling (SPL) technique to take advantage of the unlabelled samples in the target domain. Surprisingly, data distribution discrepancy across the source and target domains can be well handled by a computationally simple classifier (e.g., a shallow Multi-Layer Perceptron) trained in the original feature space. Besides, we propose a novel generative model norm-AE to generate synthetic features for the target domain as a data augmentation strategy to enhance the classifier training. Experimental results on several benchmark datasets demonstrate the pseudo-labelling strategy itself can lead to comparable performance to many state-of-the-art methods whilst the use of norm-AE for feature augmentation can further improve the performance in most cases. As a result, our proposed methods (i.e. naive-SPL and norm-AE-SPL) can achieve comparable performance with state-of-the-art methods with the average accuracy of 93.4% and 90.4% on Office-Caltech and ImageCLEF-DA datasets, and achieve competitive performance on Digits, Office31 and Office-Home datasets with the average accuracy of 97.2%, 87.6% and 68.6% respectively.

China's enhanced urban wastewater treatment increases greenhouse gas emissions and regional inequality.

Sustainable water pollution control requires understanding of historical trajectories and spatial characteristics of greenhouse gas (GHG) emissions from wastewater treatment plants (WWTPs), which remains inadequately studied. Here, we establish plant-level monthly operational emissions inventories of China's WWTPs in 2009-2019. We show that urban wastewater treatment has been enhanced with 80% more chemical oxygen demand being removed annually. However, this progress is associated with 180% more GHG emissions at the national level, up to 58.3 Mt CO2 eq in 2019. We found significant seasonality in GHG emissions. Increasing sludge yield and electricity intensity became primary drivers after 2015 because of stricter standards, causing GHG emissions increase 12.9 and 8.3% until 2019. GHG emissions from urban wastewater treatment show high spatial difference at province, city and plant levels, with different sludge disposal and energy mix approaches combined with different influent and effluent conditions in WWTPs across China. Stricter effluent standard resulted in similar GHG emissions growth pattern in cities. We argue WWTPs focus on resource recovery in developed areas and higher operational efficiency in developing areas.

Bioinspired Nanocomplexes Comprising Phenolic Acid Derivative and Human Serum Albumin for Cancer Therapy.

Inspired by the natural phenomenon of phenolic-protein interactions, we translate this "naturally evolved interaction" to a "phenolic acid derivative based albumin bound" technology, through the synthesis of phenolic acid derivatives comprising a therapeutic cargo linked to a phenolic motif. Phenolic acid derivatives can bind to albumin and form nanocomplexes after microfluidic mixing. This strategy has been successfully applied to different types of anticancer drugs, including taxanes, anthraquinones, etoposides, and terpenoids. Paclitaxel was selected as a model drug for an in-depth study. Three novel paclitaxel-phenolic acid conjugates have been synthesized. Molecular dynamics simulations provide insights into the self-assembled mechanisms of phenolic-protein nanocomplexes. The nanocomplexes show improved pharmacokinetics, elevated tolerability, decreased neurotoxicity, and enhanced anticancer efficacies in multiple murine xenograft models of breast cancer, in comparison with two clinically approved formulations, Taxol (polyoxyethylated castor oil-formulated paclitaxel) and Abraxane (nab-paclitaxel). Such a robust system provides a broadly applicable platform for the development of albumin-based nanomedicines and has great potential for clinical translation.

Prognostic Pathways Guide Drug Indications in Pan-Cancers.

Pathway-level analysis is a powerful approach enabling the interpretation of post-genomic data at a higher level than that of individual molecules. Molecular-targeted therapy focusing on cascade signaling pathways has become a new paradigm in anticancer therapy, instead of a single protein. However, the approaches to narrowing down the long list of biological pathways are limited. Here, we proposed a strategy for in silico Drug Prescription on biological pathways across pan-Cancers (CDP), by connecting drugs to candidate pathways. Applying on a list of 120 traditional Chinese medicines (TCM), we especially identified the "TCM-pathways-cancers" triplet and constructed it into a heterogeneous network across pan-cancers. Applying them into TCMs, the computational prescribing methods deepened the understanding of the efficacy of TCM at the molecular level. Further applying them into Western medicines, CDP could promote drug reposition avoiding time-consuming developments of new drugs.

Bridging hydraulics and graph signal processing: A new perspective to estimate water distribution network pressures.

The low spatial density of monitored nodal pressures (nodal heads) has already become a bottleneck restricting the development of smart technologies for water distribution networks (WDNs). Inferring unknown nodal heads through available WDN information is an effective way to bypass data limitations, but an accurate and easy-to-implement method is still absent. For general WDNs, the spatial distribution of nodal heads is approximately 'smooth' as there are few dramatic head changes. If heads can be divided into components with different spatial varying speeds, then they can be approximated by a few slow varying components. On this basis, a graph-based head reconstruction (GHR) method is proposed, which employs graph signal processing technologies to reconstruct the slow varying parts to estimate unknown nodal heads. Four metrics are proposed to bridge WDN hydraulics and signal processing to quantify the similarity of adjacent nodal heads, which enhance the smoothness of heads over the graph, and thus increase estimation accuracy. GHR was tested with different parameter settings and compared with other head estimation methods. Results showed that GHR has less restrictive parameter requirements compared with hydraulic simulation, and outperforms traditional data interpolation methods with better accuracy. At a larger looped network under potential model uncertainties and measurement errors, GHR still accurately estimated the heads for more than 10,000 unknown nodes, achieving a mean absolute error of 0.13 m using only 100 pressure meters. Thus the proposed method provides an efficient, robust, and convenient way to estimate unknown nodal heads in WDNs.

Molecular Characterization and Clinical Relevance of ANXA1 in Gliomas via 1,018 Chinese Cohort Patients.

Annexin A1 (ANXA1) is a calcium-dependent phospholipid-binding protein and has been implicated in multiple functions essential in cancer, including cell proliferation, apoptosis, chemosensitivity, metastasis, and invasion. However, the biological role and clinical behavior of ANXA1 in glioma remain unclear. In this study, RNA-seq (n = 1018 cases) and whole-exome sequencing (WES) (n = 286 cases) data on a Chinese cohort, RNA-seq data with different histological regions of glioblastoma blocks (n = 270 cases), and scRNA-seq data (n = 7630 cells) were used. We used the R software to perform statistical calculations and graph rendering. We found that ANXA1 is closely related to the malignant progression in gliomas. Meanwhile, ANXA1 is significantly associated with clinical behavior. Furthermore, the mutational profile revealed that glioma subtypes classified by ANXA1 expression showed distinct genetic features. Functional analyses suggest that ANXA1 correlates with the immune-related function and cancer hallmark. At a single-cell level, we found that ANXA1 is highly expressed in M2 macrophages and tumor cells of the mesenchymal subtype. Importantly, our result suggested that ANXA1 expression is significant with the patient's survival outcome. Our study revealed that ANXA1 was closely related to immune response. ANXA1 plays a key factor in M2 macrophages and MES tumor cells. Patients with lower ANXA1 expression levels tended to experience improved survival. ANXA1 may become a valuable factor for the diagnosis and treatment of gliomas in clinical practice.

Conjugation-regulating synthesis of high photosensitizing activity porphyrin-based covalent organic frameworks for photodynamic inactivation of bacteria.

Preparation of porphyrin-based covalent organic frameworks (Por-COFs) with high photosensitizing activity for photodynamic inactivation of bacteria is of great challenge, but significant for economy and human health. Herein, we show a conjugation-regulating strategy to design and synthesize Por-COFs with high photosensitizing activity for the photodynamic inactivation of bacteria. Terephthalaldehyde (Da), 2,5-Dihydroxyterephthalaldehyde (Dha), and 2,5-Diethoxyterephthalaldehyde (Deta) with different conjugation degrees are selected to condense with 5,10,15,20-Tetrakis(4-aminophenyl)porphyrin (Tph) to synthesize COF-366, DhaTph, and JNU-2, respectively. The higher conjugation of Dha and Deta than Da leads to the higher conjugation of DhaTph and JNU-2, respectively. Moreover, the hydroxyl group in Dha and the ethoxy group in Deta further expand the conjugation of DhaTph and JNU-2 via the formation of intralayer extended π-cloud delocalization and p-π conjunction, respectively. The extension of conjugation for DhaTph and JNU-2 results in the increase of intersystem crossing process and significantly improves their photosensitizing activity. Furthermore, JNU-2 with the highest photosensitizing activity exhibits superior antibacterial effects toward Staphylococcus aureus (99.1%) and Escherichia coli (96.8%). This study offers a new conjugation-regulating strategy for designing high photosensitizing activity of Por-COFs for the inactivation of bacteria.

OncoPDSS: an evidence-based clinical decision support system for oncology pharmacotherapy at the individual level.

BACKGROUND: Precision oncology pharmacotherapy relies on precise patient-specific alterations that impact drug responses. Due to rapid advances in clinical tumor sequencing, an urgent need exists for a clinical support tool that automatically interprets sequencing results based on a structured knowledge base of alteration events associated with clinical implications. RESULTS: Here, we introduced the Oncology Pharmacotherapy Decision Support System (OncoPDSS), a web server that systematically annotates the effects of alterations on drug responses. The platform integrates actionable evidence from several well-known resources, distills drug indications from anti-cancer drug labels, and extracts cancer clinical trial data from the ClinicalTrials.gov database. A therapy-centric classification strategy was used to identify potentially effective and non-effective pharmacotherapies from user-uploaded alterations of multi-omics based on integrative evidence. For each potentially effective therapy, clinical trials with faculty information were listed to help patients and their health care providers find the most suitable one. CONCLUSIONS: OncoPDSS can serve as both an integrative knowledge base on cancer precision medicine, as well as a clinical decision support system for cancer researchers and clinical oncologists. It receives multi-omics alterations as input and interprets them into pharmacotherapy-centered information, thus helping clinicians to make clinical pharmacotherapy decisions. The OncoPDSS web server is freely accessible at https://oncopdss.capitalbiobigdata.com .

Irreversible Amide-Linked Covalent Organic Framework for Selective and Ultrafast Gold Recovery.

Design of stable adsorbents for selective gold recovery with large capacity and fast adsorption kinetics is of great challenge, but significant for the economy and the environment. Herein, we show the design and preparation of an irreversible amide-linked covalent organic framework (COF) JNU-1 via a building block exchange strategy for efficient recovery of gold. JNU-1 was synthesized through the exchange of 4,4'-biphenyldicarboxaldehyde (BA) in mother COF TzBA consisting of 4,4',4''-(1,3,5-triazine-2,4,6-triyl)trianiline (Tz) and BA with terephthaloyl chloride. The irreversible amide linked JNU-1 gave good stability, unprecedented fast kinetics, excellent selectivity and outstanding adsorption capacity for gold recovery. X-ray photoelectron spectroscopy along with thermodynamic study and quantum mechanics calculation reveals that the excellent performance of JNU-1 for gold recovery results from the formation of hydrogen bonds C(N)-H⋅⋅⋅Cl and coordinate interaction of O and Au. The rational design of irreversible bonds as both inherent linkage and functional groups in COFs is a promising way to prepare stable COFs for diverse applications.

Regulatory Implications of Integrated Real-Time Control Technology under Environmental Uncertainty.

Integrated real-time control (RTC) of urban wastewater systems, which can automatically adjust system operation to environmental changes, has been found in previous studies to be a cost-effective strategy to strike a balance between good surface water quality and low greenhouse gas emissions. However, its regulatory implications have not been examined. To investigate the effective regulation of wastewater systems with this technology, two permitting approaches are developed and assessed in this work: upstream-based permitting (i.e., environmental outcomes as a function of upstream conditions) and means-based permitting (i.e., prescription of an optimal RTC strategy). An analytical framework is proposed for permit development and assessment using a diverse set of high performing integrated RTC strategies and environmental scenarios (rainfall, river flow rate, and water quality). Results from a case study show that by applying means-based permitting, the best achievable, locally suitable environmental outcomes (subject to 10% deviation) are obtained in over 80% of testing scenarios (or all testing scenarios if 19% of performance deviation is allowed) regardless of the uncertain upstream conditions. Upstream-based permitting is less effective as it is difficult to set reasonable performance targets for a highly complex and stochastic environment.

Dynamical stability of water distribution networks.

Water distribution networks are hydraulic infrastructures that aim to meet water demands at their various nodes. Water flows through pipes in the network create nonlinear dynamics on networks. A desirable feature of water distribution networks is high resistance to failures and other shocks to the system. Such threats would at least transiently change the flow rate in various pipes, potentially undermining the functionality of the whole water distribution system. Here we carry out a linear stability analysis for a nonlinear dynamical system representing the flow rate through pipes that are interconnected through an arbitrary pipe network with reservoirs and consumer nodes. We show that the steady state is always locally stable and develop a method to calculate the eigenvalue that corresponds to the mode that decays the most slowly towards the equilibrium, which we use as an index for resilience of the system. We show that the proposed index is positively correlated with the recovery rate of the pipe network, which was derived from a realistic and industrially popular simulator. The present analytical framework is expected to be useful for deploying tools from nonlinear dynamics and network analysis in the design, resilience management and scenario testing of water distribution networks.

Deep learning identifies accurate burst locations in water distribution networks.

Pipe bursts in water distribution networks lead to considerable water loss and pose risks of bacteria and pollutant contamination. Pipe burst localisation methods help water service providers repair the burst pipes and restore water supply timely and efficiently. Although methods have been reported on burst detection and localisation, there is a lack of studies on accurate localisation of a burst within a potential district by accessible meters. To address this, a novel Burst Location Identification Framework by Fully-linear DenseNet (BLIFF) is proposed. In this framework, additional pressure meters are placed at limited, optimised places for a short period (minutes to hours) to monitor system behaviour after the burst. The fully-linear DenseNet (FL-DenseNet) newly developed in this study modifies the state-of-the-art deep learning algorithm to effectively extract features in the limited pressure signals for accurate burst localisation. BLIFF was tested on a benchmark network with different parameter settings, which showed that accurate burst localisation results can be achieved even with high model uncertainties. The framework was also applied to a real-life network, in which 57 of the total 58 synthetic bursts in the potential burst district were correctly located when the top five most possible pipes are considered and among them, 37 were successfully located when considering only the top one. Only one failed because of the very small pipe diameter and remote location. Comparisons with DenseNet and the traditional fully linear neural network demonstrate that the framework can effectively narrow the potential burst district to one or several pipes with good robustness and applicability. Codes are available at https://github.com/wizard1203/waternn.