Biology subjects

Fan, Y.

Publications and source records attributed to Fan, Y..

At least 109 records · Page 6Linked to original sources

bioRxiv2024

SegCSR: Weakly-Supervised Cortical Surfaces Reconstruction from Brain Ribbon Segmentations

Deep learning-based cortical surface reconstruction (CSR) methods heavily rely on pseudo ground truth (pGT) generated by conventional CSR pipelines as supervision, leading to dataset-specific challenges and lengthy training data preparation. We propose a new approach for reconstructing multiple cortical surfaces using weak supervision from brain MRI ribbon segmentations. Our approach initializes a midthickness surface and then deforms it inward and outward to form the inner (white matter) and outer (pial) cortical surfaces, respectively, by jointly learning diffeomorphic flows to align the surfaces with the boundaries of the cortical ribbon segmentation maps. Specifically, a boundary surface loss drives the initialization surface to the target inner and outer boundaries, and an inter-surface normal consistency loss regularizes the pial surface in challenging deep cortical sulci. Additional regularization terms are utilized to enforce surface smoothness and topology. Evaluated on two large-scale brain MRI datasets, our weakly-supervised method achieves comparable or superior CSR accuracy and regularity to existing supervised deep learning alternatives.

neuroscience↗

bioRxiv2024

Modest functional diversity decline and pronounced composition shifts of microbial communities in a uranium-contaminated aquifer

BackgroundMicrobial taxonomic diversity declines with increased environmental stress. Yet, few studies have explored whether phylogenetic and functional diversities track taxonomic diversity along the stress gradient. Here, we investigated bacterial communities within an aquifer in Oak Ridge, Tennessee, USA, which is characterized by a broad spectrum of stressors, including extremely high levels of nitrate, heavy metals like cadmium and chromium, radionuclides such as uranium, and extremely low pH (<3). ResultsBoth taxonomic and phylogenetic -diversities were reduced in the most impacted wells, while the decline in functional -diversity was modest and statistically insignificant, indicating a more robust buffering capacity to environmental stress. Differences in functional gene composition (i.e., functional {beta}-diversity) were pronounced in highly contaminated wells, while convergent functional gene composition was observed in uncontaminated wells. The relative abundances of most carbon degradation genes were decreased in contaminated wells, but genes associated with denitrification, adenylylsulfate reduction, and sulfite reduction were increased. Compared to taxonomic and phylogenetic compositions, environmental variables played a more significant role in shaping functional gene composition, suggesting that niche selection could be more closely related to microbial functionality than taxonomy. ConclusionsOverall, we demonstrated that despite a reduced taxonomic -diversity, microbial communities under stress maintained functionality underpinned by environmental selection.

microbiology↗

bioRxiv2024

Critical assessment of nanopore sequencing for the detection of multiple forms of DNA modifications

While nanopore sequencing is increasingly used for mapping DNA modifications, it is important to recognize associated false-positive calls, as they can mislead biological interpretations. To assist biologists and methods developers, we describe a framework, modFDR, for rigorous evaluation that emphasizes the use of the false discovery rate with rationally designed negative controls capturing both general background and confounding modifications. Our critical assessment across multiple DNA modifications shows that while nanopore sequencing performs reliably for high-abundance modifications--including 5-methylcytosine (5mC) at CpG sites in mammalian cells and 5-hydroxymethylcytosine (5hmC) in mammalian brain cells--it produces a substantial fraction of false-positive detections for low-abundance modifications, such as 5mC at CpH sites, 5hmC, and N6-methyldeoxyadenine (6mA) in most mammalian cell types. Although newer models improve certain aspects, systematic false positives remain, and we further observe elevated false negatives for 5mCpG when benchmarked against orthogonal enzymatic methods. This study highlights the urgent need to incorporate modFDR into future methods development, evaluation, and biological studies, and advocates prioritizing nanopore sequencing for mapping abundant rather than rare modifications in biomedical applications.

genomics↗

bioRxiv2024

Compositional changes of the lung extracellular matrix in acute respiratory distress syndrome

BackgroundAcute respiratory distress syndrome (ARDS) is pathologically characterized by diffuse alveolar damage (DAD) and is associated with high morbidity and mortality rates. Remodeling of the extracellular matrix (ECM), which is pivotal for both tissue repair and organ recovery, may play a large role in persistent ARDS. This study investigated the compositional changes in the ECM in different DAD stages in ARDS. MethodsParaffin-embedded lung sections collected during autopsy or from post-transplant lungs were obtained from patients with ARDS (n=28) admitted to the University Medical Center Groningen between 2010-2020. Sections were stained histochemically, and immunohistochemically for collagen III 1 chain (Col IIIa1), IV 3 chain (Col IVa3), VI 1 chain (Col VIa1), periostin (PSTN), lumican (LUM), and fibronectin (FN). The sections were divided into 118 regions based on DAD stages (54 early vs 64 advanced). The differences in the expression of selected proteins were compared between DAD stages or across ARDS duration (<7days, 7-14days, >14days). The fiber pattern of Col VIa1 was analyzed using CellProfiler. ResultsHigher tissue density, lower proportional areas of Col IIIa1, Col IVa3, and LUM, and more concentrated Col VIa1 fibers were observed in the advanced DAD stage than in the early DAD stage. Areas with higher proportions of total collagen and FN, and lower proportional areas of Col IIIa1, Col IVa3, and LUM were detected in lung regions from patients with ARDS >14days duration. ConclusionsThese findings revealed proportional changes in ECM components, strongly suggesting that dynamic changes in ECM proteins play a role in pathophysiology in ARDS during progression.

molecular biology↗

bioRxiv2024

The impact of wild-boar derived microbiota transplantation on piglet microbiota, metabolite profile and gut proinflammatory cytokine production differs from sow-derived microbiota

Colonization of co-evolved, species-specific microbes in early life plays a crucial role in gastrointestinal development and immune function. This study hypothesized modern pig production practices have resulted in the loss of co-evolved species and critical symbiotic host- microbe interactions. To test this, we reintroduced microbes from wild boars (WB) into conventional piglets to explore their colonization dynamics and effects on gut microbial communities, metabolite profiles, and immune responses. At postnatal day (PND) 21, 48 piglets were assigned to four treatment groups: 1) WB-derived mixed microbial community (MMC), 2) sow-derived MMC, 3) a combination of WB and sow MMC (Mix), or 4) Control (PBS). Post- transplantation analyses at PND 48 revealed distinct microbial communities in WB-inoculated piglets compared to Controls, with trends toward differentiation from Sow but not Mix groups. WB-derived microbes were more successful in colonizing piglets, particularly in the Mix group, where they competed with sow-derived microbes. WB group cecal digesta enriched with Lactobacillus helveticus, Lactobacillus mucosae, and Lactobacillus pontis. Cecal metabolite analysis showed that WB piglets were enriched in histamine, acetyl-ornithine, ornithine, citrulline, and other metabolites, with higher histamine levels linked to Lactobacillus abundance. WB piglets exhibited lower cecal IL-1{beta} and IL-6 levels compared to Controls and Sow groups, while the Mix group showed reduced IFN-{gamma}, IL-2, and IL-6 compared to the Sow group. No differences in weight gain, fecal scores, or plasma cytokines were observed, indicating no adverse effects. These findings support that missing WB microbes effectively colonize domestic piglets and may positively impact metabolite production and immune responses. ImportanceThis study addresses the growing concern over losing co-evolved, species-specific microbes in modern agricultural practices, particularly in pig production. The implementation of strict biosecurity measures and widespread antibiotic use in conventional farming systems may disrupt crucial host-microbe interactions that are essential for gastrointestinal development and immune function. Our research demonstrates that by reintroducing wild boar-derived microbes into domestic piglets, these co-evolved microbes can successfully colonize the gut, influence microbial community composition, and alter metabolite profiles and immune responses without causing adverse effects. These findings also suggest that these co-evolved microbes can fill an intestinal niche, positively impacting immune activation. This research lays the groundwork for future strategies to enhance livestock health and performance by restoring natural microbial populations that produce immune-modulating metabolites. Graphical abstract O_FIG O_LINKSMALLFIG WIDTH=200 HEIGHT=156 SRC="FIGDIR/small/623678v1_ufig1.gif" ALT="Figure 1"> View larger version (43K): org.highwire.dtl.DTLVardef@6ec5c2org.highwire.dtl.DTLVardef@79804corg.highwire.dtl.DTLVardef@d63016org.highwire.dtl.DTLVardef@1ef0010_HPS_FORMAT_FIGEXP M_FIG C_FIG

microbiology↗

bioRxiv2024

The Glutamatergic Projection from the Substantia Nigra Pars Reticulata to the Dorsal Raphe Nucleus Facilitates Social Hierarchy in Mice

Social hierarchy constitutes a fundamental organizational characteristic among various social species, significantly influencing individual survival, health, and reproductive success within these societies. Neurons in the substantia nigra pars reticulata (SNr) exhibit extensive connectivity with the dorsal raphe nucleus (DRN), a critical structure implicated in social interaction, reward processing, and the establishment of social rank. However, the specific neuronal types within the SNr, as well as the associated neural circuits that regulate social dominance, remain inadequately characterized. This study aims to elucidate the crucial role of SNr glutamatergic neurons in the establishment and maintenance of social hierarchy in mice. Employing fiber photometry, we observed that the activation of SNr glutamatergic neurons increased during the initiation of effortful behaviors in the tube test. Further investigations revealed that optogenetic activation or chemogenetic inhibition of the glutamatergic neural circuit connecting the SNr to the DRN induced upward or downward shifts in social ranks, respectively. Additionally, our findings indicate that the activation of SNr glutamatergic terminals in the DRN reduces anxiety levels in mice. Collectively, these results underscore the critical role of the glutamatergic pathway from the SNr to the DRN in regulating social hierarchy. This work enhances our understanding of the functions of SNr glutamatergic neurons in both physiological contexts and neurological disorders.

neuroscience↗

bioRxiv2024

Metabolic modeling of microbial communities in the chicken ceca reveals a landscape of competition and co-operation

With their ability to degrade dietary fibers to liberate otherwise unavailable substrates, members of the Bacteroidales exert a substantial influence on the microbiome of the lower intestine. Currently our knowledge of how this influence translates to the metabolic interactions that support community structure is limited. Here we applied constraints-based modeling to chicken cecal communities to investigate metabolic interactions in the presence and absence of Bacteroides. From metagenomic datasets previously generated from 33 chicken ceca, we constructed 237 metagenome-assembled genomes. Metabolic modeling of communities built from these genomes generated profiles of short chain fatty acids largely consistent with experimental assays and confirmed the role of B. fragilis as a metabolic hub, central to the production of metabolites consumed by other taxa. In its absence, communities undergo significant functional reconfiguration, with metabolic roles typically fulfilled by B. fragilis assumed by multiple taxa. Beyond B. fragilis, we found Escherichia coli and Lactobacillus crispatus also mediate influential metabolic roles that vary in the presence or absence of B. fragilis. Compensatory adaptations adopted by the microbiome in the absence of B. fragilis resulted in metabolic profiles previously associated with inflammatory bowel disease in humans, including energy deficiency, increased lactate production and altered amino acid metabolism. This work demonstrates the potential of chicken cecal microbiomes to investigate the complex metabolic interactions and key contributions that drive community dynamics.

systems biology↗

bioRxiv2024

Transient proliferation by reversible YAP-mediated increase of the cyclin D1/p27 ratio

Hippo-YAP signaling orchestrates epithelial tissue repair and is therefore an attractive target in regenerative medicine. Yet it is unresolved how YAP integrates with mitogen signaling and contact inhibition to control the underlying transient proliferative response. Here we show that reduced contact inhibition, increased mitogen signaling, and YAP-TEAD activation converge on increasing the nuclear cyclin D1/p27 protein ratio during G1 phase, towards a threshold ratio that dictates whether individual cells enter or exit the cell cycle. YAP increases this ratio indirectly, in concert with mitogen signaling, by increasing EGFR and other receptors that signal primarily through ERK. After a delay, contact inhibition suppresses YAP activity which gradually downregulates mitogen signaling and the cyclin D1/p27 ratio. Increasing YAP activity by ablating the suppressor Merlin/NF2 reveals a balancing mechanism in which YAP suppression and contact inhibition of proliferation can be recovered but only at higher local cell density. Thus, critical for tissue repair, robust proliferation responses result from the YAP-induced and receptor-mediated prolonged increase in the cyclin D1/p27 ratio, which is only reversed by delayed suppression of receptor signaling after contact inhibition of YAP.

cell biology↗

bioRxiv2024

Long-read metagenomics empowers precise tracking of bacterial strains and their genomic changes after fecal microbiota transplantation

Fecal microbiota transplantation (FMT) has revolutionized the treatment of recurrent Clostridioides difficile infection (rCDI) and is being evaluated across other diseases. Accurate tracking of bacterial strains that stably engraft in recipients is critical for understanding the determinants of strain engraftment, evaluating their correlation with clinical outcomes, and guiding the development of therapeutic bacterial consortia. While short-read sequencing has advanced FMT research, it faces challenges in strain-level de novo metagenomic assembly. In this study, we described a novel framework, LongTrack, which uses long-read metagenomic assemblies and rigorous informatics tailored for FMT strain tracking. We highlighted LongTracks advantage over short-read approaches especially when multiple strains co-exist in the same sample. We showed LongTrack uncovered hundreds of engrafted strains across six FMT cases of rCDI and inflammatory bowel disease patients. Furthermore, long reads also allowed us to assess the genomic and epigenomic stability of engrafted strains during the 5-year follow-ups, revealing structural variations that may be associated with strain adaptation in a new host environment. Combined, our study advocates the use of long-read metagenomics and LongTrack to enhance strain tracking in future FMT studies, paving the way for the development of more effective defined biotherapeutic as an alternative to FMT.

microbiology↗

bioRxiv2024

Reproducible Sex Differences in Personalized Functional Network Topography in Youth

BackgroundA key step towards understanding psychiatric disorders that disproportionately impact female mental health is delineating the emergence of sex-specific patterns of brain organization at the critical transition from childhood to adolescence. Prior work suggests that individual differences in the spatial organization of functional brain networks across the cortex are associated with psychopathology and differ systematically by sex. AimsWe aimed to evaluate the impact of sex on the spatial organization of person-specific functional brain networks. MethodWe leveraged person-specific atlases of functional brain networks defined using non-negative matrix factorization in a sample of n = 6437 youths from the Adolescent Brain Cognitive Development Study. Across independent discovery and replication samples, we used generalized additive models to uncover associations between sex and the spatial layout ("topography") of personalized functional networks (PFNs). Next, we trained support vector machines to classify participants sex from multivariate patterns of PFN topography. Finally, we leveraged transcriptomic data from the Allen Human Brain Atlas to evaluate spatial correlations between sex differences in PFN topography and gene expression. ResultsSex differences in PFN topography were greatest in association networks including the fronto-parietal, ventral attention, and default mode networks. Machine learning models trained on participants PFNs were able to classify participant sex with high accuracy. Brain regions with the greatest sex differences in PFN topography were enriched in expression of X-linked genes as well as genes expressed in astrocytes and excitatory neurons. ConclusionsSex differences in PFN topography are robust, replicate across large-scale samples of youth, and are associated with expression patterns of X-linked genes. These results suggest a potential contributor to the female-biased risk in depressive and anxiety disorders that emerge at the transition from childhood to adolescence.

neuroscience↗

bioRxiv2024

Distinct duration and diet dependent lipid profiles and renal complicationsin GCK-MODY

Heterozygous inactivating mutations in the glucokinase (GCK) gene cause one of the most common types of maturity-onset diabetes of the young type 2 (MODY2), also named GCK-MODY. Studies suggest that, unlike other types of diabetes, patients with GCK-MODY do not have increased risk of diabetic complications and therefore do not typically require antihyperglycemic therapy. However, long-term outcomes of GCK-MODY on lipid profiles and chronic complications under different dietary scenarios remain unclear. Herein, using a knock-in mouse model expressing a novel MODY causing mutation GCK-Q26L (GCKMut), we examined age- and diet-related lipid profiles and diabetic complications. We found that, although GCKMut mice exhibited mild elevated blood glucose, the lipid profiles, body fat composition, and diabetic kidney disease (DKD) were initially improved in high-fat-diet (HFD) fed mice at the age of 28 weeks, supporting potential beneficial effects of GCKMut on lipid metabolism and kidney health. Unexpectedly however, those protective effects diminished by 40 weeks, and became more severe dyslipidemia and kidney injury associated with renal fibrosis and inflammation at 60-week-old mice fed with normal diet (ND) or HFD. Those findings revealed distinct duration- and diet-dependent effects of inactivating GCK mutation on lipid profiles and DKD, highlighting previously unrealized long-term chronic complications in GCK-MODY.

physiology↗

bioRxiv2024

Modulating Prefrontal Cortex Activity to Alleviate Stress-Induced Working Memory Deficits: A Transcranial Direct Current (tDCS) Study

This study explores the impact of stress on working memory (WM) performance, and the potential mitigating effects of transcranial direct current stimulation (tDCS) over the left dorsolateral prefrontal cortex (dlPFC) and ventromedial prefrontal cortex (vmPFC). The study had a crossover, randomized, single-blind, sham-controlled design, with stress induction as within-subject and stimulation condition as between-subject factors. We assessed stress-induced WM deficits using aversive video clips to induce stress and a verbal n-back task to assess WM performance. We analyzed physiological (cortisol and heart rate), behavioral, and electroencephalographic (EEG) changes due to stress before, during, and after WM task performance and their modulation by tDCS. Stress impaired WM performance in the sham stimulation condition for the 3-back load, but not for 2-back or 4-back loads in the WM task, and was associated with elevated physiological stress markers. tDCS over the vmPFC led to better WM task performance while stimulation over the dlPFC did not. Active tDCS with both dlPFC and vmPFC stimulation blunted cortisol release in stress conditions compared to sham. The EEG analysis revealed potential mechanisms explaining the behavioral effects of vmPFC stimulation. vmPFC stimulation led to a decreased P200 event-related potential (ERP) component compared to the sham stimulation condition and resulted in higher task-related alpha desynchronization, indicating reduced distractions and better focus during task performance. This study thus shows that the vmPFC might be a potential target for mitigating the effects of stress on WM performance, and contributes to the development of targeted interventions for stress-related cognitive impairments. Significance StatementThis study investigates how stress impacts working memory performance and whether non-invasive brain stimulation can mitigate these effects. Using transcranial direct current stimulation (tDCS), we targeted specific brain areas in participants stressed by watching aversive videos. Stress reduced working memory performance and increased cortisol levels. However, tDCS applied to the ventromedial prefrontal cortex (vmPFC) improved task performance and blunted the cortisol response compared to a sham treatment. EEG data suggest that stimulation also enhanced focus during task performance and reduced emotional distraction. Our findings suggest that tDCS over the vmPFC could be a promising non-invasive brain stimulation method to counteract the negative effects of stress on cognitive functions.

neuroscience↗

bioRxiv2024

Predictive power of different Akkermansia phylogroups in clinical response to PD-1 blockade against non-small cell lung cancer

Immune checkpoint blockade has emerged as a promising form of cancer therapy. However, only some patients respond to checkpoint inhibitors, while a significant proportion of patients do not, calling for the discovery of reliable biomarkers. Recent studies reported the importance of the gut microbiome in the clinical response to PD-1 blockade against non-small cell lung cancer (NSCLC), highlighting Akkermansia muciniphila as a candidate biomarker. Motivated by the genomic and phenotypic differences across Akkermansia muciniphila strains and Akkermansia (Akk) phylogroups (AmIa, AmIb, AmII, AmIII and AmIV), we analyzed fecal metagenomic sequencing data from four publicly available NSCLC cohorts (n = 575). Encouragingly, we found that patients responses to PD-1 blockade are significantly different across different Akk phylogroups, highlighting the relatively stronger association between AmIa and positive responses than the other phylogroups. Importantly, we also highlight the importance of considering the clinical heterogeneity among independent cohorts in across validation analysis. We built a machine learning model based on Akk gene profiles, which shed light on a group of Akk genes that may be associated with the response to PD-1 blockade. In summary, our study underlines the benefits of high-resolution analysis of Akk genomes in the search for biomarkers that may improve the prediction of patients responses to cancer immunotherapy.

genomics↗

bioRxiv2024

A biodegradable and restorative peripheral neural interface for the interrogation of neuropathic injuries

Monitoring the early-stage healing of severe traumatic nerve injuries is essential to gather physiological and pathological information for timely interventions and optimal clinical outcomes. While implantable peripheral nerve interfaces provide direct access to nerve fibers for precise interrogation and modulation, conventional non-degradable designs pose limited utilization in nerve injury rehabilitation. Here, we introduce a biodegradable and restorative neural interface for wireless real-time tracking and recovery of long-gap nerve injuries. Leveraging machine learning techniques, this electronic platform deciphers nerve recovery status and identifies traumatic neuroma formation at the early phase, enabling timely intervention and significantly improved therapeutic outcomes. The biodegradable nature of the device eliminates the need for retrieval procedures, reducing infection risks and secondary tissue damage. This research sheds light on bioresorbable multifunctional peripheral nerve interfaces for probing neuropathic injuries, offering vital information for early diagnosis and therapeutic intervention.

bioengineering↗

bioRxiv2024

Toward De Novo Protein Design from Natural Language

Programming biological function-designing bespoke proteins to perform specified molecular tasks-is a foundational goal of molecular engineering. However, current design paradigms remain fundamentally limited: they typically require either natural proteins as starting points for optimization or manual reformulation of functional goals as geometric and sequence-level constraints to guide candidate generation. Here we introduce Pinal, a 16-billion-parameter foundation model that designs candidate proteins from natural-language descriptions of desired function. Trained on 1.7 billion synthetically annotated protein-text pairs, Pinal links functional intent to protein sequence and structure. In computational evaluations, generated candidates combined high predicted foldability with functional-description alignment and sequence diversity, providing a basis for prioritizing experimentally testable designs. We applied Pinal to four distinct design tasks-a fluorescent protein, a polyethylene terephthalate hydrolase, an alcohol dehydrogenase and a metabolic H-protein-and experimentally observed the intended function in each case, including catalytic activity for both designed enzymes. Crucially, without iterative experimental optimization, a Pinal-designed H-protein increased product titer by 1.7-fold relative to the corresponding native E. coli H-protein in a multi-enzyme CO2 fixation pathway. These findings support natural language as a high-level interface for candidate generation in protein design, enabling programmable exploration with reduced reliance on manually specified structural or sequence constraints.

bioengineering↗

bioRxiv2024

Overcrowding Drives Tumor Invasion by Inducing Nanotopographical Transition of Plasma Membrane

During the progression from epithelial neoplasms to invasive carcinoma, cells are subjected to prolonged confinement. However, the response of cancer cells to such mild yet sustained compressive pressure during the initial stages of tumor invasion remain poorly understood. Here, using a spontaneous crowding model to recapitulate the progressive compressive stress caused by cell proliferation, we demonstrated that prolonged crowding alone is sufficient to induce the acquisition of an invasive phenotype and associated gene expression patterns in cancer cells. This invasiveness persisted even after cells were removed from the crowded environment, a phenomenon mediated by mechanomemory. By combining genetic manipulations, mechanical modeling, and biophysical measurements, we revealed that the disaggregation of membrane domains--driven by a nanoscale smooth-corrugated topography transition of plasma membranes induced by Laplace pressure under crowded conditions--is essential for initiating cancer cell invasion. Inhibiting membrane domains disaggregation through membrane-to-cortex-attachment effectively suppresses cancer cell invasion in both cellular crowding models and mouse xenograft models. This study underscores the critical role of tissue-scale mechanics in regulating the biophysics of mechanosensitive membrane domains during the early stages of tumor invasion.

cancer biology↗

bioRxiv2024

Coordinated regulation of chemotaxis and resistance to copper by CsoR in Pseudomonas putida

Copper is an essential enzyme cofactor in bacteria, but excess copper is highly toxic. Bacteria can cope with copper stress by increasing copper resistance and initiating chemorepellent response. However, it remains unclear how bacteria coordinate chemotaxis and resistance to copper. By screening proteins that interacted with the chemotaxis kinase CheA, we identified a copper-binding repressor CsoR that interacted with CheA in Pseudomonas putida. CsoR interacted with the HPT (P1), Dimer (P3), and HATPase_c (P4) domains of CheA and inhibited CheA autophosphorylation, resulting in decreased chemotaxis. The copper-binding of CsoR weakened its interaction with CheA, which relieved the inhibition of chemotaxis by CsoR. In addition, CsoR bound to the promoter of copper-resistance genes to inhibit gene expression, and copper-binding released CsoR from the promoter, leading to increased gene expression and copper resistance. P. putida cells exhibited a chemorepellent response to copper in a CheA-dependent manner, and CsoR inhibited the chemorepellent response to copper. Besides, the CheA-CsoR interaction also existed in proteins from several other bacterial species. Our results revealed a mechanism by which bacteria coordinately regulated chemotaxis and resistance to copper by CsoR.

microbiology↗

bioRxiv2024

Segmentation and Feature Extraction of Fingernail Plate and Lunula Based on Deep Learning

This paper proposes a novel deep learning method for accurate segmentation of the fingernail plate and lunula. To achieve this, we designed a new network structure called Nailnet, which segments the fingernail from images of the whole hand. The results show that Nailnet achieved an Intersection over Union (IoU) score of 0.9529 and an accuracy of 0.9725 for fingernail plate segmentation. For lunula segmentation, Nailnet achieved an IoU score of 0.7784 and an accuracy of 0.8846. Additionally, Nailnet successfully recognized the fingernail index, enabling the extraction of various fingernail phenotypes, including plate color, plate shape, lunula color, and lunula proportion.

bioinformatics↗