Nonparametric receiver operating characteristic curve analysis with an imperfect gold standard.

This article addresses the challenge of estimating receiver operating characteristic (ROC) curves and the areas under these curves (AUC) in the context of an imperfect gold standard, a common issue in diagnostic accuracy studies. We delve into the nonparametric identification and estimation of ROC curves and AUCs when the reference standard for disease status is prone to error. Our approach hinges on the known or estimable accuracy of this imperfect reference standard and the conditional independent assumption, under which we demonstrate the identifiability of ROC curves and propose a nonparametric estimation method. In cases where the accuracy of the imperfect reference standard remains unknown, we establish that while ROC curves are unidentifiable, the sign of the difference between two AUCs is identifiable. This insight leads us to develop a hypothesis-testing method for assessing the relative superiority of AUCs. Compared to the existing methods, the proposed methods are nonparametric so that they do not rely on the parametric model assumptions. In addition, they are applicable to both the ROC/AUC analysis of continuous biomarkers and the AUC analysis of ordinal biomarkers. Our theoretical results and simulation studies validate the proposed methods, which we further illustrate through application in two real-world diagnostic studies.

Diffusion-/perfusion-weighted imaging fusion to automatically identify stroke within 4.5 h.

OBJECTIVES: We aimed to develop machine learning (ML) models based on diffusion- and perfusion-weighted imaging fusion (DP fusion) for identifying stroke within 4.5 h, to compare them with DWI- and/or PWI-based ML models, and to construct an automatic segmentation-classification model and compare with manual labeling methods. METHODS: ML models were developed from multimodal MRI datasets of acute stroke patients within 24 h of clear symptom onset from two centers. The processes included manual segmentation, registration, DP fusion, feature extraction, and model establishment (logistic regression (LR) and support vector machine (SVM)). A segmentation-classification model (X-Net) was proposed for automatically identifying stroke within 4.5 h. The area under the receiver operating characteristic curve (AUC), sensitivity, Dice coefficients, decision curve analysis, and calibration curves were used to evaluate model performance. RESULTS: A total of 418 patients (≤ 4.5 h: 214; > 4.5 h: 204) were evaluated. The DP fusion model achieved the highest AUC in identifying the onset time in the training (LR: 0.95; SVM: 0.92) and test sets (LR: 0.91; SVM: 0.90). The DP fusion-LR model displayed consistent positive and greater net benefits than other models across a broad range of risk thresholds. The calibration curve demonstrated the good calibration of the DP fusion-LR model (average absolute error: 0.049). The X-Net model obtained the highest Dice coefficients (DWI: 0.81; Tmax: 0.83) and achieved similar performance to manual labeling (AUC: 0.84). CONCLUSIONS: The automatic segmentation-classification models based on DWI and PWI fusion images had high performance in identifying stroke within 4.5 h. CLINICAL RELEVANCE STATEMENT: Perfusion-weighted imaging (PWI) fusion images had high performance in identifying stroke within 4.5 h. The automatic segmentation-classification models based on DWI and PWI fusion images could provide clinicians with decision-making guidance for acute stroke patients with unknown onset time. KEY POINTS: • The diffusion/perfusion-weighted imaging fusion model had the best performance in identifying stroke within 4.5 h. • The X-Net model had the highest Dice and achieved performance close to manual labeling in segmenting lesions of acute stroke. • The automatic segmentation-classification model based on DP fusion images performed well in identifying stroke within 4.5 h.

A novel regression method for the analysis of multireader multicase-free-response receiver operating characteristics studies.

In diagnostic radiology, the multireader multicase (MRMC) design and the free-response receiver operating characteristics (FROC) method are often used in combination. The cross-correlated data generated by the MRMC-FROC study leads to difficulties in the corresponding analysis, and the need to include covariates in the model further complicates the subsequent analysis. In this paper, we propose a regression approach based on three new measures with good interpretability. The correlation structure of the original test results is taken directly into account in the estimation procedure. The proposed method also allows the inclusion of continuous or discrete covariates. Consistent and asymptotically normal estimators are derived for the new measures. Simulation studies are conducted to evaluate the performance of the proposed approach. The simulation results show that the regression approach performs well under a wide range of scenarios. We also apply the proposed regression approach to a diagnostic study of computer-aided diagnosis in lung cancer.

Alterations in the human oral and gut microbiomes and lipidomics in COVID-19.

OBJECTIVE: To characterise the oral microbiome, gut microbiome and serum lipid profiles in patients with active COVID-19 and recovered patients; evaluate the potential of the microbiome as a non-invasive biomarker for COVID-19; and explore correlations between the microbiome and lipid profile. DESIGN: We collected and sequenced 392 tongue-coating samples, 172 faecal samples and 155 serum samples from Central China and East China. We characterised microbiome and lipid molecules, constructed microbial classifiers in discovery cohort and verified their diagnostic potential in 74 confirmed patients (CPs) from East China and 37 suspected patients (SPs) with IgG positivity. RESULTS: Oral and faecal microbial diversity was significantly decreased in CPs versus healthy controls (HCs). Compared with HCs, butyric acid-producing bacteria were decreased and lipopolysaccharide-producing bacteria were increased in CPs in oral cavity. The classifiers based on 8 optimal oral microbial markers (7 faecal microbial markers) achieved good diagnostic efficiency in different cohorts. Importantly, diagnostic efficacy reached 87.24% in the cross-regional cohort. Moreover, the classifiers successfully diagnosed SPs with IgG antibody positivity as CPs, and diagnostic efficacy reached 92.11% (98.01% of faecal microbiome). Compared with CPs, 47 lipid molecules, including sphingomyelin (SM)(d40:4), SM(d38:5) and monoglyceride(33:5), were depleted, and 122 lipid molecules, including phosphatidylcholine(36:4p), phosphatidylethanolamine (PE)(16:0p/20:5) and diglyceride(20:1/18:2), were enriched in confirmed patients recovery. CONCLUSION: This study is the first to characterise the oral microbiome in COVID-19, and oral microbiomes and lipid alterations in recovered patients, to explore their correlations and to report the successful establishment and validation of a diagnostic model for COVID-19.

Agaricus bisporus-Derived Glucosamine Hydrochloride Facilitates Skeletal Injury Repair through Bmp Signaling in Zebrafish Osteoporosis Model.

Glucosamine hydrochloride (GAH), one of the most basic and important derivatives of chitin, is obtained by hydrolysis of chitin in concentrated hydrochloric acid. At present, little is known about how GAH functions in skeletal development. In this report, we demonstrate that GAH, extracted from the cell wall of Agaricus bisporus, acts in a dose-dependent manner to promote not only cartilage and bone development in larvae but also caudal fin regeneration in adult fish. Furthermore, GAH treatment causes a significant increase in expression of bone-related marker genes, indicating its important role in promoting skeletal development. We show that in both larval and adult osteoporosis models induced by high iron osteogenic defects are significantly ameliorated after treatment with GAH, which regulates expression of a series of bone-related genes. Finally, we demonstrate that GAH promotes skeletal development and injury repair through bone morphogenetic protein (Bmp) signaling, and it works at the downstream of the receptor level. Taken together, our findings not only provide a strong research foundation and strategy for the screening of natural osteoporosis drugs and product development using a zebrafish model but also establish the potential for the development of Agaricus bisporus-derived GAH as a new drug for osteoporosis treatment.

Hsp90 Relieves Heat Stress-Induced Damage in Mouse Kidneys: Involvement of Antiapoptotic PKM2-AKT and Autophagic HIF-1α Signaling.

Heat stress can particularly affect the kidney because of its high rate of adenosine triphosphate consumption. Competition between apoptosis and autophagy-mediated survival always exists in damaged tissue. And Hsp90 can enhance cellular protection to resist heat stress. However, the relationship between Hsp90 and the above competition and its underlying mechanism in the kidney are unclear. The present study found that heat stress induced obvious histopathological and oxidative injury, which was connected with cellular apoptosis and autophagy in the kidney and was associated with the levels of Hsp90 expression or function. The data showed that during heat stress, Hsp90 activated the PKM2-Akt signaling pathway to exert antiapoptotic effects and induce Hsp70 expression regulated by HSF-1, stimulated autophagy-mediated survival through the HIF-1α-BNIP3/BNIP3L pathway, and finally protected the kidney from heat-stress injury. Moreover, the nuclear translocation of PKM2, (p-) Akt, HSF-1, and HIF-1α was enhanced by heat stress, but only intranuclear p-Akt and HSF-1 were specifically influenced by Hsp90, contributing to regulate the cellular ability of resisting heat-stress damage. Our study provided new insights regarding the molecular mechanism of Hsp90 in the kidney in response to heat-stress injury, possibly contributing to finding new targets for the pharmacological regulation of human or animal acute kidney injury from heat stress in future research.

Vitamin C mitigates heat damage by reducing oxidative stress, inducing HSP expression in TM4 Sertoli cells.

Heat stress is a major stressor that can lead to male reproductive dysfunction. Sertoli cells play a crucial role in spermatogenesis by providing germ cells with structural and nutritional support, and contributing to blood-testis barrier formation. Vitamin C (Vc) is an antioxidant capable of neutralizing reactive oxygen species and preventing lipid peroxidation widely used because it is inexpensive and highly accessible. In the present study, we investigated the protective effect of Vc on TM4 cells following heat stress. Pretreatment with Vc could effectively inhibit apoptosis (p < 0.01), lipid peroxidation, and lactate dehydrogenase (LDH) activity. However, a significant increase in the malondialdehyde (MDA) level and LDH activity (p < 0.01) was observed in TM4 cells without Vc-pretreatment, in conjunction with vacuole degeneration and karyopyknosis. In addition, both the messenger RNA and protein levels of CryAB, Hsp27, Hsp70, and Hsp110 substantially increased in the 3 and 12 hr recovery groups (p < 0.01). Vc also prevented microtubule aggregation following heat stress. These results suggest that pretreatment with Vc-protected TM4 cells against heat stress by reducing the level of oxidative stress and inducing heat shock protein expression.

Correction to: Co-enzyme Q10 and acetyl salicylic acid enhance Hsp70 expression in primary chicken myocardial cells to protect the cells during heat stress.

In the original publication of the article, one of the images was selected by mistake in Fig. 3 (HS + ASA, 5 h). The correct version of Fig. 3 is given in this correction.

Enantiomeric NMR discrimination of carboxylic acids using actinomycin D as a chiral solvating agent.

Actinomycin D (Act-D) is a biologically important polypeptide antibiotic clinically used to treat several malignant tumors. Herein, we extended its hitherto-unexplored application as an applicable chiral solvating agent (CSA) for the rapid enantiomeric determination of different chiral carboxylic acids in deuterated chloroform by 1H NMR spectroscopy. Notable enantiodiscrimination with well-splitting α-H or α-CH3 resonance signals of the enantiomers of carboxylic acids were achieved without significant interference from Act-D. To check its applicability for the determination of enantiomeric excess (ee) values, various mandelic acid (MA) samples were determined and compared with the observed ones, resulting in an excellent linear relationship. To our knowledge, this is the first example of using a natural antibiotic compound as a CSA to achieve chiral recognition for carboxylic acids.

Correction: Enantiomeric NMR discrimination of carboxylic acids using actinomycin D as a chiral solvating agent.

Correction for 'Enantiomeric NMR discrimination of carboxylic acids using actinomycin D as a chiral solvating agent' by Liwen Bai, et al., Org. Biomol. Chem., 2019, 17, 1466-1470.

Co-enzyme Q10 upregulates Hsp70 and protects chicken primary myocardial cells under in vitro heat stress via PKC/MAPK.

In this report, we investigate the protective mechanism of co-enzyme Q10 on chicken primary myocardial cells during heat stress. Morphological observations indicate that addition of co-enzyme Q10 protects myocardial cells from heat stress, reduces the damage of mitochondria and nucleus, and decreases the mean number of vacuolated mitochondria. We have previously shown that co-enzyme Q10 can protect myocardial cells by upregulating the expression of Hsp70. Therefore, signaling pathways involved in this process were explored. No changes of total MAPK protein (P38MAPK, JNK, ERK) expression in the experimental groups were detected, with the exception of total JNK1. Co-enzyme Q10 failed to increase the expression of JNK1 compared to the HS group which was treated with heat stress only. Addition of Q10 upregulated the expression of p-P38MAPK, p-JNK, and p-ERK1. Inhibitors of P38MAPK and JNK, SB203580 and SP600125, respectively, weakened the upregulation of Hsp70 by co-enzyme Q10, indicating that MAPK pathways participate in the Hsp70 upregulation by co-enzyme Q10. Co-enzyme Q10 upregulates the expression of p-MEK3/6 and p-MEK4, but not p-MEK7 during heat stress. Expression of p-PKCα and p-PKCß1 was also elevated following the addition of co-enzyme Q10 during heat stress, and addition of PKC inhibitors decreased the expression of Hsp70 induced by co-enzyme Q10. This confirms that PKC is also associated with the upregulation of Hsp70. In HS+Q10 group, addition of SP600125 or SB203580 could increase cell apoptosis under heat stress. Our results suggest that co-enzyme Q10 upregulates the expression of Hsp70 during heat stress to protect chicken primary myocardial cells via the PKC-MEK3/4/6-P38MAPK/JNK pathways.

Co-enzyme Q10 and acetyl salicylic acid enhance Hsp70 expression in primary chicken myocardial cells to protect the cells during heat stress.

We investigated the effects of co-enzyme Q10 (Q10) and acetyl salicylic acid (ASA) on expression of Hsp70 in the protection of primary chicken myocardial cells during heat stress. Western blot analysis showed that Q10 and ASA accelerated the induction of Hsp70 when chicken myocardial cells were exposed to hyperthermia. In the absence of heat stress, however, neither Q10 nor ASA are able to upregulate Hsp70 expression. Analysis of enzymes that respond to cellular damage and pathological examination revealed that ectopic expression of ASA and Q10 alleviate cellular damage during heat stress. Quantification of heat shock factors (HSF) indicated that treatment of ASA increased the expression of HSF-1 and HSF-3 during heat stress. Treatment with Q10 resulted in the elevation of HSF-1 expression. Expression of HSF-2 and HSF-4 was not affected by ASA or Q10. Subcellular distribution analysis of HSF-1 and HSF-3 showed that in response to heat stress ASA promoted nuclear translocation of HSF-1 and HSF-3, while Q10 promoted only HSF-1 nuclear translocation. Chromatin immunoprecipitation (ChIP) analysis indicated that HSF-1 occupies the Hsp70 promoter in chicken primary myocardial cells during heat stress and under normal conditions, while HSF-3 occupies the Hsp70 promoter only during heat stress. Real-time PCR analysis revealed that ASA induces HSF-1 and HSF-3 binding to Hsp70 HSE, while Q10 only induces HSF1 binding to Hsp70 HSE, in agreement with the impact of HSF1 and HSF3 silencing on Hsp70 expression. These data demonstrate that ASA and Q10 both induce the expression of Hsp70 to protect chicken primary myocardial cells during heat stress, but through distinct pathways.

Efficient Online Stream Clustering Based on Fast Peeling of Boundary Micro-Cluster.

A growing number of applications generate streaming data, making data stream mining a popular research topic. Classification-based streaming algorithms require pre-training on labeled data. Manually labeling a large number of samples in the data stream is impractical and cost-prohibitive. Stream clustering algorithms rely on unsupervised learning. They have been widely studied for their ability to effectively analyze high-speed data streams without prior knowledge. Stream clustering plays a key role in data stream mining. Currently, most data stream clustering algorithms adopt the online-offline framework. In the online stage, micro-clusters are maintained, and in the offline stage, they are clustered using an algorithm similar to density-based spatial clustering of applications with noise (DBSCAN). When data streams have clusters with varying densities and ambiguous boundaries, traditional data stream clustering algorithms may be less effective. To overcome the above limitations, this article proposes a fully online stream clustering algorithm called fast boundary peeling stream clustering (FBPStream). First, FBPStream defines a decay-based kernel density estimation (KDE). It can discover clusters with varying densities and identify the evolving trend of streams well. Then, FBPStream implements an efficient boundary micro-cluster peeling technique to identify the potential core micro-clusters. Finally, FBPStream employs a parallel clustering strategy to effectively cluster core and boundary micro-clusters. The proposed algorithm is compared with ten popular algorithms on 15 data streams. Experimental results show that FBPStream is competitive with the other ten popular algorithms.

Multi-grained contrastive representation learning for label-efficient lesion segmentation and onset time classification of acute ischemic stroke.

Ischemic lesion segmentation and the time since stroke (TSS) onset classification from paired multi-modal MRI imaging of unwitnessed acute ischemic stroke (AIS) patients is crucial, which supports tissue plasminogen activator (tPA) thrombolysis decision-making. Deep learning methods demonstrate superiority in TSS classification. However, they often overfit task-irrelevant features due to insufficient paired labeled data, resulting in poor generalization. We observed that unpaired data are readily available and inherently carry task-relevant cues, but are less often considered and explored. Based on this, in this paper, we propose to fully excavate the potential of unpaired unlabeled data and use them to facilitate the downstream AIS analysis task. We first analyze the utility of features at the varied grain and propose a multi-grained contrastive learning (MGCL) framework to learn task-related prior representations from both coarse-grained and fine-grained levels. The former can learn global prior representations to enhance the location ability for the ischemic lesions and perceive the healthy surroundings, while the latter can learn local prior representations to enhance the perception ability for semantic relation between the ischemic lesion and other health regions. To better transfer and utilize the learned task-related representation, we designed a novel multi-task framework to simultaneously achieve ischemic lesion segmentation and TSS classification with limited labeled data. In addition, a multi-modal region-related feature fusion module is proposed to enable the feature correlation and synergy between multi-modal deep image features for more accurate TSS decision-making. Extensive experiments on the large-scale multi-center MRI dataset demonstrate the superiority of the proposed framework. Therefore, it is promising that it helps better stroke evaluation and treatment decision-making.

Sensitive quantification of mevalonate pathway intermediates and prediction of relative novel analogs by chemical derivatization-based LC-MS/MS.

The mevalonate (MVA) pathway plays a crucial role in the occurrence and progression of various diseases, such as osteoporosis, breast cancer, and lung cancer, etc. However, determining all the MVA pathway intermediates is still challenging due to their high polarity, low concentration, chelation effect with metal compartments, and poor mass spectrometric response. In this study, we established a liquid chromatography-tandem mass spectrometry (LC-MS/MS) method coupled with N2, N2, N4, N4-tetramethyl-6-(4-(piperazin-1-ylsulfonyl) phenyl)-1,3,5-triazine-2,4-diamine (Tmt-PP) labeling for the simultaneous analysis of all MVA intermediates in biospecimens. Chemical derivatization significantly improved the chromatographic retention, peak shape, and detection sensitivity of the analytes. Moreover, we employed a method named mass spectrum calculation to achieve the absolute quantification of the isomers, i.e., isopentenyl pyrophosphate (IPP) and dimethylallyl pyrophosphate (DMAPP). The established method was fully qualified and applied to explore the difference of these metabolites in cisplatin-resistant non-small cell lung cancer (NSCLC) cells. Additionally, several MVA intermediate analogs, including isopentenyl monophosphate or dimethylallyl monophosphate (IMP/DMAMP), geranyl monophosphate (GMP), 5-triphosphomevalonate (MTP), and isopentenyl triphosphate or dimethylallyl triphosphate (ITP/DMATP), were identified for the first time using a knowledge-driven prediction strategy. We further explored the tissue distribution of these novel metabolites. Overall, this work developed a sensitive quantification method for all MVA intermediates, which will enhance our understanding of the role of this pathway in various health and disease conditions. The novel metabolites we discovered warrant further investigations into their biosynthesis and biological functions.

Pathological Asymmetry-Guided Progressive Learning for Acute Ischemic Stroke Infarct Segmentation.

Quantitative infarct estimation is crucial for diagnosis, treatment and prognosis in acute ischemic stroke (AIS) patients. As the early changes of ischemic tissue are subtle and easily confounded by normal brain tissue, it remains a very challenging task. However, existing methods often ignore or confuse the contribution of different types of anatomical asymmetry caused by intrinsic and pathological changes to segmentation. Further, inefficient domain knowledge utilization leads to mis-segmentation for AIS infarcts. Inspired by this idea, we propose a pathological asymmetry-guided progressive learning (PAPL) method for AIS infarct segmentation. PAPL mimics the step-by-step learning patterns observed in humans, including three progressive stages: knowledge preparation stage, formal learning stage, and examination improvement stage. First, knowledge preparation stage accumulates the preparatory domain knowledge of the infarct segmentation task, helping to learn domain-specific knowledge representations to enhance the discriminative ability for pathological asymmetries by constructed contrastive learning task. Then, formal learning stage efficiently performs end-to-end training guided by learned knowledge representations, in which the designed feature compensation module (FCM) can leverage the anatomy similarity between adjacent slices from the volumetric medical image to help aggregate rich anatomical context information. Finally, examination improvement stage encourages improving the infarct prediction from the previous stage, where the proposed perception refinement strategy (RPRS) further exploits the bilateral difference comparison to correct the mis-segmentation infarct regions by adaptively regional shrink and expansion. Extensive experiments on public and in-house NCCT datasets demonstrated the superiority of the proposed PAPL, which is promising to help better stroke evaluation and treatment.

A new chemical derivatization reagent sulfonyl piperazinyl for the quantification of fatty acids using LC-MS/MS.

In our previous study, a chemical derivatization reagent named 5-(dimethylamino) naphthalene-1-sulfonyl piperazine (Dns-PP) was developed to enhance the chromatographic retention and the mass spectrometric response of free fatty acids (FFAs) in reversed-phase liquid chromatography coupled with electrospray ionization-mass spectrometry (RPLC-ESI-MS). However, Dns-PP exhibited strong preferences for long-chain FFAs, with limited improvement for short- or medium-chain FFAs. In this study, a new series of labeling reagents targeting FFAs were designed, synthesized, and evaluated. Among these reagents, Tmt-PP (N2, N2, N4, N4-tetramethyl-6-(4-(piperazin-1-ylsulfonyl) phenyl)-1,3,5-triazine-2,4-diamine) exhibited the best MS response and was selected for further evaluations. We compared Tmt-PP with Dns-PP and four commonly used carboxyl labeling reagents from existing studies, demonstrating the advantages of Tmt-PP. Further comparisons between Tmt-PP and Dns-PP in measuring FFAs from biological samples revealed that Tmt-PP labeling enhanced the MS response for about 80 % (30/38) of the measured FFAs, particularly for short- and medium-chain FFAs. Moreover, Tmt-PP labeling significantly improved the chromatographic retention of short-chain FFAs. To ensure accurate quantification, we developed a stable isotope-labeled Tmt-PP (i.e., d12-Tmt-PP) to react with chemical standards and serve as one-to-one internal standards (IS). The method was validated for accuracy, precision, sensitivity, linearity, stability, extraction efficiency, as well as matrix effect. Overall, this study introduced a new chemical derivatization reagent Tmt-PP (d12-Tmt-PP), providing a sensitive and accurate option for quantifying FFAs in biological samples.

Nuclear bodies protect phase separated proteins from degradation in stressed proteome.

RNA-binding proteins (RBPs) containing intrinsically disordered domains undergo liquid-liquid phase separation to form nuclear bodies under stress conditions. This process is also connected to the misfolding and aggregation of RBPs, which are associated with a series of neurodegenerative diseases. However, it remains elusive how folding states of RBPs changes upon the formation and maturation of nuclear bodies. Here, we describe SNAP-tag based imaging methods to visualize the folding states of RBPs in live cells via time-resolved quantitative microscopic analyses of their micropolarity and microviscosity. Using these imaging methods in conjunction with immunofluorescence imaging, we demonstrate that RBPs, represented by TDP-43, initially enters the PML nuclear bodies in its native state upon transient proteostasis stress, albeit it begins to misfolded during prolonged stress. Furthermore, we show that heat shock protein 70 co-enters the PML nuclear bodies to prevent the degradation of TDP-43 from the proteotoxic stress, thus revealing a previously unappreciated protective role of the PML nuclear bodies in the prevention of stress-induced degradation of TDP-43. In summary, our imaging methods described in the manuscript, for the first time, reveal the folding states of RBPs, which were previously challenging to study with conventional methods in nuclear bodies of live cells. This study uncovers the mechanistic correlations between the folding states of a protein and functions of nuclear bodies, in particular PML bodies. We envision that the imaging methods can be generally applied to elucidating the structural aspects of other proteins that exhibit granular structures under biological stimulus.

Automatic identification and morphological comparison of bivalve and brachiopod fossils based on deep learning.

Fossil identification is an essential and fundamental task for conducting palaeontological research. Because the manual identification of fossils requires extensive experience and is time-consuming, automatic identification methods are proposed. However, these studies are limited to a few or dozens of species, which is hardly adequate for the needs of research. This study enabled the automatic identification of hundreds of species based on a newly established fossil dataset. An available "bivalve and brachiopod fossil image dataset" (BBFID, containing >16,000 "image-label" data pairs, taxonomic determination completed) was created. The bivalves and brachiopods contained in BBFID are closely related in morphology, ecology and evolution that have long attracted the interest of researchers. We achieved >80% identification accuracy at 22 genera and ∼64% accuracy at 343 species using EfficientNetV2s architecture. The intermediate output of the model was extracted and downscaled to obtain the morphological feature space of fossils using t-distributed stochastic neighbor embedding (t-SNE). We found a distinctive boundary between the morphological feature points of bivalves and brachiopods in fossil morphological feature distribution maps. This study provides a possible method for studying the morphological evolution of fossil clades using computer vision in the future.

Bioinformatics-based analysis reveals elevated CYTL1 as a potential therapeutic target for BRAF-mutated melanoma.

Introduction: Despite many recent emerging therapeutic modalities that have prolonged the survival of melanoma patients, the prognosis of melanoma remains discouraging, and further understanding of the mechanisms underlying melanoma progression is needed. Melanoma patients often have multiple genetic mutations, with BRAF mutations being the most common. In this study, public databases were exploited to explore a potential therapeutic target for BRAF-mutated melanoma. Methods: In this study, we analyzed differentially expressed genes (DEGs) in normal tissues and melanomas, Braf wild-type and Braf mutant melanomas using information from TCGA databases and the GEO database. Subsequently, we analyzed the differential expression of CYTL1 in various tumor tissues and its effect on melanoma prognosis, and resolved the mutation status of CYTL1 and its related signalling pathways. By knocking down CYTL1 in melanoma cells, the effects of CYTL1 on melanoma cell proliferation, migration and invasion were further examined by CCK8 assay, Transwell assay and cell migration assay. Results: 24 overlapping genes were identified by analyzing DEGs common to melanoma and normal tissue, BRAF-mutated and BRAF wild-type melanoma. Among them, CYTL1 was highly expressed in melanoma, especially in BRAF-mutated melanoma, and the high expression of CYTL1 was associated with epithelial-mesenchymal transition (EMT), cell cycle, and cellular response to UV. In melanoma patients, especially BRAF-mutated melanoma patients, clinical studies showed a positive correlation between increased CYTL1 expression and shorter overall survival (OS) and disease-free survival (DFS). In vitro experiments further confirmed that the knockdown of CYTL1 significantly inhibited the migration and invasive ability of melanoma cells. Conclusion: CYTL1 is a valuable prognostic biomarker and a potentially effective therapeutic target in melanoma, especially BRAF-mutated melanoma.