DREAMER: a computational framework to evaluate readiness of datasets for machine learning.

BACKGROUND: Machine learning (ML) has emerged as the predominant computational paradigm for analyzing large-scale datasets across diverse domains. The assessment of dataset quality stands as a pivotal precursor to the successful deployment of ML models. In this study, we introduce DREAMER (Data REAdiness for MachinE learning Research), an algorithmic framework leveraging supervised and unsupervised machine learning techniques to autonomously evaluate the suitability of tabular datasets for ML model development. DREAMER is openly accessible as a tool on GitHub and Docker, facilitating its adoption and further refinement within the research community.. RESULTS: The proposed model in this study was applied to three distinct tabular datasets, resulting in notable enhancements in their quality with respect to readiness for ML tasks, as assessed through established data quality metrics. Our findings demonstrate the efficacy of the framework in substantially augmenting the original dataset quality, achieved through the elimination of extraneous features and rows. This refinement yielded improved accuracy across both supervised and unsupervised learning methodologies. CONCLUSION: Our software presents an automated framework for data readiness, aimed at enhancing the integrity of raw datasets to facilitate robust utilization within ML pipelines. Through our proposed framework, we streamline the original dataset, resulting in enhanced accuracy and efficiency within the associated ML algorithms.

Associations Between Life's Essential 8 and Abdominal Aortic Calcification Among Middle-Aged and Elderly Populations.

BACKGROUND: Abdominal aortic calcification (AAC) is an independent risk factor for cardiovascular disease. We aim to examine the associations between Life's Essential 8 (LE8), the recently updated measurement of cardiovascular health (CVH), and AAC among participants aged ≥40 years. METHODS AND RESULTS: This population-based cross-sectional study used data from the National Health and Nutrition Examination Survey in 2013 to 2014. AAC (AAC score>0) and severe AAC (AAC score>6) were quantified by the Kauppila score system. Multiple linear, multivariable logistic, and restricted cubic spline models were used to assess the associations. A total of 2369 participants were included with a mean AAC score of 1.41 (0.13). Participants in the high-cardiovascular-health group had lower AAC scores, lower prevalence of AAC, and lower prevalence of severe AAC. After the adjustment of potential confounders (age, sex, race and ethnicity, education levels, marital status, poverty income ratio, estimated glomerular filtration rate, serum creatinine, serum uric acid, serum phosphorus, and serum total calcium), higher cardiovascular health was significantly associated with lower risk of AAC. Meanwhile, elevated nicotine exposure score, blood glucose score, and blood pressure score within the LE8 components were significantly associated with lower risk of AAC. Also, nonlinear dose-response relationships were observed. Subgroup analyses (age strata, sex, poverty income ratio, education levels, marital status) indicated the inverse associations of LE8 and AAC were generally similar in different populations. CONCLUSIONS: LE8 was negatively and nonlinearly related to the risk of AAC among middle-aged and older populations. Meanwhile, LE8 components should prioritize higher scores for nicotine exposure, blood glucose, and blood pressure evaluations.

DreamStone: Image as a Stepping Stone for Text-Guided 3D Shape Generation.

This paper presents a new text-guided 3D shape generation approach DreamStone that uses images as a stepping stone to bridge the gap between the text and shape modalities for generating 3D shapes without requiring paired text and 3D data. The core of our approach is a two-stage feature-space alignment strategy that leverages a pre-trained single-view reconstruction (SVR) model to map CLIP features to shapes: to begin with, map the CLIP image feature to the detail-rich 3D shape space of the SVR model, then map the CLIP text feature to the 3D shape space through encouraging the CLIP-consistency between the rendered images and the input text. Besides, to extend beyond the generative capability of the SVR model, we design the text-guided 3D shape stylization module that can enhance the output shapes with novel structures and textures. Further, we exploit pre-trained text-to-image diffusion models to enhance the generative diversity, fidelity, and stylization capability. Our approach is generic, flexible, and scalable. It can be easily integrated with various SVR models to expand the generative space and improve the generative fidelity. Extensive experimental results demonstrate that our approach outperforms the state-of-the-art methods in terms of generative quality and consistency with the input text.

Point Set Self-Embedding.

This work presents an innovative method for point set self-embedding, that encodes the structural information of a dense point set into its sparser version in a visual but imperceptible form. The self-embedded point set can function as the ordinary downsampled one and be visualized efficiently on mobile devices. Particularly, we can leverage the self-embedded information to fully restore the original point set for detailed analysis on remote servers. This task is challenging, since both the self-embedded point set and the restored point set should resemble the original one. To achieve a learnable self-embedding scheme, we design a novel framework with two jointly-trained networks: one to encode the input point set into its self-embedded sparse point set and the other to leverage the embedded information for inverting the original point set back. Further, we develop a pair of up-shuffle and down-shuffle units in the two networks, and formulate loss terms to encourage the shape similarity and point distribution in the results. Extensive qualitative and quantitative results demonstrate the effectiveness of our method on both synthetic and real-scanned datasets. The source code and trained models will be publicly available at https://github.com/liruihui/Self-Embedding.

Inferring RNA-binding protein target preferences using adversarial domain adaptation.

Precise identification of target sites of RNA-binding proteins (RBP) is important to understand their biochemical and cellular functions. A large amount of experimental data is generated by in vivo and in vitro approaches. The binding preferences determined from these platforms share similar patterns but there are discernable differences between these datasets. Computational methods trained on one dataset do not always work well on another dataset. To address this problem which resembles the classic "domain shift" in deep learning, we adopted the adversarial domain adaptation (ADDA) technique and developed a framework (RBP-ADDA) that can extract RBP binding preferences from an integration of in vivo and vitro datasets. Compared with conventional methods, ADDA has the advantage of working with two input datasets, as it trains the initial neural network for each dataset individually, projects the two datasets onto a feature space, and uses an adversarial framework to derive an optimal network that achieves an optimal discriminative predictive power. In the first step, for each RBP, we include only the in vitro data to pre-train a source network and a task predictor. Next, for the same RBP, we initiate the target network by using the source network and use adversarial domain adaptation to update the target network using both in vitro and in vivo data. These two steps help leverage the in vitro data to improve the prediction on in vivo data, which is typically challenging with a lower signal-to-noise ratio. Finally, to further take the advantage of the fused source and target data, we fine-tune the task predictor using both data. We showed that RBP-ADDA achieved better performance in modeling in vivo RBP binding data than other existing methods as judged by Pearson correlations. It also improved predictive performance on in vitro datasets. We further applied augmentation operations on RBPs with less in vivo data to expand the input data and showed that it can improve prediction performances. Lastly, we explored the predictive interpretability of RBP-ADDA, where we quantified the contribution of the input features by Integrated Gradients and identified nucleotide positions that are important for RBP recognition.

A Rotation-Invariant Framework for Deep Point Cloud Analysis.

Recently, many deep neural networks were designed to process 3D point clouds, but a common drawback is that rotation invariance is not ensured, leading to poor generalization to arbitrary orientations. In this article, we introduce a new low-level purely rotation-invariant representation to replace common 3D Cartesian coordinates as the network inputs. Also, we present a network architecture to embed these representations into features, encoding local relations between points and their neighbors, and the global shape structure. To alleviate inevitable global information loss caused by the rotation-invariant representations, we further introduce a region relation convolution to encode local and non-local information. We evaluate our method on multiple point cloud analysis tasks, including (i) shape classification, (ii) part segmentation, and (iii) shape retrieval. Extensive experimental results show that our method achieves consistent, and also the best performance, on inputs at arbitrary orientations, compared with all the state-of-the-art methods.

Involvement of non-coding RNAs during infection of rice by Acidovorax oryzae.

The expression of non-coding RNAs (ncRNAs) has been observed in a variety of bacteria. However, the function of ncRNAs and their regulatory targets are largely unknown, and few ncRNAs are found to be associated with bacterial virulence. The bacterial brown stripe pathogen Acidovorax oryzae (Ao) RS-1 shows a high level of condition-dependent differential expression of ncRNA, which we identified in a genome wide screen. We experimentally validated 66 differentially expressed ncRNAs using an integrative analysis of conservative genome sequences and transcriptomic data during in vivo interaction of the bacterial pathogen with the rice plant. To test the relevance of the differentially expressed ncRNAs, we chose four with different positions within the genome, and with different secondary structures and promoter activities. The results show that the overexpression of the four ncRNAs caused a significant change in virulence-related phenotypes, resistance to various environmental stresses, expression of secretion systems and effector proteins, while changing the expression of ncRNA putative target genes. We conclude that these ncRNAs are examples for the inherent regulatory roles for many of the observed ncRNAs in response to changing conditions such as host interaction or environmental adaption.

Effect of Osteoporosis on Adjacent Segmental Degeneration After Posterior Lumbar Interbody Fusion Under Whole Body Vibration.

BACKGROUND: Adjacent segmental degeneration (ASD) is one of the common complications after posterior lumbar interbody fusion (PLIF). Both whole body vibration (WBV) and osteoporosis are important factors associated with the biomechanics of the lumbar spine. However, to the best of our knowledge, no studies have investigated the effects of osteoporosis on ASD after PLIF under WBV. METHODS: In the present study, using one normal model, one PLIF model and one PLIF with osteoporosis model of the L1-S1 segment were developed. A 5-Hz, 40-N sinusoidal vertical load was imposed on the superior surface of L1 of each model to simulate WBV, and the dynamic responses and maximal values of intradiscal pressure, shear stress on annulus fibrosus, total deformation, and disc bulge were evaluated in the L1-L2, L2-L3, L3-L4, and L5-S1 segments. RESULTS: At the L1-L2, L2-L3, and L3-L4 levels, the differences in the dynamic responses and maximal values in intradiscal pressure, shear stress, total deformation, and disc bulge between the PLIF and PLIF with osteoporosis models were slight. However, at the L5-S1 level, the dynamic response curves and maximal intradiscal pressure, shear stress, and disc bulge values in the PLIF with osteoporosis model were significantly lower than those in the PLIF model. CONCLUSIONS: Osteoporosis can mitigate the development of ASD in the lower adjacent segment but has no obvious influence on the upper adjacent segments during WBV.

DNF-Net: A Deep Normal Filtering Network for Mesh Denoising.

This article presents a deep normal filtering network, called DNF-Net, for mesh denoising. To better capture local geometry, our network processes the mesh in terms of local patches extracted from the mesh. Overall, DNF-Net is an end-to-end network that takes patches of facet normals as inputs and directly outputs the corresponding denoised facet normals of the patches. In this way, we can reconstruct the geometry from the denoised normals with feature preservation. Besides the overall network architecture, our contributions include a novel multi-scale feature embedding unit, a residual learning strategy to remove noise, and a deeply-supervised joint loss function. Compared with the recent data-driven works on mesh denoising, DNF-Net does not require manual input to extract features and better utilizes the training data to enhance its denoising performance. Finally, we present comprehensive experiments to evaluate our method and demonstrate its superiority over the state of the art on both synthetic and real-scanned meshes.

CB1 receptor-dependent desensitisation of TRPV1 channels contributes to the analgesic effect of dipyrone in sensitised primary sensory neurons.

BACKGROUND AND PURPOSE: While dipyrone is a widely used analgesic, its mechanism of action is not completely understood. Recently, we have reported that the dipyrone metabolite 4-aminoantipyrine (4-AA) reduces PGE2 -induced pain-related behaviour through cannabinoid CB1 receptors. Here, we ascertained, in naive and PGE2 -induced "inflamed" conditions, both in vivo and in vitro, the molecular mechanisms involved in the 4-AA-induced analgesic effects. EXPERIMENTAL APPROACH: The effect of local administration of 4-AA (160 µg per paw) on capsaicin (0.12 µg per paw) injection-induced pain-related behaviour and 4-AA's effect on 500-nM capsaicin-induced changes in intracellular calcium concentration ([Ca2+ ]i ) in cultured primary sensory neurons were assessed in vivo and in vitro, respectively. KEY RESULTS: 4-AA reduced capsaicin-induced nociceptive behaviour in naive and inflamed conditions through CB1 receptors. 4-AA (100 µM) reduced capsaicin-induced increase in [Ca2+ ]i in a CB1 receptor-dependent manner, when PGE2 was not present. Following PGE2 application, 4-AA (1-50 µM) increased the [Ca2+ ]i . Although 4-AA activated both TRPV1 and TRPA1 channels, increased [Ca2+ ]i was mediated through TRPV1 channels. Activation of TRPV1 channels resulted in their desensitisation. Blocking CB1 receptors reduced both the excitatory and desensitising effects of 4-AA. CONCLUSION AND IMPLICATIONS: CB1 receptor-mediated inhibition of TRPV1 channels and TRPV1-mediated Ca2+ -influx- and CB1 receptor-dependent desensitisation of TRPV1 channels contribute to the anti-nociceptive effect of 4-AA in naive and inflamed conditions respectively. Agonists active at both CB1 receptors and TRPV1 channels might be useful as analgesics, particularly in inflammatory conditions.

Effects of the tumor suppressor PTEN on the pathogenesis of idiopathic pulmonary fibrosis in Chinese patients.

Idiopathic pulmonary fibrosis (IPF) is characterized by progressive interstitial fibrosis, and is associated with a fatal outcome. The critical pathological mechanisms underlying IPF are largely unknown; however, accumulating evidence has indicated similarities between IPF and cancer. Therefore, the present study examined the expression levels of the tumor suppressor phosphatase and tensin homolog deleted on chromosome 10 (PTEN) in Chinese patients with IPF, using an enzyme­linked immunosorbent assay. To determine the effects of PTEN on the development of pulmonary fibrosis, PTEN was overexpressed in transforming growth factor (TGF)­ß1­treated human embryonic lung fibroblasts (HFL­I cells). The serum levels of PTEN were significantly lower in 42 patients with IPF, as compared with in the healthy controls. In addition, PTEN overexpression enhanced apoptosis, and suppressed basal levels of proliferation and migration in fibroblasts. Notably, PTEN was able to specifically inhibit TGF­ß1­induced proliferation and migration of the cells. Overexpression of PTEN also suppressed phosphorylation of Akt and Smad3, and decreased the expression levels of numerous proteins with critical roles in TGF­ß1­induced fibrosis, including α­smooth muscle actin, matrix metalloproteinase (MMP)­2 and MMP­9. These results indicated that PTEN may inhibit TGF­ß1­mediated myofibroblast differentiation of fibroblasts by attenuating signaling via the phosphatidylinositol 3­kinase/Akt and TGF­ß/Smad3 pathways.

[Motion signal extraction method based on sEMG energy Gauss distribution characteristics].

Motion segment and extraction from continuous signals is the premise of surface electromyography (sEMG) analysis. For the problem that sEMG energy threshold required repeated manual testing to set, this the paper established a this mathematical model of continuous actions based on Gaussian sEMG energy curve, in which the energy threshold was set according to the distribution of Gaussian signal section, and differentiated the action signals from no-action signals combined with energy comparison method. The experiment results showed the method can achieve continuous repetitive action segmentation, and compared with manual segmentation of the same signal, has a higher degree of coincidence.

[Peripheral primitive neuroectodermal tumor of trachea: a case report and review of literatures].

OBJECTIVE: To improve the understanding of tracheal peripheral primitive neuroectodermal tumor (PNET). METHODS: A case of tracheal PNET diagnosed in July 2010 was reported and the related literatures were reviewed. The literature review was carried out respectively with "primitive neuroectodermal tumor", "peripheral" as the search terms in Wanfang med online and PubMed database by September 2011. RESULTS: A case of 63 year-old female patient, who had been misdiagnosed as having chronic pharyngitis, chronic bronchitis and bronchial asthma, was admitted to the hospital because of cough and sputum production for 50 days, and anhelation for 1 month. After admission, the chest computerized tomography showed a space-occupying lesion in the middle of the trachea. Bronchoscopy showed a pedicle neoplasm 4 cm under the subglottic, with integral capsule, smooth surface and rich vascellum. Subsequently, tumor resection under bronchoscope was performed. Pathology report after operation showed infiltration of flake small round malignant cells under bronchial mucosa. Immunohistochemistry showed CD(99)(+), Syn(+) and S-100(+). EWS-FLI-1 fusion transcript was detected by RT-PCR. Accordingly, it was diagnosed as PNET. The symptoms of cough and anhelation were disappeared after operation. So far, there was no local recurrence and distant metastasis with 14 months follow-up. A total of 111 literatures were received in Pubmed, including one of prospective study, one of review, 22 of retrospective study and 87 of case report. Forty literatures and 187 cases in all were received in Wanfang Med Online, including 24 of retrospective study and 16 of case report. But, there were no reports about tracheal PNET. CONCLUSIONS: PNET can occur in the trachea and is easy to be misdiagnosed. To make a definite diagnosis, histopathology and immunohistochemistry are needed and detection of EWS-FLI-1 fusion transcript is a reliable marker for molecular diagnosis. The tracheal pPNET may be different with the pPNETs in other parts, and has a lower-grade invasion and less distant metastasis.

Clinical implications for BRCA gene mutation in breast cancer.

To investigate the mutations of BRCA1 and BRCA2 and determine whether clinic-pathological factors related to BRCA gene mutation. Mastectomy specimens from 360 breast cancers were enrolled and examined in the study. The relationship between BRCA gene mutation and clinic-pathological factors was evaluated. Overall, 280 patients were BRCA negative and 80 got BRCA gene mutation. Triple-negative breast cancers--i.e., breast cancers that do not express estrogen receptors (ER), progesterone receptors (PR) or human epidermal growth factor receptor 2 (HER2/neu)--was observed in 53.85% of the BRCA1 mutation patients, in 28.57% of the BRCA2 mutation cases, while 14.29% of BRCA negative patients. BRCA1 mutation patients got a heavy lymph node metastasis and higher nuclear grade tumors than the others (P = 0.004, 0.007). Furthermore, BRCA mutation was also found to be significantly related to ER, PR and HER2/neu status (P < 0.05). BRCA1 expression was not associated with breast cancer-specific survival in the triple-negative breast cancers (P = 0.742). After Cox regression, BRCA1 mutation was not shown to be an independent prognostic factor for breast cancer. These findings substantiated the possibility of tumors associated with BRCA1 mutations divided into two distinct groups, triple-negative and non-triple-negative groups requires further investigation.

[Sinus histiocytosis with massive lymphadenopathy (Rosai-Dorfman disease) of the airway: a case report and review of the literature].

OBJECTIVE: To improve the awareness of sinus histiocytosis with massive lymphadenopathy (Rosai-Dorfman disease) involving the airways. METHODS: The clinical presentations, endoscopic findings in the airways, pathological characteristics, and diagnosis and treatment of a case of Rosai-Dorfman disease was reported, and related literatures were reviewed. RESULTS: A 60-year-old female patient was admitted to this hospital because of recurrent wheezing for 18 months and aggravated for 1 month on March 6, 2007. The diagnosis of "bronchial asthma" had been made and oral prednisolone and inhaled budesonide resulted in symptom improvement. One month ago, she had wheezing again with inspiratory dyspnea, which was more obvious at recumbent position.She had been found to have high blood pressure and left adrenal adenoma 23 years ago, and as the diagnosis of "primary aldosteronism" was made but underwent no surgery. Left parotid gland tumor and left submandibular lymph nodes had been found, and surgical resection implemented in 1999. Lacrimal gland tumor resection of her eyes had been performed in 2000. Multiple subcutaneous nodules, rising and disappearing spontaneously, had been demonstrated in 2001. After admission, physical examination revealed nodules of 3.0 cm x 2.0 cm in her left submandibular area, and soybean sized nodules at both arms, back, chest, abdomen, buttocks and thighs. Chest CT scan and tracheal reconstruction showed that there were multiple nodules in the tracheal wall with narrow lumen, with no obvious enlargement of mediastinal lymph nodes. Lymph node biopsy showed faintly stained areas and the formation of plasma cells and lymphocytes of the deeply stained area, presenting as a sinus-like structure, and plasma cells and lymphocytes were engulfed in the plasma of the histiocytes, consistent with the diagnosis of Rosai-Dorfman disease. CONCLUSIONS: Rosai-Dorfman disease involving the airway was a rare disease often misdiagnosed. Bronchoscopy was very helpful for the diagnosis. Histiocytosis with phagocytosis of plasma cells and lymphocytes was the pathological feature, and immunohistochemical staining positive for S100 protein and CD(68) was suggestive of the diagnosis. Surgical resection combined with corticosteroids or radiotherapy was effective treatment of the airway diseases.