Machine learning algorithms were explored for the fast estimation of HOMO and LUMO orbital energies calculated by DFT B3LYP, on the basis of molecular descriptors exclusively based on connectivity. ...The whole project involved the retrieval and generation of molecular structures, quantum chemical calculations for a database with >111 000 structures, development of new molecular descriptors, and training/validation of machine learning models. Several machine learning algorithms were screened, and an applicability domain was defined based on Euclidean distances to the training set. Random forest models predicted an external test set of 9989 compounds achieving mean absolute error (MAE) up to 0.15 and 0.16 eV for the HOMO and LUMO orbitals, respectively. The impact of the quantum chemical calculation protocol was assessed with a subset of compounds. Inclusion of the orbital energy calculated by PM7 as an additional descriptor significantly improved the quality of estimations (reducing the MAE in >30%).
Leukaemia is a dysfunction that affects the production of white blood cells in the bone marrow. Young cells are abnormally produced, replacing normal blood cells. Consequently, the person suffers ...problems in transporting oxygen and in fighting infections. This article proposes a convolutional neural network (CNN) named LeukNet that was inspired on convolutional blocks of VGG-16, but with smaller dense layers. To define the LeukNet parameters, we evaluated different CNNs models and fine-tuning methods using 18 image datasets, with different resolution, contrast, colour and texture characteristics. We applied data augmentation operations to expand the training dataset, and the 5-fold cross-validation led to an accuracy of 98.61%. To evaluate the CNNs generalisation ability, we applied a cross-dataset validation technique. The obtained accuracies using cross-dataset experiments on three datasets were 97.04, 82.46 and 70.24%, which overcome the accuracies obtained by current state-of-the-art methods. We conclude that using the most common and deepest CNNs may not be the best choice for applications where the images to be classified differ from those used in pre-training. Additionally, the adopted cross-dataset validation approach proved to be an excellent choice to evaluate the generalisation capability of a model, as it considers the model performance on unseen data, which is paramount for CAD systems.
•A semi-automatic segmentation method for dermoscopic image is proposed.•Related state-of-art is reviewed.•Five public image datasets are used in the experiments;•The results obtained by the proposed ...methods are very promising.•The results confirm the high robustness of the proposed method.
Display omitted
Dermoscopic images are commonly used in the early diagnosis of skin lesions, and several computational systems have been proposed to analyze them. The segmentation of the lesions is a fundamental step in many of these systems. Therefore, a semi-automatic segmentation method is proposed here, which begins by building the superpixels of the image under analysis based on the zero parameter version of the simple linear iterative clustering (SLIC0) algorithm. Then, each superpixel is represented using a descriptor built by combining the grey-level co-occurrence matrix and Tamura texture features. Afterward, the gain ratios of the features are used to select the input for the semi-supervised seeded fuzzy C-means clustering algorithm. Hence, from a few specialist-selected superpixels, this clustering algorithm groups the built superpixels into lesion or background regions. Finally, the segmented image undergoes a post-processing step to eliminate sharp edges. The experiments were performed on 1380 images: 401 images from the PH2 and DermIS datasets, which were used to establish the parameters of the method, and 3,573 images from the ISIC 2016, ISIC 2017 and ISIC 2018 datasets were used for the analysis of the method’s performance. The findings suggest that, by manually identifying just a few of the generated superpixels, the method can achieve an average segmentation accuracy of 96.78%, which confirms its superiority to the ones in the literature.
The disturbing emergence of multidrug-resistant strains of Mycobacterium tuberculosis (Mtb) has been driving the scientific community to urgently search for new and efficient antitubercular drugs. ...Despite the various drugs currently under evaluation, isoniazid is still the key and most effective component in all multi-therapeutic regimens recommended by the WHO. This paper describes the QSAR-oriented design, synthesis and in vitro antitubercular activity of several potent isoniazid derivatives (isonicotinoyl hydrazones and isonicotinoyl hydrazides) against H37Rv and two resistant Mtb strains. QSAR studies entailed RFs and ASNNs classification models, as well as MLR models. Strict validation procedures were used to guarantee the models' robustness and predictive ability. Lipophilicity was shown not to be relevant to explain the activity of these derivatives, whereas shorter N–N distances and lengthy substituents lead to more active compounds. Compounds 1, 2, 4, 5 and 6, showed measured activities against H37Rv higher than INH (i.e., MIC ≤ 0.28 μM), while compound 9 exhibited a six fold decrease in MIC against the katG (S315T) mutated strain, by comparison with INH (i.e., 6.9 vs. 43.8 μM). All compounds were ineffective against H37RvINH (ΔkatG), a strain with a full deletion of the katG gene, thus corroborating the importance of KatG in the activation of INH-based compounds. The most potent compounds were also shown not to be cytotoxic up to a concentration 500 times higher than MIC.
Display omitted
•Robust and highly predictive QSAR models were developed.•17 isoniazid (INH) derivatives were designed and 13 actually synthesized.•Five newly synthesized INH derivatives showed MICs against H37Rv lower than INH.•One compound showed a six fold fall in MIC against the katG (S315T) mutated strain.•Compounds were shown not to be cytotoxic.
The YEAst Search for Transcriptional Regulators And Consensus Tracking (YEASTRACT) information system (http://www.yeastract.com) was developed to support the analysis of transcription regulatory ...associations in Saccharomyces cerevisiae. Last updated in June 2010, this database contains over 48 200 regulatory associations between transcription factors (TFs) and target genes, including 298 specific DNA-binding sites for 110 characterized TFs. All regulatory associations stored in the database were revisited and detailed information on the experimental evidences that sustain those associations was added and classified as direct or indirect evidences. The inclusion of this new data, gathered in response to the requests of YEASTRACT users, allows the user to restrict its queries to subsets of the data based on the existence or not of experimental evidences for the direct action of the TFs in the promoter region of their target genes. Another new feature of this release is the availability of all data through a machine readable web-service interface. Users are no longer restricted to the set of available queries made available through the existing web interface, and can use the web service interface to query, retrieve and exploit the YEASTRACT data using their own implementation of additional functionalities. The YEASTRACT information system is further complemented with several computational tools that facilitate the use of the curated data when answering a number of important biological questions. Since its first release in 2006, YEASTRACT has been extensively used by hundreds of researchers from all over the world. We expect that by making the new data and services available, the system will continue to be instrumental for yeast biologists and systems biology researchers.
Eighty-four staphylococcal isolates were obtained from milk samples from cows, sheep, goats, and buffalo with subclinical mastitis and from colonization samples from ostriches. The animals were ...hosted in 18 small dairy herds and an ostrich breeding located in 10 municipalities of the state of Rio de Janeiro, Brazil. Thirty isolates were identified as Staphylococcus aureus by biochemical and molecular techniques and were comparatively characterized by phenotypic and genotypic methods. The molecular characterization by pulsed-field gel electrophoresis (PFGE), spa typing, and multilocus sequence typing (MLST) revealed five clonal types (PFGE A, spa type t359, sequence type 747 ST747; PFGE B, spa type t1180, ST750; PFGE C, spa type t605, ST126; PFGE D, spa type t127, ST751; and PFGE F, spa type t002, ST5). None of the isolates harbored the Panton-Valentine leukocidin or exfoliative toxin D gene. The detection of major clone A (in 63% of the isolates) in different herds, among all animal species studied, and in infection and colonization samples evidenced its geographical spread among Rio de Janeiro State and no host preference among the animal species. Comparison with S. aureus from a human origin suggested that all but one clone found in the present study might be animal specific.
Background and Purpose
Neutrophil overstimulation plays a crucial role in tissue damage during severe infections. Because pathogen‐derived neuraminidase (NEU) stimulates neutrophils, we investigated ...whether host NEU can be targeted to regulate the neutrophil dysregulation observed in severe infections.
Experimental Approach
The effects of NEU inhibitors on lipopolysaccharide (LPS)‐stimulated neutrophils from healthy donors or COVID‐19 patients were determined by evaluating the shedding of surface sialic acids, cell activation, and reactive oxygen species (ROS) production. Re‐analysis of single‐cell RNA sequencing of respiratory tract samples from COVID‐19 patients also was carried out. The effects of oseltamivir on sepsis and betacoronavirus‐induced acute lung injury were evaluated in murine models.
Key Results
Oseltamivir and zanamivir constrained host NEU activity, surface sialic acid release, cell activation, and ROS production by LPS‐activated human neutrophils. Mechanistically, LPS increased the interaction of NEU1 with matrix metalloproteinase 9 (MMP‐9). Inhibition of MMP‐9 prevented LPS‐induced NEU activity and neutrophil response. In vivo, treatment with oseltamivir fine‐tuned neutrophil migration and improved infection control as well as host survival in peritonitis and pneumonia sepsis. NEU1 also is highly expressed in neutrophils from COVID‐19 patients, and treatment of whole‐blood samples from these patients with either oseltamivir or zanamivir reduced neutrophil overactivation. Oseltamivir treatment of intranasally infected mice with the mouse hepatitis coronavirus 3 (MHV‐3) decreased lung neutrophil infiltration, viral load, and tissue damage.
Conclusion and Implications
These findings suggest that interplay of NEU1–MMP‐9 induces neutrophil overactivation. In vivo, NEU may serve as a host‐directed target to dampen neutrophil dysfunction during severe infections.
In the present study, several experimental approaches were carried out to evaluate the regulatory role of host neuraminidase (NEU) on the neutrophil response: (1) Lipopolysaccharide (LPS)‐induced NEU activity triggers human neutrophil activation, an effect significantly inhibited by either oseltamivir or zanamivir; (2) mice oral treatment with oseltamivir and inhibition of host NEU fine‐tunes neutrophil migration, improving infection control and survival rates in peritonitis and pneumonia‐induced sepsis; (3) treatment of whole blood from severe COVID‐19 patients with either oseltamivir or zanamivir reduced sialic acid cleavage and neutrophil overactivation; and (4) oseltamivir treatment of intranasally infected mice with a mouse betacoronavirus decreases lung neutrophil infiltration, viral load, and pulmonary damage.
The combination of chemoinformatics approaches with NMR techniques and the increasing availability of data allow the resolution of problems far beyond the original application of NMR in structure ...elucidation/verification. The diversity of applications can range from process monitoring, metabolic profiling, authentication of products, to quality control. An application related to the automatic analysis of complex mixtures concerns mixtures of chemical reactions. We encoded mixtures of chemical reactions with the difference between the (1)H NMR spectra of the products and the reactants. All the signals arising from all the reactants of the co-occurring reactions were taken together (a simulated spectrum of the mixture of reactants) and the same was done for products. The difference spectrum is taken as the representation of the mixture of chemical reactions. A data set of 181 chemical reactions was used, each reaction manually assigned to one of 6 types. From this dataset, we simulated mixtures where two reactions of different types would occur simultaneously. Automatic learning methods were trained to classify the reactions occurring in a mixture from the (1)H NMR-based descriptor of the mixture. Unsupervised learning methods (self-organizing maps) produced a reasonable clustering of the mixtures by reaction type, and allowed the correct classification of 80% and 63% of the mixtures in two independent test sets of different similarity to the training set. With random forests (RF), the percentage of correct classifications was increased to 99% and 80% for the same test sets. The RF probability associated to the predictions yielded a robust indication of their reliability. This study demonstrates the possibility of applying machine learning methods to automatically identify types of co-occurring chemical reactions from NMR data. Using no explicit structural information about the reactions participants, reaction elucidation is performed without structure elucidation of the molecules in the mixtures.
Abstract Background Hepatitis B virus (HBV) and tuberculosis (TB) represent major public health problems. There is currently little data on HBV infection among TB patients with and without human ...immunodeficiency virus (HIV). Objectives To assess HBV prevalence among TB patients with and without HIV. Study design From April 2008 to March 2010, a cross-sectional study was conduct among TB patients attended at a reference hospital in Goiânia City, Brazil. The participants were tested for serological markers of HBV infection and HIV antibodies. HBV DNA was detected in HBsAg-positive samples, and also in HBsAg-negative/anti-HBc-positive samples to look for HBV occult infection. Results Of 425 patients, 402 (94.6%) agreed to participate in the study. The overall prevalence of HBV (HBsAg and/or anti-HBc positive) and HIV infections were 25.6% (103/402) and 27.6% (111/402), respectively. A higher HBV infection rate was found among HIV-infected patients (36.9%; 41/111) compared to patients infected with TB only (20.0%; 57/285). A multivariate analysis of risk factors showed that age ≥50 years ( p = 0.03), non-injecting ( p < 0.01) and injecting ( p < 0.01) drugs use were associated with HBV infection. Among the HBsAg-positive samples ( n = 13), HBV DNA was detected in 10 (76.9%) samples. Of the 90 anti-HBc-positive samples, 13 were HBV DNA positive (with very low levels) resulting in an occult HBV infection rate of 14.4%. PCR-RFLP was successfully performed in 20 HBV DNA-positive samples: 15 were genotype A and 5 were genotype D. Conclusions HBV infection was common, particularly among this with HIV infection.
Display omitted
•Divaricatic acid exhibits toxicity against B. glabrata embryos and adult snails.•Malformations and delay in embryonic development were observed.•Divaricatic acid showed lethal ...effects against cercariae of Schistosoma mansoni.•Divaticatic acid was not toxic to Artemia salina.
In this study, the molluscicidal and antiparasitic activities of divaricatic acid was evaluated, targeting the mollusc Biomphalaria glabrata and cercariae of the helminth Schistosoma mansoni. In addition, the environmental toxicity of divaricatic acid was assessed by bioassay using the microcrustacean Artemia salina. Divaricatic acid showed high toxicity against both adult snails (5μg/mL) and embryos (20μg/mL after 6h of exposure). Similar activity was observed in Schistosoma mansoni cercariae after only a short exposure time (10μg/mL after 30min of exposure). The divaricatic acid did not show toxicity in the acute test using Artemia salina at concentrations equal to or below 200μg/mL. The divaricatic acid proved to be a promising substance for the elimination of the snail Biomphalaria glabrata, an intermediate host of schistosomiasis, as well as the cercariae of the pathogen, while being non-toxic to the Artemia salina at the same concentrations. This is the first experimental observation of the molluscicidal and cercaricide activity of divaricatic acid.