Search

Chemogenomics, also known as proteochemometrics, covers various computational methods for predicting interactions between related drugs and targets on large-scale data. Chemogenomics is used in the early stages of drug discovery to predict the off-target effects of proteins against therapeutic candidates. This study aims to predict unknown ligand–target interactions using one-dimensional SMILES as inputs for ligands and binding site residues for proteins in a computationally efficient manner. We first formulate a Deep learning CNN model using one-dimensional SMILES for drugs and motif-rich binding pocket subsequences of proteins as inputs. We evaluate and compare the proposed deep learning model trained on expert-based features against shallow feature-based machine learning methods. The proposed method achieved better or similar performance on the MSE and AUPR metrics than the shallow methods. Additionally, We show that our deep learning model, DeepPS is computationally more efficient than the deep learning model trained on full-length raw sequences of proteins. We conclude that a beneficial research approach would be to integrate structural information of proteins for modeling drug-target interaction prediction of large datasets for more interpretability, high throughput, and broad applicability. Graphical abstract

Background: Wound dehiscence is dened as a partial or total disruption of the abdominal wound closure, with or without abdominal contents protrusion. It's one of surgeons' most dreaded consequences, and it's considered a serious postoperative complication with mortality rates as high as 45 percent. In the literature, the incidence ranges from 0.4 percent to 3.5 percent. The goal of this study was to determine the prevalence of abdominal wound dehiscence in relation to various risk variables, as well as to investigate effective management of abdominal wound dehiscence. Methods: Patients with abdominal wound dehiscence after surgery were included. In light of the substantial risk factors, the types of surgery conducted, including surgical incisions made, and the type of disease involved, an extensive clinical history was obtained. This prospective study comprised a total of 60 patients. Appropriate software was used to analyse the data. Results: Male patients had higher incidence for abdominal wound dehiscence in fth decade. Patients presenting with peritonitis secondary to hollow viscus perforation are more prone to abdominal wound dehiscence. Class 3 surgery i.e., contaminated surgeries in emergency nature has higher risk for wound dehiscence. Conclusions: Co-morbidities such as diabetes, malnutrition, anaemia, and COPD all contribute to the slow healing of wounds. Simple routine laboratory tests may aid in the identication of predisposing factors and their correction. The majority of patients can be treated conservatively with secondary suturing rather than undergoing re-exploration and surgery.

The fast growth in Internet‐of‐Things (IoT) applications has increased the number of end‐devices communicating over the Internet. As these resource‐constrained devices are connected over the Internet, they are exposed to various security and privacy issues. Traditionally, to provide end‐to‐end security, research efforts have been carried out using elliptic curve cryptography‐based authentication schemes. These existing schemes use a single set of elliptic curve parameters to generate the public and private keys, which are prone to be hacked under intense cryptanalysis. Thereby to increase the security strength the proposed method uses two sets of dynamic elliptic curves for performing digital signature and encryption processes. The method is evaluated on a client‐server model using the Raspberry Pi‐3 device. Herein, the choice of elliptic curves is made random at the client node and the reference of each elliptic curve is exchanged with the server during the key‐exchange process. The choice of elliptic curves is delegated to the client machine to avoid the unwanted delay that would be encounter if server had to choose the curve. This is done because the client senses the data at regular intervals of time and forwards it to the server securely. Experiments were conducted to measure the time taken for hashing function, key generation, signature generation, signature verification, encryption and decryption process. On comparing the proposed DEC‐LADE with cBLAKE2b, an improvement was seen at 13.76%, 2.57%, 18.36%, 6.12%, 9.91% and 6.08% less time, respectively, than LWDSA with mBLAKE2b. Theoretical and real‐time security evaluations are performed for man‐in‐the‐middle attack, replay attack, and a denial‐of‐service attack.

Solar and wind energy are the renewable energy sources that have the great potential to fulfill the electricity needs of the world. They are available in abundance and also while generating electricity, they produce little or no global warming emissions. A lot of work has been carried out in the literature in the field of solar and wind energy systems. This has been taught as courses in various universities. 3DEXPERIENCE platform of Dassault Systemes has an integrated mathematical Modelling application known as Dymola. This integrated Dymola software allows solving complex multi-domain system modeling and analysis by using modelica and simulation technology. In this work, a virtual lab module for wind and solar PV systems have been designed and developed in 3DEXPERIENCE platform. The characteristic Plots of solar PV system for various configurations are plotted and effect of partial shading is also analyzed. The variation of mechanical power of wind system for various pitch angles are plotted.

The Internet-of-Things (IoT) is a combination of an intelligent infrastructure combined with various self-organizing devices. These devices are used to monitor the environment and help to exchange sensitive data over the Internet without much human interference. Such a huge network of unmanned devices are subjected to various security and privacy concern. As these devices are battery powered and have low inbuilt resources, it is important to enable secure and resource-constrained security solutions to secure the devices. Thereby, to address the security and privacy of these devices and the data, the authentication plays an important role along with data integrity. Through this paper, we have analyzed the various lightweight solution and their security threats under the authentication and data integrity of the IoT applications. From the study, it can be seen that the major security concern of these protocols is to perform with less computation and resist to attacks like man-in-the-middle, replay attacks, denial of service attacks, forgery and chosen-ciphertext attacks. Also, this review provides an insight into using the Microsoft threat modeling tool used for IoT based applications.

Predicting the binding affinity between compounds and proteins with reasonable accuracy is crucial in drug discovery. Computational prediction of binding affinity between compounds and targets greatly enhances the probability of finding lead compounds by reducing the number of wet-lab experiments. Machine-learning and deep-learning techniques using ligand-based and target-based approaches have been used to predict binding affinities, thereby saving time and cost in drug discovery efforts. In this review, we discuss about machine-learning and deep-learning models used in virtual screening to improve drug-target interaction (DTI) prediction. We also highlight current knowledge and future directions to guide further development in this field.

The goal of Internet-of-Things (IoT) is that every object across the globe be interconnected under the Internet Infrastructure. IoT is expanding its application domain to range from environmental monitoring to industrial automation thereby leading to vast research challenges. Vast presence of devices in the Internet has increased the possible challenges faced by devices and data. The devices communicate on a public channel that is more likely to be accessed by unauthorized users and disturb the privacy of genuine users. The existing solutions that ensure data authenticity and user privacy, use MD5 and SHA-family of hashing algorithms under digital signature schemes. These algorithms create a trade-off between the security concern and energy consumption of IoT devices. To provide an energy efficient authentication method, we propose a customized BLAKE2b hashing algorithm with modified elliptic curve digital signature scheme (ECDSA). The parameters considered for the evaluation of the proposed methods are signature generation time, signature verification time and hashing time. The experiments are conducted under client server model using Raspberry Pi-3. The proposed method has shown about 0.7–1.91% improvement in the signature generation time and 7.67–9.13 % improvement in signature verification time when compared with BLAKE2b based signature generation/verification. The proposed method is resistant to Man-in-the-Middle attack, Distributed DoS attack (DDoS), pre-image resistance, second pre-image resistance and collision resistance. Based on the performance obtained by the experiments, it can be inferred that the proposed scheme is feasible for resource-constrained IoT devices.

Security is an essential part of the improvement for value programming, so as Usability is natural and significant factor for creating quality system. The discrepancy among Usability and protection be generally perceived examine issue in diligence as well as for scholarly community. Disappointment to plan frameworks, which are at the same time usable as well as secure, may perhaps cause incident anywhere individual mistakes show the way towards safety breaks. Scholarly study distinguishes to facilitate usability vs. safety struggle can be real best handle by requirement along with design phase of the framework improvement. The principle target of the security is to give restricted access to the security concentrated data though the goal of usability is to give simple access of the verified application. Usable security can be more interesting because of the expanding use of PCs with upgraded usability and protection criteria in it. While recovering the usability through security of system, fundamental securities as well as usability qualities assume a significant work. Thus, usable security assessment utilizes security and usability credits towards accomplish ideal security actions through usability. In this paper a Fuzzy approach system is assess to identify the needs and overall usable—secure and the effect of safety on the Usability and vice versa assessed by quantitatively. The outcomes got with ends helpful for professionals to get better usable–secure of the system.

Machine learning is very widely used for many applications like classification and regression. Diseases in the soybean crop are classified using machine learning techniques. Physic crop properties and weather parameters are used as a attributes for classification. K nearest neighbor, naive Bayes, decision tree, neural network algorithms are used for classification. The result is compared with the ensemble classifier called bagging.

Internet-of-Things (IoT) can also be defined as interconnection of “factual-and-virtual” objects placed across the globe that are attracting attentions of both “makers-and-hackers”. IoT devices are self-organizing and self-adaptive that communicate with each other over the public channel. These communications are vulnerable to security and privacy attacks of user and data. Hence to provide lightweight crypto-solution, a hybrid authentication and data integrity scheme is proposed using elliptic curve cryptography based digital signature and encryption scheme. The experiment is performed on a Raspberry Pi-3 based client-server network. Through the experimental analysis, it can be inferred that the proposed method has shown improvement in the time of about 28.3-33.3% in the signature phase and 15.6 % in the verification phase than existing ECDSA based schemes. Also, the use of cBLAKE2b has shown less time in encryption and decryption of 11.73-5.45% and 7.11-5.63%, respectively.

Feature selection is a necessary step in machine learning regression problems that aims to find relevant and reduced set of features. In this research, we assessed the performance of three different learning models on a Quantitative structure activity relationship (QSAR) dataset. Learning models were developed from a pool of features selected by three different variable selection techniques. The results indicate that the final learning models built using statistically significant features exhibit improved predictive performance. Further, Partial least squares (PLS) learning model has shown better predictive performance compared to other learning models on the external test set.