Ayan Chatterjee

Ayan Chatterjee, Robin Walters, Zohair Shafi et al.

Identifying novel drug-target interactions (DTI) is a critical and rate limiting step in drug discovery. While deep learning models have been proposed to accelerate the identification process, we show that state-of-the-art models fail to generalize to novel (i.e., never-before-seen) structures. We first unveil the mechanisms responsible for this shortcoming, demonstrating how models rely on shortcuts that leverage the topology of the protein-ligand bipartite network, rather than learning the node features. Then, we introduce AI-Bind, a pipeline that combines network-based sampling strategies with unsupervised pre-training, allowing us to limit the annotation imbalance and improve binding predictions for novel proteins and ligands. We illustrate the value of AI-Bind by predicting drugs and natural compounds with binding affinity to SARS-CoV-2 viral proteins and the associated human proteins. We also validate these predictions via docking simulations and comparison with recent experimental evidence, and step up the process of interpreting machine learning prediction of protein-ligand binding by identifying potential active binding sites on the amino acid sequence. Overall, AI-Bind offers a powerful high-throughput approach to identify drug-target combinations, with the potential of becoming a powerful tool in drug discovery.

Ayan Chatterjee, Ali Shahaab, Martin W. Gerdes et al.

Health data is a sensitive category of personal data. It might result in a high risk to individual and health information handling rights and opportunities unless there is a palatable defense. Reasonable security standards are needed to protect electronic health records (EHR). All personal data handling needs adequate explanation. Maintaining access to medical data even in the developing world would favor health and well-being across the world. Unfortunately, there are still countries that hinder the portability of medical records. Numerous occurrences have shown that it still takes weeks for the medical data to be ported from one general physician (GP) to another. Cross border portability is nearly impossible due to the lack of technical infrastructure and standardization. We demonstrate the difficulty of the portability of medical records with some example case studies as a collaborative engagement exercise through a data mapping process to describe how different people and datapoints interact and evaluate EHR portability techniques. We then propose a blockchain-based EHR system that allows secure, and cross border sharing of medical data. The ethical and technical challenges around having such a system have also been discussed in this study.

Pankaj Khatiwada, Ayan Chatterjee, Matrika Subedi

In smart healthcare, Human Activity Recognition (HAR) is considered to be an efficient model in pervasive computation from sensor readings. The Ambient Assisted Living (AAL) in the home or community helps the people in providing independent care and enhanced living quality. However, many AAL models were restricted using many factors that include computational cost and system complexity. Moreover, the HAR concept has more relevance because of its applications. Hence, this paper tempts to implement the HAR system using deep learning with the data collected from smart sensors that are publicly available in the UC Irvine Machine Learning Repository (UCI). The proposed model involves three processes: (1) Data collection, (b) Optimal feature selection, (c) Recognition. The data gathered from the benchmark repository is initially subjected to optimal feature selection that helps to select the most significant features. The proposed optimal feature selection is based on a new meta-heuristic algorithm called Colliding Bodies Optimization (CBO). An objective function derived by the recognition accuracy is used for accomplishing the optimal feature selection. Here, the deep learning model called Recurrent Neural Network (RNN) is used for activity recognition. The proposed model on the concerned benchmark dataset outperforms existing learning methods, providing high performance compared to the conventional models.

Pankaj Khatiwada, Hari Bhusal, Ayan Chatterjee et al.

Healthcare data in cloud computing facilitates the treatment of patients efficiently by sharing information about personal health data between the healthcare providers for medical consultation. Furthermore, retaining the confidentiality of data and patients' identity is a another challenging task. This paper presents the concept of an access control-based (AC) privacy preservation model for the mutual authentication of users and data owners in the proposed digital system. The proposed model offers a high-security guarantee and high efficiency. The proposed digital system consists of four different entities, user, data owner, cloud server, and key generation center (KGC). This approach makes the system more robust and highly secure, which has been verified with multiple scenarios. Besides, the proposed model consisted of the setup phase, key generation phase, encryption phase, validation phase, access control phase, and data sharing phase. The setup phases are run by the data owner, which takes input as a security parameter and generates the system master key and security parameter. Then, in the key generation phase, the private key is generated by KGC and is stored in the cloud server. After that, the generated private key is encrypted. Then, the session key is generated by KGC and granted to the user and cloud server for storing, and then, the results are verified in the validation phase using validation messages. Finally, the data is shared with the user and decrypted at the user-end. The proposed model outperforms other methods with a maximal genuine data rate of 0.91.