Md Toki Tahmid

Identifying DNA-binding proteins and their binding residues is critical for understanding diverse biological processes, but conventional experimental approaches are slow and costly. Existing machine learning methods, while faster, often lack accuracy and struggle with data imbalance, relying heavily on evolutionary profiles like PSSMs and HMMs derived from multiple sequence alignments (MSAs). These dependencies make them unsuitable for orphan proteins or those that evolve rapidly. To address these challenges, we introduce TransBind, an alignment-free deep learning framework that predicts DNA-binding proteins and residues directly from a single primary sequence, eliminating the need for MSAs. By leveraging features from pre-trained protein language models, TransBind effectively handles the issue of data imbalance and achieves superior performance. Extensive evaluations using diverse experimental datasets and case studies demonstrate that TransBind significantly outperforms state-of-the-art methods in terms of both accuracy and computational efficiency

The method of finding new petroleum deposits beneath the earth’s surface is always challenging for having low accuracy while simultaneously being highly expensive. As a remedy, this paper presents a novel way to predict the locations of petroleum deposits. Here, we focus on a region of the Middle East, Iraq to be specific, and conduct a detailed study on predicting locations of petroleum deposits there based on our proposed method. To do so, we develop a new method of predicting the location of a new petroleum deposit based on publicly available data sensed by an open satellite named Gravity Recovery and Climate Experiment (GRACE). Using GRACE data, we calculate the gravity gradient tensor of the earth over the region of Iraq and its surroundings. We use this calculated data to predict the locations of prospective petroleum deposits over the region of Iraq. In the process of our study for making the …

Automated classification of cardiovascular diseases from electrocardiogram (ECG) signals using deep learning has gained significant interest due to its wide range of applications. However, existing deep learning approaches often overlook inter-channel shared information or lose time-sequence dependent information when considering 1D and 2D ECG representations, respectively. Moreover, besides considering spatial dimension, it is necessary to understand the context of the signals from a global feature space. We propose MD-CardioNet, an efficient deep learning architecture that captures temporal, spatial, and volumetric features from multi-lead ECG signals using multidimensional (1D, 2D, and 3D) convolutions to address these challenges. Sequential feature extractors capture time-dependent information, while a 2D convolution is applied to form an image representation from the multi-channel ECG signal, extracting inter-channel features. Additionally, a volumetric feature extraction network is designed to incorporate intra-channel, inter-channel, and inter-filter global space information. To reduce computational complexity, we introduce a practical knowledge distillation framework that reduces the number of trainable parameters by up to eight times (from 4,304,910 parameters to 94,842 parameters) while maintaining satisfactory performance compatible with the other existing approaches. The proposed architecture is evaluated on a large publicly available dataset containing ECG signals from over 10,000 patients, achieving an accuracy of 97.3% in classifying six heartbeat rhythms. Our results surpass the performance of some state-of-the-art approaches. This paper presents a novel deep-learning approach for ECG classification that addresses the limitations of existing methods. The experimental results highlight the robustness and accuracy of MD-CardioNet in cardiovascular disease classification, offering valuable insights for future research in this field.

The number of disasters, accidents, and casualties in disasters is increasing, however, technological advancement has yet to ripe benefits to emergency rescue operations. This contrast is even more prominent in the Global South. The consequences are a huge loss of wealth and resources, but more importantly, the loss of lives. Locating victims of disasters as quickly as possible while speeding up rescue operations can lessen these losses. Traditional approaches for effective victim localization and rescue often requires the establishment of additional infrastructure during the construction period. Which in the context of countries of the global south such as - Bangladesh, is not followed for most of the industrial and household constructions. In this paper, we conduct a study to better understand the challenges of victim localization in emergency rescue operations and to overcome them using “whatever” resources available at hand without needing prior infrastructure facilities and pre-calibration. We design and develop a solution for this purpose and deployed it in several emulated disaster-like scenarios. We analyze and discuss the results obtained from our experiments. Finally, we point out the design implications of an infrastructure-independent and extensive emergency rescue system.

Though many countries have already launched COVID-19 mass vaccination programs to control the disease outbreak quickly, numerous countries around worldwide are grappling with unprecedented surges of new COVID-19 cases due to a more contagious and deadly variant of coronavirus. As the number of new cases is skyrocketing, pandemic fatigue and public apathy towards different intervention strategies pose new challenges to government officials to combat the pandemic. Henceforth, it is indispensable for the government officials to understand the future dynamics of COVID-19 flawlessly to develop strategic preparedness and resilient response planning. In light of the above circumstances, probable future outbreak scenarios in Brazil, Russia, and the United kingdom have been sketched in this study with the help of four deep learning models: long short term memory (LSTM), gated recurrent unit (GRU), convolutional neural network (CNN) and multivariate convolutional neural network (MCNN). In our analysis, the CNN algorithm has outperformed other deep learning models in terms of validation accuracy and forecasting consistency. It is unearthed in our study that CNN can provide robust long-term forecasting results in time-series analysis due to its capability of essential features learning, distortion invariance, and temporal dependence learning. However, the prediction accuracy of the LSTM algorithm has been found to be poor as it tries to discover seasonality and periodic intervals from any time-series dataset, which were absent in our studied countries. Our study has highlighted the promising validation of using convolutional neural networks instead of recurrent neural networks when forecasting with very few features and less amount of historical data.