Faculty Publications

Permanent URI for this communityhttp://192.168.24.11:4000/handle/123456789/7

Scholarly Publications by Integral Academia

Browse

Has files: YesSubject: search.filters.subject.Machine learning (ML)

Search Results

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    Data-Driven Approach of Species DNA Sequencing Based on Similar Patterns Using Machine Learning
    (Bentham Science, 2025) Manoj Kumar, Anil Kumar Yadav, Vivek Kumar, Bably Dolly
    Bioinformatics is majorly used to infer hidden information from biological datasets using advanced techniques. Genomics uses machine learning and deep learning extensively to understand hidden facts and dependencies in new biological hypotheses. Recent advancements in dataset development have increased hope in understanding biologically inherited diseases, and a lot of computational models have shown promising results in deoxyribonucleic acid (DNA) sequencing to detect similar and dissimilar kinds of species. Two sequences are called homogeneous if similarities exceed, and we can conclude that two sequences are likely to have an evolutionary relationship. It has already been proven that chimpanzees are ancestors of humans, but can we prove it based on DNA similarity? This work is an effort to understand DNA structure and species of similar kinds based on genome sequencing. We have used the human, chimpanzee, and dog datasets to interpret their DNA sequence. The result shows that humans and chimpanzees share closeness in terms of DNA sequence, which confirms that both organisms are related to each other. Naïve Bays algorithm has shown similarity between chimpanzees and humans by scoring 99.30% and 98.40%, which are the closest figures compared to the dog with a score of 92.60%. This work has a lot of future scope to testify different species and their ancestor, which will help us understand life sciences more closely.
  • Thumbnail Image
    Item
    ARTIFICIAL INTELLIGENCE AND MACHINE LEARNING IN DRUG DESIGN
    (M/S Academic Publishers & Distributors/ZENODO, 2025) Aleena, Pushpendra Soni, Ahsan Ahmed Khan, Mohammad Ahmad
    Artificial Intelligence (AI) and Machine Learning (ML) have transformed drug discovery, significantly improving efficiency, accuracy and speed in drug research and development. Compared to the older, time-consuming, and expensive traditional approach, AI-driven methodologies optimize molecular design, predict drug-target interactions and streamline clinical trial processesto the potential saving of both costs and timelines. AI-powered computational tools, such as virtual screening, de novo drug design, and structure-based drug development, have also helped enhance the selection of more accurate drug candidates to be brought to development, improving success in drug development. AI has also affected prediction in Drug-Drug Interactions (DDIs) and adverse drug reactions (ADRs), enhancing safety due to patient improvements from advanced techniques indata analysis like National Language Processing (NLP) and network-based modeling. Optimistic to this notion, clinical trials have become improved through AI: better patient selection, adaptive design and constant monitoring, maximizing efficiency while trimming costs. Currently, challenges encountered encompass data quality model interpretability along with ethical debates, yet research in pharmaceutical fields continues with momentum. Quantum Computing, automated laboratories and more such drugs repurposing by AI make it all work the faster way it is meant. This advancement of AI will continue to shape health care, hasten drug development, and enhance patients’ outcomes and therefore, is essential in modern medicine.