Shaik Abdul

I’m a Machine Learning Engineer evaluating a low-code/no-code IDE for ML workflows, focusing on seamless integrations and reliable model development for end users. I design, train, and optimize ML models inside the platform to validate features and improve system performance, and I collaborate closely with developers to strengthen ML components for faster experimentation.

I completed my B.Tech in Computer Science Engineering (Specialization in AI) from Amrita Vishwa Vidhyapeetham, building a strong foundation across Python, databases, and modern ML frameworks. I work with tools like VS code, IntelliJ, and Eclipse, and I’ve used libraries and stacks including NumPy, Pandas, Matplotlib, SciPy, scikit-learn, Seaborn, Keras, TensorFlow, and PyTorch.

In my projects, I directed an Antimicrobial Peptides Prediction effort on 2150 peptide sequences from the DADP dataset, identifying 1923 unique bioactive sequences and improving predictive accuracy by 25%. For Breast Cancer Detection, I trained a deep learning model on a 10GB dataset and reached 95% accuracy using data augmentation and cross-validation, improving accuracy by 20%.

My research outputs include evaluating abstractive summarization models (GPT-2, BART, T5-Small, and Pegasus) and publishing hybrid approaches for miRNA-disease prediction and biomarker-disease relationship analysis, including a BioLinker graph-based model achieving 99% AUC. I’m driven by measurable results—accuracy, precision/recall/F1-score, and interpretability—while staying focused on building practical, dependable AI solutions.