This article provides a gentle introduction to machine learning techniques for biologists, focusing on key methodologies and their applications in biological data. It highlights the growing importance of machine learning in biology due to the expanding scale and complexity of biological data. The authors discuss the differences between supervised and unsupervised learning, classification, regression, and clustering problems, and introduce concepts such as loss functions, parameters, hyperparameters, and overfitting/underfitting. They also cover traditional machine learning methods and deep learning techniques, including artificial neural networks, convolutional neural networks (CNNs), recurrent neural networks (RNNs), attention mechanisms, transformers, and graph convolutional networks (GCNs). The article emphasizes the importance of data availability, avoiding data leakage, and model interpretability in biological applications. It concludes by discussing future directions in machine learning for biology, emphasizing the need for rigorous benchmarking and the importance of understanding the underlying mechanisms and factors responsible for model predictions.This article provides a gentle introduction to machine learning techniques for biologists, focusing on key methodologies and their applications in biological data. It highlights the growing importance of machine learning in biology due to the expanding scale and complexity of biological data. The authors discuss the differences between supervised and unsupervised learning, classification, regression, and clustering problems, and introduce concepts such as loss functions, parameters, hyperparameters, and overfitting/underfitting. They also cover traditional machine learning methods and deep learning techniques, including artificial neural networks, convolutional neural networks (CNNs), recurrent neural networks (RNNs), attention mechanisms, transformers, and graph convolutional networks (GCNs). The article emphasizes the importance of data availability, avoiding data leakage, and model interpretability in biological applications. It concludes by discussing future directions in machine learning for biology, emphasizing the need for rigorous benchmarking and the importance of understanding the underlying mechanisms and factors responsible for model predictions.