I'm gonna start working on a machine learning project that concerns a bioinformatics issue (proteins, DNA, RNA,......, etc), but I don't know how to get the datasets of these components, and how to use them , so is there anyone can send me datasets and guide me how to exploit them ?
From reading the discussion in the comments above, it seems to me that the teacher wants students to find a bioinformatics question that can be addressed using machine learning and then have a go at tackling it. My suggestion would be to go over the topics discussed in class and get ideas from there. Alternatively look for ideas in textbooks or even the literature.
The process goes like this: first find a question you want to address, second collect relevant data and third identify relevant analysis methods and tools.
As others have already pointed out, just throwing any dataset at you will not help.
I suggest you start browsing the scientific literature first, what types of ML problems are commonly addressed in the biomedical domain. As a starter, think e.g. text-processing of scientific literature or patient dossiers, image classification of pathology slides, image segmentation in microcopy, variant calling in genomic sequencing data etc.
Once you have an idea what type of task your ML approach should solve, then we might be able to help. Also mind that training an ML model from scratch is usually very time and resource demanding. Look e.g. at Huggingface for pretrained models that you can refine with some additional training. On the same site, you will also find a diverse collection of datasets. Kaggle datasets is another source for already well annotated ML training data.