Traditional drug discovery methods, such as synthesis operations, validations, and testing in a wet laboratory, are time-consuming and expensive. The use of artificial intelligence (AI) methods in the pharmaceutical industry has been transformed by recent developments in the field. Artificial intelligence methods, when coupled with easily available data resources, are altering the course of medication development. For different phases of drug development, a number of AI-based models have been created in the last few decades. By supplementing traditional trials, these models have hastened the process of drug discovery. Molecular representation techniques are used to transform data into representations that computers can understand. We began by outlining the most popular drug discovery data sites, including ChEMBL and DrugBank. At the same time, we compiled a list of all the algorithms that went into creating AI models for medication development. We then moved on to talk about how artificial intelligence (AI) methods may be used in pharmaceutical research to forecast things like a drug's physicochemical properties, bioactivity, and toxicity. In addition, we presented the AI-powered models for creating new drugs, predicting their structures and interactions with targets, and determining their binding affinities. We went on to mention AI's cutting-edge uses in nanomedicine design and drug synergism/antagonism prediction. Lastly, we covered the benefits, drawbacks, and potential future directions of artificial intelligence in the pharmaceutical industry.