Astronomical spectroscopy is a field that has been growing for a number of years, analyzing the features of molecular spectral lines from astronomical data cubes provides insight to the composition of our universe. With the arrival of state-of-the-art radiotelescopes like ALMA, the size of the data cubes will be constantly growing in time. This is why we believe that some automatic analysis methods will be required to ease the astrochemists work. We would like, in some way, to recreate the experiment performed by Madden et.al in 2009 by training a molecular spectrum classification learner, using synthetic spectra, and validate it using radio astronomical data cubes from ALMA Band 7 Science Verification data. A summary of related projects is presented, and also a brief list of the astronomical complexities surrounding the nature of a molecular spectrum. A naive model is considered to start the problem and two Machine Learning methods are tested for the task of classifying molecular spectra, Support Vector Machines and Neural Networks, results for SVM resulted in accuracy of over 90 percent with the basic model. The Neural Network approach, provided even better results.