To bridge the gap between protein sequences and attributes, in a timely manner, prompts the challenge to develop computational methods for prediction various attributes of proteins based on their sequence information alone. To fill this gap, we have developed four new methods implementing deep learning solving protein attribute prediction problems; (1) extracting a comprehensive feature set from protein sequences, (2) the prediction of beta-lactamase enzymes; (3) predictions of S-glutathionylation sites from protein sequences; and (4) prediction of phosphorylation sites in the Chlamydominas reinhardtii (C. reinhardtii) organism. The beta-Lactamase (BL) enzyme family is an important class of enzymes that plays a key role in bacterial resistance to antibiotics. As the newly identified number of BL enzymes is increasing daily, it is imperative to develop a computational tool to classify the newly identified BL enzymes into one of its classes. There are two types of classification of BL enzymes: Molecular Classification and Functional Classification. Existing computational methods only address Molecular Classification and the performance of these existing methods is unsatisfactory. S-glutathionylation is a post-translational modification process that occurs during periods of oxidative stress. This process prevents further oxidation of a modified cysteine residue. More recently, S-glutathionylation has emerged as an important PTM in a wide range of physiological and pathological processes. In this work, we have used a deep learning method known as Convolution Neural Network to predict of S-glutathionylation sites in proteins using only the primary amino acid sequence as input. This type of prediction can offer insights into putative sites of glutathionylation in protein sequences. C.reinhardtii is the most intensively-studied and well-developed model for investigation of a wide-range of micro algal processes. These efforts have identified that phosphorylation based regulation of proteins in the C.reinhardtii is essential for its underlying biology. However, characterization of this organism's phosphoproteome has been limited. Here, we have to build a predictor that is capable of identifying phosphorylation sites in the C.reinhardtii using only the primary amino acid sequence.