Motivation: Combination therapies have emerged as a treatment strategy for cancers to reduce the probability of drug resistance and to improve outcome. Large databases curating the results of many drug screening studies on preclinical cancer cell lines have been developed, capturing the synergistic and antagonistic effects of combination of drugs in different cell lines. However, due to the high cost of drug screening experiments and the sheer size of possible drug combinations, these databases are quite sparse. This necessitates the development of transductive computational models to accurately impute these missing values. Results: Here, we developed MARSY, a deep learning multi-task model that incorporates information on gene expression profile of cancer cell lines, as well as the differential expression signature induced by each drug to predict drug-pair synergy scores. By utilizing two encoders to capture the interplay between the drug-pairs, as well as the drug-pairs and cell lines, and by adding auxiliary tasks in the predictor, MARSY learns latent embeddings that improve the prediction performance compared to state-of-the-art and traditional machine learning models. Using MARSY, we then predicted the synergy scores of 133,722 new drug-pair cell line combinations, which we have made available to the community as part of this study. Moreover, we validated various insights obtained from these novel predictions using independent studies, confirming the ability of MARSY in making accurate novel predictions. Availability and Implementation: An implementation of the algorithms in Python and cleaned input datasets are provided in https://github.com/Emad-COMBINE-lab/MARSY.

Motivation Understanding an enzyme’s function is one of the most crucial problem domains in computational biology. Enzymes are a key component in all organisms and many industrial processes as they help in fighting diseases and speed up essential chemical reactions. They have wide applications and therefore, the discovery of new enzymatic proteins can accelerate biological research and commercial productivity. Biological experiments, to determine an enzyme’s function, are time-consuming and resource expensive. Results In this study, we propose a novel computational approach to predict an enzyme’s function up to the fourth level of the Enzyme Commission (EC) Number. Many studies have attempted to predict an enzyme’s function. Yet, no approach has properly tackled the fourth and final level of the EC number. The fourth level holds great significance as it gives us the most specific information of how an enzyme performs its function. Our method uses innovative deep learning approaches along with an efficient hierarchical classification scheme to predict an enzyme’s precise function. On a dataset of 11,353 enzymes and 402 classes, we achieved a hierarchical accuracy and Macro-F1 score of 91.2% and 81.9%, respectively, on the 4th level. Moreover, our method can be used to predict the function of enzyme isoforms with considerable success. This methodology is broadly applicable for genome-wide prediction that can subsequently lead to automated annotation of enzyme databases and the identification of better/cheaper enzymes for commercial activities. Availability The web-server can be freely accessed at http://hecnet.cbrlab.org/. Supplementary information Supplementary data are available at Bioinformatics online.

Motivation Combination therapies have emerged as a treatment strategy for cancers to reduce the probability of drug resistance and to improve outcome. Large databases curating the results of many drug screening studies on preclinical cancer cell lines have been developed, capturing the synergistic and antagonistic effects of combination of drugs in different cell lines. However, due to the high cost of drug screening experiments and the sheer size of possible drug combinations, these databases are quite sparse. This necessitates the development of transductive computational models to accurately impute these missing values. Results Here, we developed MARSY, a deep learning multi-task model that incorporates information on gene expression profile of cancer cell lines, as well as the differential expression signature induced by each drug to predict drug-pair synergy scores. By utilizing two encoders to capture the interplay between the drug-pairs, as well as the drug-pairs and cell lines, and by adding auxiliary tasks in the predictor, MARSY learns latent embeddings that improve the prediction performance compared to state-of-the-art and traditional machine learning models. Using MARSY, we then predicted the synergy scores of 133,722 new drug-pair cell line combinations, which we have made available to the community as part of this study. Moreover, we validated various insights obtained from these novel predictions using independent studies, confirming the ability of MARSY in making accurate novel predictions. Availability and implementation An implementation of the algorithms in Python and cleaned input datasets are provided in https://github.com/Emad-COMBINE-lab/MARSY. Supplementary information Online-only supplementary data are available at Bioinformatics online.

Enzymes are critical proteins in every organism. They speed up essential chemical reactions, help fight diseases, and have a wide use in the pharmaceutical and manufacturing industries. Wet lab experiments to figure out an enzyme's function are time consuming and expensive. Therefore, the need for computational approaches to address this problem are becoming necessary. Usually, an enzyme is extremely specific in performing its function. However, there exist enzymes that can perform multiple functions. A multi‐functional enzyme has vast potential as it reduces the need to discover/use different enzymes for different functions. We propose an approach to predict a multi‐functional enzyme's function up to the most specific fourth level of the hierarchy of the Enzyme Commission (EC) number. Previous studies can only predict the function of the enzyme till level 1. Using a dataset of 2,583 multi‐functional enzymes, we achieved a hierarchical subset accuracy of 71.4% and a Macro F1 Score of 96.1% at the fourth level. The robustness of the network was further tested on a multi‐functional isoforms dataset. Our method is broadly applicable and may be used to discover better enzymes. The web‐server can be freely accessed at http://hecnet.cbrlab.org/.

The enzyme Protein Tyrosine Phosphatase 1B (PTP1B) is widely studied due to its role in a number of important cellular signaling pathways, including those related to type 2 diabetes and certain forms of cancer. Although wild type PTP1B has 435 residues, to date, most studies of PTP1B have focused on the catalytic domain, residues 1-301 or 1-321. In this study, we present a method for purifying a construct containing residues 1-393, which includes much of the previously excluded disordered C-terminus. We also perform a kinetic assay to compare the kinetics of the 1-301 catalytic domain and our 1-393 residue construct. We find that the 1-301 and 1-393 constructs display very similar kinetic characteristics under the conditions studied.