New target prediction and visualization tools incorporating open source molecular fingerprints for TB Mobile 2.0

Abstract

Background: We recently developed a freely available mobile app (TB Mobile) for both iOS and Android platforms that displays Mycobacterium tuberculosis (Mtb) active molecule structures and their targets with links to associated data. The app was developed to make target information available to as large an audience as possible.

Results: We now report a major update of the iOS version of the app. This includes enhancements that use an implementation of ECFP_6 fingerprints that we have made open source. Using these fingerprints, the user can propose compounds with possible anti-TB activity, and view the compounds within a cluster landscape. Proposed compounds can also be compared to existing target data, using a näive Bayesian scoring system to rank probable targets. We have curated an additional 60 new compounds and their targets for Mtb and added these to the original set of 745 compounds. We have also curated 20 further compounds (many without targets in TB Mobile) to evaluate this version of the app with 805 compounds and associated targets.

Conclusions: TB Mobile can now manage a small collection of compounds that can be imported from external sources, or exported by various means such as email or app-to-app inter-process communication. This means that TB Mobile can be used as a node within a growing ecosystem of mobile apps for cheminformatics. It can also cluster compounds and use internal algorithms to help identify potential targets based on molecular similarity. TB Mobile represents a valuable dataset, data-visualization aid and target prediction tool.

Keywords: Mobile app; Mycobacterium tuberculosis; TB mobile; Target prediction; Tuberculosis.

Figure 1

Predictions for the InhA target: (a) the ROC curve with ECFP_6 and FCFP_6 fingerprints; (b) modified Bayesian estimators for active and inactive compounds; (c) structures of selected binders.

Figure 2

Importing compounds from the web: (a) setting up an SDfile download with CDD Vault; (b) selecting the TB Mobile app as the destination; (c) molecule import on launch; (d) the personal stash, with imported structures.

Figure 3

Sending selected compounds by email: (a) initiating the transmission for structures shown onscreen; (b) writing the email, with prepackaged attachments.

Figure 4

Exporting the personal collection: (a) initiating the export, the molecules in the compound collection havebar icons representing predicted targets using the Bayesian models with extended connectivity fingerprints. The top icons (from left to right) represent adding molecules – which can be drawn in the app, drawn with other apps on the device, pasted in from elsewhere or there is the option to remove all structures. The second icon allows the contents of the molecule stash to be opened in other apps on the device. The third icon allows you to email the contents of the molecule stash and the fourth icon generated target predictions.The arrow icon aligned with each molecule allows the molecule to be either copied to the clipboard, transferred to the main window on the app or the structure can be edited or deleted; (b) importing the datasheet into MMDS, with predictions included.

Figure 5

Exporting presentation graphics for a cluster. An example of clustering with the known targets of molecules highlighted in different colors. This is enabled by selecting the icon on the top left and choosing the desired targets. Molecules from the collection are shown with a white circle, molecules from the app have a grey background and compounds of interest for clustering have a blue background. The cluster image can be expanded or contracted with a pinching motion on the screen. and molecules can be moved which causes the network clusters to reconfigure. The cluster image can be output and printed as a PDF. (a) the interactive display; (b) previewing the PDF file, prior to sending by email or printing.

Figure 6

Principal component analysis. a. Using the 745 compounds in TB Mobile version 1 and the 60 additional compounds added in TB Mobile 2. 3 Principal Components represent 88.4% of the variance. b. Using the 805 compounds in TB Mobile version 2 and the 20 additional compounds used to evaluate it. 3 Principal Components represent 88.4% of the variance.