Genome scale enzyme–metabolite and drug–target interaction predictions using the signature molecular descriptor

Abstract

Motivation: Identifying protein enzymatic or pharmacological activities are important areas of research in biology and chemistry. Biological and chemical databases are increasingly being populated with linkages between protein sequences and chemical structures.There is now sufficient information to apply machine-learning techniques to predict interactions between chemicals and proteins at a genome scale. Current machine-learning techniques use as input either protein sequences and structures or chemical information. We propose here a method to infer protein-chemical interactions using heterogeneous input consisting of both protein sequence and chemical information. Results: Our method relies on expressing proteins and chemicals with a common cheminformatics representation. We demonstrate our approach by predicting whether proteins can catalyze reactions not present in training sets. We also predict whether a given drug can bind a target, in the absence of prior binding information for that drug and target. Such predictions cannot be made with current machine-learning techniques requiring binding information for individual reactions or individual targets. Availability and Contact: For questions, paper reprints, please contact Jean-Loup Faulon at jfaulon@sandia.gov. Additional information on the signature molecular descriptor and codes can be downloaded at:

Large margin transductive transfer learning

“…One family we discard since it has too few proteins and interactions. For the proteins we extracted features using the signature molecular descriptors [13], for the chemicals we used a frequent subgraph feature representation approach [20,34], and we used a threshold on the feature frequencies to obtain about 100 features each. We then built the feature vector for a given protein-chemical pair by taking the tensor product between the protein and chemical feature vectors.…”

Expanding Biosensing Abilities through Computer-Aided Design of Metabolic Pathways

“…Molecular signatures 41 (MS) are graph-based descriptors that encodes the "neighborhood" of each atom of a molecule, similarly to Morgan's or ECFP fingerprints. Each kind of "neighborhood", or atom environment, is a feature of MS. A reaction's signature (RS) is computed by subtracting the MS of the substrates to the MS of the products of the reaction, 24 and takes the general form…”

Signature molecular descriptor : advanced applications.

“…The assay depositor reported a compound as active if IC 50 < 50 µM was obtained in all three IC 50 determinations, inconclusive if IC 50 < 50 µM in only one or two determinations, and inactive for IC 50 > 50 µM. 51 In this work, we reduced the active classification to 5 µM resulting in 47 active and 68 inactive compounds.…”

“…In our work the input vectors used in the SVM are atomic Signatures. Note that Signature has previously been used with a SVM to predict both protein-protein 49 and drug-target 50 interactions. Note that the number of descriptors (referred to as features when used in statistical learning methods) compared to the number of observations is an important consideration to avoid overfitting.…”