Reconciling Inconsistent Molecular Structures from Biochemical Databases
Information on the structure of molecules, retrieved via biochemical databases, plays a pivotal role in various disciplines, such as metabolomics, systems biology, and drug discovery. However, no such database can be complete, and the chemical structure for a given compound is not necessarily consistent between databases. This paper presents StructRecon, a novel tool for resolving unique and correct molecular structures from database identifiers. StructRecon traverses the cross-links between database entries in different databases to construct what we call an identifier graph, which offers a more complete view of the total information available on a particular compound across all the databases. In order to reconcile discrepancies between databases, we first present an extensible model for chemical structure which supports multiple independent levels of detail, allowing standardisation of the structure to be applied iteratively. In some cases, our standardisation approach results in multiple structures for a given compound, in which case a random walk-based algorithm is used to select the most likely structure among incompatible alternates. We applied StructRecon to the EColiCore2 model, resolving a unique chemical structure for 85.11 % of identifiers. StructRecon is open-source and modular, which enables the potential support for more databases in the future.
Code (0)
등록된 구현이 없습니다.
Tasks
Drug DiscoverySimilar Papers 제목 키워드 기반
Mol-JEPA: A multimodal Joint Embedding Predictive Architecture for Molecules
Despite recent advances in molecular foundation models, several limitations remain, such as chemically invalid augmentations, modality collapse, and incomplete representation of biochemical environments. To address these…
Drug DiscoveryA Generalist Cross-Domain Molecular Learning Framework for Structure-Based Drug Discovery
Structure-based drug discovery (SBDD) is a systematic scientific process that develops new drugs by leveraging the detailed physical structure of the target protein. Recent advancements in pre-trained models for biomolec…
DenoisingDrug DiscoveryMixture-of-ExpertsMolecular Property Prediction+1Molecular Odor Prediction Based on Multi-Feature Graph Attention Networks
Olfactory perception plays a critical role in both human and organismal interactions, yet understanding of its underlying mechanisms and influencing factors remain insufficient. Molecular structures influence odor percep…
Graph AttentionTwins in rotational spectroscopy: Does a rotational spectrum uniquely identify a molecule?
Rotational spectroscopy is the most accurate method for determining structures of molecules in the gas phase. It is often assumed that a rotational spectrum is a unique "fingerprint" of a molecule. The availability of la…
Property Enhanced Instruction Tuning for Multi-task Molecule Generation with Large Language Models
Large language models (LLMs) are widely applied in various natural language processing tasks such as question answering and machine translation. However, due to the lack of labeled data and the difficulty of manual annot…
Machine TranslationMolecular Property PredictionMolecule CaptioningProperty Prediction+1