Dataset Information

MAHOMES II: A webserver for predicting if a metal binding site is enzymatic.

ABSTRACT: Recent advances have enabled high-quality computationally generated structures for proteins with no solved crystal structures. However, protein function data remains largely limited to experimental methods and homology mapping. Since structure determines function, it is natural that methods capable of using computationally generated structures for functional annotations need to be advanced. Our laboratory recently developed a method to distinguish between metalloenzyme and non-enzyme sites. Here we report improvements to this method by upgrading our physicochemical features to alleviate the need for structures with sub-angstrom precision and using machine learning to reduce training data labeling error. Our improved classifier identifies protein bound metal sites as enzymatic or non-enzymatic with 94% precision and 92% recall. We demonstrate that both adjustments increased predictive performance and reliability on sites with sub-angstrom variations. We constructed a set of predicted metalloprotein structures with no solved crystal structures and no detectable homology to our training data. Our model had an accuracy of 90 - 97.5% depending on the quality of the predicted structures included in our test. Finally, we found the physicochemical trends that drove this model's successful performance were local protein density, second shell ionizable residue burial, and the pocket's accessibility to the site. We anticipate that our model's ability to correctly identify catalytic metal sites could enable identification of new enzymatic mechanisms and improve de novo metalloenzyme design success rates.

Significance statement

Identification of enzyme active sites on proteins with unsolved crystallographic structures can accelerate discovery of novel biochemical reactions, which can impact healthcare, industrial processes, and environmental remediation. Our lab has developed an ML tool for predicting sites on computationally generated protein structures as enzymatic and non-enzymatic. We have made our tool available on a webserver, allowing the scientific community to rapidly search previously unknown protein function space.

SUBMITTER: Feehan R

PROVIDER: S-EPMC10028950 | biostudies-literature | 2023 Mar

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

MAHOMES II: A webserver for predicting if a metal binding site is enzymatic.

Feehan Ryan R Copeland Matthew M Franklin Meghan W MW Slusky Joanna S G JSG

bioRxiv : the preprint server for biology 20230312

Recent advances have enabled high-quality computationally generated structures for proteins with no solved crystal structures. However, protein function data remains largely limited to experimental methods and homology mapping. Since structure determines function, it is natural that methods capable of using computationally generated structures for functional annotations need to be advanced. Our laboratory recently developed a method to distinguish between metalloenzyme and non-enzyme sites. Here ...[more]

PMID: 36945603

Similar Datasets

Project description:MotivationProtein-protein interactions (PPIs) play an essential role in a great variety of cellular processes and are therefore of significant interest for the design of new therapeutic compounds as well as the identification of side effects due to unexpected binding. Here, we present ProteinPrompt, a webserver that uses machine learning algorithms to calculate specific, currently unknown PPIs. Our tool is designed to quickly and reliably predict contact propensities based on an input sequence in order to scan large sequence libraries for potential binding partners, with the goal to accelerate and assure the quality of the laborious process of drug target identification.ResultsWe collected and thoroughly filtered a comprehensive database of known binders from several sources, which is available as download. ProteinPrompt provides two complementary search methods of similar accuracy for comparison and consensus building. The default method is a random forest (RF) algorithm that uses the auto-correlations of seven amino acid scales. Alternatively, a graph neural network (GNN) implementation can be selected. Additionally, a consensus prediction is available. For each query sequence, potential binding partners are identified from a protein sequence database. The proteom of several organisms are available and can be searched for binders. To evaluate the predictive power of the algorithms, we prepared a test dataset that was rigorously filtered for redundancy. No sequence pairs similar to the ones used for training were included in this dataset. With this challenging dataset, the RF method achieved an accuracy rate of 0.88 and an area under the curve of 0.95. The GNN achieved an accuracy rate of 0.86 using the same dataset. Since the underlying learning approaches are unrelated, comparing the results of RF and GNNs reduces the likelihood of errors. The consensus reached an accuracy of 0.89.Availability and implementationProteinPrompt is available online at: http://proteinformatics.org/ProteinPrompt, where training and test data used to optimize the methods are also available. The server makes it possible to scan the human proteome for potential binding partners of an input sequence within minutes. For local offline usage, we furthermore created a ProteinPrompt Docker image which allows for batch submission: https://gitlab.hzdr.de/proteinprompt/ProteinPrompt. In conclusion, we offer a fast, accurate, easy-to-use online service for predicting binding partners from an input sequence.

Project description:BACKGROUND: Identification of drug-like molecules is one of the major challenges in the field of drug discovery. Existing approach like Lipinski rule of 5 (Ro5), Operea have their own limitations. Thus, there is a need to develop computational method that can predict drug-likeness of a molecule with precision. In addition, there is a need to develop algorithm for screening chemical library for their drug-like properties. RESULTS: In this study, we have used 1347 approved and 3206 experimental drugs for developing a knowledge-based computational model for predicting drug-likeness of a molecule. We have used freely available PaDEL software for computing molecular fingerprints/descriptors of the molecules for developing prediction models. Weka software has been used for feature selection in order to identify the best fingerprints. We have developed various classification models using different types of fingerprints like Estate, PubChem, Extended, FingerPrinter, MACCS keys, GraphsOnlyFP, SubstructureFP, Substructure FPCount, Klekota-RothFP, Klekota-Roth FPCount. It was observed that the models developed using MACCS keys based fingerprints, discriminated approved and experimental drugs with higher precision. Our model based on one hundred fifty nine MACCS keys predicted drug-likeness of the molecules with 89.96% accuracy along with 0.77 MCC. Our analysis indicated that MACCS keys (ISIS keys) 112, 122, 144, and 150 were highly prevalent in the approved drugs. The screening of ZINC (drug-like) and ChEMBL databases showed that around 78.33% and 72.43% of the compounds present in these databases had drug-like potential. CONCLUSION: It was apparent from above study that the binary fingerprints could be used to discriminate approved and experimental drugs with high accuracy. In order to facilitate researchers working in the field of drug discovery, we have developed a webserver for predicting, designing, and screening novel drug-like molecules (http://crdd.osdd.net/oscadd/drugmint/).

Dataset Information

MAHOMES II: A webserver for predicting if a metal binding site is enzymatic.

Significance statement

Publications

MAHOMES II: A webserver for predicting if a metal binding site is enzymatic.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets