Machine Learning Predicts Degree of Aromaticity from Structural Fingerprints

Ponting, David J.; Deursen, Ruud van; Ott, Martin A.

doi:10.1021/acs.jcim.0c00483

Cited by 5 publications

(4 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These observations, also found for the remaining correlation plots (Supplementary Figs. [32][33][34][35][36][37], suggest that the here proposed group electron delocalization is a much more robust and trustworthy metric Fig. 5 | 13P-CO 2 complexation and guest release.…”

Section: Chemical Insights From Schnet4aim Predictionsmentioning

confidence: 70%

“…In fact, the large efficiency of state-of-the-art AI brings the possibility of accurately performing complex tasks in feasible time scales. The success of this field is directly evidenced by the outburst of AI tools in the modeling of virtually any physico-chemical property [22][23][24][25] ranging from molecular structure [26][27][28] , energy landscapes 29,30 , spectroscopic transitions 31 , aromaticity and reactivity trends 32 , magnetism 33 , mechanical features 34 , or even chemical fragrances 35 , to name just a few examples. As such, the implementation of AI marks a crucial step forward in many realms, such as the fields of drug discovery 36 and materials design 37 , showcasing its ability to lead modern scientific and technological research.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Explainable chemical artificial intelligence from accurate machine learning of real-space chemical descriptors

Gallegos,

Vassilev-Galindo,

Poltavsky

et al. 2024

Nat Commun

View full text Add to dashboard Cite

Machine-learned computational chemistry has led to a paradoxical situation in which molecular properties can be accurately predicted, but they are difficult to interpret. Explainable AI (XAI) tools can be used to analyze complex models, but they are highly dependent on the AI technique and the origin of the reference data. Alternatively, interpretable real-space tools can be employed directly, but they are often expensive to compute. To address this dilemma between explainability and accuracy, we developed SchNet4AIM, a SchNet-based architecture capable of dealing with local one-body (atomic) and two-body (interatomic) descriptors. The performance of SchNet4AIM is tested by predicting a wide collection of real-space quantities ranging from atomic charges and delocalization indices to pairwise interaction energies. The accuracy and speed of SchNet4AIM breaks the bottleneck that has prevented the use of real-space chemical descriptors in complex systems. We show that the group delocalization indices, arising from our physically rigorous atomistic predictions, provide reliable indicators of supramolecular binding events, thus contributing to the development of Explainable Chemical Artificial Intelligence (XCAI) models.

show abstract

Section: Chemical Insights From Schnet4aim Predictionsmentioning

confidence: 70%

mentioning

confidence: 99%

Explainable chemical artificial intelligence from accurate machine learning of real-space chemical descriptors

Gallegos,

Vassilev-Galindo,

Poltavsky

et al. 2024

Nat Commun

View full text Add to dashboard Cite

show abstract

“…ECFPs are a variant of the Morgan algorithm that solves the molecular isomorphism problem, where two molecules numbered differently should produce the same fingerprint vector. ECFPs are very useful for the representation of topological structural information and have been used in a diverse set of applications, such as virtual screening [ 42 ], activity modeling [ 43 ], and machine learning [ 44 , 45 , 46 ]. Since the maximum number of molecules participating in a single reaction is 8, it results in an 8 × 512 matrix composed for every reaction.…”

Section: Methodsmentioning

confidence: 99%

Prediction of Chromatography Conditions for Purification in Organic Synthesis Using Deep Learning

2021

View full text Add to dashboard Cite

In this research, a process for developing normal-phase liquid chromatography solvent systems has been proposed. In contrast to the development of conditions via thin-layer chromatography (TLC), this process is based on the architecture of two hierarchically connected neural network-based components. Using a large database of reaction procedures allows those two components to perform an essential role in the machine-learning-based prediction of chromatographic purification conditions, i.e., solvents and the ratio between solvents. In our paper, we build two datasets and test various molecular vectorization approaches, such as extended-connectivity fingerprints, learned embedding, and auto-encoders along with different types of deep neural networks to demonstrate a novel method for modeling chromatographic solvent systems employing two neural networks in sequence. Afterward, we present our findings and provide insights on the most effective methods for solving prediction tasks. Our approach results in a system of two neural networks with long short-term memory (LSTM)-based auto-encoders, where the first predicts solvent labels (by reaching the classification accuracy of 0.950 ± 0.001) and in the case of two solvents, the second one predicts the ratio between two solvents (R2 metric equal to 0.982 ± 0.001). Our approach can be used as a guidance instrument in laboratories to accelerate scouting for suitable chromatography conditions.

show abstract

“…The SMILES representation is essentially a text-based representation of the chemical structure of a given compound [37]. For each terminal modification, we used its SMILES representation to extract its Extended-Connectivity Fingerprint (ECFP), also known as Morgan Fingerprint, through RDKit [38]. This fingerprint representation is a topological representation of a chemical compound and captures its structural composition.…”

Section: Extended Connectivity Fingerprint (Ecfp4) Of N and C Modific...mentioning

confidence: 99%

HemoNet: Predicting hemolytic activity of peptides with integrated feature learning

Yaseen

Gull

Akhtar

et al. 2021

J. Bioinform. Comput. Biol.

View full text Add to dashboard Cite

Quantifying the hemolytic activity of peptides is a crucial step in the discovery of novel therapeutic peptides. Computational methods are attractive in this domain due to their ability to guide wet-lab experimental discovery or screening of peptides based on their hemolytic activity. However, existing methods are unable to accurately model various important aspects of this predictive problem such as the role of N/C-terminal modifications, D- and L- amino acids, etc. In this work, we have developed a novel neural network-based approach called HemoNet for predicting the hemolytic activity of peptides. The proposed method captures the contextual importance of different amino acids in a given peptide sequence using a specialized feature embedding in conjunction with SMILES-based fingerprint representation of N/C-terminal modifications. We have analyzed the predictive performance of the proposed method using stratified cross-validation in comparison with previous methods, non-redundant cross-validation as well as validation on external peptides and clinical antimicrobial peptides. Our analysis shows the proposed approach achieves significantly better predictive performance (AUC-ROC of 88%) in comparison to previous approaches (HemoPI and HemoPred with AUC-ROC of 73%). HemoNet can be a useful tool in the search for novel therapeutic peptides. The python implementation of the proposed method is available at the URL: https://github.com/adibayaseen/HemoNet.

show abstract

Machine Learning Predicts Degree of Aromaticity from Structural Fingerprints

Cited by 5 publications

References 40 publications

Explainable chemical artificial intelligence from accurate machine learning of real-space chemical descriptors

Explainable chemical artificial intelligence from accurate machine learning of real-space chemical descriptors

Prediction of Chromatography Conditions for Purification in Organic Synthesis Using Deep Learning

HemoNet: Predicting hemolytic activity of peptides with integrated feature learning

Contact Info

Product

Resources

About