Evaluation of Deep Learning Architectures for Aqueous Solubility Prediction
Ontology highlight
ABSTRACT:
SUBMITTER: Panapitiya G
PROVIDER: S-EPMC9096921 | biostudies-literature | 2022 Apr
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:Shallow machine learning methods have been applied to chemoinformatics problems with some success. As more data becomes available and more complex problems are tackled, deep machine learning methods may also become useful. Here, we present a brief overview of deep learning methods and show in particular how recursive neural network approaches can be applied to the problem of predicting molecular properties. However, molecules are typically described by undirected cyclic graphs, while recursive approaches typically use directed acyclic graphs. Thus, we develop methods to address this discrepancy, essentially by considering an ensemble of recursive neural networks associated with all possible vertex-centered acyclic orientations of the molecular graph. One advantage of this approach is that it relies only minimally on the identification of suitable molecular descriptors because suitable representations are learned automatically from the data. Several variants of this approach are applied to the problem of predicting aqueous solubility and tested on four benchmark data sets. Experimental results show that the performance of the deep learning methods matches or exceeds the performance of other state-of-the-art methods according to several evaluation metrics and expose the fundamental limitations arising from training sets that are too small or too noisy. A Web-based predictor, AquaSol, is available online through the ChemDB portal ( cdb.ics.uci.edu ) together with additional material.
| S-EPMC3739985 | biostudies-literature
Project description:Aqueous solubility is an important physicochemical property of compounds in anti-cancer drug discovery. Artificial intelligence solubility prediction tools have scored impressive performances by employing regression, machine learning, and deep learning methods. The reported performances vary significantly partly because of the different datasets used. Solubility prediction on novel compounds needs to be improved, which may be achieved by going deeper with deep learning. We constructed deeper-net models of ~20-layer modified ResNet convolutional neural network architecture, which were trained and tested with 9,943 compounds encoded by molecular fingerprints. Retrospectively tested by 62 recently-published novel compounds, one deeper-net model outperformed four established tools, shallow-net models, and four human experts. Deeper-net models also outperformed others in predicting the solubility values of a series of novel compounds newly-synthesized for anti-cancer drug discovery. Solubility prediction may be improved by going deeper with deep learning. Our deeper-net models are accessible at http://www.npbdb.net/solubility/index.jsp.
| S-EPMC7026387 | biostudies-literature
Project description:MotivationDeep learning architectures have recently demonstrated their power in predicting DNA- and RNA-binding specificity. Existing methods fall into three classes: Some are based on convolutional neural networks (CNNs), others use recurrent neural networks (RNNs) and others rely on hybrid architectures combining CNNs and RNNs. However, based on existing studies the relative merit of the various architectures remains unclear.ResultsIn this study we present a systematic exploration of deep learning architectures for predicting DNA- and RNA-binding specificity. For this purpose, we present deepRAM, an end-to-end deep learning tool that provides an implementation of a wide selection of architectures; its fully automatic model selection procedure allows us to perform a fair and unbiased comparison of deep learning architectures. We find that deeper more complex architectures provide a clear advantage with sufficient training data, and that hybrid CNN/RNN architectures outperform other methods in terms of accuracy. Our work provides guidelines that can assist the practitioner in choosing an appropriate network architecture, and provides insight on the difference between the models learned by convolutional and recurrent networks. In particular, we find that although recurrent networks improve model accuracy, this comes at the expense of a loss in the interpretability of the features learned by the model.Availability and implementationThe source code for deepRAM is available at https://github.com/MedChaabane/deepRAM.Supplementary informationSupplementary data are available at Bioinformatics online.
| S-EPMC6612801 | biostudies-literature
Project description:While accurate prediction of aqueous solubility remains a challenge in drug discovery, machine learning (ML) approaches have become increasingly popular for this task. For instance, in the Second Challenge to Predict Aqueous Solubility (SC2), all groups utilized machine learning methods in their submissions. We present SolTranNet, a molecule attention transformer to predict aqueous solubility from a molecule's SMILES representation. Atypically, we demonstrate that larger models perform worse at this task, with SolTranNet's final architecture having 3,393 parameters while outperforming linear ML approaches. SolTranNet has a 3-fold scaffold split cross-validation root-mean-square error (RMSE) of 1.459 on AqSolDB and an RMSE of 1.711 on a withheld test set. We also demonstrate that, when used as a classifier to filter out insoluble compounds, SolTranNet achieves a sensitivity of 94.8% on the SC2 data set and is competitive with the other methods submitted to the competition. SolTranNet is distributed via pip, and its source code is available at https://github.com/gnina/SolTranNet.
| S-EPMC8900744 | biostudies-literature
Project description:MotivationProtein solubility plays a vital role in pharmaceutical research and production yield. For a given protein, the extent of its solubility can represent the quality of its function, and is ultimately defined by its sequence. Thus, it is imperative to develop novel, highly accurate in silico sequence-based protein solubility predictors. In this work we propose, DeepSol, a novel Deep Learning-based protein solubility predictor. The backbone of our framework is a convolutional neural network that exploits k-mer structure and additional sequence and structural features extracted from the protein sequence.ResultsDeepSol outperformed all known sequence-based state-of-the-art solubility prediction methods and attained an accuracy of 0.77 and Matthew's correlation coefficient of 0.55. The superior prediction accuracy of DeepSol allows to screen for sequences with enhanced production capacity and can more reliably predict solubility of novel proteins.Availability and implementationDeepSol's best performing models and results are publicly deposited at https://doi.org/10.5281/zenodo.1162886 (Khurana and Mall, 2018).Supplementary informationSupplementary data are available at Bioinformatics online.
| S-EPMC6355112 | biostudies-literature
Project description:MotivationInterpretable deep learning (DL) models that can provide biological insights, in addition to accurate predictions, are of great interest to the biomedical community. Recently, interpretable DL models that incorporate signaling pathways have been proposed for drug response prediction (DRP). While these models improve interpretability, it is unclear whether this comes at the cost of less accurate DRPs, or a prediction improvement can also be obtained.ResultsWe comprehensively and systematically assessed four state-of-the-art interpretable DL models using three pathway collections to assess their ability in making accurate predictions on unseen samples from the same dataset, as well as their generalizability to an independent dataset. Our results showed that models that explicitly incorporate pathway information in the form of a latent layer perform worse compared to models that incorporate this information implicitly. However, in most evaluation setups, the best performance was achieved using a black-box multilayer perceptron, and the performance of a random forests baseline was comparable to those of the interpretable models. Replacing the signaling pathways with randomly generated pathways showed a comparable performance for the majority of the models. Finally, the performance of all models deteriorated when applied to an independent dataset. These results highlight the importance of systematic evaluation of newly proposed models using carefully selected baselines. We provide different evaluation setups and baseline models that can be used to achieve this goal.Availability and implementationImplemented models and datasets are provided at https://doi.org/10.5281/zenodo.7787178 and https://doi.org/10.5281/zenodo.7101665, respectively.
| S-EPMC10301685 | biostudies-literature
Project description:Solubility is a key metric for therapeutic compounds. Conversely, insoluble compounds cloud the accuracy of assays at all stages of chemical biology and drug discovery. Herein, we disclose naïve Bayesian classifier models to predict aqueous solubility. Publicly accessible aqueous solubility data were used to create two full, or nonpruned, training sets. These two sets were also combined to create a full fused set, and a training set comprised of a literature collation of solubility data was also considered as a reference. We tested different extents of data pruning on the training sets and constructed machine learning models that were evaluated with two independent, external test sets that contained compounds that were different from the training sets. The best pruned and fused model was significantly more accurate, in comparison to either the full model or the full fused model, with the prediction of these external test sets. By carefully removing data from the training set, less information can be used to create more accurate machine learning models for aqueous solubility. This knowledge and the curated training sets should prove useful to future machine learning approaches.
| S-EPMC7364544 | biostudies-literature
Project description:MotivationResidue-residue contact prediction is important for protein structure prediction and other applications. However, the accuracy of current contact predictors often barely exceeds 20% on long-range contacts, falling short of the level required for ab initio structure prediction.ResultsHere, we develop a novel machine learning approach for contact map prediction using three steps of increasing resolution. First, we use 2D recursive neural networks to predict coarse contacts and orientations between secondary structure elements. Second, we use an energy-based method to align secondary structure elements and predict contact probabilities between residues in contacting alpha-helices or strands. Third, we use a deep neural network architecture to organize and progressively refine the prediction of contacts, integrating information over both space and time. We train the architecture on a large set of non-redundant proteins and test it on a large set of non-homologous domains, as well as on the set of protein domains used for contact prediction in the two most recent CASP8 and CASP9 experiments. For long-range contacts, the accuracy of the new CMAPpro predictor is close to 30%, a significant increase over existing approaches.AvailabilityCMAPpro is available as part of the SCRATCH suite at http://scratch.proteomics.ics.uci.edu/.Contactpfbaldi@uci.eduSupplementary informationSupplementary data are available at Bioinformatics online.
| S-EPMC3463120 | biostudies-literature
Project description:A reliable and practical determination of a chemical species' solubility in water continues to be examined using empirical observations and exhaustive experimental studies alone. Predictions of chemical solubility in water using data-driven algorithms can allow us to create a rationally designed, efficient, and cost-effective tool for next-generation materials and chemical formulations. We present results from two machine learning (ML) modeling studies to adequately predict various species' solubility using data for over 8400 compounds. Molecular-descriptors, the most used method in previous studies, and Morgan fingerprint, a circular-based hash of the molecules' structures, were applied to produce water solubility estimates. We trained all models on 80% of the total datasets using the Random Forest (RFs) technique as the regressor and tested the prediction performance using the remaining 20%, resulting in coefficient of determination (R2) test values of 0.88 and 0.81 and root-mean-square deviation (RMSE) test values 0.64 and 0.80 for the descriptors and circular fingerprint methods, respectively. We interpreted the produced ML models and reported the most effective features for aqueous solubility measures using the Shapley Additive exPlanations (SHAP) and thermodynamic analysis. Low error, ability to investigate the molecular-level interactions, and compatibility with thermodynamic quantities made the fingerprint method a distinct model compared to other available computational tools. However, it is worth emphasizing that physicochemical descriptor model outperformed the fingerprint model in achieving better predictive accuracy for the given test set.
| S-EPMC10583449 | biostudies-literature
Project description:Background: Prognostic risk factors for completely resected stage IA non-small-cell lung cancers (NSCLCs) have advanced minimally over recent decades. Although several biomarkers have been found to be associated with cancer recurrence, their added value to TNM staging and tumor grade are unclear. Methods: Features of preoperative low-dose CT image and histologic findings of hematoxylin- and eosin-stained tissue sections of resected lung tumor specimens were extracted from 182 stage IA NSCLC patients in the National Lung Screening Trial. These features were combined to predict the risk of tumor recurrence or progression through integrated deep learning evaluation (IDLE). Added values of IDLE to TNM staging and tumor grade in progression risk prediction and risk stratification were evaluated. Results: The 5-year AUC of IDLE was 0.817 ± 0.037 as compared to the AUC = 0.561 ± 0.042 and 0.573 ± 0.044 from the TNM stage and tumor grade, respectively. The IDLE score was significantly associated with cancer recurrence (p < 0.0001) even after adjusting for TNM staging and tumor grade. Synergy between chest CT image markers and histological markers was the driving force of the deep learning algorithm to produce a stronger prognostic predictor. Conclusions: Integrating markers from preoperative CT images and pathologist’s readings of resected lung specimens through deep learning can improve risk stratification of stage 1A NSCLC patients over TNM staging and tumor grade alone. Our study suggests that combining markers from nonoverlapping platforms can increase the cancer risk prediction accuracy.
| S-EPMC9454871 | biostudies-literature