Classifying Large Chemical Data Sets: Using A Regularized Potential Function Method

Mussa, Hamse Y.; Hawizy, Lezan; Nigsch, Florian; Glen, Robert C.

doi:10.1021/ci100022u

Cited by 14 publications

(17 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Starting from innovative ways to encode and compare chemical environments in molecules,7,8,10 several steps have been taken to link chemical with biological properties of molecules20 based on statistical modelling techniques 21,22. Thereby, the fields of cheminformatics and bioinformatics increasingly overlap and even fuse, leading to approaches like proteochemometric modelling (PCM) 23,24.…”

Section: Discussionmentioning

confidence: 99%

Effects of Fenton Pre‐Treatment on Waste Activated Sludge Properties

Erden

Filibeli

2011

CLEAN Soil Air Water

View full text Add to dashboard Cite

Research Article Effects of Fenton Pre-Treatment on Waste Activated Sludge PropertiesFenton process was investigated for the purpose of biological sludge disintegration. The Box-Wilson experimental design was employed to evaluate the effects of major process variables (Fe(II) and H 2 O 2 concentrations) on both disintegration and dewatering performance of sludge. Results showed that 4 g Fe(II)/kg total solids (TSs) and 60 g H 2 O 2 /kg TS are efficient for floc disintegration. Fenton pre-treatment enhanced the biodegradability of sludge. For 4 g Fe(II)/kg TS and 60 g H 2 O 2 /kg TS, 19.4% higher methane production was achieved compared to raw sludge in biochemical methane potential assay. Fenton pre-treatment resulted in the release of organic sludge components into the liquid phase. For 4 g Fe(II)/kg TS and 60 g H 2 O 2 /kg TS, dissolved organic carbon and total nitrogen in sludge's supernatant increased by 75.74 and 60.60%, respectively. Fenton pre-treatment enhanced the filterability of sludge and it can be applied for conditioning purpose before mechanical dewatering units.

show abstract

Section: Discussionmentioning

confidence: 99%

Effects of Fenton Pre‐Treatment on Waste Activated Sludge Properties

Erden

Filibeli

2011

CLEAN Soil Air Water

View full text Add to dashboard Cite

show abstract

“…We shall discuss some of their key strengths and weaknesses and, in particular, we consider the relative merits of linear and non-linear modeling approaches. The following discussion of QSAR is by no means exhaustive, so readers are referred elsewhere for greater detail on this topic [23,90,122,[143][144][145][146][147][148][149][150][151][152].…”

Section: Qsar Modeling Methodsmentioning

confidence: 99%

The Challenges Involved in Modeling Toxicity Data In Silico: A Review

Gleeson¹,

Modi²,

Bender³

et al. 2012

CPD

View full text Add to dashboard Cite

The percentage of failures in late pharmaceutical development due to toxicity has increased dramatically over the last decade or so, resulting in increased demand for new methods to rapidly and reliably predict the toxicity of compounds. In this review we discuss the challenges involved in both the building of in silico models on toxicology endpoints and their practical use in decision making. In particular, we will reflect upon the predictive strength of a number of different in silico models for a range of different endpoints, different approaches used to generate the models or rules, and limitations of the methods and the data used in model generation. Given that there exists no unique definition of a 'good' model, we will furthermore highlight the need to balance model complexity/interpretability with predictability, particularly in light of OECD/REACH guidelines. Special emphasis is put on the data and methods used to generate the in silico toxicology models, and their strengths and weaknesses are discussed. Switching to the applied side, we next review a number of toxicity endpoints, discussing the methods available to predict them and their general level of predictability (which very much depends on the endpoint considered). We conclude that, while in silico toxicology is a valuable tool to drug discovery scientists, much still needs to be done to, firstly, understand more completely the biological mechanisms for toxicity and, secondly, to generate more rapid in vitro models to screen compounds. With this biological understanding, and additional data available, our ability to generate more predictive in silico models should significantly improve in the future.

show abstract

“…As discussed in the Previous work section (see below), to our best knowledge – at the time of writing – the target-fishing approaches employed in cheminformatics (with a few exceptions) rely on the assumption that a given ligand can only interact with one target protein, i.e., | Y | = 1 [ 10 – 13 , 15 , 17 , 22 , 23 ]. In other words, these ligand-based target predicting methods, probabilistic or not, can be considered as single-label multi-class classification models [ 10 , 11 , 13 , 15 , 17 , 22 , 23 ]. In these methods a single-label multi-class classification model can be | L | induced binary (one–vs–all) classifiers [ 10 , 12 , 15 ], or just a single conventional multi-class classifier [ 11 , 13 , 17 , 22 , 23 ].…”

Section: Introductionmentioning

confidence: 99%

A multi-label approach to target prediction taking ligand promiscuity into account

et al. 2015

View full text Add to dashboard Cite

BackgroundAccording to Cobanoglu et al., it is now widely acknowledged that the single target paradigm (one protein/target, one disease, one drug) that has been the dominant premise in drug development in the recent past is untenable. More often than not, a drug-like compound (ligand) can be promiscuous – it can interact with more than one target protein.In recent years, in in silico target prediction methods the promiscuity issue has generally been approached computationally in three main ways: ligand-based methods; target-protein-based methods; and integrative schemes. In this study we confine attention to ligand-based target prediction machine learning approaches, commonly referred to as target-fishing.The target-fishing approaches that are currently ubiquitous in cheminformatics literature can be essentially viewed as single-label multi-classification schemes; these approaches inherently bank on the single target paradigm assumption that a ligand can zero in on one single target. In order to address the ligand promiscuity issue, one might be able to cast target-fishing as a multi-label multi-class classification problem. For illustrative and comparison purposes, single-label and multi-label Naïve Bayes classification models (denoted here by SMM and MMM, respectively) for target-fishing were implemented. The models were constructed and tested on 65,587 compounds/ligands and 308 targets retrieved from the ChEMBL17 database.ResultsOn classifying 3,332 test multi-label (promiscuous) compounds, SMM and MMM performed differently. At the 0.05 significance level, a Wilcoxon signed rank test performed on the paired target predictions yielded by SMM and MMM for the test ligands gave a p-value < 5.1 × 10−94 and test statistics value of 6.8 × 105, in favour of MMM. The two models performed differently when tested on four datasets comprising single-label (non-promiscuous) compounds; McNemar’s test yielded χ2 values of 15.657, 16.500 and 16.405 (with corresponding p-values of 7.594 × 10−05, 4.865 × 10−05 and 5.115 × 10−05), respectively, for three test sets, in favour of MMM. The models performed similarly on the fourth set.ConclusionsThe target prediction results obtained in this study indicate that multi-label multi-class approaches are more apt than the ubiquitous single-label multi-class schemes when it comes to the application of ligand-based classifiers to target-fishing.Electronic supplementary materialThe online version of this article (doi:10.1186/s13321-015-0071-9) contains supplementary material, which is available to authorized users.

show abstract

Classifying Large Chemical Data Sets: Using A Regularized Potential Function Method

Cited by 14 publications

References 31 publications

Effects of Fenton Pre‐Treatment on Waste Activated Sludge Properties

Effects of Fenton Pre‐Treatment on Waste Activated Sludge Properties

The Challenges Involved in Modeling Toxicity Data In Silico: A Review

A multi-label approach to target prediction taking ligand promiscuity into account

Contact Info

Product

Resources

About