Machine Learning is the study of methods for programming computers to learn. Computers are applied to a wide range of tasks, and for most of these it is relatively easy for programmers to design and implement the necessary software. However, there are many tasks for which this is difficult or impossible. These can be divided into four general categories. First, there are problems for which there exist no human experts. For example, in modern automated manufacturing facilities, there is a need to predict machine failures before they occur by analyzing sensor readings. Because the machines are new, there are no human experts who can be interviewed by a programmer to provide the knowledge necessary to build a computer system. A machine learning system can study recorded data and subsequent machine failures and learn prediction rules. Second, there are problems where human experts exist, but where they are unable to explain their expertise. This is the case in many perceptual tasks, such as speech recognition, hand-writing recognition, and natural language understanding. Virtually all humans exhibit expert-level abilities on these tasks, but none of them can describe the detailed steps that they follow as they perform them. Fortunately, humans can provide machines with examples of the inputs and correct outputs for these tasks, so machine learning algorithms can learn to map the inputs to the outputs. Third, there are problems where phenomena are changing rapidly. In finance, for example, people would like to predict the future behavior of the stock market, of consumer purchases, or of exchange rates. These behaviors change frequently, so that even if a programmer could construct a good predictive computer program, it would need to be rewritten frequently. A learning program can relieve the programmer of this burden by constantly modifying and tuning a set of learned prediction rules. Fourth, there are applications that need to be customized for each computer user separately. Consider, for example, a program to filter unwanted electronic mail messages. Different users will need different filters. It is unreasonable to expect each user to program his or her own rules, and it is infeasible to provide every user with a software engineer to keep the rules up-to-date. A machine learning system can learn which mail messages the user rejects and maintain the filtering rules automatically. Machine learning addresses many of the same research questions as the fields of statistics, data mining, and psychology, but with differences of emphasis. Statistics focuses on understanding the phenomena that have generated the data, often with the goal of testing different hypotheses about those phenomena. Data mining seeks to find patterns in the data that are understandable by people. Psychological studies of human learning aspire to understand the mechanisms underlying the various learning behaviors exhibited by people (concept learning, skill acquisition, strategy change, etc.).

Machine learning

Prediction performance often depends on the cross- and test validation protocols applied Several combinations of different cross-validation variants and model-building techniques were used

Modelling methods and cross-validation variants in QSAR: a multi-level analysis$.

Zika virus (ZIKV) is a mosquito-borne flavivirus for which there are no vaccines or specific therapeutics. To find drugs active on the virus is a complex, expensive and time-consuming process. The prospect of drug repurposing, which consists of finding new indications for existing drugs, is an interesting alternative to expedite drug development for specific diseases. In theory, drug repurposing is also able to respond much more rapidly to a crisis than a classical drug discovery process. Consequently, the methodology is attractive for vector-borne diseases that can emerge or re-emerge worldwide with the risk to become pandemic quickly. Different drugs, showing various structures, have been repurposed to be used against ZIKV infection. They are reviewed in this study and the conditions for their potential use in practice are discussed.

Repurposing drugs for use against Zika virus infection.

Most methods in molecular and drug design are currently based on physicochemical descriptors. However, molecular topology, which relies on topological descriptors, has also shown value for molecula...

What place does molecular topology have in today's drug discovery?

Repellents disrupt the behaviour of blood-seeking mosquitoes protecting humans against their bites which can transmit serious diseases. Since the mid-1950s, N,N-diethyl-m-toluamide (DEET) is considered as the standard mosquito repellent worldwide. However, DEET presents numerous shortcomings. Faced with the heightening risk of mosquito expansion caused by global climate changes and increasing international exchanges, there is an urgent need for a better repellent than DEET and the very few other commercialised repelling molecules such as picaridin and IR3535. In silico approaches have been used to find new repellents and to provide better insights into their mechanism of action. In this context, the goal of our study was to retrieve from the literature all the papers dealing with qualitative and quantitative structure-activity relationships on mosquito repellents. A critical analysis of the SAR and QSAR models was made focusing on the quality of the biological data, the significance of the molecular descriptors and the validity of the statistical tools used for deriving the models. The predictive power and domain of application of these models were also discussed. The hypotheses to compute homology and pharmacophore models, their interest to find new repellents and to provide insights into the mechanisms of repellency in mosquitoes were analysed. The interest to consider the mosquito olfactory system as the target to compute new repellents was discussed. The potential environmental impact of these chemicals as well as new ways of research were addressed.

2D and 3D structure–activity modelling of mosquito repellents: a review$

QSAR models are proposed for predicting the toxicity of 33 piperidine derivatives against Aedes aegypti. From 2D topological descriptors, calculated with the PaDEL software, ordinary least squares multilinear regression (OLS-MLR) treatment from the QSARINS software and machine learning and related approaches including linear and radial support vector machine (SVM), projection pursuit regression (PPR), radial basis function neural network (RBFNN), general regression neural network (GRNN) and k-nearest neighbours (k-NN), led to four-variable models. Their robustness and predictive ability were evaluated through both internal and external validation. Determination coefficients (r2) greater than 0.85 on the training sets and 0.8 on the test sets were obtained with OLS-MLR and linear SVM. They slightly outperform PPR, radial SVM and RBFNN, whereas GRNN and k-NN showed lower performance. The easy availability of the involved structural descriptors and the simplicity of the MLR model make the corresponding model attractive at an exploratory level for proposing, from this limited dataset, guidelines in the design of new potentially active molecules.

QSAR models for predicting the toxicity of piperidine derivatives against Aedes aegypti.

Aedes aegypti vector control is of paramount importance owing to the damages induced by the various severe diseases that these insects may transmit, and the increasing risk of important outbreaks of these pathologies. Search for new chemicals efficient against Aedes aegypti, and devoid of side-effects, which have been associated to the currently most used active substance i. e. N,N-diethyl-m-toluamide (DEET), is therefore an important issue. In this context, we developed various Quantitative Structure Activity Relationship (QSAR) models to predict the repellent activity against Aedes aegypti of 43 carboxamides, by using Multiple Linear Regression (MLR) and various machine learning approaches. The easy computation of the four topological descriptors selected in this study, compared to the CODESSA descriptors used in the literature, and the predictive ability of the here proposed MLR and machine learning models developed using the software QSARINS and R, make the here proposed QSARs attractive. As demonstrated in this study, these models can be applied at the screening level, to guide the design of new alternatives to DEET.

E. Papa

Papers

QSAR models for predicting the toxicity of piperidine derivatives against Aedes aegypti.

Topological QSAR Modelling of Carboxamides Repellent Activity to Aedes Aegypti