Search

Motivation: Machine learning based prediction of compound-protein interactions (CPIs) is important for drug design, screening and repurposing studies and can improve the efficiency and cost-effectiveness of wet lab assays. Despite the publication of many research papers reporting CPI predictors in the recent years, we have observed a number of fundamental issues in experiment design that lead to over optimistic estimates of model performance. Results: In this paper, we analyze the impact of several important factors affecting generalization perfor-mance of CPI predictors that are overlooked in existing work: 1. Similarity between training and test examples in cross-validation 2. The strategy for generating negative examples, in the absence of experimentally verified negative examples. 3. Choice of evaluation protocols and performance metrics and their alignment with real-world use of CPI predictors in screening large compound libraries. Using both an existing state-of-the-art method (CPI-NN) and a proposed kernel based approach, we have found that assessment of predictive performance of CPI predictors requires careful con-trol over similarity between training and test examples. We also show that random pairing for gen-erating synthetic negative examples for training and performance evaluation results in models with better generalization performance in comparison to more sophisticated strategies used in existing studies. Furthermore, we have found that our kernel based approach, despite its simple design, exceeds the prediction performance of CPI-NN. We have used the proposed model for compound screening of several proteins including SARS-CoV-2 Spike and Human ACE2 proteins and found strong evidence in support of its top hits. Availability: Code and raw experimental results available at https://github.com/adibayaseen/HKRCPI Contact: Fayyaz.minhas@warwick.ac.uk, Comment: Supplementary information: Supplementary data files are available as part of the GitHub repository

If you want to tell people the truth, make them laugh, otherwise they'll kill you. (source unclear) Machine learning and deep learning are the technologies of the day for developing intelligent automatic systems. However, a key hurdle for progress in the field is the literature itself: we often encounter papers that report results that are difficult to reconstruct or reproduce, results that mis-represent the performance of the system, or contain other biases that limit their validity. In this semi-humorous article, we discuss issues that arise in running and reporting results of machine learning experiments. The purpose of the article is to provide a list of watch out points for researchers to be aware of when developing machine learning models or writing and reviewing machine learning papers., Comment: 11 pages, 8 figures

Motivation: A major challenge in the development of machine learning based methods in computational biology is that data may not be accurately labeled due to the time and resources required for experimentally annotating properties of proteins and DNA sequences. Standard supervised learning algorithms assume accurate instance-level labeling of training data. Multiple instance learning is a paradigm for handling such labeling ambiguities. However, the widely used large-margin classification methods for multiple instance learning are heuristic in nature with high computational requirements. In this paper, we present stochastic sub-gradient optimization large margin algorithms for multiple instance classification and ranking, and provide them in a software suite called pyLEMMINGS. Results: We have tested pyLEMMINGS on a number of bioinformatics problems as well as benchmark datasets. pyLEMMINGS has successfully been able to identify functionally important segments of proteins: binding sites in Calmodulin binding proteins, prion forming regions, and amyloid cores. pyLEMMINGS achieves state-of-the-art performance in all these tasks, demonstrating the value of multiple instance learning. Furthermore, our method has shown more than 100-fold improvement in terms of running time as compared to heuristic solutions with improved accuracy over benchmark datasets. Availability and Implementation: pyLEMMINGS python package is available for download at: http://faculty.pieas.edu.pk/fayyaz/software.html#pylemmings.

Background: The increasing volume and variety of genotypic and phenotypic data is a major defining characteristic of modern biomedical sciences. At the same time, the limitations in technology for generating data and the inherently stochastic nature of biomolecular events have led to the discrepancy between the volume of data and the amount of knowledge gleaned from it. A major bottleneck in our ability to understand the molecular underpinnings of life is the assignment of function to biological macromolecules, especially proteins. While molecular experiments provide the most reliable annotation of proteins, their relatively low throughput and restricted purview have led to an increasing role for computational function prediction. However, accurately assessing methods for protein function prediction and tracking progress in the field remain challenging. Methodology: We have conducted the second Critical Assessment of Functional Annotation (CAFA), a timed challenge to assess computational methods that automatically assign protein function. One hundred twenty-six methods from 56 research groups were evaluated for their ability to predict biological functions using the Gene Ontology and gene-disease associations using the Human Phenotype Ontology on a set of 3,681 proteins from 18 species. CAFA2 featured significantly expanded analysis compared with CAFA1, with regards to data set size, variety, and assessment metrics. To review progress in the field, the analysis also compared the best methods participating in CAFA1 to those of CAFA2. Conclusions: The top performing methods in CAFA2 outperformed the best methods from CAFA1, demonstrating that computational function prediction is improving. This increased accuracy can be attributed to the combined effect of the growing number of experimental annotations and improved methods for function prediction., Comment: Submitted to Genome Biology

The phase space flow of a dynamical system leading to the solution of Linear Programming (LP) problems is explored as an example of complexity analysis in an analog computation framework. An ensemble of LP problems with $n$ variables and $m$ constraints ($n>m$), where all elements of the vectors and matrices are normally distributed is studied. The convergence time of a flow to the fixed point representing the optimal solution is computed. The cumulative distribution ${\cal F}^{(n,m)}(\Delta)$ of the convergence rate $\Delta_{min}$ to this point is calculated analytically, in the asymptotic limit of large $(n,m)$, in the framework of Random Matrix Theory. In this limit ${\cal F}^{(n,m)}(\Delta)$ is found to be a scaling function, namely it is a function of one variable that is a combination of $n$, $m$ and $\Delta$ rather then a function of these three variables separately. From numerical simulations also the distribution of the computation times is calculated and found to be a scaling function as well., Comment: 8 pages, latex, 2 eps figures; final published version

In this paper we address the complexity of solving linear programming problems with a set of differential equations that converge to a fixed point that represents the optimal solution. Assuming a probabilistic model, where the inputs are i.i.d. Gaussian variables, we compute the distribution of the convergence rate to the attracting fixed point. Using the framework of Random Matrix Theory, we derive a simple expression for this distribution in the asymptotic limit of large problem size. In this limit, we find that the distribution of the convergence rate is a scaling function, namely it is a function of one variable that is a combination of three parameters: the number of variables, the number of constraints and the convergence rate, rather than a function of these parameters separately. We also estimate numerically the distribution of computation times, namely the time required to reach a vicinity of the attracting fixed point, and find that it is also a scaling function. Using the problem size dependence of the distribution functions, we derive high probability bounds on the convergence rates and on the computation times., Comment: 1+37 pages, latex, 5 eps figures. Version accepted for publication in the Journal of Complexity. Changes made: Presentation reorganized for clarity, expanded discussion of measure of complexity in the non-asymptotic regime (added a new section)