scholarly journals Systematic auditing is essential to debiasing machine learning in biology

2020 ◽  
Author(s):  
Fatma-Elzahraa Eid ◽  
Haitham Elmarakeby ◽  
Yujia Alina Chan ◽  
Nadine Fornelos Martins ◽  
Mahmoud ElHefnawi ◽  
...  
Keyword(s):  
Machine Learning ◽  
Protein Interactions ◽  
Drug Target ◽  
Peptide Binding ◽  
Life Sciences ◽  
Prediction Performance ◽  
Biological Data ◽  
Training Data ◽  
Protein Protein Interactions ◽  
Interest Prediction

AbstractRepresentational biases that are common in biological data can inflate prediction performance and confound our understanding of how and what machine learning (ML) models learn from large complicated datasets. However, auditing for these biases is not a common practice in ML in the life sciences. Here, we devise a systematic auditing framework and harness it to audit three different ML applications of significant therapeutic interest: prediction frameworks of protein-protein interactions, drug-target bioactivity, and MHC-peptide binding. Through this, we identify unrecognized biases that hinder the ML process and result in low model generalizability. Ultimately, we show that, when there is insufficient signal in the training data, ML models are likely to learn primarily from representational biases.

Targeting Virus-host Protein Interactions: Feature Extraction and Machine Learning Approaches

2019 ◽  
Vol 20 (3) ◽  
pp. 177-184 ◽  
Author(s):  
Nantao Zheng ◽  
Kairou Wang ◽  
Weihua Zhan ◽  
Lei Deng
Keyword(s):  
Machine Learning ◽  
Computational Methods ◽  
Protein Interactions ◽  
Prediction Models ◽  
Learning Algorithms ◽  
Biological Data ◽  
Machine Learning Algorithms ◽  
Host Protein ◽  
Protein Protein Interactions ◽  
Protein Motifs

Background:Targeting critical viral-host Protein-Protein Interactions (PPIs) has enormous application prospects for therapeutics. Using experimental methods to evaluate all possible virus-host PPIs is labor-intensive and time-consuming. Recent growth in computational identification of virus-host PPIs provides new opportunities for gaining biological insights, including applications in disease control. We provide an overview of recent computational approaches for studying virus-host PPI interactions.Methods:In this review, a variety of computational methods for virus-host PPIs prediction have been surveyed. These methods are categorized based on the features they utilize and different machine learning algorithms including classical and novel methods.Results:We describe the pivotal and representative features extracted from relevant sources of biological data, mainly include sequence signatures, known domain interactions, protein motifs and protein structure information. We focus on state-of-the-art machine learning algorithms that are used to build binary prediction models for the classification of virus-host protein pairs and discuss their abilities, weakness and future directions.Conclusion:The findings of this review confirm the importance of computational methods for finding the potential protein-protein interactions between virus and host. Although there has been significant progress in the prediction of virus-host PPIs in recent years, there is a lot of room for improvement in virus-host PPI prediction.

scholarly journals Ens-PPI: A Novel Ensemble Classifier for Predicting the Interactions of Proteins Using Autocovariance Transformation from PSSM

2016 ◽  
Vol 2016 ◽  
pp. 1-8 ◽  
Author(s):  
Zhen-Guo Gao ◽  
Lei Wang ◽  
Shi-Xiong Xia ◽  
Zhu-Hong You ◽  
Xin Yan ◽  
...  
Keyword(s):  
Machine Learning ◽  
Protein Interactions ◽  
Biological Activities ◽  
Ensemble Classifier ◽  
Prediction Performance ◽  
Protein Protein Interactions ◽  
Rotation Forest ◽  
Proposed Model ◽  
Protein Amino Acids ◽  
Scoring Matrix

Protein-Protein Interactions (PPIs) play vital roles in most biological activities. Although the development of high-throughput biological technologies has generated considerable PPI data for various organisms, many problems are still far from being solved. A number of computational methods based on machine learning have been developed to facilitate the identification of novel PPIs. In this study, a novel predictor was designed using the Rotation Forest (RF) algorithm combined with Autocovariance (AC) features extracted from the Position-Specific Scoring Matrix (PSSM). More specifically, the PSSMs are generated using the information of protein amino acids sequence. Then, an effective sequence-based features representation, Autocovariance, is employed to extract features from PSSMs. Finally, the RF model is used as a classifier to distinguish between the interacting and noninteracting protein pairs. The proposed method achieves promising prediction performance when performed on the PPIs ofYeast,H.pylori, andindependent datasets. The good results show that the proposed model is suitable for PPIs prediction and could also provide a useful supplementary tool for solving other bioinformatics problems.

scholarly journals Systematic auditing is essential to debiasing machine learning in biology

2021 ◽  
Vol 4 (1) ◽  
Author(s):  
Fatma-Elzahraa Eid ◽  
Haitham A. Elmarakeby ◽  
Yujia Alina Chan ◽  
Nadine Fornelos ◽  
Mahmoud ElHefnawi ◽  
...  
Keyword(s):  
Machine Learning ◽  
Biomedical Applications ◽  
Life Sciences ◽  
Model Performance ◽  
Prediction Performance ◽  
Biological Data ◽  
Reduced Model

AbstractBiases in data used to train machine learning (ML) models can inflate their prediction performance and confound our understanding of how and what they learn. Although biases are common in biological data, systematic auditing of ML models to identify and eliminate these biases is not a common practice when applying ML in the life sciences. Here we devise a systematic, principled, and general approach to audit ML models in the life sciences. We use this auditing framework to examine biases in three ML applications of therapeutic interest and identify unrecognized biases that hinder the ML process and result in substantially reduced model performance on new datasets. Ultimately, we show that ML models tend to learn primarily from data biases when there is insufficient signal in the data to learn from. We provide detailed protocols, guidelines, and examples of code to enable tailoring of the auditing framework to other biomedical applications.

scholarly journals The rise and fall of machine learning methods in biomedical research

F1000Research ◽  
2017 ◽  
Vol 6 ◽  
pp. 2012 ◽  
Author(s):  
Hashem Koohy
Keyword(s):  
Machine Learning ◽  
Biomedical Research ◽  
Life Sciences ◽  
Biological Data ◽  
Research Note ◽  
Machine Learning Techniques ◽  
Learning Methods ◽  
The Past ◽  
Machine Learning Methods ◽  
Learning Techniques

In the era of explosion in biological data, machine learning techniques are becoming more popular in life sciences, including biology and medicine. This research note examines the rise and fall of the most commonly used machine learning techniques in life sciences over the past three decades.

Prediction of Compound-Protein Interactions with Machine Learning Methods

2011 ◽  
pp. 304-317
Author(s):  
Yoshihiro Yamanishi ◽  
Hisashi Kashima
Keyword(s):  
Machine Learning ◽  
Protein Interactions ◽  
Chemical Structure ◽  
Genomic Sequence ◽  
Sequence Data ◽  
Binary Classification ◽  
Biological Data ◽  
Supervised Machine Learning ◽  
Learning Methods ◽  
Machine Learning Methods

In silico prediction of compound-protein interactions from heterogeneous biological data is critical in the process of drug development. In this chapter the authors review several supervised machine learning methods to predict unknown compound-protein interactions from chemical structure and genomic sequence information simultaneously. The authors review several kernel-based algorithms from two different viewpoints: binary classification and dimension reduction. In the results, they demonstrate the usefulness of the methods on the prediction of drug-target interactions and ligand-protein interactions from chemical structure data and genomic sequence data.

scholarly journals A Novel Phosphorylation Site-Kinase Network-Based Method for the Accurate Prediction of Kinase-Substrate Relationships

2017 ◽  
Vol 2017 ◽  
pp. 1-11 ◽  
Author(s):  
Minghui Wang ◽  
Tao Wang ◽  
Binghua Wang ◽  
Yu Liu ◽  
Ao Li
Keyword(s):  
Protein Interactions ◽  
Phosphorylation Site ◽  
Prediction Performance ◽  
Accurate Prediction ◽  
Phosphorylation Sites ◽  
Protein Protein Interactions ◽  
Biological Mechanisms ◽  
Kinase Substrate ◽  
Prediction Tools ◽  
Local Sequence

Protein phosphorylation is catalyzed by kinases which regulate many aspects that control death, movement, and cell growth. Identification of the phosphorylation site-specific kinase-substrate relationships (ssKSRs) is important for understanding cellular dynamics and provides a fundamental basis for further disease-related research and drug design. Although several computational methods have been developed, most of these methods mainly use local sequence of phosphorylation sites and protein-protein interactions (PPIs) to construct the prediction model. While phosphorylation presents very complicated processes and is usually involved in various biological mechanisms, the aforementioned information is not sufficient for accurate prediction. In this study, we propose a new and powerful computational approach named KSRPred for ssKSRs prediction, by introducing a novel phosphorylation site-kinase network (pSKN) profiles that can efficiently incorporate the relationships between various protein kinases and phosphorylation sites. The experimental results show that the pSKN profiles can efficiently improve the prediction performance in collaboration with local sequence and PPI information. Furthermore, we compare our method with the existing ssKSRs prediction tools and the results demonstrate that KSRPred can significantly improve the prediction performance compared with existing tools.

scholarly journals Issues in performance evaluation for host–pathogen protein interaction prediction

2016 ◽  
Vol 14 (03) ◽  
pp. 1650011 ◽  
Author(s):  
Wajid Arshad Abbasi ◽  
Fayyaz Ul Amir Afsar Minhas
Keyword(s):  
Machine Learning ◽  
Protein Interactions ◽  
Cross Validation ◽  
Protein Protein Interactions ◽  
Evaluation Scheme ◽  
Host Pathogen ◽  
Pathogen Protein ◽  
Protein Interaction Prediction ◽  
Underlying Mechanisms ◽  
Fold Cross Validation

The study of interactions between host and pathogen proteins is important for understanding the underlying mechanisms of infectious diseases and for developing novel therapeutic solutions. Wet-lab techniques for detecting protein–protein interactions (PPIs) can benefit from computational predictions. Machine learning is one of the computational approaches that can assist biologists by predicting promising PPIs. A number of machine learning based methods for predicting host–pathogen interactions (HPI) have been proposed in the literature. The techniques used for assessing the accuracy of such predictors are of critical importance in this domain. In this paper, we question the effectiveness of K-fold cross-validation for estimating the generalization ability of HPI prediction for proteins with no known interactions. K-fold cross-validation does not model this scenario, and we demonstrate a sizable difference between its performance and the performance of an alternative evaluation scheme called leave one pathogen protein out (LOPO) cross-validation. LOPO is more effective in modeling the real world use of HPI predictors, specifically for cases in which no information about the interacting partners of a pathogen protein is available during training. We also point out that currently used metrics such as areas under the precision-recall or receiver operating characteristic curves are not intuitive to biologists and propose simpler and more directly interpretable metrics for this purpose.

scholarly journals Parasites, proteomes and systems: has Descartes’ clock run out of time?

Parasitology ◽  
2012 ◽  
Vol 139 (9) ◽  
pp. 1103-1118 ◽  
Author(s):  
J. M. WASTLING ◽  
S. D. ARMSTRONG ◽  
R. KRISHNA ◽  
D. XIA
Keyword(s):  
Systems Biology ◽  
Protein Interactions ◽  
Biological Data ◽  
Protein Protein Interactions ◽  
Proteomics Data ◽  
Data Types ◽  
Quality Of Data ◽  
Post Translational Modifications ◽  
Systems Modelling ◽  
New Generation

SUMMARYSystems biology aims to integrate multiple biological data types such as genomics, transcriptomics and proteomics across different levels of structure and scale; it represents an emerging paradigm in the scientific process which challenges the reductionism that has dominated biomedical research for hundreds of years. Systems biology will nevertheless only be successful if the technologies on which it is based are able to deliver the required type and quality of data. In this review we discuss how well positioned is proteomics to deliver the data necessary to support meaningful systems modelling in parasite biology. We summarise the current state of identification proteomics in parasites, but argue that a new generation of quantitative proteomics data is now needed to underpin effective systems modelling. We discuss the challenges faced to acquire more complete knowledge of protein post-translational modifications, protein turnover and protein-protein interactions in parasites. Finally we highlight the central role of proteome-informatics in ensuring that proteomics data is readily accessible to the user-community and can be translated and integrated with other relevant data types.

Sign in / Sign up

Export Citation Format

Share Document