Prediction of Ion Channels and their Types from Protein Sequences: Comprehensive Review and Comparative Assessment

Abstract

Background: Ion channels are a large and growing protein family. Many of them are associated with diseases, and consequently, they are targets for over 700 drugs. Discovery of new ion channels is facilitated with computational methods that predict ion channels and their types from protein sequences. However, these methods were never comprehensively compared and evaluated. </P><P> Objective: We offer first-of-its-kind comprehensive survey of the sequence-based predictors of ion channels. We describe eight predictors that include five methods that predict ion channels, their types, and four classes of the voltage-gated channels. We also develop and use a new benchmark dataset to perform comparative empirical analysis of the three currently available predictors. </P><P> Results: While several methods that rely on different designs were published, only a few of them are currently available and offer a broad scope of predictions. Support and availability after publication should be required when new methods are considered for publication. Empirical analysis shows strong performance for the prediction of ion channels and modest performance for the prediction of ion channel types and voltage-gated channel classes. We identify a substantial weakness of current methods that cannot accurately predict ion channels that are categorized into multiple classes/types. </P><P> Conclusion: Several predictors of ion channels are available to the end users. They offer practical levels of predictive quality. Methods that rely on a larger and more diverse set of predictive inputs (such as PSIONplus) are more accurate. New tools that address multi-label prediction of ion channels should be developed.

PSIONplusm Server for Accurate Multi-Label Prediction of Ion Channels and Their Types

“…Moreover, over 400 putative ion channels were already identified in human and they are estimated to account for as much as 1% of the protein coding genes in human [ 11 ]. The number of the annotated ion channel proteins has grown rapidly in recent years, from about 400 in the mid-1990s to close to 3000 by 2015 [ 13 ]. However, thousands of ion channels remain to be identified among the over 175 million of the already sequenced proteins (source: UniProt release 2019_11 [ 14 ]).…”

“…The other three predictors, which include the method by Tiwari and Srivastava [ 21 ], the method by Han et al [ 22 ], and PSIONplus [ 23 ], address the prediction of ion channels, their types (voltage- vs. ligand-gated) and the four subtypes of the voltage-gated channels (potassium, sodium, calcium, and anions). These predictors use sophisticated machine learning algorithms, such as support vector machines [ 18 , 19 , 20 , 22 , 23 ] and random forest [ 21 , 22 ], and secure relatively good predictive performance [ 13 ].…”

“…A recent survey points to three major drawbacks of the current methods [ 13 ]. First , only three of the six tools, IonchanPred2.0 [ 20 ], VGIchan [ 18 ] and PSIONplus [ 23 ], are available to the end user.…”

“…The lack of available implementations renders the other three tools practically unusable. The survey states that the provision of the implementation or webserver should be required at the time the corresponding article is published [ 13 ]. Second , each of the six current methods is composed of three separate predictive models that make predictions in parallel, i.e., a given input sequence is predicted as ion channel vs. non-ion channel; as voltage- vs. ligand-gated channel; and as one of the four subtypes of the voltage-gated channels.…”

“…Such sequential test regimes may result in an accumulation of errors along the subsequent steps. A recent comparative survey evaluated the current methods using the sequential regime and concluded that the most accurate PSIONplus offers modest levels of predictive performance [ 13 ]. Third , the current tools predict a single outcome for each input protein sequence, while in fact some of the channels may transport multiple types of ions.…”