==== Front HeliyonHeliyonHeliyon2405-8440Elsevier S2405-8440(18)32945-110.1016/j.heliyon.2018.e00705e00705ArticleafpCOOL: A tool for antifreeze protein prediction Eslami Morteza aShirali Hossein Zade Ramin bTakalloo Zeinab cMahdevar Ghasem dEmamjomeh Abbasali eSajedi Reza H. cZahiri Javad zahiri@modares.ac.irfg∗a Department of Computer Engineering, Arak University, Arak, Iranb Department of Computer Engineering, Sharif University of Technology, Tehran, Iranc Department of Biochemistry, Faculty of Biological Sciences, Tarbiat Modares University, Tehran, Irand Department of Mathematics, Faculty of Sciences, University of Isfahan, Isfahan, Irane Laboratory of Computational Biotechnology and Bioinformatics (CBB), Department of Plant Breeding and Biotechnology (PBB), Faculty of Agriculture, University of Zabol, Zabol, Iranf Bioinformatics and Computational Omics Lab (BioCOOL), Department of Biophysics, Faculty of Biological Sciences, Tarbiat Modares University, Tehran, Irang School of Biological Sciences, Institute for Research in Fundamental Sciences (IPM), P.O. Box 19395-5746, Tehran, Iran∗ Corresponding author. zahiri@modares.ac.ir25 7 2018 7 2018 25 7 2018 4 7 e0070519 6 2018 20 7 2018 © 2018 The Authors2018This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).Various cold-adapted organisms produce antifreeze proteins (AFPs), which prevent the freezing of cell fluids by inhibiting the growth of ice crystals. AFPs are currently being recognized in various organisms, living in extremely low temperatures. AFPs have several important applications in increasing freeze tolerance of plants, maintaining the tissue in frozen conditions and producing cold-hardy plants by applying transgenic technology. Substantial differences in the sequence and structure of the AFPs, pose a challenge for researchers to identify these proteins. In this paper, we proposed a novel method to identify AFPs, using supportive vector machine (SVM) by incorporating 4 types of features. Results of the two used benchmark datasets, revealed the strength of the proposed method in AFP prediction. According to the results of an independent test setup, our method outperformed the current state-of-the-art methods. In addition, the comparison results of the discrimination power of different feature types revealed that physicochemical descriptors are the most contributing features in AFP detection. This method has been implemented as a stand-alone tool, named afpCOOL, for various operating systems to predict AFPs with a user friendly graphical interface. Keywords Computer scienceBioinformaticsComputational biologyMathematical biosciencesBiochemistry ==== Body 1 Introduction Organisms, which are exposed to the freezing conditions, produce special proteins, called antifreeze proteins (AFPs) [1, 2]. AFPs bind to small ice crystals to forestall additional crystallization and depress the freezing point of the solution below the melting point [3, 4, 5, 6]. Additional terms have also been proposed in the literature to name the AFPs: ice structuring proteins and thermal hysteresis proteins [4, 7]. For the first time, AFPs were found in the species of fish and insect that had adapted to extremely low temperatures [3, 8], and the structures of 5 structurally distinct AFPs were identified by Davies and Hew in 1990 [9]. AFPs have also been found in fungi, bacterial species and overwintering plants [10, 11, 12]. AFPs have potential applications in preservation, gene transformation, cryosurgery of tumors, and also in agriculture to produce economically efficient fishes and plants, resisting against extremely low temperatures [13, 14]. Recently, two computational approaches have been proposed to discriminate AFPs from non-AFPs [15, 16], but these methods do not have a satisfactory performance. By considering the substantial differences in the sequence and structure of AFPs [17, 18], it is needed to use suitable machine learning methods to predict AFPs. An appropriate machine learning algorithm offers a cost-effective approach to construct predictive models to identify AFPs by exploiting experimentally validated training data. In this article, we proposed a computational method to identify AFPs, which achieved an accuracy of 95% and 91% on two benchmark datasets and the accuracy of 96% on an independent test dataset. 2 Methods 2.1 Dataset In this study, we had used two independent datasets (Fig. 1) to evaluate the strength of the predictor and also compare the prediction performance of the proposed method with the current state-of-the-art methods.Fig. 1 Schematic representation of AFP517 dataset construction. a) Positive dataset contains 843 AFPs. b) Negative dataset contains 843 non-AFPs. Fig. 1 2.1.1 AFP481 dataset The first benchmark dataset (AFP481) was extracted from Kandaswamy et al. [15]. This dataset contains 481 AFPs and 9493 non-AFPs, which were used for the positive and the negative datasets, respectively. In this dataset, the proteins with ≥40% sequence similarity were omitted using CD-HIT [19]. Train dataset consists of 300 out of all the 481 AFPs and 300 out of all the 9493 non-AFPs, which had been selected randomly for each positive and negative datasets, respectively. Also, the remaining 181 AFPs and 9193 non-AFPs were used as an independent test dataset. 2.1.2 AFP517 dataset For a better assessment of the strength of the proposed method, a more comprehensive benchmark dataset, named AFP517, was assembled as following (Fig. 1b). Antifreeze protein sequences were extracted from UniProtKB [20]. For this goal, UniProtKB was scanned with a list of keywords, implying antifreeze proteins. The “antifreeze”, “thermal hysteresis”, “ice-structuring”, and “AFP” were used as keywords. We retrieved 943 proteins in total, where the number of proteins corresponding to “antifreeze”, “thermal hysteresis”, ”ice-structuring” and “AFP” keywords were 734, 22, 52, and 135, respectively. Finally, the proteins with ≥90% sequence similarity were removed using CD-HIT, which resulted in 517 AFP proteins, used as positive instances. To select negative examples (non-AFP proteins), we took advantage of PISCES [21] as a public server to cull sets of protein sequences from the Protein Data Bank (PDB) [22] by determining sequence identity and structural quality criteria (Fig. 1). We used the same number of AFP and non-AFP proteins to construct a balanced dataset. 2.2 Features We trained our model to detect AFPs by exploiting four types of descriptors including hydropathy (3 descriptors), physicochemical properties (218 descriptors), amino acid composition (20 descriptors), and evolutionary profile (400 descriptors). 2.2.1 Hydropathy descriptors According to the hydropathy, 20 amino acids were categorized into 3 feature groups as following: strongly hydrophilic (RDENQKH), strongly hydrophobic (LIVAMF), and weakly hydrophilic or weakly hydrophobic (STYW). For each feature of these three groups in a protein sequence, the number of occurrences of each group was computed and divided by the length of the sequence. 2.2.2 Physicochemical descriptors To compute physicochemical descriptors, 544 different physicochemical indices were extracted from AAINDEX database [23], which is a database of numerical indices representing various physicochemical and biochemical properties of amino acids. For reducing the biases, which can be a result of having many correlated indices, we considered each pair of indices with a correlation coefficient greater than 0.8 and less than −0.8 as redundant indices. Finally, a subset of 218 non-redundant indices were selected to encode proteins. More precisely, the 20-dimensional amino acid composition vector was multiplied by the AAINDEX matrix (dimension: 218 × 20), resulted into a 218-dimensional feature vector. 2.2.3 Amino acid composition Each protein was encoded by a 20-dimensional feature vector, indicating the amino acid composition of the protein. Each element of this vector indicates the frequency of an amino acid of the protein sequence. 2.2.4 Evolutionary information It has been shown that evolutionary information is effective in detecting diverse properties of proteins [16, 24, 25]. We used evolutionary information of the protein in the form of Position-Specific Scoring Matrix (PSSM). Position Specific Iterated BLAST (PSI-BLAST) was used against the NCBI non-redundant dataset with three iterations and the e-value of 0.0001, to generate PSSMs for all the proteins. Regarding substitution scores in the PSSMs, each protein was encoded as a 400-dimensional feature vector. Each element of this vector is the sum of all positive substitution scores of an amino acid to one of the twenty standard amino acids. 2.2.5 Normalization In all of the four above-mentioned descriptor types, every element was normalized according to the length of the sequence to avoid the bias, which can be the result of different sequence lengths. 2.3 Support vector machines In recent years, support vector machine (SVM) has been widely used in various prediction problems in bioinformatics [26]. SVM classifies the input samples, represented in the form of n-dimensional feature vectors, into two classes using an optimal hyper-plane in the feature space. In this study, the input of the SVM classifier is a 641-dimensional vector that encodes the features of a given protein, and the output is a binary label, indicating whether the given protein is an AFP or not. We used the SVM implementation by means of WEKA package [27] with Pearson VII function-based universal kernel (PUK). 2.4 Evaluation parameters for the prediction performance A 10 fold cross-validation (10-fold CV) approach was used to evaluate the performance of the proposed prediction model. Positive and negative instances were distributed randomly into 10 folds. In each of the 10 iterative steps, 9 of the 10 folds were used to train the classifier, and then the classifier was evaluated by using the remaining data (test data). The predictions made for the test instances in all the 10 iterations were combined and used to compute the following performance measures: Sensitivity(orRecall)=TPTP+FN Precision=TPTP+FP Specificity=TNTN+FP Accuracy=TP+TNTP+FP+TN+FN MCC=TP*TN−FP*FN(TP+FP)(TP+FN)(TN+FP)(TN+FN) F-measure=2*Precision*RecallPrecision+Recall Where, TP and TN are the correctly predicted AFP and non-AFP instances, respectively. Similarly, FP and FN are the number of proteins, wrongly predicted as AFP and non-AFP. In addition to the mentioned measures, we used the receiver operating characteristic (ROC) curve, which is an important graphical tool for assessing the classification performance. ROC plots sensitivity (true positive rate) against false positive rate and shows the trade-off between sensitivity and specificity. We also used the area under the ROC curve (AUC), as a reliable performance measurement. For further assessment of the afpCOOL, in addition to the mentioned 10-fold cross validation, we also obtained the prediction results by applying leave-one-out-cross-validation procedure (LOOCV). LOOCV is similar to the 10-fold CV but the number of folds is equal to the number of instances. 3 Results and discussion We compared afpCOOL with two recently published methods, to show the strength of the proposed method regarding the current state-of-the-art methods: AFP-Pred and AFP-PSSM [16]. The prediction results of afpCOOL in the two benchmark datasets, AFP481 and AFP517, and also an independent test set are described in the following. 3.1 Results on the AFP481 dataset Table 1 shows the most important prediction performance measures for afpCOOL on the AFP481 dataset. This dataset contains 300 AFPs and 300 non-AFPs. According to the 10-fold cross validation results, our method performed well in AFP detection: the method achieved an accuracy rate of 93% with an f-measure of 93%.Table 1 Prediction performance of the afpCOOL on two benchmark datasets in a 10-fold cross validation (10-fold CV) and leave-one-out (LOOCV) procedures. The AFP481 dataset contains 300 AFPs and 300 non-AFPs; and, the AFP517 dataset contains 517AFPs and 517non-AFPs. Table 1Dataset Performance measures Accuracy Precision Sensitivity F-Measure MCC AUC 10-Fold CV AFP481 0.93 0.93 0.93 0.93 0.87 0.93 AFP517 0.91 0.92 0.92 0.92 0.84 0.92 LOOCV AFP481 0.89 0.90 0.88 0.86 0.78 0.91 AFP517 0.91 0.90 0.89 0.90 0.81 0.90 3.2 Results on the AFP517 dataset This dataset contains 1668 proteins with equal number of positive (AFPs) and negative (non-AFPs) instances. The various performance measures in a 10-fold cross validation procedure revealed the strength of afpCOOL (Table 1). Our method achieved an accuracy of 91.9%, precision and sensitivity of 92% with an MCC of 84%. Fig. 2 shows the ROC curve of the method on the two mentioned benchmark datasets. The proposed model performed better on the larger dataset (AFP517 dataset), as these curves disclose. It was clear that the results of LOOCV show the robustness of the method.Fig. 2 The receiver operating characteristic (ROC) curves of our method on the two benchmark dataset calculated from the ten-fold cross validation. The AFP481 dataset contains 300 AFPs and 300 non-AFPs; and, the AFP517 dataset contains 517AFPs and 517non-AFPs. Fig. 2 3.3 Comparison with the current state-of-the-art methods For further evaluation of our method, an independent test set was used to compare the method with the current state-of-the-art methods. We used a test dataset, which has been recently exploited by Zhao et al [16] as the benchmark for comparison purposes; this dataset contains 181 AFPs and 9193 non-AFPs. We have trained our model with the same data that has been used by the two competitor methods (AFP481), to have a fair comparison. As Table 2 shows, AFP-Pred performed better in sensitivity measurement, but on the other hand it's the worse method according to the specificity and accuracy. The accuracy of afpCOOL (96%) is higher than the accuracy rate of AFP-Pred (83%) and AFP-PSSM (93%). It was clear that our method outperformed the other methods in terms of specificity.Table 2 Performance comparison of the proposed method (afpCOOL) with the two current state-of-the-art methods in AFP prediction. All methods are trained on the AFP481 dataset in a 10-fold cross validation procedure and tested on an independent test dataset with 181 AFP and 9193 non-AFPs. Table 2Method Performance Measure Sensitivity Specificity Accuracy afpCOOL 0.72 0.98 0.96 AFP-Pred (Griffith and Yaish 2004) 0.85 0.82 0.83 AFP-PSSM (Zhao et al. 2012) 0.76 0.93 0.93 3.4 afpCOOL tool We have developed the afpCOOL as a tool, enabling fast in-silico AFP detection. This tool has been implemented as a stand-alone java application for various operating systems with a user-friendly graphical interface (Fig. 3). Users can use the afpCOOL simply by providing sequences (in fasta format) and PSSMs of the interested proteins; afpCOOL extracts features from the provided inputs and then uses the trained SVM-based model to assign AFP or non-AFP labels to the queries. The afpCOOL is freely downloadable for non-commercial use at http://biocool.ir.Fig. 3 Graphical user interface of afpCOOL. Fig. 3 3.5 Need for a reliable computational tool for AFP prediction: BLAST cannot effectively detect the AFPs We ran BLAST by using each of the AFPs as the query against the last update (August 12, 2015) of the UniProt Archive (UniParc) database with e-value ≤1e-3, to show the strength of the afpCOOL. It should be mentioned that 801 proteins have been mapped to UniParc identifiers, and as a result, 801 BLAST searches were used for this analysis. More details were presented in Fig. 4.a. One can see that the BLAST does not have a satisfactory specificity in AFP detection; more than 62% (539 out of 801) and more than 87% of the BLAST searches had specificity rates of less than 10% and ≤50%, respectively. Considering the large dataset, used for BLAST searches, it may be expected to have a low specificity and very good sensitivity. Nevertheless, by considering the sensitivity of the BLAST searches, Fig. 4.b, the condition is worse than the specificity: there is no BLAST search with sensitivity higher than 10%; and also, 84% of the BLAST searches have sensitivity ≤5% (673 search out of 801 BLAST searches).Fig. 4 Sensitivity (a) and specificity(b) of the BLAST when using each of the 801 AFPs as the query against the last update. Fig. 4 Interestingly, there are 35 proteins without any search results in the BLAST search and 11 proteins with a sensitivity rate of 0%. These proteins are listed in Tables 3 and 4, respectively. As it can be clear 5 out of 11 (45%) proteins with sensitivity rates of 0% were extracted from Boreogadus saida (Polar cod). In addition, the proteins of these two categories have a significantly different amino acid composition comparing to the other AFPs. As more details were presented in Fig. 5, alanine was the major building blocks of these AFPs (43% in the AFPs without any hit in the BLAST search and 47% in the AFPs with 0% sensitivity in the BLAST search).Fig. 5 Amino acid composition of AFP proteins that have been used in the BLAST searches. Fig. 5Table 3 Anti-freeze proteins with no any hit in the BLAST search (35 proteins). Table 3Proteins (UniProt ID) Organism Q9DF23; P04367; P04368 Myoxocephalus scorpius (Shorthorn sculpin) (Cottusscorpius). Q1AMR6; Q1AMR7 Parachaenichthyscharcoti (Charcot's dragonfish) (Chaenichthyscharcoti). Q1AMR9; Q9DFU2 Gymnodraco acuticeps (Antarctic dragonfish). P02733; P02734 Pseudopleuronectes americanus (Winter flounder) (Pleuronectes americanus). P20421; P20617 Myoxocephalus aenaeus (Grubby sculpin) (Cottusaenaeus). P11920; P11921 Eleginus gracilis (Saffron cod) (Gadusgracilis). Q9S8C6; Q9S8C5 Secale cereale (Rye). Q90402 Dissostichus mawsoni (Antarctic cod). Q8JHE3 Notothenia microlepidota. Q1AMR4 Chaenocephalus aceratus (Blackfinicefish) (Chaenichthysaceratus). Q6JIC7 Liparis atlanticus (Atlantic seasnail). F8UWP2 Tautogolabrus adspersus (Cunner). Q1AMS2 Pogonophryne cerebropogon. Q9DF18 Myoxocephalus octodecemspinosus (Longhorn sculpin) (Cottus octodecemspinosus). Q6JIC6 Liparis gibbus (variegated snailfish). B3EWE8 Trapa natans (Water chestnut). P84794 Solanum tuberosum (Potato). P02732 Pagothenia borchgrevinki (Bald rockcod) (Trematomusborchgrevinki). P86268 Antarctomycespsychrotrophicus. Q3HYD3 Tenebrio molitor (Yellow mealworm beetle). D7PBP2 Hypogastrura harveyi. Q9S9D9 Nicotiana tabacum (Common tobacco). H0SH19 Bradyrhizobium sp. ORS 375. P85102 Cullen corylifolia (Malaysian scurfpea) (Psoralea corylifolia). K0P291 Cardinium endosymbiont cEper1 of Encarsia pergandiella. B4RIE8 Phenylobacterium zucineum (strain HLK1). Q091Z2 Stigmatella aurantiaca (strain DW4/3-1). Table 4 Anti-freeze proteins with 0% sensitivity in the BLAST search (11 proteins). Table 4Proteins (UniProt ID) Organism J7HY61; H2KMI2; H2KMI4; J7I1U4; J7I1K6 Boreogadus saida (Polar cod). A8P5U5 Coprinopsis cinerea (strain Okayama-7/130/ATCC MYA-4618/FGSC 9003) C6KF34 Ammopiptanthusnanus. F2XFX1 Dissostichus mawsoni (Antarctic cod). Q1AMR5 Chaenocephalus aceratus (Blackfinicefish) (Chaenichthys aceratus). H2KMI6 Gadus ogac (Greenland cod). Q1AMR8 Gymnodraco acuticeps (Antarctic dragonfish). 3.6 Feature importance We have integrated the scores of three feature selection (FS) methods including, gain ration, information gain and PCA, to select the most important features. To use the scores obtained from the two first FS methods, scores have been normalized into the range 0–1. For PCA, evi × wi for each feature was used as a score, where evi is the Eigenvalue of the ith PC and wi is the weight of the feature in the corresponding Eigenvector. Then, the PCA scores was also normalized into the range 0–1. Finally, the sum of these three normalized scores, have been used as the feature importance score. Fig. 6 shows the contribution of each feature type in the 100 most important features. As it is apparent, the physicochemical descriptors are the most important features.Fig. 6 The percent of each feature type score regarding the total score of the 100 most important features. Fig. 6 According to the top 10 important features, presented in Table 5, physicochemical descriptors are the most informative features to discriminate between AFPs and non-AFPs. The importance of physicochemical properties of AFPs' amino acids has been suggested in many studies. For example, it was suggested that AFPs mainly bind to ice surfaces through hydrogen bonding or polar interaction between water molecules and hydrophilic side chains of Thr, Gln and Glu [28, 29]. However, a number of mutagenesis studies revealed that hydrogen bonds may not be necessarily essential for the ice surface binding [18, 28, 30]. Also, there were reports that the ice-binding sites of AFPs mainly consist of hydrophobic residues [31]. However, it has been shown that the hydrophilic residue of serine (Ser) may be partially responsible for its inferior antifreeze activity [18, 30].Table 5 The 10 most important features. Table 5Rank Feature Type Feature's Detail 1 Physicochemical The number of atoms in the side chain labeled 2 + 1 (AAIndex Code: CHAM830104) 2 Physicochemical Normalized positional residue frequency at helix termini C (AAIndex Code: AURR980118) 3 Physicochemical Average non-bonded energy per residue (AAIndex Code: OOBM770104) 4 Physicochemical Free energy change of epsilon(i) to alpha(Rh) (AAIndex Code: WERD780104) 5 Physicochemical The number of bonds in the longest chain (AAIndex Code: CHAM830106) 6 PSSM-based H to H 7 Physicochemical Normalized positional residue frequency at helix termini C4 (AAIndex Code: AURR980120) 8 PSSM-based H to G 9 Physicochemical Relative population of conformational state C (AAIndex Code: VASM830102) 10 Physicochemical Loss of Side chain hydropathy by helix formation (AAIndex Code: ROSM880103) In addition, the existence of α-helical structure is one the most important characteristics of the different AFP types [3, 18, 28, 32, 33]. In agreement with the mentioned AFPs' property, four of the most informative features (out of ten) were related to the helix structures. 4 Conclusion We developed a novel SVM-based method to predict AFPs. In this method, each protein has been encoded by four features (evolutionary profile, amino acid composition, Hydropathy, and physicochemical properties). The results indicated that these types of features can significantly improve the prediction of AFPs. The obtained results on two benchmark datasets revealed the strength of our method in AFP detection. Also, the results on an independent test set confirmed the better performance of the proposed method regarding the current state-of-the-art AFP prediction methods. In addition, the more analysis we did, disclosed the poor performance of BLAST in AFP detection and so indicates the critical need for an accurate tool for this purpose. Finally, evolutionary profile and amino acid composition showed the most applicable power in discriminating AFPs from non-AFPs. Declarations Author contribution statement Morteza Eslami: Conceived and designed the experiments; Performed the experiments; Analyzed and interpreted the data; Contributed reagents, materials, analysis tools or data. Ramin Shirali Hossein Zade: Performed the experiments; Analyzed and interpreted the data. Zeinab Takalloo, Emamjomeh Abbasali: Analyzed and interpreted the data. Ghasem Mahdevar, Reza H. Sajedi: Analyzed and interpreted the data; Wrote the paper. Javad Zahiri: Conceived and designed the experiments; Analyzed and interpreted the data; Contributed reagents, materials, analysis tools or data; Wrote the paper. Funding statement This work is supported in part by a grant (BS-1395-01-01) from the Institute for Research in Fundamental Sciences (IPM), Tehran, Iran. Competing interest statement The authors declare no conflict of interest. Additional information afpCOOL is freely available at http://bioinf.modares.ac.ir:8080/AFPCOOL/page/afpcool.jsp. ==== Refs References 1 Jørgensen S. Keskin S. Kitsios D. Commerou P. Nilsson B. Antifreeze Proteins - the Applications of Antifreeze Proteins in the Food Industries 2008 2 Graham L.A. Hobbs R.S. Fletcher G.L. Davies P.L. Helical antifreeze proteins have independently evolved in fishes on four occasions PLoS One 8 2013 e81285 3 Davies P.L. Baardsnes J. Kuiper M.J. Walker V.K. Hall D. Marahiel M.A. Smallwood M. Smith D. Haymet T. Knight C. Structure and function of antifreeze proteins Philos. Trans. R. Soc. B Biol. Sci. 357 2002 927 935 4 Drori R. Davies P.L. Braslavsky I. Experimental correlation between thermal hysteresis activity and the distance between antifreeze proteins on an ice surface RSC Adv. 5 2015 7848 7853 5 Drori R. Davies P.L. Braslavsky I. When are antifreeze proteins in solution essential for ice growth inhibition? Langmuir 31 2015 5805 5811 25946514 6 Yeh Y. Feeney R.E. Antifreeze proteins:  structures and mechanisms of function Chem. Rev. 96 1996 601 618 11848766 7 Venketesh S. Dayananda C. Properties, potentials, and prospects of antifreeze proteins Crit. Rev. Biotechnol. 28 2008 57 82 18322856 8 Fletcher G.L. Goddard S.V. Wu Y.L. Antifreeze proteins and their genes: from basic research to business opportunity Chemtech 29 1999 17 28 9 Davies P.L. Hew C.L. Biochemistry of fish antifreeze proteins FASEB J. 4 1990 2460 2468 2185972 10 Cheng C.H.C. Evolution of the diverse antifreeze proteins Curr. Opin. Genet. Dev. 8 1998 715 720 9914209 11 Ewart K.V. Lin Q. Hew C.L.C.N.-C. Structure, function and evolution of antifreeze proteins Cell Mol. Life Sci. 55 1999 271 283 10188586 12 Logsdon J.M. Doolittle W.F. Origin of antifreeze protein genes - a cool tale in molecular evolution Proc. Natl. Acad. Sci. U. S. A. 94 1997 3485 3487 9108001 13 Zealand F.S.A.N. Ice structuring protein as a processing aid in ice cream and edible ices: a safety assessment / Food Standards Australia New Zealand Final Assess. Rep. 2005 1 92 14 Wang R. Zhang P. Gong Z. Hew C.L. Expression of the antifreeze protein gene in transgenic goldfish (Carassius auratus) and its implication in cold adaptation Mol. Mar. Biol. Biotechnol. 4 1995 20 26 http://www.ncbi.nlm.nih.gov/pubmed/7749462 7749462 15 Kandaswamy K.K. Chou K.C. Martinetz T. Möller S. Suganthan P.N. Sridharan S. Pugalenthi G. AFP-Pred: a random forest approach for predicting antifreeze proteins from sequence-derived properties J. Theor. Biol. 270 2011 56 62 21056045 16 Zhao X. Ma Z. Yin M. Using support vector machine and evolutionary profiles to predict antifreeze protein sequences Int. J. Mol. Sci. 13 2012 2196 2207 22408447 17 Griffith M. Yaish W.F.M. Antifreeze proteins in overwintering∖nplants: a tale of two activities Trends Plant Sci. 9 2004 399 405 15358271 18 Jia Z. Davies P.L. Antifreeze proteins: an unusual receptor-ligand interaction Trends Biochem. Sci. 27 2002 101 106 11852248 19 Li W. Jaroszewski L. Godzik A. Clustering of high homologuous sequences to reduce the size of large protein database Bioinformatics 17 2001 282 283 11294794 20 Bairoch A. Apweiler R. Wu C.H. Barker W.C. Boeckmann B. Ferro S. Gasteiger E. Huang H. Lopez R. Magrane M. Martin M.J. Natale D.A. O'Donovan C. Redaschi N. Yeh L.S.L. The universal protein resource (UniProt) Nucleic Acids Res. 33 2005 D154 D159 15608167 21 Wang G. Dunbrack R.L. Jr. PISCES : a protein sequence culling server Bioinformatics 19 2003 1589 1591 12912846 22 Berman H.M. The protein data bank Nucleic Acids Res. 28 2000 235 242 10592235 23 Kawashima S. Ogata H. Kanehisa M. AAindex: amino acid index database Nucleic Acids Res. 27 1999 368 369 9847231 24 Zahiri J. Mohammad-noori M. Ebrahimpour R. Saadat S. Bozorgmehr J.H. Goldberg T. Masoudi-nejad A. LocFuse: human protein – protein interaction prediction via classifier fusion using protein localization information Genomics 104 2014 4 11 25 Zahiri J. Yaghoubi O. Mohammad-noori M. Ebrahimpour R. Masoudi-nejad A. Genomics PPIevo: protein – protein interaction prediction from PSSM based evolutionary information Genomics 102 2013 237 242 23747746 26 Zahiri J. Bozorgmehr J. Masoudi-Nejad A. Computational prediction of protein–protein interaction networks: algorithms and resources Curr. Genom. 14 2013 397 414 27 Hall Mark H.W.I. Frank Eibe Holmes Geoffrey Bernhard Pfahringer Reutemann Peter The WEKA data mining software: an update SIGKDD Explor. 11 2009 10 18 28 Cid F.P. Rilling J.I. Graether S.P. Bravo L.A. De La Luz Mora M. Jorquera M.A. Properties and biotechnological applications of ice-binding proteins in bacteria FEMS Microbiol. Lett. 363 2016 1 12 29 Kar R.K. Bhunia A. Biophysical and biochemical aspects of antifreeze proteins: using computational tools to extract atomistic information Prog. Biophys. Mol. Biol. 119 2015 194 204 26362837 30 Duman J.G. Animal ice-binding (antifreeze) proteins and glycolipids: an overview with emphasis on physiological function J. Exp. Biol. 218 2015 1846 1855 26085662 31 Wang C. Pakhomova S. Newcomer M.E. Christner B.C. Luo B.H. Structural basis of antifreeze activity of a bacterial multi-domain antifreeze protein PLoS One 12 2017 e0187169 32 Deng G. Andrews D.W. Laursen R.A. Amino acid sequence of a new type of antifreeze protein, from the longhorn sculpin Myoxocephalus octodecimspinosis FEBS Lett. 402 1997 17 20 9013849 33 Nada H. Furukawa Y. Antifreeze proteins: computer simulation studies on the mechanism of ice growth inhibition Polym. J. 44 2012 690 698