To support experimental researchers, numerous in silico tools have been developed to screen proteins and peptides for various types of toxicity, such as cytotoxicity, hemotoxicity, neurotoxicity and immunotoxicity. These computational tools and algorithms provide valuable insights by predicting potential toxic effects, enabling researchers to prioritize safer and more effective candidates for further experimental validation. Below, we have compiled a list of tools and algorithms specifically designed for predicting different types of toxicity in peptides and proteins, offering a resource to streamline the early stages of research and development. See the User Guide.
| Tool Name | Description | Link |
|---|---|---|
| BTXpred (2007) | Classification of bacterial toxins (exotoxins and endotoxins) | https://webs.iiitd.edu.in/raghava/btxpred/ |
| ClanTox (2009) | Classification of animal toxins from their primary protein sequences | https://www.hsls.pitt.edu/obrc/index.php?page=URL1250871319 |
| ToxinPred (2014) | In silico approach for predicting toxicity of peptides and proteins | https://webs.iiitd.edu.in/raghava/toxinpred/ |
| SpiderP (2013) | Prediction of the propeptide cleavage sites in spider toxins | https://arachnoserver.qfab.org/spiderP.html |
| ToxClassifier (2016) | Prediction of venom toxins from other proteins | http://bioserv7.bioinfo.pbf.hr/ToxClassifier/ | https://github.com/rgacesa/ToxClassifier |
| TOXIFY (2019) | Deep learning approach for the classification of animal venom proteins | https://github.com/tijeco/toxify |
| ATSE (2021) | Prediction of peptide toxicity with their structural and evolutionary information | http://server.malab.cn/ATSE |
| ToxIBLT (2022) | A deep learning approach for the prediction of peptide toxicity using information bottleneck and transfer-learning | http://server.wei-group.net/ToxIBTL | https://github.com/WLYLab/ToxIBTL |
| ToxinPred2.0 (2022) | A method for predicting toxicity of proteins | https://webs.iiitd.edu.in/raghava/toxinpred2/ | https://github.com/raghavagps/toxinpred2 |
| ToxinPred3.0 (2024) | Improved method for predicting the toxicity of peptides | https://webs.iiitd.edu.in/raghava/toxinpred3/ | https://github.com/raghavagps/toxinpred3 |
| VISH-pred (2024) | Ensemble of fine-tuned esm models for protein toxicity prediction | http://ec2-35-170-123-194.compute-1.amazonaws.com:7860/ |
| MultiToxPred 1.0 (2024) | Tool for predicting 27 classes of protein toxins using an ensemble machine learning | https://www.biochemintelli.com/MultiToxPred-v1 | https://github.com/jfbldevs/MultiToxPred |
| Tool Name | Description | Link |
|---|---|---|
| HemoPI (2016) | Website and mobile application designed for computing the hemolytic activity of peptides | https://webs.iiitd.edu.in/raghava/hemopi/ |
| HemoPred (2017) | RF-based Web server dedicated to predicting the hemolytic potency of peptides | https://github.com/chaninn/HemoPred |
| HemoPImod (2020) | A web-based prediction model for chemically modified hemolytic peptides. | https://webs.iiitd.edu.in/raghava/hemopimod/ |
| HLPpred-Fuse (2020) | Enhanced and resilient prediction of hemolytic peptide activity through the fusion of multiple feature representations | http://thegleelab.org/HLPpred-Fuse |
| HAPPENN (2020) | An innovative tool for predicting hemolytic potency in therapeutic peptides utilizing neural networks | https://research.timmons.eu/happenn |
| AMPDeep (2022) | PLMs based hemolytic activity prediction of antimicrobial peptides | https://zenodo.org/records/6992526 | https://github.com/milad73s/AMPDeep |
| Ansari et al. (2023) | Serverless prediction of peptide properties using recurrent neural networks, focusing on classification tasks such as hemolysis, nonfouling, and solubility | https://peptide.bio |
| PeptideBERT (2023) | A transformer-based language model for peptide property prediction, specializing in classification tasks such as hemolysis, nonfouling, and solubility | https://github.com/ChakradharG/PeptideBERT |
| HemoPI2 (2024) | Prediction of Hemolytic Peptides and their Hemolytic Concentration (HC50) | https://webs.iiitd.edu.in/raghava/hemopi2/ | https://github.com/raghavagps/hemopi2 |
| Tool Name | Description | Link |
|---|---|---|
| NTXPred (2007) | Tool for predicting neurotoxins and classifying them based on their function and origin | https://webs.iiitd.edu.in/raghava/ntxpred/ |
| Yang et al. (2008) | Prediction of presynaptic and postsynaptic neurotoxins by the increment of diversity | https://www.sciencedirect.com/science/article/pii/S0887233308002956?via%3Dihub#aep-section-id8 |
| Guang et al. (2010) | SVM based ML model to predict neurotoxicity | https://link.springer.com/article/10.1007/s12539-010-0044-7 |
| Song et al (2012) | Prediction of presynaptic and postsynaptic neurotoxins by bi-layer SVM with multi-features | https://academicjournals.org/journal/AJMR/article-full-text-pdf/28B73DC13695 |
| Tang et al. (2017) | Predicting Presynaptic and Postsynaptic Neurotoxins by Developing Feature Selection Technique | https://pmc.ncbi.nlm.nih.gov/articles/PMC5337787/ |
| Huo et al. (2017) | Prediction of presynaptic and postsynaptic neurotoxins by combining various Chou's pseudo components | https://www.nature.com/articles/s41598-017-06195-y |
| Koua et al. (2017) | Spider Neurotoxins, Short Linear Cationic Peptides and Venom Protein Classification Improved by an Automated Competition between Exhaustive Profile HMM Classifiers | https://pmc.ncbi.nlm.nih.gov/articles/PMC5577579/ |
| Mei et al. (2018) | Analysis and prediction of presynaptic and postsynaptic neurotoxins by Chou's general pseudo amino acid composition and motif features | https://www.sciencedirect.com/science/article/pii/S0022519318301486 |
| Li et al. (2020) | Pippin: A random forest-based method for identifying presynaptic and postsynaptic neurotoxins | https://doi.org/10.1142/S0219720020500080 |
| Lee et al. (2021) | A Deep Learning Approach with Data Augmentation to Predict Novel Spider Neurotoxic Peptides | https://github.com/bzlee-bio/NT_estimation |
| Wan et al. (2023) | Utilize a few features to classify presynaptic and postsynaptic neurotoxins | https://www.sciencedirect.com/science/article/pii/S0010482522010885?via%3Dihub |
| Tool Name | Description | Link |
|---|---|---|
| Stadler et al. (2003) | Motif based Allergenicity prediction by protein sequence | https://doi.org/10.1096/fj.02-1052fje |
| AlgPred (2006) | Prediction of allergenic proteins and mapping of IgE epitopes | https://webs.iiitd.edu.in/raghava/algpred/ |
| AllerHunter (2009) | SVM-based allergenicity and cross-reactivity prediction of Proteins | https://pubmed.ncbi.nlm.nih.gov/19516900/ |
| ProAP (2013) | Sequence-based (ProAp-SVM), motif-based (ProAp-motif) and SVM-based allergen prediction | http://gmobl.sjtu.edu.cn/proAP/main.html |
| AllerTOP (2013) | First alignment-free server for in silico prediction of allergens | https://bmcbioinformatics.biomedcentral.com/articles/10.1186/1471-2105-14-S6-S4 |
| AllergenFP (2014) | Allergenicity prediction by descriptor fingerprints of proteins | https://ddg-pharmfac.net/AllergenFP |
| AllerCatPro (2019) | Prediction of allergenic potential of proteins based on 3D protein structure similarity and amino acid sequence | https://allercatpro.bii.a-star.edu.sg/ |
| AlgPred2.0 (2021) | A method for predicting allergenic proteins and mapping of IgE epitopes | https://webs.iiitd.edu.in/raghava/algpred2/ | https://github.com/raghavagps/algpred2 |
| AllerCatPro 2.0 (2022) | Tool to predict protein allergenicity potential | https://allercatpro.bii.a-star.edu.sg/help.html |
| ALLERDET (2022) | Deep Learning combination with the Decision Tree method for the prediction of allergenicity | http://allerdet.frangam.com | https://github.com/frangam/ALLERDET |
| SEP-AlgPro (2024) | Prediction tool utilizing traditional ML and DL techniques with protein language model features | https://balalab-skku.org/SEP-AlgPro/ |