SwissTargetPrediction is a web server for predicting the targets of bioactive small molecules using a combination of 2D and 3D similarity measures with known ligands. The tool allows predictions in five organisms (human, mouse, rat, cow, and horse) and enables mapping predictions by homology within and between species for close paralogs and orthologs. It is freely accessible at http://www.swisstargetprediction.ch. The method is based on the observation that similar bioactive molecules are more likely to share similar targets. Targets are predicted by identifying proteins with known ligands that are highly similar to the query molecule. Both 2D and 3D similarity measures are used, with 2D similarity calculated using FP2 fingerprints and the Tanimoto coefficient, while 3D similarity is calculated using ElectroShape vectors and Manhattan distance. The final score is derived from a logistic regression of the similarity values. The dataset includes 280,381 small molecules interacting with 2,686 targets across five organisms. The tool provides results in the form of a list of predicted targets, ranked by their scores, with links to databases such as GeneCards, UniProt, and ChEMBL. The probability of a prediction being correct is derived from the target scores and is used to rank predicted targets. Homology-based predictions are also available, allowing users to map predictions between and within organisms based on target homology. This expands the list of predicted targets from 2,686 to over 12,188 in all five organisms. The tool has been validated using an external test set, resulting in an average AUC value of 0.87. It has been shown to accurately predict known targets for many molecules, including CHEMBL2325087, which binds to EGFR and ERBB2. SwissTargetPrediction is part of an initiative by the Swiss Institute of Bioinformatics to provide online tools for computer-aided drug design. Future developments include integrating the tool with other tools, such as SwissDock, and regularly updating it with new organisms and data. The tool is freely available and does not require login.SwissTargetPrediction is a web server for predicting the targets of bioactive small molecules using a combination of 2D and 3D similarity measures with known ligands. The tool allows predictions in five organisms (human, mouse, rat, cow, and horse) and enables mapping predictions by homology within and between species for close paralogs and orthologs. It is freely accessible at http://www.swisstargetprediction.ch. The method is based on the observation that similar bioactive molecules are more likely to share similar targets. Targets are predicted by identifying proteins with known ligands that are highly similar to the query molecule. Both 2D and 3D similarity measures are used, with 2D similarity calculated using FP2 fingerprints and the Tanimoto coefficient, while 3D similarity is calculated using ElectroShape vectors and Manhattan distance. The final score is derived from a logistic regression of the similarity values. The dataset includes 280,381 small molecules interacting with 2,686 targets across five organisms. The tool provides results in the form of a list of predicted targets, ranked by their scores, with links to databases such as GeneCards, UniProt, and ChEMBL. The probability of a prediction being correct is derived from the target scores and is used to rank predicted targets. Homology-based predictions are also available, allowing users to map predictions between and within organisms based on target homology. This expands the list of predicted targets from 2,686 to over 12,188 in all five organisms. The tool has been validated using an external test set, resulting in an average AUC value of 0.87. It has been shown to accurately predict known targets for many molecules, including CHEMBL2325087, which binds to EGFR and ERBB2. SwissTargetPrediction is part of an initiative by the Swiss Institute of Bioinformatics to provide online tools for computer-aided drug design. Future developments include integrating the tool with other tools, such as SwissDock, and regularly updating it with new organisms and data. The tool is freely available and does not require login.