Background: Deep learning’s automatic feature extraction has proven to give superior performance in many sequence classification tasks. However, deep learning models generally require a massive amount of data to train, which in the case of Hemolytic Activity Prediction of Antimicrobial Peptides creates a challenge due to the small amount of available data. Results: Three different datasets for hemolysis activity prediction of therapeutic and antimicrobial peptides are gathered and the AMPDeep pipeline is implemented for each. The result demonstrate that AMPDeep outperforms the previous works on all three datasets, including works that use physicochemical features to represent the peptides or those who solely rely on the sequence and use deep learning to learn representation for the peptides. Moreover, a combined dataset is introduced for hemolytic activity prediction to address the problem of sequence similarity in this domain. AMPDeep fine-tunes a large transformer based model on a small amount of peptides and successfully leverages the patterns learned from other protein and peptide databases to assist hemolysis activity prediction modeling. Conclusions: In this work transfer learning is leveraged to overcome the challenge of small data and a deep learning based model is successfully adopted for hemolysis activity classification of antimicrobial peptides. This model is first initialized as a protein language model which is pre-trained on masked amino acid prediction on many unlabeled protein sequences in a self-supervised manner. Having done so, the model is fine-tuned on an aggregated dataset of labeled peptides in a supervised manner to predict secretion. Through transfer learning, hyper-parameter optimization and selective fine-tuning, AMPDeep is able to achieve state-of-the-art performance on three hemolysis datasets using only the sequence of the peptides. This work assists the adoption of large sequence-based models for peptide classification and modeling tasks in a practical manner.
Deep learning’s automatic feature extraction has been a revolutionary addition to computational drug discovery, infusing both the capabilities of learning abstract features and discovering complex molecular patterns via learning from molecular data. Since biological and chemical knowledge are necessary for overcoming the challenges of data curation, balancing, training, and evaluation, it is important for databases to contain information regarding the exact target and disease of each bioassay. The existing depositories such as PubChem or ChEMBL offer the screening data for millions of molecules against a variety of cells and targets, however, their bioassays contain complex biological descriptions which can hinder their usage by the machine learning community. In this work, a comprehensive disease and target-based dataset is collected from PubChem in order to facilitate and accelerate molecular machine learning for better drug discovery. MolData is one the largest efforts to date for democratizing the molecular machine learning, with roughly 170 million drug screening results from 1.4 million unique molecules assigned to specific diseases and targets. It also provides 30 unique categories of targets and diseases. Correlation analysis of the MolData bioassays unveils valuable information for drug repurposing for multiple diseases including cancer, metabolic disorders, and infectious diseases. Finally, we provide a benchmark of more than 30 models trained on each category using multitask learning. MolData aims to pave the way for computational drug discovery and accelerate the advancement of molecular artificial intelligence in a practical manner. The MolData benchmark data is available at https://GitHub.com/Transilico/MolData as well as within the additional files.
30 November 2017 in Clinical and Experimental Immunology
Summary: Identification of autoimmune processes and introduction of new autoantigens involved in the pathogenesis of multiple sclerosis (MS) can be helpful in the design of new drugs to prevent unresponsiveness and side effects in patients. To find significant changes, we evaluated the autoantibody repertoires in newly diagnosed relapsing–remitting MS patients (NDP) and those receiving disease-modifying therapy (RP). Through a random peptide phage library, a panel of NDP- and RP-specific peptides was identified, producing two protein data sets visualized using Gephi, based on protein-–protein interactions in the STRING database. The top modules of NDP and RP networks were assessed using Enrichr. Based on the findings, a set of proteins, including ATP binding cassette subfamily C member 1 (ABCC1), neurogenic locus notch homologue protein 1 (NOTCH1), hepatocyte growth factor receptor (MET), RAF proto-oncogene serine/threonine-protein kinase (RAF1) and proto-oncogene vav (VAV1) was found in NDP and was involved in over-represented terms correlated with cell-mediated immunity and cancer. In contrast, transcription factor RelB (RELB), histone acetyltransferase p300 (EP300), acetyl-CoA carboxylase 2 (ACACB), adiponectin (ADIPOQ) and phosphoenolpyruvate carboxykinase 2 mitochondrial (PCK2) had major contributions to viral infections and lipid metabolism as significant events in RP. According to these findings, further research is required to demonstrate the pathogenic roles of such proteins and autoantibodies targeting them in MS and to develop therapeutic agents which can ameliorate disease severity.
Deep learning’s automatic feature extraction has proven its superior performance over traditional fingerprint-based features in the implementation of virtual screening models. However, these models face multiple challenges in the field of early drug discovery, such as over-training and generalization to unseen data, due to the inherently unbalanced and small datasets. In this work, the TranScreen pipeline is proposed, which utilizes transfer learning and a collection of weight initializations to overcome these challenges. An amount of 182 graph convolutional neural networks are trained on molecular source datasets and the learned knowledge is transferred to the target task for fine-tuning. The target task of p53-based bioactivity prediction, an important factor for anti-cancer discovery, is chosen to showcase the capability of the pipeline. Having trained a collection of source models, three different approaches are implemented to compare and rank them for a given task before fine-tuning. The results show improvement in performance of the model in multiple cases, with the best model increasing the area under receiver operating curve ROC-AUC from 0.75 to 0.91 and the recall from 0.25 to 1. This improvement is vital for practical virtual screening via lowering the false negatives and demonstrates the potential of transfer learning. The code and pre-trained models are made accessible online.
Compound screening is a vital and impactful stage of non-target based early drug discovery. Achieving a high hit rate demands intelligent selection of the input libraries. If the chosen scaffolds have high potency, low toxicity, and high diversity, the drug discovery process has a higher chance of success. Virtual screening has proven to increase the efficiency of the early stage