DVDaniel Veltri

Daniel Veltri

*This is an algorithmically generated author record based on publicly available information.

Daniel Veltri has a total of 158 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Chromosomal microarray analysis reveals copy number variants contribute to disease in children with suspected inborn errors of immunity

    by Breanna Beers, Morgan Similuk, Rajarshi Ghosh, Bryce Seifert, Wenjia Cao, Daniel Veltri, Steven Holland, Luis Franco, Magdalena Walkiewicz, Jia Yan

  • Open Access

    PhenoRerank: A re-ranking model for phenotypic concept recognition pre-trained on human phenotype ontology

    by Shankai Yan, Ling Luo, Po-Ting Lai, Daniel Veltri, Andrew J. Oler, Sandhya Xirasagar, Rajarshi Ghosh, Morgan Similuk, Peter N. Robinson, Zhiyong Lu


  • Open Access

    Exploring target specificity of antimicrobial peptides through deep learning embeddings

    by Lauren Losin, Daniel Veltri

    In the face of increasing bacterial resistance to antibiotics, antimicrobial peptides (AMPs) have stood out as an encouraging target for the development of new drugs. Machine learning approaches can be applied to this area to characterize large sets of AMPs based on their bacterial targets, activity measures, and other sequence features. Such methods enable wet-laboratory researchers to optimize the speed and accuracy of their work by focusing on prioritized candidates [5]. Prior work on computational AMP recognition has largely focused on binary sequence classification (predicting AMP vs non-AMP) but is beginning to venture into de novo peptide design [5]. This work takes steps to further understand AMP function and specificity by learning sequence embeddings based on both molecular sequence and activity measures against different bacteria targets. The model uses a Siamese network architecture [1] to learn from pairs of AMPs to predict how their activity differs against 10 different genera of bacteria. Unlike many other approaches, we also consider N- and C-termini modifications to sequences. Training and testing data originates from the Database of Antimicrobial Activity and Structure of Peptides (DBAASP) [4] and was parsed to consider monomer AMPs with activity measurements recorded as minimum inhibitory concentration (MIC). Due to the large heterogeneity of bacteria at the species-level, responses were grouped by genera and MIC values averaged. Based on the percentage of all AMPs with a mean MIC response available, the top 10 genera were considered. That data set was split into training (4, 170 AMPs), validation (1, 142 AMPs), and testing (535 AMPs) partitions. To reduce the chance of data leakage between testing and training data, the CD-HIT server [2] was used (after removing termini modifications) to ensure all testing sequences share < 90% identity with all training/validation sequences. Each partition was further arranged into pairs of sequences sharing the same target, with responses calculated as the difference in mean MIC values. The Siamese network consists of an embedding and long short-term memory layer [3] that are trained in a supervised setting. It compares AMP sequence pairs to train a shared set of weights. All input sequences are padded to be the same length and a tokenizer is used to encode both amino acids and termini modifications. The model outputs sequence embeddings based on the difference in MIC for each AMP pair. To obtain insight into AMP activity and specificity, separate models are trained for gram-positive and gram-negative genera. Trained embeddings for each model are then plotted and compared to visualize how bacterial membrane structure can influence AMP sequence composition. These results present another step towards making AMP deep learning models more informative and understandable to the research community.


  • Open Access

    PhenoTagger: a hybrid method for phenotype concept recognition using human phenotype ontology

    by Ling Luo, Shankai Yan, Po-Ting Lai, Daniel Veltri, Andrew Oler, Sandhya Xirasagar, Rajarshi Ghosh, Morgan Similuk, Peter N Robinson, Zhiyong Lu

    Automatic phenotype concept recognition from unstructured text remains a challenging task in biomedical text mining research. Previous works that address the task typically use dictionary-based matching methods, which can achieve high precision but suffer from lower recall. Recently, machine learning-based methods have been proposed to identify biomedical concepts, which can recognize more unseen concept synonyms by automatic feature learning. However, most methods require large corpora of manually annotated data for model training, which is difficult to obtain due to the high cost of human annotation. In this article, we propose PhenoTagger, a hybrid method that combines both dictionary and machine learning-based methods to recognize Human Phenotype Ontology (HPO) concepts in unstructured biomedical text. We first use all concepts and synonyms in HPO to construct a dictionary, which is then used to automatically build a distantly supervised training dataset for machine learning. Next, a cutting-edge deep learning model is trained to classify each candidate phrase (n-gram from input sentence) into a corresponding concept label. Finally, the dictionary and machine learning-based prediction results are combined for improved performance. Our method is validated with two HPO corpora, and the results show that PhenoTagger compares favorably to previous methods. In addition, to demonstrate the generalizability of our method, we retrained PhenoTagger using the disease ontology MEDIC for disease concept recognition to investigate the effect of training on different ontologies. Experimental results on the NCBI disease corpus show that PhenoTagger without requiring manually annotated training data achieves competitive performance as compared with state-of-the-art supervised methods. The source code, API information and data for PhenoTagger are freely available at https://github.com/ncbi-nlp/PhenoTagger. Supplementary data are available at Bioinformatics online.


  • Open Access

    Structure and function of a malaria transmission blocking vaccine targeting Pfs230 and Pfs230-Pfs48/45 proteins

    by Kavita Singh, Martin Burkhardt, Sofia Nakuchima, Raul Herrera, Olga Muratova, Apostolos G. Gittis, Emily Kelnhofer, Karine Reiter, Margery Smelkinson, Daniel Veltri, et al.

    Proteins Pfs230 and Pfs48/45 arePlasmodium falciparumtransmission-blocking (TB) vaccine candidates that form a membrane-bound protein complex on gametes. The biological role of Pfs230 or the Pfs230-Pfs48/45 complex remains poorly understood. Here, we present the crystal structure of recombinant Pfs230 domain 1 (Pfs230D1M), a 6-cysteine domain, in complex with the Fab fragment of a TB monoclonal antibody (mAb) 4F12. We observed the arrangement of Pfs230 on the surface of macrogametes differed from that on microgametes, and that Pfs230, with no known membrane anchor, may exist on the membrane surface in the absence of Pfs48/45. 4F12 appears to sterically interfere with Pfs230 function. Combining mAbs against different epitopes of Pfs230D1 or of Pfs230D1 and Pfs48/45, significantly increased TB activity. These studies elucidate a mechanism of action of the Pfs230D1 vaccine, model the functional activity induced by a polyclonal antibody response and support the development of TB vaccines targeting Pfs230D1 and Pfs230D1-Pfs48/45.


  • Global distribution of mating types shows limited opportunities for mating across populations of fungi causing boxwood blight disease

    by Martha Malapi-Wight, Daniel Veltri, Bjorn Gehesquière, Kurt Heungens, Yazmín Rivera, Catalina Salgado-Salazar, Jo Anne Crouch


  • Open Access

    Hypomorphic caspase activation and recruitment domain 11 (CARD11) mutations associated with diverse immunologic phenotypes with or without atopic disease

    by Batsukh Dorjbal, Jeffrey R. Stinson, Chi A. Ma, Michael A. Weinreich, Bahar Miraghazadeh, Julia M. Hartberger, Stefanie Frey-Jakobs, Stephan Weidinger, Lena Moebus, Andre Franke, et al.


  • Guiding Exploration of Antimicrobial Peptide Space with a Deep Neural Network

    by Manpriya Dua, Daniel Veltri, Barney Bishop, Amarda Shehu

    Antibiotic resistance has become a serious concern, and many health organizations are sounding the alarm and the need for new drug templates. Naturally-occurring antimicrobial peptides (AMPs) have long promised to serve as such templates, as they have shown lower likelihood for bacteria to form resistance. This has motivated wet and dry laboratories to seek novel AMPs. The sequence diversity of these peptides renders systematic screening studies either infeasible or too narrow in scope. Dry-laboratory approaches, most notably under the umbrella of machine learning, have contributed discriminative models of increasing accuracy. In this paper we investigate the capability of a state-of-the-art discriminative model based on deep learning to guide the exploration of peptide space in search of novel AMPs. The model is encapsulated within randomized heuristic search. Results show that such a generative framework is promising at providing wet laboratories with diverse options for toxicity and further biophysical screening, constituting a first step in dry and wet-laboratory integration studies.

  • Open Access

    Genome wide analysis of the transition to pathogenic lifestyles in Magnaporthales fungi

    by Ning Zhang, Guohong Cai, Dana C. Price, Jo Anne Crouch, Pierre Gladieux, Bradley Hillman, Chang Hyun Khang, Marc-Henri LeBrun, Yong-Hwan Lee, Jing Luo, et al.

    The rice blast fungus Pyricularia oryzae (syn. Magnaporthe oryzae, Magnaporthe grisea), a member of the order Magnaporthales in the class Sordariomycetes, is an important plant pathogen and a model species for studying pathogen infection and plant-fungal interaction. In this study, we generated genome sequence data from five additional Magnaporthales fungi including non-pathogenic species, and performed comparative genome analysis of a total of 13 fungal species in the class Sordariomycetes to understand the evolutionary history of the Magnaporthales and of fungal pathogenesis. Our results suggest that the Magnaporthales diverged ca. 31 millon years ago from other Sordariomycetes, with the phytopathogenic blast clade diverging ca. 21 million years ago. Little evidence of inter-phylum horizontal gene transfer (HGT) was detected in Magnaporthales. In contrast, many genes underwent positive selection in this order and the majority of these sequences are clade-specific. The blast clade genomes contain more secretome and avirulence effector genes, which likely play key roles in the interaction between Pyricularia species and their plant hosts. Finally, analysis of transposable elements (TE) showed differing proportions of TE classes among Magnaporthales genomes, suggesting that species-specific patterns may hold clues to the history of host/environmental adaptation in these fungi.


  • Top Cited Papers
    Open Access

    Deep learning improves antimicrobial peptide recognition

    by Daniel Veltri, Uday Kamath, Amarda Shehu

    Bacterial resistance to antibiotics is a growing concern. Antimicrobial peptides (AMPs), natural components of innate immunity, are popular targets for developing new drugs. Machine learning methods are now commonly adopted by wet-laboratory researchers to screen for promising candidates. In this work, we utilize deep learning to recognize antimicrobial activity. We propose a neural network model with convolutional and recurrent layers that leverage primary sequence composition. Results show that the proposed model outperforms state-of-the-art classification models on a comprehensive dataset. By utilizing the embedding weights, we also present a reduced-alphabet representation and show that reasonable AMP recognition can be maintained using nine amino acid types. Models and datasets are made freely available through the Antimicrobial Peptide Scanner vr.2 web server at www.ampscanner.com. Supplementary data are available at Bioinformatics online.