My name is Abolfazl. I am a senior research scientist at Wang Genomics Lab at Perelman School of Medicine at the University of Pennsylvania. I am also a proud member of Raymond G. Perelman Center for Cellular and Molecular Therapeutics at the Children's Hospital of Philadelphia.

Prior to moving to Philadelphia, we were a part of the Department of Biomedical Informatics and the Institute for Genomic Medicine at Columbia University. I did my postdoc in Computer Science and Systems Biology at the University of California, Santa Barbara and Harvard University. I earned my PhD in Industrial and Systems Engineering (minor in System biology) from Amirkabir University of Technology (former Tehran Polytechnic), Iran, in 2015. I am broadly interested in Computational Systems Biology of complex diseases such as schizophrenia and autism spectrum disorders, Machine Learning, Network and Cell-Type Deconvolution, Single-Cell Genomics, and Bioinformatics.

Publications

Here I have shortlisted my recent publications in chronological order. Full list is available on Google Scholar.

A. Doostparast Torshizi, et al., Deconvolution of Transcriptional Networks Identifies TCF4 as a Master Regulator in Schizophrenia. Tissue-specific reverse engineering of transcriptional networks has uncovered master regulators (MRs) of cellular networks in various cancers, yet the application of this method to neuropsychiatric disorders is largely unexplored. Here, using RNA-Seq data on postmortem dorsolateral prefrontal cortex (DLPFC) from schizophrenia (SCZ) patients and control subjects, we deconvolved the transcriptional network to identify MRs that mediate expression of a large body of target genes. Together with an independent RNA-Seq data on cultured cells derived from olfactory neuroepithelium, we identified TCF4, a leading SCZ risk locus implicated by genome-wide association studies, as one of the top candidate MRs that may be potentially dysregulated in SCZ. We validated the dysregulated TCF4-related transcriptional network through examining the transcription factor binding footprints inferred from human induced pluripotent stem cell (hiPSC)-derived neuronal ATAC-Seq data (Paper URL).

K.E. Borgmann-Winter, K. Wang, S. Bandyopadhyay, A. Doostparast Torshizi, I. Blair, C.G. Hahn, The proteome and its dynamics: A missing piece for integrative multi-omics in schizophrenia. The complex and heterogeneous pathophysiology of schizophrenia can be deconstructed by integration of large-scale datasets encompassing genes through behavioral phenotypes. Genome-wide datasets are now available for genetic, epigenetic and transcriptomic variations in schizophrenia, which are then analyzed by newly devised systems biology algorithms. A missing piece, however, is the inclusion of information on the proteome and its dynamics in schizophrenia. Proteomics has lagged behind omics of the genome, transcriptome and epigenome since analytic platforms of proteins were previously not as robust as those for nucleic acids. In recent years, however, there has been an unprecedented progress in the instrumentation (liquid chromatography (LC) and mass spectrometry (MS)), experimental paradigms, and bioinformatics of the proteome. Large-scale analyses of the schizophrenia proteome are now possible and ought to be pursued vigorously and integrated with other omics results. With that in our view, we review proteomics studies that have been conducted in schizophrenia to date, present a summary of methodological innovations of recent years in MS based proteomics and the power of new generation proteomics, and propose how such data can be analyzed and integrated with other omics results (Publication URL.)

A. Doostparast Torshizi, K. Wang, Next-generation sequencing in drug development: target identification and genetically stratified clinical trials. Next-generation sequencing (NGS) enabled high-throughput analysis of genotype-phenotype relationships on human populations, ushering in a new era of genetics-informed drug development. The year 2017 was remarkable, with the first US Food and Drug Administration (FDA)-approved gene therapy for cancer (Kymriah) and for inherited diseases (LUXTURNA), the first multiplex NGS panel for companion diagnostics (MSK-IMPACT), and the first drug targeting a genetic signature rather than a disease (Keytruda®). We envision that population-scale NGS with paired electronic health records (EHRs) will become a routine measure in the drug development process for the identification of novel drug targets, and that genetically stratified clinical trials may be widely adopted to improve power in precision medicine-guided drug development. More can be found here.

A. Doostparast Torshizi, L. Petzold, Graph-based semi-supervised learning with genomic data integration using condition-responsive genes applied to phenotype classification, (Featured Article & Editor's Choice). Data integration methods that combine data from different molecular levels such as genome, epigenome, transcriptome, etc., have received a great deal of interest in the past few years. It has been demonstrated that the synergistic effects of different biological data types can boost learning capabilities and lead to a better understanding of the underlying interactions among molecular levels. In this paper we present a graph-based semi-supervised classification algorithm that incorporates latent biological knowledge in the form of biological pathways with gene expression and DNA methylation data. The process of graph construction from biological pathways is based on detecting condition-responsive genes, where 3 sets of genes are finally extracted: all condition responsive genes, high-frequency condition-responsive genes, and P-value–filtered genes. More can be found here.

A. Doostparast Torshizi, L. Petzold, Sparse Pathway-Induced Dynamic Network Biomarker Discovery for Early Warning Signal Detection in Complex Diseases. In many complex diseases, the transition process from the healthy stage to the catastrophic stage does not occur gradually. Recent studies indicate that the initiation and progression of such diseases are comprised of three steps including healthy stage, pre-disease stage, and disease stage. It has been demonstrated that a certain set of trajectories can be observed in the genetic signatures at the molecular level, which might be used to detect the pre-disease stage and to take necessary medical interventions. In this paper, we propose two optimization-based algorithms for extracting the dynamic network biomarkers responsible for catastrophic transition into the disease stage, and to open new horizons to reverse the disease progression at an early stage through pinpointing molecular signatures provided by high-throughput microarray data. The first algorithm relies on meta-heuristic intelligent search to characterize dynamic network biomarkers represented as a complete graph. The second algorithm induces sparsity on the adjacency matrix of the genes by taking into account the biological signaling and metabolic pathways, since not all the genes in the ineractome are biologically linked. Comprehensive numerical and meta-analytical experiments verify the effectiveness of the results of the proposed approaches in terms of network size, biological meaningfulness, and verifiability. More can be found here.

A. Doostparast Torshizi, L. Petzold, M. Cohen, Multivariate soft repulsive system identification for constructing rule-based classification systems: Application to trauma clinical data. Rule-based classification systems constructed upon linguistic terms in the antecedent and consequent of the rules lack sufficient generalization capabilities. This paper proposes a new multivariate fuzzy system identification algorithm to design binary rule-based classification structures through making use of the repulsive forces between the cluster prototypes of different class labels. This approach is coupled with the potential discrimination power of each dimension in the feature space to increase the generalization potential. To address this issue, first the multivariate variant of a newly proposed soft clustering algorithm along with its mathematical foundations is proposed. Next, the discriminatory power of each individual feature is computed, using the multivariate membership values in the proposed clustering algorithm to achieve the most accurate firing degree in each rule. The main advantage of this method is to handle unbalanced datasets yielding superior true positive measure while keeping the false positive rate low enough to avoid the natural bias toward class labels containing larger number of training samples. To validate the proposed approaches, a series of numerical experiments on publicly available datasets and a real clinical dataset collected by our team were conducted. Simulation results demonstrated achievement of the primary goals of this research. More can be found here.

A. Doostparast Torshizi, M.H. Fazel Zarandi, A new cluster validity measure based on general type-2 fuzzy sets: Application in gene expression data clustering. As a widespread pattern recognition technique, clustering has been widely used in various disciplines including: science, engineering, medicine, etc. One the latest progresses in this field is introduction of general type-2 fuzzy sets and the new clustering method represented on its basis called general type-2 fuzzy c-means. In this paper, the aim is to develop a robust and accurate similarity measure between general type-2 fuzzy sets. Utilizing philosophy behind this developed similarity measure, the first exclusively developed general type-2 fuzzy cluster validity index will be proposed to be used for finding the optimal number of clusters through using general type-2 fuzzy c-means. To verify quality of the proposed approaches, several heavy computations have been conducted on artificial datasets and also real gene expression datasets. Numerical comparisons reveal robustness and quality of the proposed approach compared to several similar approaches in the literature. More can be found here.

News & Media

I usually share my career-related news here.

Funding & Awards

Funding

  • Mar. 2019: Roberts Rapid Grant for the project "Genome-wide structural variation detection in acute lymphocytic leukemia using long-read sequencing technology" ($10,000, Role: Senior/Key Personnel).

Honors and Awards

  • Oct. 2019: Featured Research Trainee, Children's Hospital of Philadelphia.
  • May 2019: Alavi-Dabiri Postdoctoral Fellowship Award, Perelman School of Medicine, University of Pennsylvania, The Children's Hospital of Philadelphia.
  • Dec. 2018: Distinguished Research Trainee Award Nominee, The Children's Hospital of Philadelphia.
  • Apr. 2015: Excellent PhD Dissertation Award, Amirkabir University of Technology (Tehran Polytechnic), Iran.
  • Nov. 2014: Recognized Reviewer Award, Elsevier Publishers.
  • Aug. 2014: Best Student Paper Award, IEEE-North American Fuzzy Information Processing Society Conference (NAFIPS), Boston, USA.
  • Sep. 2011: Admission with Honor as an Exceptional Graduate Student to Doctoral Program, Amirkabir University of Technology (Tehran Polytechnic), Iran.
  • Jan. 2011: Top-ranked MS Student Award, Isfahan University of Technology.
  • Sep. 2009: Fellowship and Summer School Grant, German Academic Exchange Service (DAAD).
  • Jun. 2009 - Jun. 2011: Isfahan University of Technology Fellowship, Ranked First among all of the graduate students, Isfahan University of Technology, Iran.

Service

  • Organizing Committee Member and Chair, International Conference on Intelligent Biology and Medicine (ICIBM 2018), Los Angeles, CA, USA.
  • Workshop Organizer and Chair, International Workshop on Translational Bioinformatics in Precision Medicine (TBPM 2017), In Conjunction with 2017 IEEE International Conference on Bioinformatics and Biomedicine (IEEE-BIBM 2017), Kansas City, MO, USA.
  • ad hoc Reviewer:
      • Scientific Reports, Nature Publishing Group
      • Frontiers in Genetics
      • PLoS One
      • Applied Soft Computing
      • Engineering Applications of Artificial Intelligence
      • Computer Methods and Programs in Biomedicine
      • International Journal of Electrical Power & Energy Systems
      • Reliability Engineering and System Safety
      • Hydrological Sciences Journal
      • Journal of Intelligent and Fuzzy Systems
      • British Journal of Applied Science & Technology
      • International Journal of Engineering
      • Ain Shams Engineering Journal
      • North American Fuzzy Information Processing Society (IEEE-NAFIPS)
      • IEEE Microwave and Radio Electronics Week 2017 (IEEE MAREW 2017)
  • Instructor: 'Multiple Criteria Decision Making course', Graduate Course, Amirkabir University of Technology (International Campus), October 2012.
  • Instructor: 'Foundations of Information Technology', Undergrad Course, Ershad University, Tehran, Iran.
  • Instructor: 'Applied Optimization', Undergrad Course, Ershad University, Tehran, Iran, 2012.
  • Research Assistant: Intelligent Systems Laboratory, Amirkabir University of Technology, 2011-2015.
  • Teaching Assistant: 'Management of Information Systems' course of undergraduate level, Amirkabir University of Technology, 2013-2015.
  • Research Assistant: 'Data Management', Amirkabir University of Technology, 2014-2015 .

Mentoring Experience

  • John Gregg, PhD Student of Genomics and Computational Biology, University of Pennsylvania, 2018 (co-mentored).
  • Karen Xu, MS Student of Biostatistics, Columbia University, 2017 (co-mentored).
  • Eshan Agarwal, BS Student of Computer Science, Columbia University, 2017.
  • Richard Jiang, PhD Student of Computer Science, University of California, Santa Barbara (UCSB), 2016.
  • Destinee Cheng, PhD Student of Computer Science, University of California, Santa Barbara (UCSB), 2016.

Social Footprints

My professional accounts. I use my Twitter primarily for science. My Github and Linkedin profiles project my other scientific achievements. Finally, I have recently linked my Instagram to my website.