Prediction and validation of protein-protein interactors from genome-wide DNA-binding data using a knowledge-based machine-learning approach

PeSA 2.0: A software tool for peptide specificity analysis implementing positive and negative motifs and motif-based peptide scoring

There are a vast number of molecular interactions that occur at the cellular level. Among these molecular interactions, interactions between multiple proteins are a widely studied area of research due to the importance of these interactions in cellular function and their potential in drug development. PeSA is a desktop application developed to facilitate the in vitro peptide study analysis to predict protein-protein interactions. PeSA can effortlessly generate visual outputs like motifs, bar charts, and visual matrices. Our implementation of PeSA version 2.0 includes additional tools, including the ability to further score peptide lists for consensus amongst interactions. The software is also able to design de novo peptides based on sequence motifs (sequence generator), which can be used to help design additional experiments for motif validation. Further, the efficacy of the sequence generator was validated using the lysine methyltransferase, SETD8, to identify new substrates of methylation based on motif-based predictions developed using PeSA2.0.

Drug design targeting active posttranslational modification protein isoforms

Modern drug design aims to discover novel lead compounds with attractable chemical profiles to enable further exploration of the intersection of chemical space and biological space. Identification of small molecules with good ligand efficiency, high activity, and selectivity is crucial toward developing effective and safe drugs. However, the intersection is one of the most challenging tasks in the pharmaceutical industry, as chemical space is almost infinity and continuous, whereas the biological space is very limited and discrete. This bottleneck potentially limits the discovery of molecules with desirable properties for lead optimization. Herein, we present a new direction leveraging posttranslational modification (PTM) protein isoforms target space to inspire drug design termed as "Post-translational Modification Inspired Drug Design (PTMI-DD)." PTMI-DD aims to extend the intersections of chemical space and biological space. We further rationalized and highlighted the importance of PTM protein isoforms and their roles in various diseases and biological functions. We then laid out a few directions to elaborate the PTMI-DD in drug design including discovering covalent binding inhibitors mimicking PTMs, targeting PTM protein isoforms with distinctive binding sites from that of wild-type counterpart, targeting protein-protein interactions involving PTMs, and hijacking protein degeneration by ubiquitination for PTM protein isoforms. These directions will lead to a significant expansion of the biological space and/or increase the tractability of compounds, primarily due to precisely targeting PTM protein isoforms or complexes which are highly relevant to biological functions. Importantly, this new avenue will further enrich the personalized treatment opportunity through precision medicine targeting PTM isoforms.

Mesoderm patterning by a dynamic gradient of retinoic acid signalling

Retinoic acid (RA), derived from vitamin A, is a major teratogen, clinically recognized in 1983. Identification of its natural presence in the embryo and dissection of its molecular mechanism of action became possible in the animal model with the advent of molecular biology, starting with the cloning of its nuclear receptor. In normal development, the dose of RA is tightly controlled to regulate organ formation. Its production depends on enzymes, which have a dynamic expression profile during embryonic development. As a small molecule, it diffuses rapidly and acts as a morphogen. Here, we review advances in deciphering how endogenously produced RA provides positional information to cells. We compare three mesodermal tissues, the limb, the somites and the heart, and discuss how RA signalling regulates antero-posterior and left-right patterning. A common principle is the establishment of its spatio-temporal dynamics by positive and negative feedback mechanisms and by antagonistic signalling by FGF. However, the response is cell-specific, pointing to the existence of cofactors and effectors, which are as yet incompletely characterized. This article is part of a discussion meeting issue 'Contemporary morphogenesis'.

Predicting transcription factor binding using ensemble random forest models

Background: Understanding the location and cell-type specific binding of Transcription Factors (TFs) is important in the study of gene regulation. Computational prediction of TF binding sites is challenging, because TFs often bind only to short DNA motifs and cell-type specific co-factors may work together with the same TF to determine binding. Here, we consider the problem of learning a general model for the prediction of TF binding using DNase1-seq data and TF motif description in form of position specific energy matrices (PSEMs).

Methods: We use TF ChIP-seq data as a gold-standard for model training and evaluation. Our contribution is a novel ensemble learning approach using random forest classifiers. In the context of the ENCODE-DREAM in vivo TF binding site prediction challenge we consider different learning setups.

Results: Our results indicate that the ensemble learning approach is able to better generalize across tissues and cell-types compared to individual tissue-specific classifiers or a classifier built based upon data aggregated across tissues. Furthermore, we show that incorporating DNase1-seq peaks is essential to reduce the false positive rate of TF binding predictions compared to considering the raw DNase1 signal.

Conclusions: Analysis of important features reveals that the models preferentially select motifs of other TFs that are close interaction partners in existing protein protein-interaction networks. Code generated in the scope of this project is available on GitHub: https://github.com/SchulzLab/TFAnalysis (DOI: 10.5281/zenodo.1409697).

Model-based and Model-free Machine Learning Techniques for Diagnostic Prediction and Classification of Clinical Outcomes in Parkinson's Disease

In this study, we apply a multidisciplinary approach to investigate falls in PD patients using clinical, demographic and neuroimaging data from two independent initiatives (University of Michigan and Tel Aviv Sourasky Medical Center). Using machine learning techniques, we construct predictive models to discriminate fallers and non-fallers. Through controlled feature selection, we identified the most salient predictors of patient falls including gait speed, Hoehn and Yahr stage, postural instability and gait difficulty-related measurements. The model-based and model-free analytical methods we employed included logistic regression, random forests, support vector machines, and XGboost. The reliability of the forecasts was assessed by internal statistical (5-fold) cross validation as well as by external out-of-bag validation. Four specific challenges were addressed in the study: Challenge 1, develop a protocol for harmonizing and aggregating complex, multisource, and multi-site Parkinson's disease data; Challenge 2, identify salient predictive features associated with specific clinical traits, e.g., patient falls; Challenge 3, forecast patient falls and evaluate the classification performance; and Challenge 4, predict tremor dominance (TD) vs. posture instability and gait difficulty (PIGD). Our findings suggest that, compared to other approaches, model-free machine learning based techniques provide a more reliable clinical outcome forecasting of falls in Parkinson's patients, for example, with a classification accuracy of about 70-80%.

Mechanisms of retinoic acid signaling during cardiogenesis

Substantial experimental and epidemiological data have highlighted the interplay between nutritional and genetic factors in the development of congenital heart defects. Retinoic acid (RA), a derivative of vitamin A, plays a key role during vertebrate development including the formation of the heart. Retinoids bind to RA and retinoid X receptors (RARs and RXRs) which then regulate tissue-specific genes. Here, we will focus on the roles of RA signaling and receptors in gene regulation during cardiogenesis, and the consequence of deregulated retinoid signaling on heart formation and congenital heart defects.