Species tree estimation is frequently based on phylogenomic approaches that use multiple genes from throughout the genome. However, for a combination of reasons (ranging from sampling biases to more biological causes, as in gene birth and loss), gene trees are often incomplete, meaning that not all species of interest have a common set of genes. Incomplete gene trees can potentially impact the accuracy of phylogenomic inference. We, for the first time, introduce the problem of imputing the quartet distribution induced by a set of incomplete gene trees, which involves adding the missing quartets back to the quartet distribution. We present QT-GILD, an automated and specially tailored unsupervised deep learning technique, accompanied by cues from natural language processing (NLP), which learns the quartet distribution in a given set of incomplete gene trees and generates a complete set of quartets accordingly. QT-GILD is a general-purpose technique needing no explicit modeling of the subject system or reasons for missing data or gene tree heterogeneity. Experimental studies on a collection of simulated and empirical data sets suggest that QT-GILD can effectively impute the quartet distribution, which results in a dramatic improvement in the species tree accuracy. Remarkably, QT-GILD not only imputes the missing quartets but it can also account for gene tree estimation error. Therefore, QT-GILD advances the state-of-the-art in species tree estimation from gene trees in the face of missing data. QT-GILD is freely available in open source form at https://github.com/pythonLoader/QT-GILD. 

Motivation: Protein–protein interactions (PPIs) are central to most biological processes. However, reliable identification of PPI sites using conventional experimental methods is slow and expensive. Therefore, great efforts are being put into computational methods to identify PPI sites.

Results: We present Edge Aggregated GRaph Attention NETwork (EGRET), a highly accurate deep learning-based method for PPI site prediction, where we have used an edge aggregated graph attention network to effectively leverage the structural information. We, for the first time, have used transfer learning in PPI site prediction. Our proposed edge aggregated network, together with transfer learning, has achieved notable improvement over the best alternate methods. Furthermore, we systematically investigated EGRET’s network behavior to provide insights about the causes of its decisions.

Availability: EGRET is freely available as an open source project at https://github.com/Sazan-Mahbub/EGRET.

Proteins are responsible for most biological functions, many of which require the interaction of more than one protein molecule. However, predicting protein-protein interaction (PPI) sites (the interfacial residues of a protein that interact with other protein molecules) remains a challenge. The growing demand and cost associated with the reliable identification of PPI sites using conventional experimental methods call for computational tools for automated prediction and understanding of PPIs. Here, we present Pair-EGRET, an edge-aggregated graph attention network that leverages the features extracted from pre-trained transformerlike models to accurately predict pairwise protein-protein interaction sites. PairEGRET works on a k-nearest neighbor graph, representing the three-dimensional structure of a protein, and utilizes the cross-attention mechanism on top of a siamese network to accurately identify interfacial residues of a pair of proteins. Through an extensive evaluation study using a diverse array of experimental data, evaluation metrics, and case studies on representative protein sequences, we find that our method outperforms other state-of-the-art methods for predicting PPI sites. Moreover, Pair-EGRET can provide interpretable insights from the learned cross-attention matrix. Pair-EGRET is freely available at https://github.com/1705004/Pair-EGRET.

Motivation: Protein structures provide basic insight into how they can interact with other proteins, their functions and biological roles in an organism. Experimental methods (e.g. X-ray crystallography and nuclear magnetic resonance spectroscopy) for predicting the secondary structure (SS) of proteins are very expensive and time consuming. Therefore, developing efficient computational approaches for predicting the SS of protein is of utmost importance. Advances in developing highly accurate SS prediction methods have mostly been focused on 3-class (Q3) structure prediction. However, 8-class (Q8) resolution of SS contains more useful information and is much more challenging than the Q3 prediction.

Results: We present SAINT, a highly accurate method for Q8 structure prediction, which incorporates self-attention mechanism (a concept from natural language processing) with the Deep Inception-Inside-Inception network in order to effectively capture both the short- and long-range interactions among the amino acid residues. SAINT offers a more interpretable framework than the typical black-box deep neural network methods. Through an extensive evaluation study, we report the performance of SAINT in comparison with the existing best methods on a collection of benchmark datasets, namely, TEST2016, TEST2018, CASP12 and CASP13. Our results suggest that self-attention mechanism improves the prediction accuracy and outperforms the existing best alternate methods. SAINT is the first of its kind and offers the best known Q8 accuracy. Thus, we believe SAINT represents a major step toward the accurate and reliable prediction of SSs of proteins.

Availability and implementation: SAINT is freely available as an open-source project at https://github.com/SAINTProtein/SAINT.

Motivation: Protein structure provides insight into how proteins interact with one another as well as their functions in living organisms. Protein backbone torsion angles (ϕ and ψ) prediction is a key sub-problem in predicting protein structures. However, reliable determination of backbone torsion angles using conventional experimental methods is slow and expensive. Therefore, considerable effort is being put into developing computational methods for predicting backbone angles.

Results: We present SAINT-Angle, a highly accurate method for predicting protein backbone torsion angles using a self-attention based deep learning network called SAINT, which was previously developed for the protein secondary structure prediction. We extended and improved the existing SAINT architecture as well as used transfer learning to predict backbone angles. We compared the performance of SAINT-Angle with the state-of-the-art methods through an extensive evaluation study on a collection of benchmark datasets, namely, TEST2016, TEST2018, CAMEO, and CASP. The experimental results suggest that our proposed self-attention based network, together with transfer learning, has achieved notable improvements over the best alternate methods.

Availability and implementation: SAINT-Angle is freely available as an open-source project at https://github.com/bayzidlab/SAINT-Angle.

Event cameras offer high frame rates, minimal motion blur, and excellent dynamic range. As a result they excel at reconstructing the geometry of 3D scenes. However, their measurements do not contain absolute intensity information, which can make accurately reconstructing the appearance of 3D scenes from events challenging. In this work, we develop a multimodal neural 3D scene reconstruction framework that simultaneously reconstructs scene geometry from events and scene appearance from grayscale images. Our framework—which is based on neural surface representations, as opposed to the neural radiance fields used in previous works—is able to reconstruct both the structure and appearance of 3D scenes more accurately than existing unimodal reconstruction methods.

There has been a rise in automated technologies to screen potential job applicants through affective signals captured from video-based interviews. These tools can make the interview process scalable and objective, but they often provide little to no information of how the machine learning model is making crucial decisions that impacts the livelihood of thousands of people. We built an ensemble model – by combining Multiple-Instance-Learning and Language-Modeling based models – that can predict whether an interviewee should be hired or not. Using both model-specific and model-agnostic interpretation techniques, we can decipher the most informative time-segments and features driving the model's decision making. Our analysis also shows that our models are significantly impacted by the beginning and ending portions of the video. Our model achieves 75.3% accuracy in predicting whether an interviewee should be hired on the ETS Job Interview dataset. Our approach can be extended to interpret other video-based affective computing tasks like analyzing sentiment, measuring credibility, or coaching individuals to collaborate more effectively in a team. 

Context: Learning-based automatic program repair techniques are showing promise to provide quality fix suggestions for detected bugs in the source code of the software. These tools mostly exploit historical data of buggy and fixed code changes and are heavily dependent on bug localizers while applying to a new piece of code. With the increasing popularity of code review, dependency on bug localizers can be reduced. Besides, the code review-based bug localization is more trustworthy since reviewers’ expertise and experience are reflected in these suggestions.

Objective: The natural language instructions scripted on the review comments are enormous sources of information about the bug’s nature and expected solutions. However, none of the learning-based tools has utilized the review comments to fix programming bugs to the best of our knowledge. In this study, we investigate the performance improvement of repair techniques using code review comments.

Method: We train a sequence-to-sequence model on 55,060 code reviews and associated code changes. We also introduce new tokenization and preprocessing approaches that help to achieve significant improvement over state-of-the-art learning-based repair techniques.

Results: We boost the top-1 accuracy by 20.33% and top-10 accuracy by 34.82%. We could provide a suggestion for stylistics and non-code errors unaddressed by prior techniques.

Conclusion: We believe that the automatic fix suggestions along with code review generated by our approach would help developers address the review comment quickly and correctly and thus save their time and effort.

With the advent of pervasive usage of online platforms, online abusive behavior has become an indispensable part of our life demanding great attention from the research community. Accordingly, the research community is spending its effort on the demanding task, however, perhaps having much less effort on emails, even though emails are identified as a prominent source of exchanging online abusive behaviors. To fill in this gap in the literature, we conduct an in-depth study to investigate online abusive behavior having a special focus on emails. To do so, we perform a mixed-method user study consisting of formative interviews (n=15) and a survey (n=65) over user’s experience, coping strategies, etc., pertinent to online abuse in Bangladesh, especially focusing on abuse over emails. We also dig into users’ perspectives to analyze strengths and challenges associated with different types of abuse detection systems for online platforms, especially for emails. One of the noteworthy findings of our study is that there exists a significant demand for abuse detection systems over emailing platforms even after having a lesser frequency of abuse occurring over emails. Our findings also highlight a certain level of user preference for an automated abuse detection system potentially considering its more control and fewer privacy concerns to users, however, being challenged due to having the limitation of lesser ability to detect implicit abuse. We also identify several limiting factors associated with a human-moderator-based abuse detection system, including less comfort, less trust in different types of moderators, inhumane demands to the moderators, and time delay in detecting abuses. These findings point to opportunities for design interventions for hybrid abuse detection systems, which is the most preferred system to the users, to overcome all the limitations of automated and human-moderator-based systems.