Human leukocyte antigen or HLA plays a crucial role in the recognition of antigenic peptides as this binding is responsible for subsequent immune response by eliciting T-cell activation. Accurate prediction of peptide-HLA binding affinity is imperative for facilitating vaccine development and immunotherapies. Recent advancements in transformer-based models and protein language models in predicting peptide-HLA interactions have shown significant improvements. Current methodologies rely on deep learning methods and GPU-intensive computations. We propose a simple and computationally cheaper method that demonstrates efficacy. Our tree-based model, named FEATUREPHLA, utilizes the physico-chemical fingerprints obtained from peptides and HLA sequences and is highly interpretable.Our goal was to estimate the predictive efficacy of these physico-chemical features for the task of peptide-HLA binding prediction. Our proposed method outperforms other methods on experimentally verified peptide-HLA binders from the HPV vaccine data securing the highest number of true positives and the lowest number of false negatives, thereby, showcasing its predictive power on real-world scenarios. Our study reveals the relevance of biology-inspired features for the calculation of molecular interactions and lays the groundwork towards developing more accurate biology-informed predictive models.

Peptide- and protein-based therapeutics are becoming a promising treatment regimen for myriad diseases. Toxicity of proteins is the primary hurdle for protein-based therapies. Thus, there is an urgent need for accurate in silico methods for determining toxic proteins to filter the pool of potential candidates. At the same time, it is imperative to precisely identify non-toxic proteins to expand the possibilities for protein-based biologics. To address this challenge, we proposed an ensemble framework, called VISH-Pred, comprising models built by fine-tuning ESM2 transformer models on a large, experimentally validated, curated dataset of protein and peptide toxicities. The primary steps in the VISH-Pred framework are to efficiently estimate protein toxicities taking just the protein sequence as input, employing an under sampling technique to handle the humongous class-imbalance in the data and learning representations from fine-tuned ESM2 protein language models which are then fed to machine learning techniques such as Lightgbm and XGBoost. The VISH-Pred framework is able to correctly identify both peptides/proteins with potential toxicity and non-toxic proteins, achieving a Matthews correlation coefficient of 0.737, 0.716 and 0.322 and F1-score of 0.759, 0.696 and 0.713 on three non-redundant blind tests, respectively, outperforming other methods by over $10\%$ on these quality metrics. Moreover, VISH-Pred achieved the best accuracy and area under receiver operating curve scores on these independent test sets, highlighting the robustness and generalization capability of the framework. By making VISH-Pred available as an easy-to-use web server, we expect it to serve as a valuable asset for future endeavors aimed at discerning the toxicity of peptides and enabling efficient protein-based therapeutics.

Active learning algorithms are effective in identifying the salient and exemplar samples from large amounts of unlabeled data. This tremendously reduces the human annotation effort in inducing a machine learning model as only a few samples, which are identified by the algorithm, need to be labeled manually. In problem domains like text mining and video classification, human oracles peruse the data instances incrementally to derive an opinion about their class labels (such as reading a movie review progressively to assess its sentiment). In such applications, it is not necessary for the human oracles to review an unlabeled sample end-to-end in order to provide a label; it may be more efficient to identify an optimal subinstance size (percentage of the sample from the start) for each unlabeled sample, and request the human annotator to label the sample by analyzing only the subinstance, instead of the whole data sample. In this paper, we propose a novel framework to address this challenging problem, in an effort to further reduce the labeling burden on the human oracles and utilize the available labeling budget more efficiently. We pose the sample and subinstance size selection as a constrained optimization problem and derive a linear programming relaxation to select a batch of exemplar samples, together with the optimal subinstance size of each, which can potentially augment maximal information to the underlying classification model. Our extensive empirical studies on six challenging datasets from the text mining domain corroborate the practical usefulness of our framework over competing baselines.

Abstract In the modern world, wireless mesh networks (WMN) are widely used in Internet of Things (IoT) applications. It is a dynamic, infrastructure‐less multihop network with mobility features. In WMN, to design an effective and strong routing protocol is a challenge. Conventional protocols for routing using a remote vector or link‐state routing are not ideal for a wireless network. The shortest routing path is used with all current traditional routing protocols to pick a route with a minimum number of hops. The decisions must be done in real‐time in high‐traffic networks for the route selection and for the packets to be diversified into other routes. The routing protocols should adapt to the traffic conditions, that is, the network load changes and the route must be selected accordingly. The route may not be the shortest in number, but the best in terms of the actual time a packet requires to reach the target. The key objective of this research work is to design such an adaptive routing algorithm, while minimizing the delivery time and preventing the network from congestion. The rationale for this research work is to optimize adaptive routing protocol based on reinforcement learning, which efficiently delivers packets in the WMN. The experimental evaluation demonstrates that the obtained results significantly improve the system performance compared to the benchmark routing protocols. The Quality of Service (QoS) parameters such as packet delivery ratio (PDR), delay, and throughput metrics are used to assess the performance of the proposed technique using the NS‐3 simulator.

Abstract The increased usage of online social networks in recent days attracts the attention of researchers. That makes analysis of social networks a significant concern. Link prediction is one of the problem of social networks, where links are predicted between users by analyzing the relationships between the nodes. As the size and usability of the social network grows, the accurate prediction of connections with limited public information is a challenge. This article introduces a novel approach for predicting missing links using a nature‐inspired method, the gravitational search algorithm. We selected seven real‐world networks and five widely used algorithms and also considered the sparsity of networks for the experimental evaluation of the proposed approach. The proposed GSA‐driven algorithm has shown a better or comparable AUC result than the other standard algorithms on these networks.

Deep learning has emerged as an effective machine learning algorithm to automatically learn a representative set of features and has revolutionized multimedia computing research. However, training a reliable deep model necessitates a large amount of labeled training data, which is time-consuming and labor-intensive to acquire. Active Learning (AL) algorithms address this challenge by automatically identifying the salient and exemplar samples from large amounts of unlabeled data; this drastically reduces human annotation effort, as only a handful of samples, that are identified by the algorithm, need to be labeled manually. However, in applications like vision-based facial age estimation, providing the exact labels (age of a person) may be challenging even for human annotators, as it maybe difficult to accurately estimate the age of a person merely from a facial image; it maybe much easier to provide relative label feedback, such as whether a particular subject is older than another subject. In this paper, we propose a novel deep active learning algorithm (DALRel) which requires only relative label feedback in response to the queried samples. We formulate a loss function relevant to the research task and exploit the gradient descent algorithm to optimize the loss and train the deep network. To the best of our knowledge, this is the first research effort to develop an active learning framework to train a deep neural network, which poses only relative label queries to the labeling oracles. Our extensive empirical studies demonstrate the promise and potential of this method for real-world active learning applications, where providing the exact labels to queried instances can be challenging.

Recently, there is increasing interest in multilingual automatic speech recognition (ASR) where a speech recognition system caters to multiple low resource languages by taking advantage of low amounts of labeled corpora in multiple languages. With multilingualism becoming common in today's world, there has been increasing interest in code-switching ASR as well. In code-switching, multiple languages are freely interchanged within a single sentence or between sentences. The success of low-resource multilingual and code-switching ASR often depends on the variety of languages in terms of their acoustics, linguistic characteristics as well as the amount of data available and how these are carefully considered in building the ASR system. In this challenge, we would like to focus on building multilingual and code-switching ASR systems through two different subtasks related to a total of seven Indian languages, namely Hindi, Marathi, Odia, Tamil, Telugu, Gujarati and Bengali. For this purpose, we provide a total of ~600 hours of transcribed speech data, comprising train and test sets, in these languages including two code-switched language pairs, Hindi-English and Bengali-English. We also provide a baseline recipe for both the tasks with a WER of 30.73% and 32.45% on the test sets of multilingual and code-switching subtasks, respectively.

In recent years, deep learning has revolutionized the field of computer vision and has achieved state-of-the-art performance in a variety of applications. However, training a robust deep neural network necessitates a large amount of hand-labeled training data, which is time-consuming and labor-intensive to acquire. Active learning and transfer learning are two popular methodologies to address the problem of learning with limited labeled data. Active learning attempts to select the salient and exemplar instances from large amounts of unlabeled data; transfer learning leverages knowledge from a labeled source domain to develop a model for a (related) target domain, where labeled data is scarce. In this paper, we propose a novel active transfer learning algorithm with the objective of learning informative feature representations from a given dataset using a deep convolutional neural network, under the constraint of weak supervision. We formulate a loss function relevant to the research task and exploit the gradient descent algorithm to optimize the loss and train the deep network. To the best of our knowledge, this is the first research effort to propose a task-specific loss function integrating active and transfer learning, with the goal of learning informative feature representations using a deep neural network, under weak human supervision. Our extensive empirical studies on a variety of challenging, real-world applications depict the merit of our framework over competing baselines.

One of the most important decisions made by managers in a baseball game is when to pull the starting pitcher. It has a direct consequence on the outcome of the game and also on the physical fitness of the pitcher. Traditionally, managers rely on various heuristics for this decision. In this paper, we propose a machine learning based approach to determine when to replace the starting pitcher. We curate a large dataset of more than one million samples, spanning more than 10 years of baseball games (2007 - 2017), and study the performance of various classification algorithms on this dataset. We further perform feature analysis to gain insights on the most important features influencing the replacement of starting pitchers. To the best of our knowledge, this is the first research effort to leverage machine learning and data analytics to model managers' decisions of pulling a starting pitcher from historic data. Such a system can be immensely useful in assisting managers make more informed decisions during an ongoing game and has the potential to reduce the risk of baseball related injuries. We hope that our curated dataset and initial research findings will promote further work toward this important problem of deciding when to pull a starting pitcher in an ongoing baseball game.

This poster describes a low-cost and robust embedded platform, designed for vehicle mounted sensing of particulate matter (PM2.5 and PM10). The prototype is specifically designed to be mounted on the Delhi Integrated Multi-Modal Transit System (DIMTS) buses. Movement of the buses adds noise to pollution data. Error in GPS measurement causes issues in detecting moving vs. stationary state of the buses, useful to filter out noisy pollution data collected in the moving state. Intermittent cellular network connectivity causes frequent disconnects with the remote server. Our prototype is designed to handle such real world deployment challenges. Pilot deployment with this platform is currently ongoing. Preliminary data analysis from the pilot deployment will be discussed as part of the poster presentation, along with demonstration of the prototype sensor platform. This hardware prototype has the potential of creating locality wise, dense air pollution data providing crucial insights into the causes of air pollution.

BACKGROUND: The advent of human genome sequencing project has led to a spurt in the number of protein sequences in the databanks. Success of structure based drug discovery severely hinges on the availability of structures. Despite significant progresses in the area of experimental protein structure determination, the sequence-structure gap is continually widening. Data driven homology based computational methods have proved successful in predicting tertiary structures for sequences sharing medium to high sequence similarities. With dwindling similarities of query sequences, advanced homology/ ab initio hybrid approaches are being explored to solve structure prediction problem. Here we describe Bhageerath-H, a homology/ ab initio hybrid software/server for predicting protein tertiary structures with advancing drug design attempts as one of the goals. RESULTS: Bhageerath-H web-server was validated on 75 CASP10 targets which showed TM-scores ≥ 0.5 in 91% of the cases and Cα RMSDs ≤ 5 Å from the native in 58% of the targets, which is well above the CASP10 water mark. Comparison with some leading servers demonstrated the uniqueness of the hybrid methodology in effectively sampling conformational space, scoring best decoys and refining low resolution models to high and medium resolution. CONCLUSION: Bhageerath-H methodology is web enabled for the scientific community as a freely accessible web server. The methodology is fielded in the on-going CASP11 experiment.