BRBrajesh Rai

Brajesh Rai

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

Brajesh Rai has a total of 67 co-authors. Here are the top co-authors by number of shared publications:

  • Alan M. Mathiowetz

    Medicine Design, Pfizer Inc., 1 Portland Street, Cambridge, Massachusetts 02139, United States

    4 shared publications
  • Gregory A. Bakken

    Digital, Pfizer, Eastern Point Road, Groton, Connecticut 06340, United States

    4 shared publications
  • Qingyi Yang

    Medicine Design, Pfizer Inc., 1 Portland Street, Cambridge, Massachusetts 02139, United States

    4 shared publications
  • Meihua Tu

    Medicine Design, Pfizer Worldwide Research Development and Medical, 610 Main Street, Cambridge, Massachusetts 02139, United States

    3 shared publications
  • Vishnu Sresht

    Simulation and Modeling Sciences, Pfizer Worldwide Research Development and Medical, 610 Main Street, Cambridge, Massachusetts 02139, United States

    3 shared publications
  • Anton V. Sinitskiy

    College of Professional Studies, Northeastern University, Boston, MA 02115, USA

    2 shared publications

Latest Publications

  • Open Access

    Limitations of general protein language models and public TCRpMHC data in training specificity prediction models

    by Brajesh Rai, Sarah Hall-Swan

    T cell receptor (TCR) specificity prediction is critical for understanding adaptive immunity and for enabling the development of therapeutic interventions. Current machine learning models for predicting TCR-peptide-MHC interactions perform poorly, despite large efforts by many groups and advances in protein language models. This work identifies and addresses the fundamental issues that might be hindering progress in this field, focusing on current approaches for constructing training and validation sets, particularly on the strategies used by commonly used methods, which generate negative data either by shuffling TCRs between epitopes or by pairing epitopes with TCRs from background datasets of healthy donors. Here, we visualize and quantify the overlap between positive and generated negative TCR sets produced by both strategies using a range of sequence embedding approaches, including simple encodings (one-hot and BLOSUM62), general protein language models (ESM-2 and ProtGPT2), and a TCR-specific embedding model (TCR-BERT). Using paired αβTCR data from VDJdb for two well-studied epitopes (GILGFVFTL and KLGGALQAK), we train Random Forest classifiers on each embedding representation and evaluate their ability to distinguish positive from negative data examples. We find that general sequence embedding methods struggle to differentiate between positive and negative TCRs. We further show that the choice of negative data generation method significantly impacts classifier performance. Our findings highlight fundamental limitations in current TCR specificity training data and general protein language models, and underscore the need for TCR-specific embeddings, experimentally validated negative datasets, transparent reporting of negative data construction, and epitope-specific modeling approaches.

  • Open Access

    HLAIIPred: cross-attention mechanism for modeling the interaction of HLA class II molecules with peptides

    by Mojtaba Haghighatlari, Nicholas Marze, Robert Seward, Andrew Ciarla, Rachel Hindin, Jennifer Calderini, Benjamin Keenan, Santosh Dhule, Sarah Hall-Swan, Timothy P. Hickling, et al.

    We introduce HLAIIPred, a deep learning model to predict peptides presented by class II human leukocyte antigens (HLAII) on the surface of antigen presenting cells. HLAIIPred is trained using a Transformer-based neural network and a dataset comprising of HLAII-presented peptides identified by mass spectrometry. In addition to predicting peptide presentation, the model can also provide important insights into peptide-HLAII interactions by identifying core peptide residues that form such interactions. We evaluate the performance of HLAIIPred on three different tasks, peptide presentation in monoallelic samples, immunogenicity prediction of therapeutic antibodies, and neoantigen prioritization for cancer immunotherapy. Additionally, we created a dataset of biotherapeutics HLAII peptides presented by human dendritic cells. This data is used to develop screening strategies to predict the unwanted immunogenic segments of therapeutic antibodies by HLAII presentation models. HLAIIPred demonstrates superior or equivalent performance when compared to the latest models across all evaluated benchmark datasets. We achieve a 16% increase in prediction of presented peptides compared to the second-best model on a set of unseen peptides presented by less frequent alleles. The model improves clinical immunogenicity prediction, identifies epitopes in therapeutic antibodies and prioritize neoantigens with high accuracy.


  • Development and Comprehensive Benchmark of a High-Quality AMBER-Consistent Small Molecule Force Field with Broad Chemical Space Coverage for Molecular Modeling and Free Energy Calculation

    by Bai Xue, Qingyi Yang, Qiaochu Zhang, Xiao Wan, Dong Fang, Xiaolu Lin, Guangxu Sun, Gianpaolo Gobbo, Fenglei Cao, Alan M. Mathiowetz, et al.

    Biomolecular simulations have become an essential tool in contemporary drug discovery, and molecular mechanics force fields (FFs) constitute its cornerstone. Developing a high quality and broad coverage general FF is a significant undertaking that requires substantial expert knowledge and computing resources, which is beyond the scope of general practitioners. Existing FFs originate from only a limited number of groups and organizations, and they either suffer from limited numbers of training sets, lower than desired quality because of oversimplified representations, or are costly for the molecular modeling community to access. To address these issues, in this work, we developed an AMBER-consistent small molecule FF with extensive chemical space coverage, and we provide Open Access parameters for the entire modeling community. To validate our FF, we carried out benchmarks of quantum mechanics (QM)/molecular mechanics conformer comparison and free energy perturbation calculations on several benchmark data sets. Our FF achieves a higher level of performance at reproducing QM energies and geometries than two popular open-source FFs, OpenFF2 and GAFF2. In relative binding free energy calculations for 31 protein-ligand data sets, comprising 1079 pairs of ligands, the new FF achieves an overall root-mean-square error of 1.19 kcal/mol for ΔΔG and 0.92 kcal/mol for ΔG on a subset of 463 ligands without bespoke fitting to the data sets. The results are on par with those of the leading commercial series of OPLS FFs.


  • Open Access

    Development and Comprehensive Benchmark of a High Quality AMBER-Consistent Small Molecule Force Field with Broad Chemical Space Coverage for Molecular Modeling and Free Energy Calculation

    by Bai Xue, Qingyi Yang, Qiaochu Zhang, Xiao Wan, Dong Fang, Xiaolu Lin, Guangxu Sun, Gianpaolo Gobbo, Fenglei Cao, Alan Mathiowetz, et al.

    Biomolecular simulations have become an essential tool in contemporary drug discovery and molecular mechanics force fields constitute its cornerstone. Developing a high quality and broad coverage general force field is a significant undertaking that requires substantial expert knowledge and computing resources, which is beyond the scope of general practitioners. Existing force fields originate from only a limited number of groups and organizations, and they either suffer from limited numbers of training sets, lower than desired quality because of oversimplified representations, or are costly for the molecular modeling community to access. To address these issues, in this work, we developed an AMBER-consistent small molecule force field with extensive chemical space coverage and we provide Open Access parameters for the entire modeling community. To validate our force field, we carried out benchmarks of quantum mechanics/molecular mechanics conformer comparison and free energy perturbation calculations on several benchmark data sets. Our force field achieves a higher level performance at reproducing quantum mechanics energies and geometries than two popular open-source force fields, OpenFF2 and GAFF2. In relative binding free energy calculations for 31 protein-ligand data sets, comprising 1079 pairs of ligands, the new force field achieves an overall root mean square error of 1.19 kcal/mol for ∆∆G and 0.92 kcal/mol for ∆G on a subset of 463 ligands without bespoke fitting to the data sets. The results are on par with the leading commercial series of OPLS force fields.

  • Can We Quickly Learn to “Translate” Bioactive Molecules with Transformer Models?

    by Emma P. Tysinger, Brajesh K. Rai, Anton V. Sinitskiy

    Meaningful exploration of the chemical space of druglike molecules in drug design is a highly challenging task due to a combinatorial explosion of possible modifications of molecules. In this work, we address this problem with transformer models, a type of machine learning (ML) model originally developed for machine translation. By training transformer models on pairs of similar bioactive molecules from the public ChEMBL data set, we enable them to learn medicinal-chemistry-meaningful, context-dependent transformations of molecules, including those absent from the training set. By retrospective analysis on the performance of transformer models on ChEMBL subsets of ligands binding to COX2, DRD2, or HERG protein targets, we demonstrate that the models can generate structures identical or highly similar to most active ligands, despite the models having not seen any ligands active against the corresponding protein target during training. Our work demonstrates that human experts working on hit expansion in drug design can easily and quickly employ transformer models, originally developed to translate texts from one natural language to another, to "translate" from known molecules active against a given protein target to novel molecules active against the same target.


  • Open Access

    Low-data interpretable deep learning prediction of antibody viscosity using a biophysically meaningful representation

    by Brajesh K. Rai, James R. Apgar, Eric M. Bennett

    Deep learning, aided by the availability of big data sets, has led to substantial advances across many disciplines. However, many scientific problems of practical interest lack sufficiently large datasets amenable to deep learning. Prediction of antibody viscosity is one such problem where deep learning methods have not yet been explored due to the relative scarcity of relevant training data. In this work, we overcome this limitation using a biophysically meaningful representation that enables us to develop generalizable models even under limited training data. We present, PfAbNet-viscosity, a 3D convolutional neural network architecture, to predict high-concentration viscosity of therapeutic antibodies. We show that with the electrostatic potential surface of the antibody variable region as the only input to the network, the models trained on as few as couple dozen datapoints can generalize with high accuracy. Our feature attribution analysis shows that PfAbNet-viscosity has learned key biophysical drivers of viscosity. The applicability of our approach to other biological systems is discussed.


  • Open Access

    Can We Quickly Learn to “Translate” Bioactive Molecules with Transformer Models?

    by Emma Tysinger, Brajesh Rai, Anton Sinitskiy

    Meaningful exploration of the chemical space of druglike molecules in drug design is a highly challenging task due to a combinatorial explosion of possible modifications of molecules. In this work, we address this problem with transformer models, a type of machine learning (ML) model, with recent demonstrated success in applications to machine translation and other tasks. By training transformer models on pairs of similar bioactive molecules from the public ChEMBL dataset, we enable them to learn medicinal-chemistry-meaningful, context-dependent transformations of molecules, including those absent from the training set. Most generated molecules are highly plausible and follow similar distributions of simple properties (molecular weight, polarity, hydrogen bond donor and acceptor numbers) as the training dataset. By retrospective analysis of the performance of transformer models on ChEMBL subsets of ligands binding to COX2, DRD2, or HERG protein targets, we demonstrate that the models can generate structures identical or highly similar to highly active ligands, despite the models having not seen any ligands active against the corresponding protein target during training. Thus, our work demonstrates that transformer models, originally developed to translate texts from one natural language to another, can be easily and quickly extended to “translations” from known molecules active against a given protein target to novel molecules active against the same target, and thereby contribute to hit expansion in drug design.

  • TorsionNet: A Deep Neural Network to Rapidly Predict Small-Molecule Torsional Energy Profiles with the Accuracy of Quantum Mechanics

    by Brajesh K. Rai, Vishnu Sresht, Qingyi Yang, Ray Unwalla, Meihua Tu, Alan M. Mathiowetz, Gregory A. Bakken

    Fast and accurate assessment of small-molecule dihedral energetics is crucial for molecular design and optimization in medicinal chemistry. Yet, accurate prediction of torsion energy profiles remains challenging as the current molecular mechanics (MM) methods are limited by insufficient coverage of drug-like chemical space and accurate quantum mechanical (QM) methods are too expensive. To address this limitation, we introduce TorsionNet, a deep neural network (DNN) model specifically developed to predict small-molecule torsion energy profiles with QM-level accuracy. We applied active learning to identify nearly 50k fragments (with elements H, C, N, O, F, S, and Cl) that maximized the coverage of our corporate compound library and leveraged massively parallel cloud computing resources for density functional theory (DFT) torsion scans of these fragments, generating a training data set of 1.2 million DFT energies. After training TorsionNet on this data set, we obtain a model that can rapidly predict the torsion energy profile of typical drug-like fragments with DFT-level accuracy. Importantly, our method also provides an uncertainty estimate for the predicted profiles without any additional calculations. In this report, we show that TorsionNet can accurately identify the preferred dihedral geometries observed in crystal structures. Our TorsionNet-based analysis of a diverse set of protein–ligand complexes with measured binding affinity shows a strong association between high ligand strain and low potency. We also present practical applications of TorsionNet that demonstrate how consideration of DNN-based strain energy leads to substantial improvement in existing lead discovery and design workflows. TorsionNet500, a benchmark data set comprising 500 chemically diverse fragments with DFT torsion profiles (12k MM- and DFT-optimized geometries and energies), has been created and is made publicly available.


  • Open Access

    TorsionNet: A Deep Neural Network to Rapidly Predict Small Molecule Torsion Energy Profiles with the Accuracy of Quantum Mechanics

    by Brajesh Rai, Vishnu Sresht, Qingyi Yang, Rayomond J. Unwalla, Meihua Tu, Alan M. Mathiowetz, Gregory A. Bakken

    TorsionNet: A Deep Neural Network to Rapidly Predict Small Molecule Torsion Energy Profiles with the Accuracy of Quantum Mechanics Brajesh K. Rai*,1, Vishnu Sresht1, Qingyi Yang2, Ray Unwalla2, Meihua Tu2, Alan M. Mathiowetz2, and Gregory A. Bakken3 1Simulation and Modeling Sciences and 2Medicine Design, Pfizer Worldwide Research Development and Medical, 610 Main Street, Cambridge, Massachusetts 02139, United States 3Digital, Pfizer, Eastern Point Road, Groton, Connecticut 06340, United States ABSTRACT Fast and accurate assessment of small molecule dihedral energetics is crucial for molecular design and optimization in medicinal chemistry. Yet, accurate prediction of torsion energy profiles remains a challenging task as current molecular mechanics methods are limited by insufficient coverage of druglike chemical space and accurate quantum mechanical (QM) methods are too expensive. To address this limitation, we introduce TorsionNet, a deep neural network (DNN) model specifically developed to predict small molecule torsion energy profiles with QM-level accuracy. We applied active learning to identify nearly 50k fragments (with elements H, C, N, O, F, S, and Cl) that maximized the coverage of our corporate library and leveraged massively parallel cloud computing resources to perform DFT torsion scan of these fragments, generating a training dataset of 1.2 million DFT energies. By training TorsionNet on this dataset, we obtain a model that can rapidly predict the torsion energy profile of typical druglike fragments with DFT-level accuracy. Importantly, our method also provides a direct estimate of the uncertainty in the predicted profiles without any additional calculations. In this report, we show that TorsionNet can reliably identify the preferred dihedral geometries observed in crystal structures. We also present practical applications of TorsionNet that demonstrate how consideration of DNN-based strain energy leads to substantial improvement in existing lead discovery and design workflows. A benchmark dataset (TorsionNet500) comprising 500 chemically diverse fragments with DFT torsion profiles (12k DFT-optimized geometries and energies) has been created and is made freely available.

  • Comprehensive Assessment of Torsional Strain in Crystal Structures of Small Molecules and Protein–Ligand Complexes using ab Initio Calculations

    by Brajesh Kumar Rai, Vishnu Sresht, Qingyi Yang, Ray Unwalla, Meihua Tu, Alan M. Mathiowetz, Gregory A. Bakken

    The energetics of rotation around single bonds (torsions) is a key determinant of the 3D shape that drug-like molecules adopt in solution, the solid state, and in different biological environments, which in turn defines their unique physical and pharmacological properties. Therefore, accurate characterization of torsion angle preference and energetics is essential for the success of computational drug discovery and design. Here, we analyze torsional strain in crystal structures of drug-like molecules in CSD and bioactive ligand conformations in PDB, expressing the total strain energy as a sum of strain energy from constituent rotatable bonds. We utilized Cloud computing to generate torsion scan profiles of a very large collection of chemically diverse neutral fragments at DFT(B3LYP)/6-31G*//6-31G** or DFT(B3LYP)/6-31+G*//6-31+G** (for sulfur-containing molecule). With the data generated from these ab initio calculations, we performed rigorous analysis of strain due to deviation of observed torsion angles relative to their ideal gas-phase geometries. Contrary to the previous studies based on molecular mechanics, we find that in the crystalline-state molecules generally adopt low-strain conformations, with median per-torsion strain energy in CSD and PDB under 1/10th and 1/3rd of a kcal/mol, respectively. However, for a small fraction (<5%) of motifs, external effects such as steric hinderance and hydrogen bonds result in strain penalty exceeding 2.5 kcal/mol. We find that due to poor quality of PDB structures in general, bioactive structures tend to have higher torsional strain compared to small molecule crystal conformations. However, in the absence of structural fitting artifacts in PDB structures, protein-induced strain in bioactive conformations is quantitatively similar to those due to the packing forces in small molecule crystal structures. This analysis allows us to establish strain energy thresholds to help to identify biologically relevant conformers in a given ensemble. The work presented here is the most comprehensive study to date that demonstrates the utility and feasibility of gas-phase QM calculations to study conformational preference and energetics of drug-size molecules. Potential applications of this study in computational lead discovery and structure-based design are discussed.