Biology subjects

Rawat, P.

Publications and source records attributed to Rawat, P..

5 recordsLinked to original sources

bioRxiv2024

Training data composition determines machine learning generalization and biological rule discovery

Supervised machine learning models depend on training datasets with positive and negative examples. Therefore, dataset composition directly impacts model performance and bias. Given the importance of machine learning for immunotherapeutic design, we examined how different negative class definitions affect model generalization and rule discovery for antibody-antigen binding. Using synthetic structure-based binding data, we evaluated models trained with various definitions of negative sets. Our findings reveal that high out-of-distribution performance can be achieved when the negative dataset contains more similar samples to the positive dataset despite a lower within-distribution performance. Furthermore, leveraging ground truth information, we show that binding rules discovered as associated with positive data change based on the negative data used. Validation on experimental data supported simulation-based observations. This work underscores the role of dataset composition, including negative data selection, in creating robust, generalizable, and biology-aware sequence-based ML models.

bioinformatics↗

bioRxiv2024

Baselining the Buzz. Trastuzumab-HER2 Affinity, and Beyond!

Strong antibody-antigen binding is the primary consideration when developing an efficacious therapeutic antibody. In recent years, much work has been devoted to applying complex machine learning models to this cause, yet simple baselines are often lacking. Here, we show that the widely used sequence alignment method, BLOSUM, can yield diverse, binder-enriched libraries from a single starting antibody. Using Trastuzumab-HER2 as a model system, we experimentally validated 720 novel designs generated with five different computational methods using surface plasmon resonance. The BLOSUM substitution matrix outperformed all four deep learning design approaches tested, achieving an estimated minimum binder enrichment of 12.5% and producing nine sub-nanomolar binders. These results underscore the importance of comparing against simple baselines and set a benchmark to guide future computational antibody library design. O_FIG O_LINKSMALLFIG WIDTH=200 HEIGHT=141 SRC="FIGDIR/small/586756v2_ufig1.gif" ALT="Figure 1"> View larger version (32K): org.highwire.dtl.DTLVardef@1597ee9org.highwire.dtl.DTLVardef@9af4b6org.highwire.dtl.DTLVardef@1380e61org.highwire.dtl.DTLVardef@1380d29_HPS_FORMAT_FIGEXP M_FIG C_FIG

bioinformatics↗

bioRxiv2023

Cartography of the developability landscapes of native and human-engineered antibodies

Designing effective monoclonal antibody (mAb) therapeutics faces a multi-parameter optimization challenge known as "developability", which reflects an antibodys ability to progress through development stages based on its physicochemical properties. While natural antibodies may provide valuable guidance for mAb selection, we lack a comprehensive understanding of natural developability parameter (DP) plasticity (redundancy, predictability, sensitivity) and how the DP landscapes of human-engineered and natural antibodies relate to one another. These gaps hinder fundamental developability profile cartography. To chart natural and engineered DP landscapes, we computed 40 sequence- and 46 structure-based DPs of over two million native and human-engineered single-chain antibody sequences. We found lower redundancy among structure-based compared to sequence-based DPs. Sequence DP sensitivity to single amino acid substitutions varied by antibody region and DP, and structure DP values varied across the conformational ensemble of antibody structures. Sequence DPs were more predictable than structure-based ones across different machine-learning tasks and embeddings, indicating a constrained sequence-based design space. Human-engineered antibodies were localized within the developability and sequence landscapes of natural antibodies, suggesting that human-engineered antibodies explore mere subspaces of the natural one. Our work quantifies the plasticity of antibody developability, providing a fundamental resource for multi-parameter therapeutic mAb design.

bioinformatics↗

bioRxiv2023

HSP70 binds to specific non-coding RNA and regulates human RNA Polymerase III

Molecular chaperones are critical for protein homeostasis and are implicated in several human pathologies such as neurodegeneration and cancer. While the binding of chaperones to nascent and misfolded proteins has been studied in great detail, the direct interaction between chaperones and RNA has not been systematically investigated. Here we provide the evidence for widespread interaction between chaperones and RNA in human cells. We show that the major chaperone Heat-Shock Protein 70 (HSP70) binds to non-coding RNA transcribed by RNA Polymerase III (Pol III) such as tRNA and 5S rRNA. Global chromatin profiling revealed that HSP70 binds genomic sites of transcription by Pol III. Detailed biochemical analyses showed that HSP70 facilitates transcription of its target non-coding RNA by binding to Pol III. Thus our study uncovers an unexpected role of HSP70-RNA interaction in the biogenesis of a specific class of non-coding RNA with wider implications in neurodegeneration and cancer.

biochemistry↗

bioRxiv2020

PAX8 orchestrates an angiogenic program through interaction with SOX17

Worldwide, the number of new ovarian cancer cases approaches 300,000 with more than 180,000 deaths every year. The low survival-rate reflects the limitations of current therapies and highlights the importance of identifying new therapeutic targets. Despite significant recent efforts to identify novel vulnerabilities in ovarian cancer, none have led to effective durable therapies with improvement in overall survival. PAX8, a lineage-transcription factor, whose expression is a major molecular feature of ovarian carcinomas, represents a novel therapeutic target. Herein, we have identified SOX17 as a bona fide PAX8-interacting partner and elucidated the impact of this interaction on the development of ovarian cancer. Importantly, we found that PAX8 and SOX17 regulate tumor angiogenesis in vitro and in vivo. The role of PAX8 and SOX17 in the regulation of angiogenesis reveals a novel function for these factors in regulating the tumor microenvironment and highlight this pathway as a viable therapeutic target.

cancer biology↗