# Research ## Publications ### Unified imputation of missing data modalities and features in multi-omic data via shared representation learning Preprint: one shared representation for several omic layers, so a missing modality or feature can be imputed from the others instead of being dropped. - Venue: bioRxiv - Date: 2026-02-04 - Authors: Ananthan Nambiar; C. Melendez; W. Noble - Kind: preprint - https://doi.org/10.64898/2026.02.04.703630 ### BPS2026 - A brighter future: Optimizing GFP fluorescence using deep learning Meeting abstract: a deep learning approach to optimizing GFP fluorescence, the work Ananthan did with the Anderson lab at the Biophysical Society meeting. - Venue: Biophysical Journal - Date: 2026-02-01 - Authors: Lydia Longfritz; Keiki Miller; Ananthan Nambiar; Greg Anderson; S. Ahuja - Kind: paper - https://doi.org/10.1016/j.bpj.2025.11.2600 ### Protein Language Models Capture Structural and Functional Epistasis in a Zero-Shot Setting Preprint: epistasis as a lens on what protein language models learn. Raw PLM scores align with residue-residue contacts, and a nonlinear transformation shifts the signal toward functional couplings between distant sites. - Venue: bioRxiv - Date: 2025-09-17 - Authors: Ananthan Nambiar; Sayantani B. Littlefield; Carlos Cuellar; Rohit Khorana; Sergei Maslov - Kind: preprint - https://doi.org/10.1101/2025.09.14.676130 ### Machine Learning for Protein Science and Engineering A collection on machine learning for protein science, edited with Peter K. Koo, Christian Dallago and Kevin K. Yang: representations, co-evolutionary statistical models, homology search, functional annotation and variant effect prediction. - Venue: Cold Spring Harbor Perspectives in Biology - Date: 2025-05-05 - Authors: Peter K. Koo; Christian Dallago; Ananthan Nambiar; Kevin K. Yang - Kind: editorial - https://doi.org/10.1101/cshperspect.a041877 ### DR-BERT: A protein language model to annotate disordered regions A compact protein language model that predicts intrinsically disordered regions without relying on evolutionary or biophysical data, outperforming existing methods on the CAID evaluation datasets. - Venue: Structure - Date: 2024-08-01 - Authors: Ananthan Nambiar; John Malcolm Forsyth; Simon Liu; Sergei Maslov - Kind: paper - https://doi.org/10.1016/j.str.2024.04.010 ### Semi-quantitative group testing for efficient and accurate qPCR screening of pathogens with a wide range of loads A group testing scheme for qPCR pathogen screening that handles viral loads spanning several orders of magnitude, with theoretical guarantees on the number of tests required. - Venue: BMC Bioinformatics - Date: 2024-05-17 - Authors: Ananthan Nambiar; Chao Pan; Vishal Rana; Mahdi Cheraghchi; João Ribeiro; Sergei Maslov; Olgica Milenkovic - Kind: paper - https://doi.org/10.1186/s12859-024-05798-3 ### A transcriptomic atlas of acute stress response to low pH in multiple Issatchenkia orientalis strains A transcriptomic atlas of the low-pH stress response across multiple strains of the acid-tolerant yeast Issatchenkia orientalis, a chassis for industrial organic acid production. - Venue: Microbiology Spectrum - Date: 2024-01-11 - Authors: Veronika Dubinkina; Shreyas Bhogale; Po-Hsien Hsieh; Pouya Dibaeinia; Ananthan Nambiar; Sergei Maslov; Yuseok Yoshikuni; Saurabh Sinha - Kind: paper - https://doi.org/10.1128/spectrum.02536-23 ### FUN-PROSE: A deep learning approach to predict condition-specific gene expression in fungi A deep learning model that predicts differential expression of individual genes across conditions from promoter sequences and transcription factor expression, with an interpretable layer that recovers promoter motifs and TF-gene interactions. - Venue: PLOS Computational Biology - Date: 2023-11-16 - Authors: Ananthan Nambiar; Veronika Dubinkina; Simon Liu; Sergei Maslov - Kind: paper - https://doi.org/10.1371/journal.pcbi.1011563 ### Transformer Neural Networks for Protein Family and Interaction Prediction Tasks Journal version of the ACM-BCB 2020 paper: a small transformer pretrained on protein sequences, fine-tuned for protein family classification and protein-protein interaction prediction at a fraction of the compute of larger models. - Venue: Journal of Computational Biology - Date: 2023-01-01 - Authors: Ananthan Nambiar; Simon Liu; Maeve Heflin; John Malcolm Forsyth; Sergei Maslov; Mark Hopkins; Anna M. Ritz - Kind: paper - https://doi.org/10.1089/cmb.2022.0132 ### Dropping diversity of products of large US firms: Models and measures Measures and models of dropping product diversity in large US firms, built on document embeddings of firm filings. - Venue: PLOS ONE - Date: 2022-03-16 - Authors: Ananthan Nambiar; Tobias Rubel; James McCaull; Jon deVries; Mark A. Bedau - Kind: paper - https://doi.org/10.1371/journal.pone.0264330 ### Transforming the Language of Life: Transformer Neural Networks for Protein Prediction Tasks Conference paper: a small transformer pretrained on protein sequence representations, fine-tuned to state-of-the-art performance on protein family classification and interaction prediction. The first paper in the language-of-life line. - Venue: ACM-BCB 2020 - Date: 2020-09-21 - Authors: Ananthan Nambiar; Maeve Heflin; Simon Liu; Sergei Maslov; Mark Hopkins; Anna M. Ritz - Kind: paper - https://doi.org/10.1145/3388440.3412467 ### Open-Ended Technological Innovation A framework for detecting open-ended growth in the space of technological innovations, applied to patent records. - Venue: Artificial Life - Date: 2019-04-01 - Authors: Mark A. Bedau; Nicholas Gigliotti; Tobias Janssen; Alec Kosik; Ananthan Nambiar; Norman H. Packard - Kind: paper - https://doi.org/10.1162/artl_a_00279 ## Talks ### Transcribing the Language of Life: An Interpretable Deep Neural Network to Predict Condition Specific Gene Regulation Poster. The interpretable neural network behind FUN-PROSE, which predicts condition-specific gene regulation and recovers the promoter motifs responsible. - Event: ISMB/ECCB 2021 - Date: 2021-07-01 - Kind: poster - Location: Virtual ### Computing the Language of Life: NLP Approaches to Feature Extraction for Protein Family Classification Poster. Feature extraction for protein family classification, treating protein sequences as language. - Event: ISMB/ECCB 2019 - Date: 2019-07-01 - Kind: poster - Location: Basel ### Detecting the On-going Emergence of Technological Innovations Oral presentation. Detection of ongoing technological innovation, later published as Open-Ended Technological Innovation in Artificial Life. - Event: ALIFE 2018, Workshop on Open-ended Evolution - Date: 2018-07-01 - Kind: talk - Location: Tokyo ### Controllability of Functional Classes in the Genetic Regulatory Network of E. coli Poster. Target controllability of functional classes of genes in E. coli, from the network biology work done at Delhi University and the Santa Fe Institute. - Event: SIAM Annual Meeting 2018 - Date: 2018-07-01 - Kind: poster - Location: Vancouver