Supplemental datasets for: 'Pan-microalgal dark proteome mapping via interpretable deep learning and synthetic chimeras'

This repository contains supplementary datasets for 'Pan-microalgal dark proteome mapping via interpretable deep learning and synthetic chimeras'. This version also contains the original vector graphics for the figures presented in the main text.

Data S1 | Neural network training sequences (4GB). Dataset comprising DNA sequences processed in two formats: with terminal information (TI-inclusive) and terminal information-free (TI-free).

Data S2 | Training and inference scripts. The LA4SR framework integrated several open-source software packages and models. We employed LORA (Low-Rank Adaptation (adapted from: https://github.com/microsoft/LoRA)), PEFT (Parameter-Efficient Fine-Tuning (https://github.com/huggingface/peft), and QLORA (Quantized Low-Rank Adaptation (adapted from: https://github.com/artidoro/qlora) for parameter-efficient post-training and used Mamba (https://github.com/state-spaces/mamba) as an alternative to transformer-based architectures. The Hugging Face Transformers library (https://github.com/huggingface/transformers) facilitated implementation, pretraining, and post-training of the open-source models. Training was performed on an HPC cluster, with jobs going to nodes with NVIDIA (Santa Clara, CA, USA) V100, A100, or H100 GPUs. Dataset available at: 10.5281/zenodo.13920001.

Data S3 | Interpretability scripts, including DeepMotifMinerPro. Includes scripts for the implementation of the custom explainer programs presented with this work, including Captum-, DeepLift, and SHAP-based approaches (Data S3) to explain how different amino acid residues and their patterns and positions affect model decisions.

Data S4 | Additional validations using new assemblies from seen species. We cultured and sequenced ten separate isogenic colonies of Chlamydomonas reinhardtii CC-1883. Of these, nine were sequenced with Illumina 150 bp paired-end short reads and one with Pacific Biosciences (PacBio, Menlo Park, CA, USA) HiFi reads and DoveTail (Sydney, Australia) Hi-C to generate a complete, axenic reference assembly. These data were also uploaded to NCBI (SAMN44618602).

Data S5 | Singularity container to run LA⁴SR. Includes an environment supporting LA⁴SR.