Focus argument for improvement as interpretability

[lzamparo]

I've described the project to a few ppl now, and one question that comes up is as follows:

• There is little dispute that higher order models for predicting TF-DNA binding are more capable than simple PWM models, there are no shortage of models that provide greater modeling capacity (e.g DeepBind, DeepSEA, DeeperBind, Basset, DanQ,...)
  -Yet there was little immediate interest in another such model whose main advance was better interpretation.
• Existing models (AFAIK) are interested in different predictions. DeepBind was interested in predicting bound-vs-unbound sequences, and also in determining if SNPs would change this status (esp. WRT splicing). Basset also tried an in-silico mutagenesis experiment to try and identify substitutions that would induce changes in predicting binding effects. DeepSEA did a similar experiment. DeepLIFT does not, but they do try to compute per-base importance scores.
• So why do we need another model which takes a variable length sequence input and tries to predict binding information?

My currently most plausible answer:

• Predicting bound versus unbound is relatively well-solved, as each of the comparators I mentioned will attest.
• But usually not the most important problem for people with sequencing data in hand.
• Usually, they wan to know what their sequencing data means. What is binding? What is changing at a given site between experimental conditions? What parts of a given sequence are most important in determining binding versus not binding? And can we interpret what those more important elements tell us about gene regulation?

This suggests I will want to incorporate a figure that shows that my method provides a rich and interpretable view of sequence decoding. Simpler and more precise than FIMO, or other comparators.

• One simple experiment would be to interpret ChIP-seq data; sample peaks, flanks and show that I can reliably rank the factor of interest as most likely to be bound ahead of other factors, and not in flanks. Can compare to FIMO.

[lzamparo]

Christina added to this, which is that we need to figure out better ways to differentiate my own project from Han's work and Meghana's work.

• The problem to focus on is attribution of information content to input sequence regions directly from the model; not by looking at bags of kmers, or what have you. Use the model to identify what regions are driving decisions, and use invitro data to offer probably explanations.
• Currently she suggests training a language model on kmers, using this to encode DNA regions, then building a CNN style model on top of that to decide open vs closed in different cell types